Cross-platform nuclear power station license process approval method, device, equipment and medium

Abstract

The invention relates to the technical field of nuclear power station informatization construction, and discloses a cross-platform nuclear power station license process approval method. The method comprises the following steps: carrying out content identification on a received license application request to obtain application content and an executor image; executing information detection operation on the application content; performing identity recognition on the image, and determining a region permission according to an identity recognition result; detecting the application content, and determining whether the license approval process meets approval permissions of other platforms according to a detection result; and if yes, obtaining platform auditing results of other platforms on each approval node, and when the platform auditing results pass, confirming that the license approval process is ended. According to the method and the device, the content identification is performed on the license application request, and the determination of the regional authority and the detection of confidentiality and urgency are realized, so that the judgment of the approval authority of other platforms is realized, the cross-platform auditing of the license approval process is realized, and the approval efficiency of the license approval process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of informatization construction of nuclear power plants, and particularly to a cross-platform license process approval method, device, equipment and medium for nuclear power plants. Background Art

[0002] At present, in the daily operation of nuclear power plants, a large number of maintenance operations are involved. When performing maintenance operations, in order to ensure safety, relevant licenses need to be issued, such as excavation permits, fire prevention permits, container operation permits, radiographic inspection permits, material storage permits, etc.

[0003] In the prior art, there are multiple license application platforms in nuclear power plants (such as SAP platform, EPM platform, business process management platform, fire load platform, radioactive effluent management platform). The data between each platform is not interoperable, which easily leads to errors, omissions and lack of license reviews, and the inability to review licenses in a timely manner, resulting in low efficiency of license approval. Moreover, for some relatively urgent license applications, they cannot be approved in a timely manner, seriously affecting user usage and experience. At the same time, the current license application platform does not detect the confidentiality of the application content and cannot ensure whether the content is leaked. In addition, it does not detect the permissions of the applicants, resulting in some staff members being unable to go to the work area to perform the task. Summary of the Invention

[0004] Embodiments of the present invention provide a cross-platform license process approval method, device, equipment and medium for nuclear power plants to solve the problem in the prior art that the data between each platform is not interoperable, which easily leads to errors, omissions and lack of current license reviews and the inability to process them in a timely manner, resulting in low efficiency of ticket approval processing.

[0005] A cross-platform license process approval method for nuclear power plants includes:

[0006] Receiving a license application request initiated by an executor on the unified management platform of the nuclear power plant according to the license approval process, and performing content recognition on the current license and attachments in the license application request to obtain the application content and the executor's image;

[0007] Performing an information detection operation on the application content, where the information detection operation includes: extracting the work area and work duration in the application content, performing nuclear radiation detection on the work area to obtain the nuclear radiation dose, and filling the nuclear radiation dose into the current license; and detecting the work duration to obtain a duration detection result, and filling the duration detection result into the current license;

[0008] Identify the identity of the image of the executor, and determine the area permissions corresponding to each executor according to the identity recognition result, so as to judge whether the area permissions of the executor allow entry into the work area;

[0009] When the area permission of the executor allows entry into the work area, perform confidentiality detection and urgency detection on the application content of the current permit to obtain the confidentiality detection result and the urgency detection result;

[0010] According to the confidentiality detection result and the urgency detection result, determine whether the permit approval process meets the approval permissions of other platforms; where meeting the approval permissions of other platforms means that platforms other than the unified nuclear power plant management platform have the permission to approve the permit approval process;

[0011] When the permit approval process meets the approval permissions of other platforms, obtain the platform review results of each approval node by other platforms corresponding to the approval permissions of other platforms, and confirm the end of the permit approval process when all the platform review results indicate that each approval node has passed.

[0012] A cross-platform nuclear power plant permit process approval device, comprising:

[0013] A request content recognition module, configured to receive a permit application request initiated by an executor on the unified nuclear power plant management platform according to the permit approval process, and perform content recognition on the current permit and attachments in the permit application request to obtain the application content and the executor image;

[0014] An application information detection module, configured to perform information detection operations on the application content, and the information detection operations include: extracting the work area and work duration in the application content, performing nuclear radiation detection on the work area to obtain the nuclear radiation dose, and filling the nuclear radiation dose into the current permit; and detecting the work duration to obtain a duration detection result, and filling the duration detection result into the current permit;

[0015] An image identity recognition module, configured to identify the identity of the executor image, and determine the area permissions corresponding to each executor according to the identity recognition result, so as to judge whether the area permissions of the executor allow entry into the work area;

[0016] An application content detection module, configured to perform confidentiality detection and urgency detection on the application content of the current permit to obtain the confidentiality detection result and the urgency detection result when the area permission of the executor allows entry into the work area;

[0017] The platform approval permission module is used to determine whether the license approval process meets the other platform approval permissions according to the confidentiality detection result and the urgency detection result; where meeting the other platform approval permissions means that platforms other than the unified nuclear power plant management platform have the permission to approve the license approval process.

[0018] The platform review result module is used to obtain the platform review results of each approval node by other platforms corresponding to the other platform approval permissions when the license approval process meets the other platform approval permissions, and confirm the end of the license approval process when all the platform review results indicate that each approval node has passed.

[0019] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is used to execute the above cross-platform nuclear power plant license process approval method.

[0020] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above cross-platform nuclear power plant license process approval method is implemented.

[0021] In the above cross-platform nuclear power plant license process approval method, device, equipment and medium, in the cross-platform nuclear power plant license process approval method of the present invention, by performing content recognition on the received license application request, the acquisition of the application content and the image of the executor, the execution of the information detection operation and the determination of the regional permissions are realized. Then, by detecting the confidentiality and urgency of the current license, the determination of the confidentiality detection result and the urgency detection result is realized, thereby realizing the judgment of the other platform approval permissions, and further realizing the cross-platform review of the license approval process, improving the approval efficiency of the license approval process. Further, all licenses are initiated on the unified nuclear power plant management platform, solving the problem of data non-interoperability between platforms resulting in omission of license approval. Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a flowchart of the cross-platform nuclear power plant license process approval method in an embodiment of the present invention;

[0024] Figure 2It is a schematic structural diagram of a cross-platform nuclear power plant license process approval device according to an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] The nuclear power work ticket circulation method provided in this embodiment can be applied in, for example, Figure 1 such an application environment, where the client communicates with the server. Among them, the client includes, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0028] In one embodiment, as Figure 1 shown, a cross-platform nuclear power plant license process approval method is provided. Taking the application of this method in the Figure 1 server as an example, the method includes the following steps:

[0029] S10: Receive the license application request initiated by the executor on the nuclear power plant unified management platform according to the license approval process, and perform content recognition on the current license and attachments in the license application request to obtain the application content and the executor's image.

[0030] It can be understood that the executor refers to the employee who executes the maintenance task or repair task. The license approval process refers to the process of verification and evaluation of specific matters by each company. The nuclear power plant unified management platform refers to a platform system that integrates the functions of platforms such as the EPM platform, business process management platform, fire load platform, and radioactive effluent management platform. The license application request refers to a request initiated on the nuclear power plant unified management platform to obtain a specific license or approval. The executor's image refers to the image of the task executor uploaded. The application content refers to the content used to describe the task to be executed.

[0031] Specifically, after receiving the target task, the executor queries the current license corresponding to the target task (i.e., the repair or maintenance task) on the unified management platform of the nuclear power plant. Then, the executor searches for the license approval process corresponding to the current license in the unified management platform of the nuclear power plant, enters the application information, and issues a license application request. After receiving the license application request initiated by the executor on the unified management platform of the nuclear power plant according to the license approval process, the server performs content recognition on the current license and attachments in the license application request, that is, recognizes the content in the current license through a text recognition model. First, the title of the current license is recognized, and then the content corresponding to the extracted title is recognized to obtain the application content. Also, that is, image detection is performed on the attachments. When the position of the face image is detected, the face image is extracted through an image segmentation network to obtain the executor image.

[0032] S20: Perform an information detection operation on the application content. The information detection operation includes: extracting the working area and working duration in the application content, performing nuclear radiation detection on the working area to obtain the nuclear radiation dose, and filling the nuclear radiation dose into the current license; and detecting the working duration to obtain a duration detection result and filling the duration detection result into the current license.

[0033] Understandably, the working area refers to the area where the target task is executed in the license. For example, different areas are divided with the nuclear reactor as the center. The working duration refers to the time required for the executor to complete the target task. The current license refers to the license corresponding to the license application request.

[0034] Specifically, after obtaining the application content, the working area and working duration in the application content are extracted through keyword recognition. Then, the nuclear radiation dose of the working area is queried in the regional radiation table, and the queried nuclear radiation dose is filled into the current license. That is, the nuclear radiation dose can be filled into the remarks to facilitate the executor to receive the corresponding radiation protection equipment. Also, the working duration is detected, that is, the historical task corresponding to the target task is queried in the historical data, and the historical duration corresponding to the historical task is determined. The historical duration and the working duration are compared to obtain a duration detection result, and the duration detection result is filled into the current license to facilitate the executor to check whether the working duration allows the task to be completed.

[0035] S30: Perform identity recognition on the executor image, and determine the regional permissions corresponding to each executor according to the identity recognition result to judge whether the regional permissions of the executor allow entry into the working area.

[0036] Understandably, regional permissions refer to the access permissions for different work areas divided according to different personnel levels. The identity recognition result is used to represent the employee level of the executing personnel.

[0037] Specifically, obtain an image segmentation model and perform background segmentation on the image of the executing personnel, that is, extract features from the images of the executing personnel at different scales through the u-net network, and perform feature fusion and classification on the features of downsampling and upsampling through skip connections, so as to extract the personnel image. Then, extract the facial features in the personnel image through the image recognition model, that is, extract the facial features of the personnel image through the residual network and the attention mechanism (such as introducing an explicit spatial prior and an attention decomposition form to improve the performance of the self-attention mechanism), so as to obtain the extracted features. Next, perform identity recognition on the extracted features based on the fully connected layer of the image recognition model, so as to obtain the identity recognition result. Further, query the regional permissions corresponding to the executing personnel in the permission level table according to the identity recognition result, and detect whether the regional permissions include work permissions, so as to judge whether the regional permissions of the executing personnel allow entry into the work area.

[0038] S40: When the regional permissions of the executing personnel allow entry into the work area, perform confidentiality detection and urgency detection on the application content of the current license to obtain a confidentiality detection result and an urgency detection result.

[0039] Understandably, the confidentiality detection result refers to the conclusion obtained after evaluating the confidentiality of the application content, and is used to represent the size of the confidentiality score and the preset confidentiality threshold. The urgency detection result refers to the conclusion obtained after evaluating the urgency of the application content, and is used to represent the size of the urgency score and the preset urgency threshold.

[0040] Specifically, when the regional permissions of the executing personnel allow entry into the work area, perform confidentiality detection and urgency detection on the application content of the current license, that is, first add the word representation, sentence representation, and position representation of the application content from the positive and negative directions respectively through the input layer of the bidirectional transformer network in the confidentiality detection model to obtain an input vector. Then, perform attention processing on the input vector through the self-attention mechanism respectively to obtain an attention vector. Finally, perform prediction on the attention vector through the fully connected layer to obtain the confidentiality score, and compare the confidentiality score with the preset threshold to obtain the confidentiality detection result. And, first perform semantic recognition on the application content through the semantic recognition module in the urgency detection model to obtain a semantic recognition result, and perform urgency evaluation on the semantic recognition result according to the prediction evaluation module in the urgency detection model to obtain the urgency score, and compare the urgency score with the preset threshold to obtain the urgency detection result.

[0041] S50: Determine whether the license approval process meets the approval authority of other platforms according to the confidentiality detection result and the urgency detection result; where meeting the approval authority of other platforms means that platforms other than the unified nuclear power plant management platform have the authority to approve the license approval process.

[0042] Understandably, meeting the approval authority of other platforms means that platforms other than the unified nuclear power plant management platform have the authority to approve the license approval process.

[0043] In step S50, that is, determining whether the license approval process meets the approval authority of other platforms according to the confidentiality detection result and the urgency detection result, includes:

[0044] S501, when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is greater than or equal to the preset urgency threshold, confirm that the license approval process meets the desensitization approval authority of the SAP platform and the third-party platform, perform information desensitization on the application content of the current license to obtain new application content, and send the new application content to the SAP platform and the third-party platform at the same time, so that while the approver approves on the unified nuclear power plant management platform, approval is also allowed on the SAP platform and the third-party platform.

[0045] S502, when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is less than the preset urgency threshold, confirm that the license approval process meets the non-desensitization approval authority of the SAP platform, and send the application content of the current license to the SAP platform, so that the approver approves on the unified nuclear power plant management platform and the SAP platform.

[0046] S503, when the confidentiality detection result indicates that the confidentiality score is less than the preset confidentiality threshold, confirm that the license approval process meets the non-desensitization approval authority of the SAP platform and the third-party platform, and send the application content of the current license to the SAP platform and the third-party platform, so that the approver approves according to the application content on the unified nuclear power plant management platform, the SAP platform and the third-party platform.

[0047] Understandably, the other platforms include the SAP platform and third-party platforms; the approval authorities of the other platforms include desensitization approval authorities and non-desensitization approval authorities. The SAP (Systems Applications and Product) platform refers to a highly integrated enterprise information management system. The third-party platform refers to a platform other than the SAP platform and the unified nuclear power plant management platform, such as the DingTalk platform, etc. The desensitization approval authority refers to the authority for reviewing the application content after desensitization of other platforms. The non-desensitization approval authority refers to the authority for reviewing the non-desensitized application content of other platforms.

[0048] Specifically, when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is greater than or equal to the preset urgency threshold, that is, when the confidentiality level is high and the task is urgent, it is confirmed that the license approval process meets the desensitization approval authorities of the SAP platform and the third-party platforms. Then, the application content of the current license is desensitized, that is, the sensitive information in the application content is eliminated, so as to obtain the new application content. And the new application content is sent to the SAP platform and the third-party platforms at the same time, so that the approvers at each approval node can approve according to the new application content while approving on the unified nuclear power plant management platform, and can also approve on the SAP platform and the third-party platforms.

[0049] Next, when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is less than the preset urgency threshold, that is, when the confidentiality level is high and the task is not urgent, it is confirmed that the license approval process meets the non-desensitization approval authority of the SAP platform, and the application content of the current license is directly sent to the SAP platform, so that the approvers at each approval node can approve according to the application content while approving on the unified nuclear power plant management platform and the SAP platform. Further, when the confidentiality detection result indicates that the confidentiality score is less than the preset confidentiality threshold, that is, when the confidentiality level is low, it is confirmed that the license approval process meets the non-desensitization approval authorities of the SAP platform and the third-party platforms, and the application content of the current license is directly sent to the SAP platform and the third-party platforms, so that the approvers at each approval node can approve according to the application content while approving on the unified nuclear power plant management platform, the SAP platform and the third-party platforms.

[0050] In this embodiment, according to the meanings represented by the confidentiality detection result and the urgency detection result, the judgment of the desensitization approval authority of the platform is realized, thereby realizing the determination of the approval platform authority, and further realizing the determination of the approval authority of other platforms.

[0051] S60: When the license approval process meets the approval permissions of other platforms, obtain the platform review results of each approval node by the other platforms corresponding to the approval permissions of the other platforms, and when all the platform review results indicate that each approval node has passed, confirm the end of the license approval process.

[0052] Understandably, the approval node refers to the review node in the license approval process, which is used to represent the progress of the process approval. The platform review result refers to the review result of the approval node on the platform corresponding to the platform approval permission. For example, pass or reject, reject to the previous level, or reject to the start node, etc.

[0053] Specifically, after obtaining the approval permissions of other platforms, parse the approval permissions of other platforms to obtain the platforms that can review the license application request, and synchronize the license application request to the platform corresponding to the platform review result, so that the approver can perform node approval on the license application request in the other platforms corresponding to the approval permissions of other platforms, thereby obtaining the platform review results corresponding to each approval node. Among them, when one of the platform review results fails or is rejected, re-approve after modification until all the platform review results indicate that each approval node has passed, issue the license, and confirm the end of the license approval process.

[0054] In the cross-platform nuclear power plant license process approval method of the present invention, by performing content recognition on the received license application request, the acquisition of the application content and the image of the executor, the execution of the information detection operation, and the determination of the regional permissions are realized. Then, by detecting the confidentiality and urgency of the current license, the determination of the confidentiality detection result and the urgency detection result is realized, thereby realizing the judgment of the approval permissions of other platforms, and further realizing the cross-platform review of the license approval process, improving the approval efficiency of the license approval process. Further, all licenses are initiated on the unified management platform of the nuclear power plant, solving the problem of data non-interoperability between platforms, resulting in omission of license approval.

[0055] In an embodiment, before the step S10, that is, before performing content recognition on the current license and attachments in the license application request, it further includes:

[0056] S101: Perform information statistics on all current licenses in the unified management platform of the nuclear power plant to obtain an information statistics result.

[0057] S102: Perform associated approval detection on all licenses in the information statistics result and the current license through the process information in the current license to determine whether there are other licenses for which the current license is associated for approval.

[0058] S103. When there are other licenses associated with the current license for approval, establish approval association information between the current license and the other licenses to determine the approval nodes where the current license and the other licenses are mutually associated and allow simultaneous approval.

[0059] Understandably, the information statistics result refers to the statistical result of the number of licenses for each type, each group, and each approval node. Other licenses associated with the current license for approval refer to those that are associated with the current license, such as an earthwork permit and a tool collection permit.

[0060] Specifically, before identifying the content of the current license and its attachments in the license application request, perform information statistics on all current licenses in the nuclear power plant unified management platform, that is, respectively count the number of licenses for each license type, each executor, each process group, and the approval node where the license is located, so as to obtain the information statistics result. Then, perform an associated approval detection between all licenses in the information statistics result and the current license through the process information in the current license, that is, perform an associated detection between all licenses and the current license through the process name and the executor in the process information, that is, find all licenses applied by the executor, and then perform an associated detection between the process name and the current license, so as to determine whether there is an association between other licenses applied by the executor and the current license, and further determine whether there are other licenses associated with the current license for approval.

[0061] Furthermore, when there are other licenses associated with the current license for approval, establish approval association information between the current license and the other licenses, so as to determine the approval nodes where the current license and the other licenses are mutually associated and allow simultaneous approval, so that when the approver approves the current license, the approver can also approve other licenses at the approval nodes that are mutually associated and allow simultaneous approval.

[0062] In this embodiment, by performing information statistics on all current licenses, the acquisition of the information statistics result is achieved, thereby realizing the judgment of whether there are other licenses associated with the current license for approval, and further realizing the determination of the approval nodes that are mutually associated and allow simultaneous approval, improving the approval efficiency of the license, and avoiding the problem of being unable to execute tasks due to the lack of licenses.

[0063] In one embodiment, in step S30, that is, perform identity recognition on the executor image and determine the area permissions corresponding to each executor according to the identity recognition result to judge whether the area permissions of the executor allow entry into the work area, including:

[0064] S301. Extract features of the operator image through the backbone network in the image recognition model to obtain image features of different scales.

[0065] S302. Perform feature fusion processing on the image features of different scales through the fusion network in the image recognition model to obtain fusion features.

[0066] S303. Perform image prediction on the fusion features through the prediction network in the image recognition model to obtain an identity recognition result.

[0067] S304. According to the identity recognition result, determine the area permissions corresponding to each operator, and compare the area permissions with the entry permissions of the work area to obtain a comparison result.

[0068] S305. When the comparison result indicates that the area permissions include the entry permissions of the work area, determine that the operator is allowed to enter the work area.

[0069] S306. When the comparison result indicates that the area permissions do not include the entry permissions of the work area, determine that the operator is not allowed to enter the work area.

[0070] Understandably, the image recognition model refers to a model used to recognize the operator image, which is improved based on yolov8. Image features refer to the descriptive attributes extracted from the operator image. Fusion features refer to the features obtained by splicing features of different dimensions.

[0071] Specifically, after obtaining the operator image, obtain the image recognition model from the database, and input the operator image into the image recognition model. Extract features of the operator image through the backbone network in the image recognition model, that is, perform convolution processing on the operator image through two-dimensional convolution, normalization, and SiLU activation function in the convolution module to reduce the dimension and enhance the nonlinear ability, so as to obtain convolution features. Then, perform feature extraction on the convolution features through the C2f module, that is, first reduce the number of channels, then extract features through convolution, and use residual connection to splice the input and output, and finally restore the number of channels to obtain image features. Then, extract image features of different scales through the convolution module and the C2f module. Among them, after the last convolution module and the C2f module, perform continuous maximum pooling and residual connection on the image features of the previous dimension through the SPPF module to obtain image features of different scales.

[0072] Furthermore, the image feature fusion network in the image recognition model performs feature fusion processing on image features of different scales, that is, the image features of the last dimension are upsampled and fused with the image features of the previous dimension to obtain the first fusion feature, and the first fusion feature is passed through the C2f layer and upsampled and fused with the image features of the previous dimension to obtain the first-dimensional feature. The first-dimensional feature is fused with the first fusion feature through the convolutional layer to obtain the second fusion feature, the second fusion feature is passed through the C2f layer to obtain the second-dimensional feature, the second-dimensional feature is fused with the image features of the last dimension through the convolutional layer to obtain the third fusion feature, and the third fusion feature is passed through the C2f layer to obtain the third-dimensional feature. Finally, the first-dimensional feature, the second-dimensional feature, and the third-dimensional feature are concatenated through residual connection to obtain the fusion feature.

[0073] Next, the prediction network in the image recognition model performs image prediction on the fusion feature, that is, performs identity prediction on the fusion feature through the fully connected layer to obtain the identity recognition result corresponding to the executor's image. Then, the regional permission of the executor is queried in the permission data table through the identity recognition result. And compare the regional permission with the entry permission of the working area, that is, compare the permission levels of the regional permission and the working area permission to obtain the comparison result. Finally, when the comparison result indicates that the regional permission includes the entry permission of the working area, it is determined that the executor is allowed to enter the working area; when the comparison result indicates that the regional permission does not include the entry permission of the working area, it is determined that the executor is not allowed to enter the working area.

[0074] In this embodiment, the image recognition model is used to recognize the executor's image, realizing the recognition of the executor's identity, thereby realizing the determination of the regional permission corresponding to the executor, and further realizing the judgment of whether the executor is allowed to enter the working area.

[0075] In one embodiment, in step S40, that is, performing confidentiality detection and urgency detection on the application content of the current license to obtain a confidentiality detection result and an urgency detection result, including:

[0076] S401, obtain an information detection model and input the application content of the current license into the information detection model.

[0077] S402, perform confidentiality detection on the application content through the confidentiality recognition module in the information detection model to obtain a confidentiality score, and compare the confidentiality score with a preset confidentiality threshold to obtain a confidentiality detection result.

[0078] S403. The urgency of the application content is detected by the emergency recognition module in the information detection model to obtain an urgency score, and the urgency score is compared with a preset urgency threshold to obtain an urgency detection result.

[0079] Understandably, the information detection model refers to a model used to evaluate confidentiality and urgency. The confidentiality score is used to evaluate the level of confidentiality. The urgency score is used to characterize the urgency of the request.

[0080] Specifically, when the regional permission of the executor allows entry into the working area, the information detection model is obtained, and the application content of the current license is input into the information detection model. Then, the confidentiality of the application content is detected by the confidentiality recognition module in the information detection model. That is, the first detection network performs a matching query on the keywords in the application content in a preset confidentiality keyword library. If the confidentiality keyword library contains synonyms of the keywords in the application content, the keywords in the application content found in the query are determined as confidentiality keywords, and according to all the confidentiality keywords in the application content and the weights corresponding to each confidentiality keyword, the confidentiality score corresponding to the application content is determined.

[0081] Among them, the confidentiality of the application content can be determined according to the corresponding relationship between the preset confidentiality threshold and the confidentiality score. If the confidentiality score is a value greater than 0 and less than 1, when the confidentiality score is greater than 0.8, the confidentiality is determined as first-level confidentiality; when the confidentiality score is greater than 0.6 and not greater than 0.8, the confidentiality is determined as second-level confidentiality; when the confidentiality score is greater than 0.4 and not greater than 0.6, the confidentiality is determined as third-level confidentiality; when the confidentiality score is greater than 0.2 and not greater than 0.4, the confidentiality is determined as fourth-level confidentiality; when the confidentiality score is greater than 0 and not greater than 0.2, the confidentiality is determined as fifth-level confidentiality; if the confidentiality score is 0, it is determined as non-confidential.

[0082] Further, the emergency detection module in the information detection model is used to detect the emergency of the application content. That is, first, the extraction network is used to extract features of different scales from the application content, so as to obtain extraction features of different scales. Then, the attention mechanism is used to perform attention processing on the extraction features of different scales. That is, first, through multiple groups of attention processing, the Q vector, K vector, and V vector corresponding to the extraction features are projected through multiple different linear transformations. Finally, different attention results are concatenated to obtain a combined vector. The combined vector is normalized to avoid the degradation of the vector after multiple layers of attention processing. Then, the normalized combined vector is non-linearly transformed through the feedforward neural network in the fully connected layer, that is, the normalized combined vector is activated, and then the activated combined vector is linearly transformed to map the activated combined vector to a high-dimensional space. After residual processing and repeating the above process a preset number of times, the semantic recognition result corresponding to the application content can be obtained. Then, according to the preset scoring rule, the emergency score is calculated for the semantic recognition result to obtain an emergency score. Finally, the emergency score is compared with the preset emergency threshold to obtain the emergency detection result.

[0083] In this embodiment, different modules in the information detection model are used to perform confidentiality detection and emergency detection on the application content respectively, so as to obtain the confidentiality score and the emergency score. By comparing the obtained scores with the preset thresholds, the confidentiality detection result and the emergency detection result are determined, and then the confidentiality and emergency of the application content are evaluated.

[0084] In one embodiment, the other platforms include the SAP platform and the third-party platform; the approval permissions of the other platforms include desensitization approval permissions and non-desensitization approval permissions;

[0085] In one embodiment, in step S501, that is, performing information desensitization on the application content of the current license to obtain new application content, includes:

[0086] S5011, the information recognition module in the information desensitization model is used to identify sensitive information in the application content of the current license to obtain sensitive information.

[0087] S5012, the information desensitization module in the information desensitization model is used to desensitize the sensitive information to obtain the desensitized application content.

[0088] S5013, the desensitization verification module in the information desensitization model is used to verify the desensitized application content to obtain a desensitization verification result.

[0089] S5014, when the desensitization verification result indicates that no sensitive information is recognized, the desensitized application content is determined as the new application content.

[0090] Understandably, sensitive information refers to data or content that cannot be known to the outside world. For example, core technologies, etc. The desensitization verification result is used to characterize whether sensitive information is recognized. The new application content refers to the content text after masking or eliminating sensitive information.

[0091] Specifically, after obtaining the application content, an information desensitization model is acquired, and the application content is input into the information desensitization model. Then, the information recognition module in the information desensitization model performs sensitive information recognition on the application content of the current license. That is, the application content is first encoded to obtain a text vector, and then entity recognition and entity position annotation are performed on the text vector through the entity recognition layer to obtain text entities and entity positions. Next, the text entities are matched with the keywords in the sensitive word library. When the match is successful, the text entities that match the keywords are determined as sensitive information, and the entity positions of non-sensitive information are deleted, thus retaining the entity positions of sensitive information. Then, the information desensitization module in the information desensitization model performs desensitization processing on the sensitive information. That is, by learning the desensitization ability during model training, the sensitive information in the application content is masked or eliminated based on the entity positions of the sensitive information, thereby obtaining the desensitized application content. For example, when desensitizing name-type data, the text replacement method is used to replace the text in the original name with the number 1; when desensitizing numerical-type data, the masking method is used to cover part of the original value, or the formula transformation method is used to obtain a new value by transforming the original value through a formula.

[0092] Furthermore, the desensitization verification module in the information desensitization model performs desensitization verification on the desensitized application content. That is, first, the desensitized application content is text-segmented through a segmentation network to obtain the text line content of each line. Then, each text line content is embedded through the input layer to obtain a content vector corresponding to each text line content. Next, multi-scale feature extraction is performed on each content vector through a convolutional network, that is, feature extraction of different scales is performed on the content vector, and the input and output of each layer are connected through a residual connection for the input of the next layer, thereby obtaining features of different scales. Then, the features of different scales are spliced and fused to obtain a scale fusion feature. Finally, sensitive word prediction is performed on the scale fusion feature through a fully connected layer to obtain the desensitization verification result. When the desensitization verification result indicates that sensitive information is recognized, the desensitized application content is re-desensitized and verified until the desensitization verification result indicates that no sensitive information is recognized, and the desensitized application content is determined as the new application content.

[0093] In this embodiment, the information recognition of the application content is carried out through the information desensitization model, the acquisition of sensitive information is realized, thus the desensitization of sensitive information is realized, and then the verification of the desensitized application content is realized, the acquisition of new application content is realized, information leakage is avoided, and the safety of nuclear power plant information is ensured.

[0094] In one embodiment, in step S50, that is, after obtaining the platform review results corresponding to the approval nodes of the license approval process and before confirming the end of the license approval process, it further includes:

[0095] S504, when all the platform review results indicate approval, perform a watermark requirement detection on the current license to obtain a watermark detection result.

[0096] S505, when the watermark detection result indicates adding a watermark, add a watermark with a preset style corresponding to the watermark addition parameters to the current license.

[0097] It can be understood that the watermark detection result is used to indicate whether a watermark is added to the current license. The watermark with a preset style refers to watermarks of different styles, for example, the names of each company under the group, etc. The watermark addition parameters refer to the parameters based on which different watermarks are added, such as parameters like license type, grouping type, etc.

[0098] Specifically, when all the platform review results indicate approval, perform a watermark requirement detection on the current license, that is, first determine the content type of the current license to obtain type information, and then, through the watermark addition table, perform a watermark requirement detection on the current license corresponding to the type information, that is, detect whether the watermark addition table contains the type name in the process information, or / and, detect whether the watermark addition table contains the confidentiality level of the current license, so as to obtain a watermark detection result. Then, when the watermark detection result indicates adding a watermark, determine the watermark addition parameters through the company to which the executor belongs in the current license, or the type name in the type information, and then, determine the watermark with a preset style corresponding to the watermark addition parameters, for example, query the watermark of the company to which the executor belongs in the watermark library, or the watermark of the hot work permit, or add the watermark of the executor's name, etc. Finally, add a watermark with a preset style to the current license.

[0099] In this embodiment, through the watermark requirement detection of the current license, the acquisition of the watermark detection result is realized, thus the watermark with a preset style corresponding to the watermark addition parameters is added to the current license, and then the flexible addition of watermarks according to the actual task is realized.

[0100] In one embodiment, after step S50, that is, after obtaining the platform review results corresponding to the approval nodes of the license approval process, it further includes:

[0101] S70, synchronize the platform review result to other platforms corresponding to the approval authorities of the other platforms, so that the executor and the approvers of each approval node can view the progress of the license approval process.

[0102] Understandably, the progress of the license approval process refers to the approval node where the license is located.

[0103] Specifically, after obtaining the platform review results corresponding to each approval node of the license approval process, synchronize the platform review results to other platforms corresponding to the platform approval authorities, that is, after the nuclear power plant unified management platform reviews this approval node, synchronize the review results to the SAP platform and / or the third-party platform, or after the SAP platform and / or the third-party platform reviews this approval node, synchronize the review results to the nuclear power plant unified management platform, so that the executor and the approvers of each approval node can view the progress of the license approval process. Among them, the other platforms for synchronizing the platform review results are determined according to the platform approval authorities. That is, in this embodiment, by synchronizing the review results to other platforms, data intercommunication between platforms is realized, the omission problem in the review process is avoided, and cross-platform review of the license approval process is realized, thereby improving the approval efficiency of the license approval process.

[0104] In one embodiment, before step S10, that is, before receiving the license application request initiated by the executor on the nuclear power plant unified management platform according to the license approval process, it further includes:

[0105] S801, receive the process information filled in the process configuration interface, and the process information includes process name, process description, process grouping, process attributes, process icons and attachments.

[0106] S802, obtain the process configuration model corresponding to the process information, parse the process configuration model, call the process approval middleware, obtain the approvers of each approval node in the preset order and determine the execution order of each approval node, and obtain the license approval process.

[0107] S803, perform a simulation test operation on the license approval process to confirm that the license approval process meets the execution conditions and publish the license approval process.

[0108] Understandably, the process information includes process name, process description, process grouping, process attributes, process icons and attachments. The process configuration model refers to the model used to configure the license approval process.

[0109] Specifically, the executor fills in the process information in the process configuration interface on the unified management platform of the nuclear power plant. Through the process name, process grouping, and process icon in the process information, the corresponding process configuration model is obtained. Then, the process configuration model is parsed to obtain the process controls corresponding to the approval process. Through the process approval middleware, the process controls are configured for the approval parties and execution order of each approval node in a preset order, thereby obtaining the license approval process. Further, a simulation test operation is performed on the license approval process, that is, a function test is performed at each review node to detect whether the function of the review node can be reviewed, and the progress synchronization function of other platforms is tested, thereby obtaining the simulation test results. Then, it is determined whether the license approval process meets the execution conditions according to the simulation test results. That is, when all functions are represented as passed in the simulation test results, it is confirmed that the license approval process meets the execution conditions, and the license approval process is released. When one or more functions are represented as failed in the simulation test results, it is confirmed that the license approval process does not meet the execution conditions, and the license approval process corresponding to the historical data is selected from the historical data through the process name, process grouping, and process icon, and the license approval process is released.

[0110] Among them, in another embodiment, when configuring each approval node, it is detected whether the process information contains the requirement to configure a sub-process for this approval node, that is, a sub-process is set on the approval node in the license approval process, and after the sub-process review is completed, the approval node in the license approval process can be reviewed. And it is detected whether a note function needs to be added to each review node so that the approval party can add annotation content during the review.

[0111] In this embodiment, through the received process information, the acquisition of the process configuration model is realized, thereby realizing the configuration of the license approval process and the simulation test operation, and further realizing the evaluation of whether the license approval process meets the execution conditions and the release of the license approval process.

[0112] In one embodiment, after step S802, that is, after obtaining the approval parties of each approval node in a preset order and determining the execution order of each approval node, it further includes:

[0113] S804, perform an association detection process on each approval node in the license approval process to determine whether each approval node meets the associated approval between multiple approval parties.

[0114] S805, when it is determined that the approval node meets the associated approval between multiple approval parties, configure that the approval node enters the next approval node when all approval parties have approved.

[0115] Specifically, after obtaining the approvers of each approval node in a preset order and determining the execution order of each approval node, correlation detection processing is performed on each approval node in the license approval process, that is, the approvers of each approval node in the license approval process are counted to obtain a quantity statistical result. Then, when it is determined that a certain approval node in the license approval process meets the associated approval among multiple approvers, that is, multiple approvers need to review this approval node simultaneously, when all approvers approve at this approval node, the next approval node is entered. That is, in this embodiment, by performing correlation detection processing on each approval node, the detection of whether each approval node meets the associated approval among multiple approvers is realized, and furthermore, the review configuration of multiple approvers for this approval node is realized.

[0116] In one embodiment, after step S803, that is, after publishing the license approval process, it further includes:

[0117] S806, recommending other associated licenses according to the recommendation module in the process configuration model and receiving the feedback selection information.

[0118] S807, parsing the selection information, and when the selection information includes a creation request for other licenses, creating a license approval process for other licenses associated with the current license.

[0119] It can be understood that the selection information refers to other associated licenses selected on the recommendation interface in the mobile terminal or other devices that can log in to the platform.

[0120] Specifically, after publishing the license approval process, other associated licenses are recommended through the recommendation module in the process configuration model, that is, the recommendation model recommends other licenses related to the published license approval process to the executor according to the process information in the published license approval process and in combination with historical data. Then, the selection information of the executor on the nuclear power plant unified management platform is received, that is, the executor selects the required license approval process on the license recommendation interface of the nuclear power plant unified management platform. Next, the selection information is parsed to determine other licenses in the selection information, and then the process configuration model is used to create a process for other licenses in the selection information to obtain a license approval process corresponding to other licenses, and a simulation test operation is performed on each license approval process. When the simulation test operation passes, it is confirmed that the license approval process meets the execution conditions, and the license approval process corresponding to each other license is published.

[0121] In this embodiment, by recommending other associated licenses to the applicant and creating a process based on the feedback selection information, the problem that a task cannot be completed due to the non-application of a certain license during the license application process is avoided, and thus the creation of the license approval process for other licenses is achieved.

[0122] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0123] In one embodiment, a cross-platform nuclear power plant license process approval device is provided. The cross-platform nuclear power plant license process approval device corresponds one-to-one with the cross-platform nuclear power plant license process approval method in the above embodiment. As Figure 2 shown, the cross-platform nuclear power plant license process approval device includes a request content recognition module 10, an application information detection module 20, an image identity recognition module 30, an application content detection module 40, a platform approval authority module 50, and a platform review result module 60. The detailed description of each functional module is as follows:

[0124] The request content recognition module 10 is configured to receive a license application request initiated by an executor on the unified management platform of the nuclear power plant according to the license approval process, and perform content recognition on the current license and attachments in the license application request to obtain the application content and the executor's image;

[0125] The application information detection module 20 is configured to perform information detection operations on the application content. The information detection operations include: extracting the working area and working duration from the application content, performing nuclear radiation detection on the working area to obtain the nuclear radiation dose, and filling the nuclear radiation dose into the current license; and detecting the working duration to obtain a duration detection result, and filling the duration detection result into the current license;

[0126] The image identity recognition module 30 is configured to perform identity recognition on the executor's image, and determine the area authority corresponding to each executor according to the identity recognition result to judge whether the executor's area authority allows entry into the working area;

[0127] The application content detection module 40 is configured to perform confidentiality detection and urgency detection on the application content of the current license when the executor's area authority allows entry into the working area, to obtain a confidentiality detection result and an urgency detection result;

[0128] The platform approval authority module 50 is used to determine whether the license approval process meets the other platform approval authorities according to the confidentiality detection result and the urgency detection result; where meeting the other platform approval authorities means that other platforms outside the unified nuclear power plant management platform have the authority to approve the license approval process.

[0129] The platform review result module 60 is used to obtain the platform review results of each approval node by other platforms corresponding to the other platform approval authorities when the license approval process meets the other platform approval authorities, and confirm the end of the license approval process when all the platform review results indicate that each approval node has passed.

[0130] Optionally, the image identity recognition module 30 includes:

[0131] The feature extraction unit is used to extract features of the executor image through the backbone network in the image recognition model to obtain image features of different scales.

[0132] The fusion processing unit is used to perform feature fusion processing on the image features of different scales through the fusion network in the image recognition model to obtain fusion features.

[0133] The image prediction unit is used to perform image prediction on the fusion features through the prediction network in the image recognition model to obtain the identity recognition result.

[0134] The permission comparison unit is used to determine the area permissions corresponding to each executor according to the identity recognition result, and compare the area permissions with the access permissions of the work area to obtain a comparison result.

[0135] The allow entry unit is used to determine that the executor is allowed to enter the work area when the comparison result indicates that the area permissions include the access permissions of the work area.

[0136] The not allow entry unit is used to determine that the executor is not allowed to enter the work area when the comparison result indicates that the area permissions do not include the access permissions of the work area.

[0137] Optionally, the device further includes:

[0138] The information statistics module is used to perform information statistics on all current licenses in the unified nuclear power plant management platform to obtain an information statistics result.

[0139] The associated approval detection module is used to perform an associated approval detection on all licenses in the information statistics result and the current license through the process information in the current license to determine whether there are other licenses with associated approvals for the current license.

[0140] A node association approval module, which is used to establish approval association information between the current license and other licenses when there are other licenses with associated approvals for the current license, so as to determine approval nodes that are mutually associated between the current license and the other licenses and allow simultaneous approval.

[0141] Optionally, the application content detection module 40 includes:

[0142] A content input unit, which is used to obtain an information detection model and input the application content of the current license into the information detection model;

[0143] A confidentiality detection unit, which is used to perform confidentiality detection on the application content through a confidentiality recognition module in the information detection model to obtain a confidentiality score, and compare the confidentiality score with a preset confidentiality threshold to obtain a confidentiality detection result;

[0144] An urgency detection unit, which is used to perform urgency detection on the application content through an urgency recognition module in the information detection model to obtain an urgency score, and compare the urgency score with a preset urgency threshold to obtain an urgency detection result.

[0145] Optionally, the other platforms include the SAP platform and third-party platforms; the approval authorities of the other platforms include de-sensitization approval authorities and non-de-sensitization approval authorities;

[0146] The platform approval authority module 50 includes:

[0147] An information de-sensitization unit, which is used to confirm that the license approval process meets the de-sensitization approval authorities of the SAP platform and third-party platforms when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold and the urgency detection result indicates that the urgency score is greater than or equal to the preset urgency threshold, de-sensitize the application content of the current license to obtain new application content, and send the new application content to the SAP platform and third-party platforms simultaneously, so that while the approver approves on the nuclear power plant unified management platform, approval is also allowed on the SAP platform and the third-party platforms;

[0148] A first approval unit, which is used to confirm that the license approval process meets the non-de-sensitization approval authorities of the SAP platform when the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold and the urgency detection result indicates that the urgency score is less than the preset urgency threshold, and send the application content of the current license to the SAP platform, so that the approver approves on the nuclear power plant unified management platform and the SAP platform;

[0149] A second approval unit, configured to, when the confidentiality detection result indicates that the confidentiality score is less than the preset confidentiality threshold, confirm that the license approval process meets the non-desensitization approval permissions of the SAP platform and the third-party platform, and send the application content of the current license to the SAP platform and the third-party platform, so that the approver can approve according to the application content on the nuclear power plant unified management platform, the SAP platform and the third-party platform.

[0150] Optionally, the information desensitization unit includes:

[0151] A sensitive information recognition subunit, configured to recognize sensitive information from the application content of the current license through the information recognition module in the information desensitization model, to obtain sensitive information;

[0152] An information desensitization processing subunit, configured to desensitize the sensitive information through the information desensitization module in the information desensitization model, to obtain the desensitized application content;

[0153] A content desensitization verification subunit, configured to verify the desensitized application content through the desensitization verification module in the information desensitization model, to obtain a desensitization verification result;

[0154] A new application content subunit, configured to, when the desensitization verification result indicates that no sensitive information is recognized, determine the desensitized application content as the new application content.

[0155] Optionally, the device further includes:

[0156] A platform progress synchronization module, configured to synchronize the platform audit result to another platform corresponding to the approval permission of the other platform, so that the executor and the approver at each approval node can view the progress of the license approval process.

[0157] Optionally, the platform audit result module 60 further includes:

[0158] A watermark requirement detection unit, configured to detect the watermark requirement of the current license when all the platform audit results indicate approval, to obtain a watermark detection result;

[0159] A style watermark adding unit, configured to add a watermark with a preset style corresponding to the watermark adding parameters to the current license when the watermark detection result indicates that a watermark is to be added.

[0160] Optionally, the device further includes:

[0161] A process information input module, which is used to receive the process information filled in the process configuration interface, where the process information includes process name, process description, process grouping, process attributes, process icons, and attachments;

[0162] An approval process determination module, which is used to obtain a process configuration model corresponding to the process information, parse the process configuration model, call a process approval middleware, obtain the approvers of each approval node in a preset order and determine the execution order of each approval node, so as to obtain a license approval process;

[0163] A simulation test operation module, which is used to perform a simulation test operation on the license approval process to confirm that the license approval process meets the execution conditions and publish the license approval process.

[0164] Optionally, the approval process determination module further includes:

[0165] An association detection and processing unit, which is used to perform association detection and processing on each approval node in the license approval process to determine whether each approval node meets the associated approval among multiple approvers;

[0166] A configured associated approval unit, which is used to configure that when it is determined that the approval node meets the associated approval among multiple approvers, the approval node enters the next approval node when all approvers approve.

[0167] Optionally, the simulation test operation module further includes:

[0168] An other license recommendation unit, which is used to recommend associated other licenses according to the recommendation module in the process configuration model and receive the selected information feedback;

[0169] An other approval process unit, which is used to parse the selected information, and when the selected information includes a creation request for an other license, create a license approval process for an other license associated with the current license.

[0170] A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor is used to execute the cross-platform nuclear power plant license process approval method.

[0171] Specific limitations on computer devices, processors, and their respective units and modules can be referred to the limitations on the cross-platform nuclear power plant license process approval method in the above text, which will not be elaborated here. Each module in the above-mentioned processor can be implemented in whole or in part by software, hardware, and their combination. Understandably, the processor includes a processor, a memory, a network interface, and a database connected through a device bus. Each module of the processor can be embedded in or independent of the processor in the form of hardware, or stored in the memory in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0172] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 3 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating device, a computer program, and a database. The internal memory provides an environment for the operation of the operating device and the computer program in the non-volatile storage medium. The database is used to store the data used in the cross-platform nuclear power plant license process approval method in the above-mentioned embodiment. The network interface is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a cross-platform nuclear power plant license process approval method.

[0173] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned cross-platform nuclear power plant license process approval method is implemented.

[0174] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0176] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A cross-platform approval method for the nuclear power plant license process, characterized in that, Including: Receiving a license application request initiated by an executor on the unified management platform of the nuclear power plant according to the license approval process, and performing content recognition on the current license and attachments in the license application request to obtain application content and an executor image; Performing an information detection operation on the application content, where the information detection operation includes: extracting the working area and working duration in the application content, performing nuclear radiation detection on the working area to obtain a nuclear radiation dose, and filling the nuclear radiation dose into the current license; and, detecting the working duration to obtain a duration detection result and filling the duration detection result into the current license; Performing identity recognition on the executor image, and determining the area permissions corresponding to each executor according to the identity recognition result to determine whether the area permissions of the executor allow entry into the working area; When the area permissions of the executor allow entry into the working area, performing confidentiality detection and urgency detection on the application content of the current license to obtain a confidentiality detection result and an urgency detection result; According to the confidentiality detection result and the urgency detection result, determining whether the license approval process meets the approval permissions of other platforms; where meeting the approval permissions of other platforms means that platforms other than the unified management platform of the nuclear power plant have the permission to approve the license approval process; When the license approval process meets the approval permissions of other platforms, obtaining the platform review results of each approval node by the other platforms corresponding to the approval permissions of other platforms, and when all the platform review results indicate that each approval node has passed, confirming the end of the license approval process.

2. The cross-platform nuclear power plant license process approval method according to claim 1, characterized in that The performing identity recognition on the executor image, and determining the area permissions corresponding to each executor according to the identity recognition result to determine whether the area permissions of the executor allow entry into the working area includes: Performing feature extraction on the executor image through the backbone network in the image recognition model to obtain image features of different scales; Performing feature fusion processing on the image features of different scales through the fusion network in the image recognition model to obtain fusion features; Performing image prediction on the fusion features through the prediction network in the image recognition model to obtain an identity recognition result; According to the identity recognition result, determining the area permissions corresponding to each executor, and comparing the area permissions and the entry permissions of the working area to obtain a comparison result; When the comparison result indicates that the area permissions include the entry permissions of the working area, determining that the executor is allowed to enter the working area; When the comparison result indicates that the area permissions do not include the entry permissions of the working area, determining that the executor is not allowed to enter the working area.

3. The cross-platform nuclear power plant license process approval method according to claim 1, characterized in that, Before performing content recognition on the current license and attachments in the license application request, it further includes: Performing information statistics on all current licenses in the unified management platform of the nuclear power plant to obtain an information statistics result; Perform an associated approval detection on all licenses in the information statistics result and the current license through the process information in the current license to determine whether there are other licenses for associated approval of the current license; When there are other licenses for associated approval of the current license, establish approval association information between the current license and the other licenses to determine the approval nodes where the current license and the other licenses are mutually associated and allow simultaneous approval.

4. The cross-platform nuclear power plant license process approval method according to claim 1, wherein, Perform confidentiality detection and urgency detection on the application content of the current license to obtain a confidentiality detection result and an urgency detection result, including: Obtain an information detection model and input the application content of the current license into the information detection model; Perform confidentiality detection on the application content through the confidentiality recognition module in the information detection model to obtain a confidentiality score, and compare the confidentiality score with a preset confidentiality threshold to obtain a confidentiality detection result; Perform urgency detection on the application content through the urgency recognition module in the information detection model to obtain an urgency score, and compare the urgency score with a preset urgency threshold to obtain an urgency detection result.

5. The cross-platform nuclear power plant license process approval method according to claim 4, wherein, The other platforms include the SAP platform and the third-party platform; The approval permissions of the other platforms include desensitization approval permissions and non-desensitization approval permissions; Determine whether the license approval process meets the approval permissions of the other platforms according to the confidentiality detection result and the urgency detection result, including: When the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is greater than or equal to the preset urgency threshold, confirm that the license approval process meets the desensitization approval permissions of the SAP platform and the third-party platform, perform information desensitization on the application content of the current license to obtain a new application content, and send the new application content to the SAP platform and the third-party platform simultaneously, so that the approver is allowed to approve on the SAP platform and the third-party platform while approving on the unified management platform of the nuclear power plant; When the confidentiality detection result indicates that the confidentiality score is greater than or equal to the preset confidentiality threshold, and the urgency detection result indicates that the urgency score is less than the preset urgency threshold, confirm that the license approval process meets the non-desensitization approval permissions of the SAP platform, and send the application content of the current license to the SAP platform, so that the approver approves on the unified management platform of the nuclear power plant and the SAP platform; When the confidentiality detection result indicates that the confidentiality score is less than the preset confidentiality threshold, confirm that the license approval process meets the non-desensitization approval permissions of the SAP platform and the third-party platform, and send the application content of the current license to the SAP platform and the third-party platform, so that the approver approves according to the application content on the unified management platform of the nuclear power plant, the SAP platform and the third-party platform.

6. The cross-platform nuclear power plant license process approval method according to claim 5, characterized in that Perform information desensitization on the application content of the current license to obtain a new application content, including: The sensitive information is identified from the application content of the current license through the information recognition module in the information de - sensitization model; The sensitive information is de - sensitized through the information de - sensitization module in the information de - sensitization model to obtain the de - sensitized application content; The de - sensitized application content is verified for de - sensitization through the de - sensitization verification module in the information de - sensitization model to obtain the de - sensitization verification result; When the de - sensitization verification result indicates that no sensitive information is identified, the de - sensitized application content is determined as the new application content.

7. The cross-platform nuclear power plant license process approval method according to claim 1, characterized in that After obtaining the platform review results corresponding to each approval node of the license approval process, it further includes: Synchronize the platform review results to other platforms corresponding to the approval permissions of other platforms, so that the executor and the approvers of each approval node can view the progress of the license approval process.

8. The cross-platform nuclear power plant license process approval method according to claim 1, wherein Before confirming the end of the license approval process after obtaining the platform review results corresponding to each approval node of the license approval process, it further includes: When all the platform review results indicate approval, the watermark requirement detection is performed on the current license to obtain the watermark detection result; When the watermark detection result indicates adding a watermark, a watermark with a preset style corresponding to the watermark addition parameters is added to the current license.

9. The cross-platform nuclear power plant license process approval method according to claim 1, characterized in that, Before receiving the license application request initiated by the executor on the nuclear power plant unified management platform according to the license approval process, it further includes: Receive the process information filled in the process configuration interface, where the process information includes process name, process description, process group, process attributes, process icon, and attachments; Obtain the process configuration model corresponding to the process information, parse the process configuration model, call the process approval middleware, and obtain the approvers of each approval node and determine the execution order of each approval node in a preset order to obtain the license approval process; Perform a simulation test operation on the license approval process to confirm that the license approval process meets the execution conditions and publish the license approval process.

10. The cross-platform nuclear power plant license process approval method according to claim 9, characterized in that, After obtaining the approvers of each approval node and determining the execution order of each approval node in a preset order, it further includes: Perform an association detection process on each approval node in the license approval process to determine whether each approval node meets the associated approval among multiple approvers; When it is determined that the approval node meets the associated approval among multiple approvers, configure the approval node to enter the next approval node when all approvers approve.

11. The cross-platform nuclear power plant license process approval method according to claim 9, characterized in that After publishing the license approval process, it further includes: Recommend associated other licenses according to the recommendation module in the process configuration model and receive the feedback selection information; Parse the selection information, and when the selection information includes a creation request for other licenses, create a license approval process for other licenses associated with the current license.

12. A cross-platform approval device for the nuclear power plant license process, characterized in that, It includes: A request content recognition module, configured to receive a license application request initiated by an executor on the unified management platform of a nuclear power plant according to the license approval process, and perform content recognition on the current license and attachments in the license application request to obtain application content and an executor image; An application information detection module, configured to perform information detection operations on the application content, where the information detection operations include: extracting a work area and a working duration from the application content, performing nuclear radiation detection on the work area to obtain a nuclear radiation dose, and filling the nuclear radiation dose into the current license; and detecting the working duration to obtain a duration detection result and filling the duration detection result into the current license; An image identity recognition module, configured to perform identity recognition on the executor image, and determine area permissions corresponding to each executor according to the identity recognition result to determine whether the area permissions of the executor allow entry into the work area; An application content detection module, configured to perform confidentiality detection and urgency detection on the application content of the current license when the area permissions of the executor allow entry into the work area to obtain a confidentiality detection result and an urgency detection result; A platform approval permission module, configured to determine whether the license approval process meets other platform approval permissions according to the confidentiality detection result and the urgency detection result; where meeting the other platform approval permissions means that other platforms outside the unified management platform of the nuclear power plant have the permission to approve the license approval process; A platform review result module, configured to obtain platform review results of other platforms corresponding to the other platform approval permissions for each approval node when the license approval process meets other platform approval permissions, and confirm the end of the license approval process when all the platform review results indicate that each approval node has passed; 13. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor is configured to execute the cross-platform nuclear power plant license process approval method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the cross-platform nuclear power plant license process approval method according to any one of claims 1 to 11.

Images