Nuclear power plant notification form generation method, device, computer equipment and storage medium
By receiving instructions, querying sample notification form and filling slots in the nuclear power plant notification form generation system, and combining the similarity matching of historical notification form, the information irregularities and redundancy in the generation of notification form in nuclear power plant notification form are solved, and the notification form is improved accuracy and database usage efficiency.
Patent Information
- Application Number
- CN202110490237.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-06
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-05-06
AI Technical Summary
In the prior art, there are irregular and errors in the information filling of notification forms for nuclear power plants, resulting in low accuracy of notification forms and easy to generate redundant same content.
By receiving notifications to generate instructions, query example notifications in the preset notification types library, use slot filling method to generate notifications to be detected, and match the similarity with historical notifications. If the similarity is less than the threshold, it is recorded as new and store notifications to avoid duplicate generation.
Improve the uniformity and accuracy of notification order generation, reduce the error rate, and avoid redundant data in notification order database.
Smart Images

Figure CN113343651B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of nuclear power plant information construction, and in particular to a method, device, computer equipment and storage medium for generating a nuclear power plant notification sheet. Background Art
[0002] When equipment in a nuclear power plant fails and needs to be detected and repaired, or when there is a demand for equipment, it is often necessary to fill out a nuclear power plant fault notification form, a demand notification form, etc. In the prior art, the above notification forms are generally filled out manually, and then the content of the paper version of the notification form is manually filled into the notification form system. The above notification form generation method has the following shortcomings: the manual filling method of the notification form has non-standard information filling, and it is easy to make mistakes, which leads to erroneous notification form data when the information is entered into the notification form system, reducing the accuracy of the notification form; and the manual filling method is prone to different staff members generating notification forms with the same content, which causes redundancy in the notification form system. Summary of the invention
[0003] The embodiment of the present invention provides a method, device, computer equipment and storage medium for generating a nuclear power plant notification form, so as to solve the problem of low accuracy in generating a nuclear power plant notification form.
[0004] A method for generating a nuclear power plant notification sheet, comprising:
[0005] Receiving a nuclear power plant notification form generation instruction; the nuclear power plant notification form generation instruction includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag;
[0006] Querying a sample notification corresponding to the notification type from a preset notification type library, and filling the notification information into the sample notification using a slot filling method to generate a notification to be tested;
[0007] Obtaining all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database;
[0008] Perform similarity matching between the notification to be detected and each of the historical notifications to obtain a notification similarity value corresponding to the notification to be detected and each of the historical notifications;
[0009] When the similarity values of the notification to be detected and the notifications corresponding to the historical notifications are both less than a preset similarity threshold, the notification to be detected is recorded as a new nuclear power plant notification;
[0010] The new nuclear power plant notification form is stored in the preset nuclear power plant notification form database.
[0011] A nuclear power plant notification sheet generating device, comprising:
[0012] A notification form generation instruction receiving module, used to receive a notification form generation instruction of a nuclear power plant; the notification form generation instruction of the nuclear power plant includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag;
[0013] A slot filling module, used to query a sample notification corresponding to the notification type from a preset notification type library, and fill the notification information into the sample notification using a slot filling method to generate a notification to be tested;
[0014] A historical notification acquisition module is used to acquire all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database;
[0015] A similarity matching module, used for performing similarity matching between the notification to be detected and each of the historical notifications, and obtaining a notification similarity value corresponding to the notification to be detected and each of the historical notifications;
[0016] A notification recording module, configured to record the notification to be detected as a new nuclear power plant notification when the notification similarity values corresponding to the notification to be detected and each of the historical notifications are less than a preset similarity threshold;
[0017] The notification storage module is used to store the new nuclear power plant notification in the preset nuclear power plant notification database.
[0018] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for generating a nuclear power plant notification sheet when executing the computer program.
[0019] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a nuclear power plant notification form is implemented.
[0020] The above-mentioned nuclear power plant notification form generation method, device, computer equipment and storage medium, the method receives a nuclear power plant notification form generation instruction; the nuclear power plant notification form generation instruction includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location label; a sample notification form corresponding to the notification form type is queried from a preset notification form type library, and the notification form information is filled into the sample notification form using a slot filling method to generate a notification form to be detected; all historical notification forms with the nuclear power plant function location label are obtained from a preset nuclear power plant notification form database; the notification form to be detected is matched with each of the historical notification forms for similarity to obtain a notification form similarity value corresponding to the notification form to be detected and each of the historical notification forms; when the notification form similarity values corresponding to the notification form to be detected and each of the historical notification forms are both less than a preset similarity threshold, the notification form to be detected is recorded as a new nuclear power plant notification; and the new nuclear power plant notification form is stored in the preset nuclear power plant notification form database.
[0021] The present invention can regularize the notification information of each type of notification by setting example notifications corresponding to the notification types, thereby improving the uniformity of notification generation and reducing the error rate of notification generation; further, after generating the notification to be tested, it is necessary to compare the notification to be tested with the historical notifications in the preset nuclear power plant notification database to avoid repeated generation of the same notification, thereby improving the effectiveness of the use of the preset nuclear power plant notification database. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0023] Figure 1 It is a schematic diagram of an application environment of a method for generating a notification form for a nuclear power plant in one embodiment of the present invention;
[0024] Figure 2 is a flow chart of a method for generating a nuclear power plant notification sheet in one embodiment of the present invention;
[0025] Figure 3 It is a principle block diagram of a nuclear power plant notification sheet generating device in one embodiment of the present invention;
[0026] Figure 4 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION
[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0028] The method for generating a nuclear power plant notification form provided in an embodiment of the present invention can be applied as follows: Figure 1 Specifically, the nuclear power plant notification form generation method is applied in a nuclear power plant notification form generation system, and the nuclear power plant notification form generation system includes: Figure 1 The client and server shown in the figure communicate with each other through the network to solve the problem of low accuracy of generating notification sheets for nuclear power plants. The client, also known as the user end, refers to a program corresponding to the server that provides local services to customers. The client can be installed on, but not limited to, various personal computers, laptops, smart phones, tablets, and portable wearable devices. The server can be implemented as an independent server or a server cluster consisting of multiple servers.
[0029] In one embodiment, if Figure 2 As shown, a method for generating a nuclear power plant notification form is provided, and the method is applied in Figure 1 The server in the example is used as an example to illustrate the process, including the following steps:
[0030] S10: receiving a nuclear power plant notification form generation instruction; the nuclear power plant notification form generation instruction includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag;
[0031] It can be understood that the nuclear power plant notification form generation instruction can be initiated by the nuclear power plant staff through the mobile device, or it can be automatically generated after the nuclear power plant staff enters the notification form type and notification form information. Among them, the notification form type refers to the classification category of the nuclear power plant notification form. Optionally, the notification form type includes fault type, demand type, coordination type or engineering type, etc.; the notification form information includes but is not limited to the nuclear power plant function location label, specific fault type or specific demand, contact person, contact phone number, etc. Among them, the nuclear power plant function location label indicates the equipment information in each area of the nuclear power plant, and one nuclear power plant equipment is associated with one nuclear power plant function location label.
[0032] S20: searching for a sample notification corresponding to the notification type from a preset notification type library, and filling the notification information into the sample notification by using a slot filling method to generate a notification to be tested;
[0033] It can be understood that for each notification type, there is a corresponding example notification, and there are multiple slots to be filled in the example notification, and each filled slot corresponds to different notification information. Then, after receiving the nuclear power plant notification generation instruction sent by the preset recipient, the example notification corresponding to the notification type is queried from the preset notification type library. For example, each type of example notification has a corresponding associated notification type tag. Then, after the example notification of the same notification type is queried, the notification information is filled with the corresponding information in the slot of the example notification using the slot filling method to generate a notification to be detected.
[0034] In one embodiment, step S20 includes:
[0035] Inputting the notification information into a preset nuclear power plant entity recognition model to perform entity recognition on the notification information to obtain each nuclear power plant entity in the notification information;
[0036] It can be understood that the nuclear power plant entity recognition model is used to extract the nuclear power plant entity in the notification information. For example, the nuclear power plant entity can be such as the notification applicant's name entity, contact information entity, nuclear power plant equipment name entity, etc.
[0037] In one embodiment, before inputting the notification information into a preset nuclear power plant entity recognition model, the process includes:
[0038] Acquire a preset nuclear power plant notification data set; the preset nuclear power plant notification data set includes at least one sample notification with a nuclear power plant notification label;
[0039] It can be understood that the label of the nuclear power plant notification form refers to the label obtained by manually labeling each word in the sample notification form in advance. For example, if "the contact person is Xiao Ming", "Xiao Ming" will be pre-labeled as a name entity; or if "the faulty equipment is a pressurized water reactor", "pressurized water reactor" will be pre-labeled as a nuclear power plant equipment name entity, etc.
[0040] Inputting the sample notification into a preset recognition model including preset initial parameters, performing label prediction on the sample notification through the preset recognition model, and obtaining a model predicted label corresponding to the sample notification;
[0041] Specifically, after obtaining the preset nuclear power plant notification data set, the sample notification with the nuclear power plant notification label is input into the preset recognition model containing preset initial parameters, and the label of the sample notification is predicted by the preset recognition model to obtain the model predicted label corresponding to the sample notification.
[0042] Furthermore, the preset recognition model will first perform word segmentation processing on the sample notification form (such as stuttering word segmentation, etc.) to obtain the labeled notification words corresponding to the sample notification form; the encoder in the preset recognition model will encode each labeled notification word to obtain a forward encoding vector and a reverse encoding vector; according to the forward encoding vector and the reverse encoding vector, the label classifier in the preset recognition model will classify each labeled notification word to obtain a model predicted label corresponding to each labeled notification word. Among them, the forward encoding refers to encoding each labeled notification word in a forward order; the reverse encoding refers to encoding each labeled notification word in a reverse order; the encoder is a bidirectional recurrent neural network encoder, so the output encoding vector contains the forward encoding vector obtained by encoding each labeled notification word in the sample notification form in a forward order, and the reverse encoding vector obtained by encoding each labeled notification word in the sample notification form in a reverse order.
[0043] Determining the predicted loss value of the preset recognition model according to the model prediction label and the label marked on the nuclear power plant notice;
[0044] It can be understood that after the sample notification form is input into a preset recognition model containing preset initial parameters, the sample notification form is labeled through the preset recognition model to obtain the model prediction label corresponding to the sample notification form, and then each direct prediction label is matched with the label of each nuclear power plant notification form, and then the prediction loss value of the preset recognition model is determined through a cross entropy loss function.
[0045] When the predicted loss value does not reach the preset convergence condition, the preset initial parameters of the preset recognition model are updated and iterated until the predicted loss value reaches the preset convergence condition, and the preset recognition model after convergence is recorded as the preset nuclear power plant entity recognition model.
[0046] It can be understood that the convergence condition can be the condition that the predicted loss value is less than the set threshold, that is, when the predicted loss value is less than the set threshold, the training is stopped; the convergence condition can also be the condition that the predicted loss value is very small and will not decrease after 10,000 calculations, that is, when the predicted loss value is very small and will not decrease after 10,000 calculations, the training is stopped, and the preset recognition model after convergence is recorded as the preset nuclear power plant entity recognition model.
[0047] Furthermore, after determining the predicted loss value of the preset identification model based on the model prediction label of the sample notification and the label marked on the nuclear power plant notification, when the predicted loss value does not reach the preset convergence condition, the preset initial parameters of the preset identification model are adjusted according to the predicted loss value, and the sample notification is re-input into the preset identification model after the preset initial parameters are adjusted, so that when the predicted loss value corresponding to the sample notification reaches the preset convergence condition, another sample notification in the preset nuclear power plant notification data set is selected, and the above steps are executed to obtain the predicted loss value corresponding to the sample notification, and when the predicted loss value does not reach the preset convergence condition, the preset initial parameters of the preset identification model are adjusted again according to the predicted loss value, so that the predicted loss value corresponding to the sample notification reaches the preset convergence condition.
[0048] In this way, after the preset recognition model is trained through all the sample notifications in the preset nuclear power plant notification data set, the results output by the preset recognition model can continue to approach the accurate results, making the recognition accuracy higher and higher, until the predicted loss values corresponding to all sample notifications reach the preset convergence conditions, and the preset recognition model after convergence is recorded as the preset nuclear power plant entity recognition model.
[0049] The nuclear power plant entity is entity matched with the entity category in the example notification form, so as to fill the nuclear power plant entity into the slot corresponding to the entity category matched with it by using the slot filling method, and generate the notification form to be detected.
[0050] It can be understood that each filling slot in the example notification has an entity category. Therefore, after the notification information is input into the preset nuclear power plant entity recognition model to perform entity recognition on the notification information and obtain the nuclear power plant entities in the notification information, the nuclear power plant entities are entity matched with the entity categories in the example notification, so that the nuclear power plant entities are filled into the slots corresponding to the entity categories that match them using the slot filling method, thereby generating a notification to be tested.
[0051] Furthermore, in this embodiment, after the nuclear power plant entity is filled into the slot corresponding to the entity category that matches it using the slot filling method, if there are still unfilled slots in the example notification form, then when subsequent staff members review the notification form to be inspected, or modify the notification form to be inspected, the unfilled slots can be filled with information.
[0052] S30: Obtain all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database;
[0053] It can be understood that the preset nuclear power plant notification database contains multiple historical notifications, and each historical notification has the functional location information of the nuclear power plant, that is, each historical notification has the nuclear power plant equipment information, and the nuclear power plant equipment information has a corresponding functional location label, so all historical notifications in the preset nuclear power plant notification database are classified by functional location labels.
[0054] Furthermore, a sample notification corresponding to the notification type is queried in the preset notification type library, and the notification information is filled into the sample notification using the slot filling method. After the notification to be inspected is generated, all historical notifications with the same nuclear power plant function location label as the notification to be inspected are queried and extracted from the preset nuclear power plant notification database.
[0055] S40: performing similarity matching between the notification to be detected and each of the historical notifications to obtain a notification similarity value corresponding to the notification to be detected and each of the historical notifications;
[0056] It can be understood that the notification similarity value represents the degree of similarity between the notification to be detected and the historical notifications. The higher the notification similarity value, the higher the degree of similarity between the notification to be detected and the historical notifications; the lower the notification similarity value, the lower the degree of similarity between the notification to be detected and the historical notifications.
[0057] In one embodiment, step S40 includes:
[0058] Performing word embedding conversion processing on the detection notification and each historical notification to obtain a detection word vector corresponding to the detection notification and a historical word vector corresponding to each historical notification;
[0059] It can be understood that the word embedding conversion process refers to converting the information in the detection notification or the information in the historical notification into a corresponding word vector method to determine the notification similarity value between the detection notification and each historical notification.
[0060] Specifically, after obtaining all historical notifications with the functional location label of the nuclear power plant from the preset nuclear power plant notification database, the inspection notification and each historical notification are subjected to word embedding conversion processing through a word embedding neural network model to obtain a detection word vector corresponding to the inspection notification and a historical word vector corresponding to each historical notification.
[0061] Determine the word vector distance between the detection word vector and each of the historical word vectors, so as to determine the similarity of the notifications corresponding to each of the historical notifications according to the word vector distance.
[0062] It can be understood that the vector distance is the Euclidean distance. The smaller the vector distance is, the closer the semantics between the detection word vector and the historical word vector are, that is, the higher the similarity between the notification to be detected and the historical notification.
[0063] Specifically, after the detection notice and each historical notice are processed by word embedding conversion to obtain the detection word vector corresponding to the detection notice and the historical word vector corresponding to each historical notice, the word vector distance between the detection word vector and each historical word vector is determined to determine the similarity of the notice corresponding to each historical notice according to the word vector distance. Exemplarily, assuming that the word vector distance is 0.1, the similarity of the notice corresponding to it can be set to 90%.
[0064] S50: When the similarity values of the notification to be detected and the notifications corresponding to the historical notifications are both less than a preset similarity threshold, the notification to be detected is recorded as a new nuclear power plant notification;
[0065] S60: Storing the new nuclear power plant notification in the preset nuclear power plant notification database.
[0066] Optionally, the preset similarity threshold may be set to 90%, 95%, etc.
[0067] Specifically, the similarity between the notification to be detected and each of the historical notifications is matched, and the notification similarity value between the notification to be detected and each of the historical notifications is obtained; the similarity value of each notification is compared with a preset similarity threshold. If the similarity between the notification to be detected and the notification corresponding to each historical notification is less than the preset similarity threshold, it indicates that in the preset nuclear power plant notification database, the historical notifications with the nuclear power plant function location label are different from the notification to be detected, and then the notification to be detected is recorded as a new nuclear power plant notification, and the new nuclear power plant notification is stored in the preset nuclear power plant notification database.
[0068] Furthermore, if the similarity between the notification to be detected and the notification corresponding to any historical notification is greater than or equal to the preset similarity threshold, it indicates that in the preset nuclear power plant notification database, there is a historical notification with a nuclear power plant functional location tag that is the same as the notification to be detected, and the notification to be detected is not stored in the preset nuclear power plant notification database. In this way, the above notification generation method can avoid repeated generation of the same notification, resulting in data redundancy in the preset nuclear power plant notification database and occupying the memory of the preset nuclear power plant notification database.
[0069] In this embodiment, by setting example notifications corresponding to the notification types, the notification information of each notification type can be processed in a regularized manner, thereby improving the uniformity of notification generation and reducing the error rate of notification generation; further, after generating the notification to be tested, it is necessary to compare the notification to be tested with the historical notifications in the preset nuclear power plant notification database to avoid repeated generation of the same notification, thereby improving the effectiveness of the use of the preset nuclear power plant notification database.
[0070] In one embodiment, after step S60, that is, after storing the new nuclear power plant notification form in the preset nuclear power plant notification form database, the process further includes:
[0071] receiving a notification modification instruction; the notification modification instruction includes container proxy information, sender information, and notification query information;
[0072] It can be understood that the notification modification instruction can be sent by the staff through the mobile terminal, or it can be automatically generated when the staff clicks the modification button. The container proxy information instruction refers to the container in which the staff modifies the notification. For example, the container proxy information may include application proxy information, web proxy information, system proxy information, etc. Among them, the application proxy information instructs the staff to modify the notification on the notification application; the web proxy information instructs the staff to modify the notification on the web page; the system proxy information instructs the staff to modify the notification on the SAP (System Applications and Products, enterprise management series software) system. The sender information refers to the login information logged in on the application, or the login information logged in on the web page, or the login information logged in on the SAP system. The notification query information refers to the notification query condition field. For example, the notification query information includes but is not limited to the nuclear power plant function location label, the notification application date range, the planned plant information, the work center information, and the creator information.
[0073] Determining a notification to be modified corresponding to the notification query information from the preset nuclear power plant notification database;
[0074] Specifically, after receiving the notification modification instruction, the preset nuclear power plant notification database is queried for the notification to be modified that matches the notification query information. The notification to be modified can be a new nuclear power plant notification just stored in the preset nuclear power plant notification database in step S60, or it can be a historical notification in the preset nuclear power plant notification database.
[0075] Furthermore, in this embodiment, all notification query information can be used to determine the notification to be modified corresponding to the notification query information; or part of the notification query information can be used for fuzzy matching to determine the notification to be modified corresponding to the notification query information. If there are multiple notifications to be modified corresponding to the notification query information, the notifications to be modified are displayed in the preset interface in order from the newest to the oldest according to the creation time of the notification.
[0076] Furthermore, when the corresponding notification to be modified is found through the notification query information, the query conditions in the notification query information can be automatically recorded, and then a notification query condition label can be generated based on the notification query information, so that the next time the notification to be modified corresponding to the notification query information needs to be queried, the notification query condition label can be directly used for query.
[0077] Detecting whether the container proxy information is application proxy information, and when the container proxy information is application proxy information, determining whether the user status of the notification to be modified is a preset creation status;
[0078] Specifically, after determining the notification to be modified corresponding to the notification query information from the preset nuclear power plant notification database, it is detected whether the container proxy information is the application proxy information, and when the container proxy information is the application proxy information, it is determined whether the user status of the notification to be modified is the preset creation status.
[0079] When the user status of the notification to be modified is the preset creation status, obtaining the creator information of the notification to be modified, and determining whether the sender information is the same as the creator information;
[0080] If the user status of the notification to be modified is the preset creation status, the representative staff can modify the notification to be modified on the application; if the user status of the notification to be modified is not the preset creation status, such as the save status, the representative staff cannot modify the notification to be modified on the application, and needs to modify it through the SAP system or web portal. Furthermore, if the user status of the notification to be modified is the preset creation status, the creator information in the notification to be modified is obtained, that is, the name or account ID of the staff who created the notification to be modified, and it is determined whether the initiator information is the same as the creator information.
[0081] When the sender information is the same as the creator information, the notification to be modified is displayed in a preset interface, and a modification permission instruction is sent to a preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
[0082] When the sender information is the same as the creator information, the notification to be modified will be displayed in the preset interface, and a modification permission instruction will be sent to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface; further, after the preset recipient modifies the notification to be modified, the modified notification to be modified by the preset recipient can be automatically saved temporarily, that is, the modification status is recorded, but not stored in the preset nuclear power plant notification database; after the preset recipient confirms that the modification is completed, the modified notification to be modified will be stored in the preset nuclear power plant notification database.
[0083] In one embodiment, after detecting whether the container proxy information is application proxy information, the method further includes:
[0084] If the container proxy information is not the application proxy information, obtaining the creator information of the notification to be modified, and determining whether the sender information is the same as the creator information;
[0085] If the container proxy information is not the application proxy information, there is no need to verify whether the user status of the notification to be modified is the preset creation status. The creator information of the notification to be modified can be directly obtained, and it is determined whether the sender information is the same as the creator information.
[0086] When the sender information is the same as the creator information, the notification to be modified is displayed in a preset interface, and a modification permission instruction is sent to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
[0087] When the sender information is the same as the creator information, the notification to be modified will be displayed in the preset interface, and a modification permission instruction will be sent to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface; further, after the preset recipient modifies the notification to be modified, the modified notification to be modified by the preset recipient can be automatically saved temporarily, that is, the modification status is recorded, but not stored in the preset nuclear power plant notification database; after the preset recipient confirms that the modification is completed, the modified notification to be modified will be stored in the preset nuclear power plant notification database.
[0088] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0089] In one embodiment, a nuclear power plant notification form generation device is provided, and the nuclear power plant notification form generation device corresponds one-to-one to the nuclear power plant notification form generation method in the above embodiment. Figure 3As shown, the nuclear power plant notification form generation device includes a notification form generation instruction receiving module 10, a slot filling module 20, a historical notification form acquisition module 30, a similarity matching module 40, a notification form recording module 50 and a notification form storage module 60. The functional modules are described in detail as follows:
[0090] The notification form generation instruction receiving module 10 is used to receive a notification form generation instruction of a nuclear power plant; the notification form generation instruction of the nuclear power plant includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag;
[0091] A slot filling module 20 is used to query a sample notification corresponding to the notification type from a preset notification type library, and fill the notification information into the sample notification using a slot filling method to generate a notification to be tested;
[0092] A historical notification acquisition module 30 is used to acquire all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database;
[0093] A similarity matching module 40 is used to perform similarity matching between the notification to be detected and each of the historical notifications to obtain a notification similarity value corresponding to the notification to be detected and each of the historical notifications;
[0094] The notification recording module 50 is used to record the notification to be detected as a new nuclear power plant notification when the notification similarity values of the notification to be detected and the notifications corresponding to the historical notifications are both less than a preset similarity threshold;
[0095] The notification storage module 60 is used to store the new nuclear power plant notification in the preset nuclear power plant notification database.
[0096] Preferably, the slot filling module comprises:
[0097] An entity recognition unit, used for inputting the notification information into a preset nuclear power plant entity recognition model to perform entity recognition on the notification information to obtain each nuclear power plant entity in the notification information;
[0098] The nuclear power plant entity is entity matched with the entity category in the example notification form, so as to fill the nuclear power plant entity into the slot corresponding to the entity category matched with it by using the slot filling method, and generate the notification form to be detected.
[0099] Preferably, the nuclear power plant notification sheet generating device further comprises:
[0100] A data set acquisition module is used to acquire a preset nuclear power plant notification data set; the preset nuclear power plant notification data set includes at least one sample notification with a nuclear power plant notification label;
[0101] A label prediction module, used for inputting the sample notification into a preset recognition model including preset initial parameters, performing label prediction on the sample notification through the preset recognition model, and obtaining a model predicted label corresponding to the sample notification;
[0102] A predicted loss value determination module, used to determine the predicted loss value of the preset recognition model according to the model prediction label and the nuclear power plant notice label;
[0103] The model training module is used to update and iterate the preset initial parameters of the preset recognition model when the predicted loss value does not reach the preset convergence condition, until the predicted loss value reaches the preset convergence condition, and record the preset recognition model after convergence as the preset nuclear power plant entity recognition model.
[0104] Preferably, the similarity matching module 40 includes:
[0105] A word embedding conversion processing unit, used to perform word embedding conversion processing on the detection notification and each historical notification to obtain a detection word vector corresponding to the detection notification and a historical word vector corresponding to each historical notification;
[0106] A word vector distance determination unit is used to determine the word vector distance between the detection word vector and each of the historical word vectors, so as to determine the similarity of the notification corresponding to each of the historical notifications according to the word vector distance.
[0107] Preferably, the nuclear power plant notification sheet generating device further comprises:
[0108] A modification instruction receiving module, used for receiving a notification modification instruction; the notification modification instruction includes container proxy information, sender information and notification query information;
[0109] A notification query module, used to determine the notification to be modified corresponding to the notification query information from the preset nuclear power plant notification database;
[0110] A container proxy information detection module, used to detect whether the container proxy information is application proxy information, and when the container proxy information is application proxy information, determine whether the user status of the notification to be modified is a preset creation status;
[0111] A first notification form judgment module, configured to obtain the creator information of the notification form to be modified and determine whether the sender information is the same as the creator information when the user status of the notification form to be modified is the preset creation status;
[0112] The first notification modification module is used to display the notification to be modified in a preset interface when the sender information is the same as the creator information, and send a modification permission instruction to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
[0113] Preferably, the nuclear power plant notification sheet generating device further comprises:
[0114] A second notification form judgment module is used for obtaining the creator information of the notification form to be modified and determining whether the sender information is the same as the creator information if the container proxy information is not the application proxy information;
[0115] The second notification modification module is used to display the notification to be modified in a preset interface when the sender information is the same as the creator information, and send a modification permission instruction to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
[0116] For the specific definition of the nuclear power plant notification form generation device, please refer to the definition of the nuclear power plant notification form generation device method above, which will not be repeated here. Each module in the above-mentioned nuclear power plant notification form generation device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0117] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data used in the method for generating a nuclear power plant notification in the above-mentioned embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for generating a nuclear power plant notification is implemented.
[0118] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for generating a nuclear power plant notification form in the above embodiment is implemented.
[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a nuclear power plant notification form in the above embodiment is implemented.
[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. 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. As an 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 (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0121] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by 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.
[0122] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for generating a nuclear power plant notification form, It is characterized in that include: Receiving a nuclear power plant notification form generation instruction; the nuclear power plant notification form generation instruction includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag; Querying a sample notification corresponding to the notification type from a preset notification type library, and filling the notification information into the sample notification using a slot filling method to generate a notification to be tested; Obtaining all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database; Perform similarity matching between the notification to be detected and each of the historical notifications to obtain a notification similarity value corresponding to the notification to be detected and each of the historical notifications; When the similarity values of the notification to be detected and the notifications corresponding to the historical notifications are both less than a preset similarity threshold, the notification to be detected is recorded as a new nuclear power plant notification; Storing the new nuclear power plant notification in the preset nuclear power plant notification database; After storing the new nuclear power plant notification in the preset nuclear power plant notification database, the method includes: receiving a notification modification instruction; the notification modification instruction includes container proxy information, sender information, and notification query information; Determining a notification to be modified corresponding to the notification query information from the preset nuclear power plant notification database; Detecting whether the container proxy information is application proxy information, and when the container proxy information is application proxy information, determining whether the user status of the notification to be modified is a preset creation status; the application proxy information instructs the staff to modify the notification on the notification application; When the user status of the notification to be modified is the preset creation status, obtaining the creator information of the notification to be modified, and determining whether the sender information is the same as the creator information; When the sender information is the same as the creator information, the notification to be modified is displayed in a preset interface, and a modification permission instruction is sent to a preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
2. The method for generating a nuclear power plant notification sheet according to claim 1, It is characterized in that The step of filling the notification information into the example notification using a slot filling method to generate a notification to be detected includes: Inputting the notification information into a preset nuclear power plant entity recognition model to perform entity recognition on the notification information to obtain each nuclear power plant entity in the notification information; The nuclear power plant entity is entity matched with the entity category in the example notification form, so as to fill the nuclear power plant entity into the slot corresponding to the entity category matched with it by using the slot filling method, and generate the notification form to be detected.
3. The method for generating a nuclear power plant notification sheet according to claim 2, It is characterized in that Before inputting the notification information into the preset nuclear power plant entity recognition model, the method includes: Acquire a preset nuclear power plant notification data set; the preset nuclear power plant notification data set includes at least one sample notification with a nuclear power plant notification label; Inputting the sample notification into a preset recognition model including preset initial parameters, performing label prediction on the sample notification through the preset recognition model, and obtaining a model predicted label corresponding to the sample notification; Determining the predicted loss value of the preset recognition model according to the model prediction label and the label marked on the nuclear power plant notice; When the predicted loss value does not reach the preset convergence condition, the preset initial parameters of the preset recognition model are updated and iterated until the predicted loss value reaches the preset convergence condition, and the preset recognition model after convergence is recorded as the preset nuclear power plant entity recognition model.
4. The method for generating a nuclear power plant notification sheet according to claim 1, It is characterized in that The similarity matching of the notification to be detected with each of the historical notifications to obtain a notification similarity value corresponding to each of the historical notifications includes: Performing word embedding conversion processing on the detection notification and each historical notification to obtain a detection word vector corresponding to the detection notification and a historical word vector corresponding to each historical notification; Determine the word vector distance between the detection word vector and each of the historical word vectors, so as to determine the similarity of the notifications corresponding to each of the historical notifications according to the word vector distance.
5. The method for generating a nuclear power plant notification sheet according to claim 1, It is characterized in that After detecting whether the container proxy information is application proxy information, the method further includes: If the container proxy information is not the application proxy information, obtaining the creator information of the notification to be modified, and determining whether the sender information is the same as the creator information; When the sender information is the same as the creator information, the notification to be modified is displayed in a preset interface, and a modification permission instruction is sent to the preset recipient, so that the preset recipient can modify the notification to be modified in the preset interface.
6. The method for generating a nuclear power plant notification sheet according to claim 1, It is characterized in that The notification query information includes the nuclear power plant function location tag, notification application date range, planned plant information, work center information and creator information.
7. A device for generating a notification form for a nuclear power plant, It is characterized in that The nuclear power plant notification form generation device is used to execute the nuclear power plant notification form generation method according to any one of claims 1 to 6, and the nuclear power plant notification form generation device includes: A notification form generation instruction receiving module, used to receive a notification form generation instruction of a nuclear power plant; the notification form generation instruction of the nuclear power plant includes a notification form type and notification form information; the notification form information includes a nuclear power plant function location tag; A slot filling module, used to query a sample notification corresponding to the notification type from a preset notification type library, and fill the notification information into the sample notification using a slot filling method to generate a notification to be tested; A historical notification acquisition module is used to acquire all historical notifications with the nuclear power plant function location tag from a preset nuclear power plant notification database; A similarity matching module, used for performing similarity matching between the notification to be detected and each of the historical notifications, and obtaining a notification similarity value corresponding to the notification to be detected and each of the historical notifications; A notification recording module, configured to record the notification to be detected as a new nuclear power plant notification when the notification similarity values corresponding to the notification to be detected and each of the historical notifications are less than a preset similarity threshold; The notification storage module is used to store the new nuclear power plant notification in the preset nuclear power plant notification database.
8. The nuclear power plant notification sheet generating device according to claim 7, It is characterized in that The slot filling module comprises: An entity recognition unit, used for inputting the notification information into a preset nuclear power plant entity recognition model to perform entity recognition on the notification information to obtain each nuclear power plant entity in the notification information; The nuclear power plant entity is entity matched with the entity category in the example notification form, so as to fill the nuclear power plant entity into the slot corresponding to the entity category matched with it by using the slot filling method, and generate the notification form to be detected.
9. The nuclear power plant notification sheet generating device according to claim 8, It is characterized in that The nuclear power plant notification sheet generating device also includes: A data set acquisition module is used to acquire a preset nuclear power plant notification data set; the preset nuclear power plant notification data set includes at least one sample notification with a nuclear power plant notification label; A label prediction module, used for inputting the sample notification into a preset recognition model including preset initial parameters, performing label prediction on the sample notification through the preset recognition model, and obtaining a model predicted label corresponding to the sample notification; A predicted loss value determination module, used to determine the predicted loss value of the preset recognition model according to the model prediction label and the nuclear power plant notification label; The model training module is used to update and iterate the preset initial parameters of the preset recognition model when the predicted loss value does not reach the preset convergence condition, until the predicted loss value reaches the preset convergence condition, and record the preset recognition model after convergence as the preset nuclear power plant entity recognition model.
10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method for generating a nuclear power plant notification sheet as described in any one of claims 1 to 6 is implemented.
11. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method for generating a nuclear power plant notification sheet as described in any one of claims 1 to 6 is implemented.
