Nuclear safety supervision data migration method and device, computer equipment, storage medium and computer program product

Abstract

The application relates to a nuclear safety supervision data migration method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: in response to a data migration instruction for a to-be-migrated data form corresponding to a nuclear safety supervision system, determining a to-be-migrated field corresponding to the to-be-migrated data form; determining a first data classification result of the to-be-migrated field and a second data classification result of a field value of the to-be-migrated field; determining a target data classification result of the to-be-migrated field according to the first data classification result and the second data classification result; determining a migration classification template corresponding to the to-be-migrated field according to the target data classification result; the migration classification template is used for representing a mapping relationship of the to-be-migrated field between the nuclear safety supervision system and a target nuclear safety supervision system; and migrating the to-be-migrated field from the nuclear safety supervision system to the target nuclear safety supervision system according to the migration classification template. The method can improve the data migration efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for migrating nuclear safety regulatory data. Background Technology

[0002] Currently, in fields such as nuclear safety regulation, efficient data migration is crucial to reducing the risk of exposure to highly sensitive data.

[0003] In traditional technologies, data migration is usually carried out manually; however, manual operation is time-consuming and labor-intensive, resulting in low efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a nuclear safety regulatory data migration method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the efficiency of data migration in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for migrating nuclear safety regulatory data, including:

[0006] In response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined;

[0007] Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated;

[0008] Based on the first data classification result and the second data classification result, the target data classification result of the field to be migrated is determined;

[0009] Based on the target data classification results, a migration classification template corresponding to the field to be migrated is determined; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system;

[0010] According to the migration classification template, the field to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0011] In one embodiment, determining the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated includes:

[0012] Obtain the business scenario coverage, decision impact weight, and field sensitivity of the field to be migrated;

[0013] The business scenario coverage, the decision impact weight, and the field sensitivity are input into the importance prediction model to obtain the predicted importance of the field to be migrated.

[0014] From all the fields to be migrated, select the fields whose predicted importance is greater than the preset importance and use them as key fields;

[0015] Based on the key fields, the first data classification result of the field to be migrated is determined.

[0016] In one embodiment, determining the first data classification result of the field to be migrated based on the key field includes:

[0017] If there is only one key field, query the correspondence between the key field and the business scenario to obtain the business scenario corresponding to the key field, which is used as the first target business scenario for the field to be migrated.

[0018] Based on the first target business scenario, the first data classification result of the field to be migrated is obtained;

[0019] or,

[0020] When there are at least two key fields, the key fields are combined to obtain the key field combination corresponding to the field to be migrated;

[0021] Query the correspondence between key field combinations and business scenarios to obtain the business scenarios corresponding to the key field combinations, which are used as the second target business scenarios for the fields to be migrated.

[0022] Based on the second target business scenario, the first data classification result of the field to be migrated is obtained.

[0023] In one embodiment, determining the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated includes:

[0024] Identify the current data type of the field value of the field to be migrated;

[0025] The correspondence between data types and feature extraction models is queried to obtain the feature extraction model corresponding to the current data type, which is then used as the target feature extraction model for the field value.

[0026] The field value is input into the target feature extraction model to obtain the data features corresponding to the field value;

[0027] Based on the data characteristics, a second data classification result for the field value is determined.

[0028] In one embodiment, determining the second data classification result of the field value based on the data features includes:

[0029] Identify the key data features in the data features;

[0030] When the key data features meet the preset conditions, the data classification result corresponding to the key data features is determined as the second data classification result of the field value;

[0031] or,

[0032] If the key data features do not meet the preset conditions, the data features are input into the trained data classification prediction model to obtain the predicted probability of the field value under each preset data classification result.

[0033] From the preset data classification results, the preset data classification results with a predicted probability greater than the preset probability are selected as the second data classification results of the field value.

[0034] In one embodiment, the method further includes:

[0035] Extract the first attachment address value of the attachment to be migrated in the nuclear safety supervision system corresponding to the data form to be migrated from the field values ​​of the field to be migrated;

[0036] Extract the second attachment address value of the attachment to be migrated in the target nuclear safety monitoring system from the data migration parameters carried by the data migration instruction;

[0037] Based on the first attachment address value and the second attachment address value, the attachment to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0038] Secondly, this application also provides a nuclear safety regulatory data migration apparatus, comprising:

[0039] The field determination module is used to determine the fields to be migrated corresponding to the data form to be migrated in response to the data migration instruction for the data form to be migrated corresponding to the nuclear safety regulatory system.

[0040] The result determination module is used to determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated;

[0041] The target determination module is used to determine the target data classification result of the field to be migrated based on the first data classification result and the second data classification result.

[0042] The template determination module is used to determine the migration classification template corresponding to the field to be migrated based on the target data classification result; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system;

[0043] The field migration module is used to migrate the field to be migrated from the nuclear safety supervision system to the target nuclear safety supervision system according to the migration classification template.

[0044] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0045] In response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined;

[0046] Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated;

[0047] Based on the first data classification result and the second data classification result, the target data classification result of the field to be migrated is determined;

[0048] Based on the target data classification results, a migration classification template corresponding to the field to be migrated is determined; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system;

[0049] According to the migration classification template, the field to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0050] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0051] In response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined;

[0052] Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated;

[0053] Based on the first data classification result and the second data classification result, the target data classification result of the field to be migrated is determined;

[0054] Based on the target data classification results, a migration classification template corresponding to the field to be migrated is determined; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system;

[0055] According to the migration classification template, the field to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0056] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0057] In response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined;

[0058] Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated;

[0059] Based on the first data classification result and the second data classification result, the target data classification result of the field to be migrated is determined;

[0060] Based on the target data classification results, a migration classification template corresponding to the field to be migrated is determined; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system;

[0061] According to the migration classification template, the field to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0062] The aforementioned nuclear safety regulatory data migration method, apparatus, computer equipment, storage medium, and computer program product first respond to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, determine the field to be migrated corresponding to the data form, then determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated, then determine the target data classification result of the field to be migrated based on the first and second data classification results, then determine the migration classification template corresponding to the field to be migrated based on the target data classification result, and finally migrate the field to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system based on the migration classification template; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system. In this way, during data migration, by first performing a dual classification of the fields to be migrated in the data form and their values, the characteristics of the data to be migrated can be identified from two dimensions: field attributes and actual data content. Then, the target classification results are fused to match an accurate migration classification template. The predefined migration classification template directly clarifies the field mapping relationship between the nuclear safety supervision system and the target system, which helps to improve the efficiency of data migration. Moreover, the entire process does not require manual intervention, avoiding the drawbacks of manual operation, which is prone to consuming a lot of time and manpower and resulting in low data migration efficiency, thus improving the efficiency of data migration. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a flowchart illustrating a nuclear safety regulatory data migration method in one embodiment;

[0065] Figure 2 This is a flowchart illustrating the steps for determining the first data classification result of the field to be migrated in one embodiment.

[0066] Figure 3 This is a flowchart illustrating a nuclear safety regulatory data migration method in another embodiment;

[0067] Figure 4 This is a structural block diagram of a nuclear safety regulatory data migration device in one embodiment;

[0068] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0069] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0070] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0071] In one exemplary embodiment, such as Figure 1 As shown, a method for migrating nuclear safety regulatory data is provided. This embodiment illustrates the application of this method to a server; it is understood that this method can also be applied to terminals, and can also be applied to systems including terminals and servers, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0072] Step S101: In response to the data migration instruction for the data form to be migrated corresponding to the nuclear safety regulatory system, determine the fields to be migrated corresponding to the data form to be migrated.

[0073] Among them, the nuclear safety regulatory system can refer to the old system of the nuclear safety regulatory department (such as the review center).

[0074] Among them, the target nuclear safety regulatory system can refer to a new system of nuclear safety regulatory authorities (such as review centers).

[0075] It should be noted that the nuclear safety regulatory system and the target nuclear safety regulatory system may also be systems of the same level but different modules (such as data migration from the nuclear safety regulatory system in region A to the system in region B).

[0076] The data form to be migrated represents a set of structured data that needs to be migrated in the nuclear safety regulatory system. It is usually presented in tabular form and includes multiple fields, among which the fields include the attachment address field corresponding to the attachment to be migrated associated with the data form to be migrated.

[0077] Among them, data migration instructions refer to operation instructions that trigger the data migration process. These instructions may be initiated manually by users (such as nuclear safety regulators) through the system interface or automatically generated by the system according to preset rules (such as periodic migration or upgrade triggers).

[0078] Among them, the field to be migrated refers to the specific data item (such as a column in the form) contained in the data form to be migrated, which is the smallest unit of data migration.

[0079] For example, the server receives a data migration instruction from the terminal, sent by the terminal, for a data form to be migrated corresponding to the nuclear safety regulatory system. Then, in response to the data migration instruction, the server extracts the form identifier from the data migration parameters carried in the instruction. Next, the server filters the form identifier (e.g., filtering the form identifier corresponding to already migrated forms) to obtain a filtered form identifier. Then, the server uses the data form corresponding to the filtered form identifier as the data form to be migrated. Finally, the server preprocesses the fields in the data form to be migrated (including data cleaning, format cleaning, link conversion, terminology validation, and data anonymization) to obtain preprocessed fields, which are then used as the fields to be migrated in the data form.

[0080] Step S102: Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated.

[0081] The first data classification result is used to represent the data classification result of the field to be migrated, which is specifically determined by the business scenario corresponding to the field to be migrated.

[0082] The second data classification result is used to represent the data classification result corresponding to the field value of the field to be migrated. Specifically, it is determined by the data characteristics (such as data update frequency) corresponding to the field value.

[0083] For example, the server performs feature extraction processing on the field to be transferred and its field values ​​to obtain feature vectors for the field to be transferred and field values. Then, the server uses the feature vectors of the field to be transferred as primary data and the feature vectors of the field values ​​as auxiliary data, and inputs them into the trained data classification prediction model to obtain the first data classification result of the field to be transferred. Then, the server uses the feature vectors of the field values ​​as primary data and the feature vectors of the field to be transferred as auxiliary data, and inputs them into the trained data classification prediction model to obtain the second data classification result of the field values ​​of the field to be transferred.

[0084] Step S103: Determine the target data classification result of the field to be migrated based on the first data classification result and the second data classification result.

[0085] The target data classification result refers to the comprehensive data classification result of the field to be migrated.

[0086] For example, the server combines the first data classification result and the second data classification result to obtain the target data classification result of the field to be migrated.

[0087] Furthermore, the server uses the first data classification result as the primary data classification result and the second data classification result as the secondary data classification result, and determines the target data classification result of the field to be migrated based on the primary and secondary data classification results.

[0088] Step S104: Based on the target data classification results, determine the migration classification template corresponding to the field to be migrated.

[0089] The migration classification template represents the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system, and is determined based on the classification result of the target data. For example, if the target data classification result of the field to be migrated is Category 1, the field name in the nuclear safety regulatory system is A, and the field name in the target nuclear safety regulatory system is a; if the target data classification result of the field to be migrated is Category 2, the field name in the nuclear safety regulatory system is A, and the field name in the target nuclear safety regulatory system is b.

[0090] For example, the server queries the correspondence between the target data classification result and the migration classification template based on the target data classification result, and obtains the migration classification template corresponding to the target data classification result, which is then used as the migration classification template for the field to be migrated.

[0091] Step S105: According to the migration classification template, migrate the field to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0092] For example, the server determines the field values ​​and field structures in the field to be migrated; then, based on the target data classification results of the field to be migrated, the server performs format conversion (such as unit conversion, date format adjustment) and security processing (such as desensitization) on the field values ​​in the field to be migrated, to obtain the processed field values; then, based on the migration classification template, the server migrates the processed field values ​​and field structures from the nuclear safety regulatory system to the target nuclear safety regulatory system; next, the server performs consistency verification on the field to be migrated in the nuclear safety regulatory system and the migrated field in the target nuclear safety regulatory system, to obtain the consistency verification result.

[0093] In the aforementioned nuclear safety regulatory data migration method, firstly, in response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined. Then, the first data classification result of the fields to be migrated and the second data classification result of the field values ​​to be migrated are determined. Next, based on the first and second data classification results, the target data classification result of the fields to be migrated is determined. Then, based on the target data classification result, the migration classification template corresponding to the fields to be migrated is determined. Finally, based on the migration classification template, the fields to be migrated are migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system. The migration classification template is used to represent the mapping relationship between the fields to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system. In this way, during data migration, by first performing a dual classification of the fields to be migrated in the data form and their values, the characteristics of the data to be migrated can be identified from two dimensions: field attributes and actual data content. Then, the target classification results are fused to match an accurate migration classification template. The predefined migration classification template directly clarifies the field mapping relationship between the nuclear safety supervision system and the target system, which helps to improve the efficiency of data migration. Moreover, the entire process does not require manual intervention, avoiding the drawbacks of manual operation, which is prone to consuming a lot of time and manpower and resulting in low data migration efficiency, thus improving the efficiency of data migration.

[0094] In one exemplary embodiment, such as Figure 2 As shown, step S102 above determines the first data classification result of the field to be migrated and the second data classification result of the field values ​​of the field to be migrated, specifically including the following steps:

[0095] Step S201: Obtain the business scenario coverage, decision impact weight, and field sensitivity of the field to be migrated.

[0096] Step S202: Input the business scenario coverage, decision influence weight, and field sensitivity into the importance prediction model to obtain the predicted importance of the field to be migrated.

[0097] Step S203: Select the fields to be migrated from the fields to be migrated whose predicted importance is greater than the preset importance, and use them as key fields.

[0098] Step S204: Determine the first data classification result of the field to be migrated based on the key fields.

[0099] Among them, business scenario coverage is used to indicate the frequency of occurrence of the field to be migrated in historical regulatory business (such as "license number" appearing in 90% of approval forms).

[0100] Among them, the decision impact weight is used to represent the impact weight of the change of the field value of the field to be migrated on the business decision (e.g., if the "equipment pressure" exceeds the standard, a message notification will be directly triggered, and the weight is set to 0.9).

[0101] Field sensitivity is used to represent the risk level (such as high risk, medium risk, and low risk) of a field.

[0102] Among them, importance prediction models refer to network models that can predict the importance of fields, such as random forest models.

[0103] Among them, the predicted importance refers to the predicted value corresponding to the importance of the field to be migrated.

[0104] The preset importance level refers to a pre-defined threshold for importance. It should be noted that the preset importance level depends on the specific circumstances.

[0105] Among them, key fields refer to fields to be migrated whose predicted importance is greater than the preset importance.

[0106] For example, the server determines the frequency of occurrence of the field to be migrated in historical regulatory business based on the number of times it appears, using this frequency as the business scenario coverage rate of the field to be migrated. Next, the server inputs the field value of the field to be migrated into an attention mechanism model for attention mechanism processing to obtain the decision influence weight of the field to be migrated. Then, the server inputs the field to be migrated into a trained sensitivity prediction model to obtain the field sensitivity of the field to be migrated. Next, the server performs feature extraction processing on the business scenario coverage rate, decision influence weight, and field sensitivity respectively to obtain a first feature vector for the business scenario coverage rate, a second feature vector for the decision influence weight, and a third feature vector for the field sensitivity. Then, the server fuses the first, second, and third feature vectors to obtain a fused feature vector. Next, the server inputs the fused feature vector into an importance prediction model to obtain the predicted importance of the field to be migrated. Then, the server selects the fields to be migrated whose predicted importance is greater than a preset importance from all the fields to be migrated, and designates these fields as key fields. Finally, the server determines the first data classification result of the field to be migrated based on the key fields.

[0107] In this embodiment, the logic of multi-dimensional evaluation, model quantification, precise screening, and classification anchoring not only improves the accuracy and efficiency of classification, but also lays the foundation for subsequent data migration processing. It avoids the subjectivity of traditionally judging the importance of fields based on experience, and fully adapts to the core requirements of data accuracy and security in nuclear security scenarios.

[0108] In an exemplary embodiment, step S204 above, determining the first data classification result of the field to be migrated based on the key fields, specifically includes the following: when there is only one key field, querying the correspondence between the key field and the business scenario to obtain the business scenario corresponding to the key field, which is taken as the first target business scenario of the field to be migrated; based on the first target business scenario, obtaining the first data classification result of the field to be migrated; or, when there are at least two key fields, combining the key fields to obtain the key field combination corresponding to the field to be migrated; querying the correspondence between the key field combination and the business scenario to obtain the business scenario corresponding to the key field combination, which is taken as the second target business scenario of the field to be migrated; based on the second target business scenario, obtaining the first data classification result of the field to be migrated.

[0109] The first target business scenario refers to the business scenario to which the key field belongs.

[0110] The second target business scenario refers to the business scenario to which the combination of key fields belongs.

[0111] For example, the server determines the number of key fields; if there is only one key field, the server queries the correspondence between the key field and the business scenario to obtain the business scenario corresponding to the key field, and uses this business scenario as the first target business scenario for the field to be migrated; then, the server uses the first target business scenario as the first data classification result for the field to be migrated; if there are at least two key fields, the server combines the key fields according to a preset combination method to obtain the key field combination corresponding to the field to be migrated; then, the server queries the correspondence between the key field combination and the business scenario to obtain the business scenario corresponding to the key field combination, and uses this business scenario as the second target business scenario for the field to be migrated; then, the server uses the second target business scenario as the first data classification result for the field to be migrated.

[0112] In this embodiment, by dynamically adjusting the business scenario matching logic based on the number of key fields, the classification efficiency in simple scenarios is guaranteed, while the classification accuracy in complex scenarios is improved. Ultimately, the classification result of the first data closely matches the actual business logic of nuclear safety supervision, effectively avoiding classification errors caused by deviations in business scenario positioning.

[0113] In an exemplary embodiment, step S102 above, which determines the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated, specifically includes the following: identifying the current data type of the field value of the field to be migrated; querying the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the current data type, which is used as the target feature extraction model for the field value; inputting the field value into the target feature extraction model to obtain the data feature corresponding to the field value; and determining the second data classification result of the field value based on the data feature.

[0114] The current data type refers to the actual data format in which the field value is presented in the nuclear safety supervision system. For example, the field value of the "Equipment Pressure Value" field is "0.1MPa", and its current data type is a numeric type with units; the field value of the "Equipment Fault Description" field is "Abnormal equipment noise, pressure fluctuation ±0.2MPa", and its current data type is text; the field value corresponding to "Facility Inspection Photo" (stored as a file path or binary stream) is currently an image type.

[0115] Feature extraction models refer to network models that can extract data features corresponding to field values. For example, numerical data (such as "equipment pressure") often uses statistical feature extraction models (network models used to extract mean, variance, unit identifiers, etc.); textual data (such as "fault descriptions, compliance report excerpts") often uses NLP (Natural Language Processing) feature extraction models (network models used to extract keyword weights, semantic vectors); and image data (such as "equipment appearance photos, monitoring instrument screenshots") often uses CNN (Convolutional Neural Network) feature extraction models (network models used to extract visual features such as edges, textures, and target contours).

[0116] The target feature extraction model refers to the feature extraction model corresponding to the current data type.

[0117] Data features refer to information that reflects the essential attributes or distinctiveness of field values.

[0118] For example, the server inputs the field value of the field to be migrated into a trained data type recognition model, which identifies the current data type of the field value. Next, based on the current data type, the server queries the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the current data type, and uses this feature extraction model as the target feature extraction model for the field value. Then, the server inputs the field value into the target feature extraction model, which performs feature extraction processing on the field value to obtain the data features corresponding to the field value. Finally, based on the data features, the server determines the second data classification result for the field value.

[0119] In this embodiment, a dedicated feature extraction model is matched based on the current data type of the field value to ensure that the feature extraction process is highly adapted to the data form, avoiding feature distortion caused by extraction. Finally, the second data classification result is determined based on the features, which not only ensures the professionalism of the classification of different types of field values, but also improves the accuracy and consistency of the classification, which meets the requirements of nuclear safety supervision for refined data processing.

[0120] In an exemplary embodiment, determining the second data classification result of the field value based on data features specifically includes the following: identifying key data features among the data features; determining the data classification result corresponding to the key data features as the second data classification result of the field value when the key data features meet preset conditions; or, when the key data features do not meet preset conditions, inputting the data features into the trained data classification prediction model to obtain the predicted probability of the field value under each preset data classification result; and selecting the preset data classification result with a predicted probability greater than the preset probability from each preset data classification result as the second data classification result of the field value.

[0121] Among them, key data features refer to data features whose importance is greater than the preset importance.

[0122] Among these, preset conditions refer to pre-defined judgment conditions. For example, for data classification results of "real-time update type", if the key data features include two core features: "update cycle identifier" and "data generation timestamp density", the preset conditions can be set as follows: "update cycle identifier = real-time" and "data generation timestamp density ≥ 1 record / minute" among the key data features; for data classification results of "periodic update type", if the key data features include two core features: "update cycle keyword" and "historical update interval", the preset conditions can be set as follows: "update cycle keyword = day / week / month (meeting one of these)," and "historical update interval fluctuation ≤ ±1 hour" among the key data features; for data classification results of "static and unchanging type", if the key data features include two core features: "data modification record identifier" and "data generation time", the preset conditions can be set as follows: "data modification record identifier = none" among the key data features, and "data generation time ≥ 1 year from the present and no update record".

[0123] Among them, data classification prediction models refer to network models that can predict the data classification results of field values, such as MLP (Multilayer Perceptron) models.

[0124] Among them, the preset data classification result refers to the pre-set data classification result, such as real-time updated class, periodically updated class, static and unchanging class, etc.

[0125] In this context, the prediction probability refers to the likelihood that a data classification prediction model will correctly determine the preset data classification result.

[0126] The preset probability refers to a pre-set probability threshold. It should be noted that the preset probability depends on the circumstances.

[0127] For example, the server inputs data features into an importance prediction model, obtains the importance of each data feature through the model, and selects data features with an importance greater than a preset importance as key data features. Next, the server judges the key data features based on preset conditions. If the key data features meet the preset conditions, the server determines the data classification result corresponding to the key data features and uses this data classification result as the second data classification result for the field value. Alternatively, if the key data features do not meet the preset conditions, the server inputs the data features into a trained data classification prediction model to obtain the predicted probability of the field value under each preset data classification result. Then, the server selects preset data classification results with a predicted probability greater than a preset probability from each preset data classification result and uses this preset data classification result as the second data classification result for the field value.

[0128] In this embodiment, by focusing on the key data features that play a decisive role in classification, if the preset conditions set based on nuclear safety specifications are met, the classification result is directly output, which helps to simplify the redundant process of model prediction and improve processing efficiency; if the key features do not meet the preset conditions, the trained model is used for prediction, avoiding classification bias in fuzzy samples not covered by hard rules, which helps to improve classification accuracy.

[0129] In an exemplary embodiment, the method further includes: extracting the first attachment address value of the attachment to be migrated in the nuclear safety regulatory system corresponding to the data form to be migrated from the field value of the field to be migrated; extracting the second attachment address value of the attachment to be migrated in the target nuclear safety regulatory system from the data migration parameters carried by the data migration instruction; and migrating the attachment to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system according to the first attachment address value and the second attachment address value.

[0130] Among them, the attachments to be migrated refer to the unstructured files associated with the data forms to be migrated, which need to be migrated synchronously from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0131] The first attachment address value refers to the unique storage location identifier of the attachment to be migrated in the nuclear safety regulatory system.

[0132] Among them, data migration parameters refer to the set of key information in the data migration instruction.

[0133] The second attachment address value refers to the preset storage location identifier of the attachment to be migrated in the target nuclear safety supervision system.

[0134] For example, the server inputs the field value of the field to be migrated into the information extraction model, and extracts the first attachment address value of the attachment to be migrated in the nuclear safety regulatory system from the field value of the field to be migrated. Then, the server inputs the data migration parameters carried by the data migration instruction into the information extraction model, and extracts the second attachment address value of the attachment to be migrated in the target nuclear safety regulatory system from the data migration parameters carried by the data migration instruction. Then, the server constructs a migration path for the attachment to be migrated based on the first attachment address value and the second attachment address value, and migrates the attachment to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system according to the migration path.

[0135] In this embodiment, targeted migration is achieved by using the first attachment address value of the attachment to be migrated in the nuclear safety regulatory system and the second attachment address value of the attachment to be migrated in the target nuclear safety regulatory system. This simplifies the redundant operations of manual location and uploading, greatly improves migration efficiency, and effectively avoids data chain breaks or security risks caused by improper attachment migration.

[0136] In one exemplary embodiment, such as Figure 3 As shown, another method for migrating nuclear safety regulatory data is provided. Taking the application of this method to a server as an example, the specific steps include:

[0137] Step S301: In response to the data migration instruction for the data form to be migrated corresponding to the nuclear safety regulatory system, determine the fields to be migrated corresponding to the data form to be migrated.

[0138] Step S302: Obtain the business scenario coverage, decision influence weight, and field sensitivity of the fields to be migrated; input the business scenario coverage, decision influence weight, and field sensitivity into the importance prediction model to obtain the predicted importance of the fields to be migrated; from each field to be migrated, select the fields to be migrated whose predicted importance is greater than the preset importance as key fields.

[0139] Step S303: If there is only one key field, query the correspondence between the key field and the business scenario to obtain the business scenario corresponding to the key field, which is used as the first target business scenario for the field to be migrated; based on the first target business scenario, obtain the first data classification result of the field to be migrated.

[0140] Step S304: When there are at least two key fields, combine the key fields to obtain the key field combination corresponding to the field to be migrated; query the correspondence between the key field combination and the business scenario to obtain the business scenario corresponding to the key field combination, which serves as the second target business scenario for the field to be migrated; based on the second target business scenario, obtain the first data classification result for the field to be migrated.

[0141] Step S305: Identify the current data type of the field value of the field to be migrated; query the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the current data type, which is used as the target feature extraction model for the field value; input the field value into the target feature extraction model to obtain the data features corresponding to the field value; identify the key data features in the data features.

[0142] Step S306: If the key data features meet the preset conditions, determine the data classification result corresponding to the key data features, and use it as the second data classification result of the field value.

[0143] Step S307: If the key data features do not meet the preset conditions, input the data features into the trained data classification prediction model to obtain the predicted probability of the field value under each preset data classification result; from each preset data classification result, select the preset data classification result with the predicted probability greater than the preset probability as the second data classification result of the field value.

[0144] Step S308: Determine the target data classification result of the field to be migrated based on the first data classification result and the second data classification result.

[0145] Step S309: Based on the target data classification results, determine the migration classification template corresponding to the field to be migrated; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system.

[0146] Step S310: According to the migration classification template, migrate the field to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

[0147] In the aforementioned nuclear safety regulatory data migration method, during data migration, the fields to be migrated and their values ​​in the data form are first classified in a dual manner. This allows the characteristics of the data to be migrated to be identified from two dimensions: field attributes and actual data content. The results are then fused to obtain the target classification result, which matches a precise migration classification template. The predefined migration classification template directly clarifies the field mapping relationship between the nuclear safety regulatory system and the target system, which helps improve the efficiency of data migration. Moreover, the entire process does not require manual intervention, avoiding the drawbacks of manual operation, which consumes a lot of time and manpower and leads to low data migration efficiency. This further improves the efficiency of data migration.

[0148] In an exemplary embodiment, to more clearly illustrate the nuclear safety regulatory data migration method provided in this application, the following specific embodiment will be used to describe the nuclear safety regulatory data migration method, which includes the following:

[0149] (1) Preparations before migration, parameter configuration and basic verification:

[0150] Before migrating nuclear safety regulatory data, it is necessary to configure multi-dimensional migration parameters to provide accurate basis for subsequent operations, specifically including:

[0151] Basic identification parameters: The unique identifier of the data form to be migrated (e.g., "HK_FORM_2024001", the prefix "HK" specifically refers to the nuclear safety regulatory form), and the regulatory business domain to which the form belongs (e.g., "Nuclear Facility Approval" "Emergency Response"), to ensure that the migration target accurately targets data in the nuclear safety field;

[0152] Storage address parameters: root directory of the new system's attachments, and backup address of the old system's data (used for data recovery in case of migration failure);

[0153] Security configuration parameters: Verification code validity period (e.g., 10 minutes, used for migration operator authentication).

[0154] In response to the unique characteristics of nuclear safety regulatory data, a new data compliance pre-verification step has been added:

[0155] Verify the completeness of the "required fields" in the forms to be migrated (e.g., nuclear facility approval forms must include core fields such as "license number" and "safety review conclusion"; if any are missing, mark them as "to be completed" and report them to the data specialist).

[0156] Verify the compliance of attachment formats (only allow traceable formats such as .pdf, .docx, and .xlsx, and prohibit risky formats such as .exe and .bat to prevent the migration of malicious files);

[0157] Mark sensitive data fields (such as "reactor power" and "radioactive material inventory") to prepare for subsequent graded migration.

[0158] (2) Repeated filtering for precise selection of unmigrated forms:

[0159] Based on the "unique form ID" configured in step (1), perform a synchronous duplicate filtering operation. The specific process is as follows:

[0160] Establish a "Nuclear Safety Regulatory Data Migration Log Library" to record the ID, migration time, operator, and migration status (success / failure) of migrated forms.

[0161] When migration is initiated, the system automatically queries the log database: if the form ID already exists and the status is "migration successful", the form is skipped directly to avoid data redundancy caused by repeated migration; if the ID exists but the status is "migration failed", it is marked as "to be retried" and associated with the failure reason (such as "attachment corrupted" or "field mapping error").

[0162] Output a "Duplicate Filtering Report" which lists the number of forms skipped, the number of forms to be retried, and the reasons, for administrators to verify and ensure that the filtering results are traceable.

[0163] (3) Data preprocessing, text field cleaning and sensitive data processing:

[0164] For Chinese text in nuclear safety regulatory forms (such as "Safety Review Comments" and "Emergency Response Plan Description"), perform refined cleaning and adaptation:

[0165] Format cleaning: Remove old system-specific tags (such as...)<old_system_style> ), and fix misaligned HTML tags (such as unclosed tags). (Tags), to ensure proper rendering in the new system;

[0166] Link conversion: Identify embedded attachment links in text (such as the old system address " / old_system / hk / attach / report_123.pdf"), automatically replace them with the new system address template (such as " / new_system / hk / general / report_123.pdf"), and record the link mapping relationship;

[0167] Terminology verification: Check the text for nuclear safety regulatory-specific terms (such as "defense in depth" and "probabilistic safety analysis") to ensure there are no typos or inaccurate expressions, so as to avoid affecting the understanding of regulatory business.

[0168] Record sensitive data processing logs, including field names, processing methods, and operators, to ensure traceability for subsequent audits.

[0169] (4) Data classification, accurately categorized based on regulatory business attributes:

[0170] By identifying key fields through importance prediction models and combining the correspondence between key fields and business scenarios, the target business scenarios of nuclear safety regulatory data can be effectively derived.

[0171] For the field set of nuclear safety regulatory data forms (such as "license number", "equipment pressure", "accident level", etc.), an importance prediction model based on machine learning can be constructed:

[0172] Input features include the frequency of field occurrence in historical regulatory business (e.g., "License Number" appears in 90% of approval forms), the weight of the impact of field value changes on business decisions (e.g., exceeding the "Equipment Pressure Value" will directly trigger a message reminder, with a weight of 0.9), and the risk level corresponding to the field (e.g., high risk, medium risk, and low risk).

[0173] The model outputs importance scores for each field through training (such as using random forest or XGBoost algorithms). Typically, the top 3-5 fields are identified as "key fields" (e.g., in nuclear facility approval forms, "license number", "approval status" and "safety review score" have the highest scores and become key fields).

[0174] Based on nuclear safety regulatory business specifications, a pre-defined mapping relationship library of "key field combinations - target business scenarios" is established:

[0175] If the key field combination is "License Number + Approval Status + Facility Type", then it corresponds to the "Facility Approval" scenario.

[0176] If the key field combination is "equipment pressure value + monitoring point + over-limit warning status", then it corresponds to the "equipment monitoring" scenario.

[0177] If the key field combination is "accident level + emergency measures + affected scope", then it corresponds to the "emergency response" scenario.

[0178] The mapping relationship needs to be dynamically optimized based on the experience of business experts (e.g., when adding the key field "material transportation number", supplement its correspondence with the "material transportation supervision" scenario).

[0179] Construct sensitive feature engineering for field values: Based on the different data types of field values, transform field values ​​into structured features that the model can process.

[0180] Final feature vector: [2,1,1,1,1,1,1,1,0.85,0.62] (corresponding to the above 9 features in order).

[0181] Phase 1: Rule Engine Preprocessing (Reducing Fuzzy Samples) Based on the nuclear safety specifications, a "hard rule base" is built to perform preliminary filtering on feature vectors. The remaining "fuzzy samples" enter the second phase of model prediction.

[0182] The second stage: Supervised learning model (output probability distribution) selects a model that supports multi-class probability output, such as a lightweight neural network (MLP): captures non-linear associations (such as the interaction of "semantic similarity + numerical fluctuation") through hidden layers and outputs a probability distribution.

[0183] Based on the primary and secondary categories, the final classification result of the field is determined.

[0184] (5) Field migration, based on precise mapping of classification templates:

[0185] For the classification results in step (4), configure a classification-specific migration template. The template must contain accurate mapping rules for nuclear safety regulatory fields.

[0186] The system automatically matches the corresponding template based on the form category. If there are new fields (such as the "Supervisory Responsible Person" field not existing in the old system), the system will prompt the administrator to supplement the mapping rules.

[0187] (6) Attachment migration:

[0188] Extract the old system attachment address field from the fields of the form to be migrated;

[0189] Extract the new system attachment address field information from the migration parameters;

[0190] Based on the storage address field information of the old system and the storage address field information of the new system, migrate the attachments corresponding to the forms to be migrated.

[0191] (7) Data consistency verification after migration:

[0192] Macro-level verification: Compare the total number of forms and attachments to be migrated from the old system with the actual number migrated from the new system to ensure no data loss (e.g., if the old system has 1,000 forms, the new system should successfully migrate at least 998 forms; if it fails, the reason must be explained).

[0193] Micro-level verification: Verify by associating "form ID-field value-attachment". For example, retrieve the "HK_FORM_2024001" form and check whether "security review score = 92" has been correctly migrated and whether the corresponding "report_123.pdf" attachment can be opened normally and has the same content.

[0194] Sensitive data validation: Verify whether the masked fields conform to the specifications (e.g., "Transportation route" should only display "XX district").

[0195] In the above embodiments, during data migration, by first performing a dual classification of the fields to be migrated and their values ​​in the data form, the characteristics of the data to be migrated can be locked from two dimensions: field attributes and actual data content. Then, the target classification results are fused to match an accurate migration classification template. The predefined migration classification template directly clarifies the field mapping relationship between the nuclear safety supervision system and the target system, which helps to improve the efficiency of data migration. Moreover, the entire process does not require manual intervention, avoiding the drawbacks of manual operation, which is prone to consuming a lot of time and manpower and resulting in low data migration efficiency, thereby improving the efficiency of data migration.

[0196] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0197] Based on the same inventive concept, this application also provides a nuclear safety regulatory data migration apparatus for implementing the aforementioned nuclear safety regulatory data migration method. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the nuclear safety regulatory data migration apparatus provided below can be found in the limitations of the nuclear safety regulatory data migration method described above, and will not be repeated here.

[0198] In one exemplary embodiment, such as Figure 4 As shown, a nuclear safety regulatory data migration device is provided, comprising: a field determination module 401, a result determination module 402, a target determination module 403, a template determination module 404, and a field migration module 405, wherein:

[0199] The field determination module 401 is used to determine the fields to be migrated corresponding to the data form to be migrated in response to the data migration instruction for the data form to be migrated corresponding to the nuclear safety regulatory system.

[0200] The result determination module 402 is used to determine the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated.

[0201] The target determination module 403 is used to determine the target data classification result of the field to be migrated based on the first data classification result and the second data classification result.

[0202] The template determination module 404 is used to determine the migration classification template corresponding to the field to be migrated based on the target data classification results; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system.

[0203] Field migration module 405 is used to migrate fields from the nuclear safety regulatory system to the target nuclear safety regulatory system according to the migration classification template.

[0204] In an exemplary embodiment, the result determination module 402 is further configured to obtain the business scenario coverage, decision influence weight, and field sensitivity of the field to be migrated; input the business scenario coverage, decision influence weight, and field sensitivity into the importance prediction model to obtain the predicted importance of the field to be migrated; select the fields to be migrated with a predicted importance greater than a preset importance from each field to be migrated as key fields; and determine the first data classification result of the field to be migrated based on the key fields.

[0205] In an exemplary embodiment, the result determination module 402 is further configured to: query the correspondence between the key field and the business scenario when there is only one key field, obtain the business scenario corresponding to the key field as the first target business scenario of the field to be migrated; obtain the first data classification result of the field to be migrated based on the first target business scenario; or, when there are at least two key fields, combine the key fields to obtain the key field combination corresponding to the field to be migrated; query the correspondence between the key field combination and the business scenario to obtain the business scenario corresponding to the key field combination as the second target business scenario of the field to be migrated; and obtain the first data classification result of the field to be migrated based on the second target business scenario.

[0206] In an exemplary embodiment, the result determination module 402 is further configured to identify the current data type of the field value of the field to be migrated; query the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the current data type, which is used as the target feature extraction model for the field value; input the field value into the target feature extraction model to obtain the data features corresponding to the field value; and determine the second data classification result of the field value based on the data features.

[0207] In an exemplary embodiment, the result determination module 402 is further configured to identify key data features in the data features; if the key data features meet preset conditions, determine the data classification result corresponding to the key data features as the second data classification result of the field value; or, if the key data features do not meet preset conditions, input the data features into the trained data classification prediction model to obtain the prediction probability of the field value under each preset data classification result; and select the preset data classification result with a prediction probability greater than the preset probability from each preset data classification result as the second data classification result of the field value.

[0208] In an exemplary embodiment, the nuclear safety regulatory data migration device further includes an attachment migration module, which is used to extract the first attachment address value of the attachment to be migrated in the nuclear safety regulatory system corresponding to the data form to be migrated from the field value of the field to be migrated; extract the second attachment address value of the attachment to be migrated in the target nuclear safety regulatory system from the data migration parameters carried by the data migration instruction; and migrate the attachment to be migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system according to the first attachment address value and the second attachment address value.

[0209] Each module in the aforementioned nuclear safety regulatory data migration device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0210] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data such as first data classification results and second data classification results. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a nuclear safety regulatory data migration method.

[0211] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0212] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0213] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0214] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0215] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0216] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0217] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for migrating nuclear safety regulatory data, characterized in that, The method includes: In response to a data migration instruction for a data form to be migrated corresponding to the nuclear safety regulatory system, the fields to be migrated corresponding to the data form to be migrated are determined; Determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated; Based on the first data classification result and the second data classification result, the target data classification result of the field to be migrated is determined; Based on the target data classification results, a migration classification template corresponding to the field to be migrated is determined; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system; According to the migration classification template, the field to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system; The determination of the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated include: Obtain the business scenario coverage, decision impact weight, and field sensitivity of the field to be migrated; The business scenario coverage, the decision impact weight, and the field sensitivity are input into the importance prediction model to obtain the predicted importance of the field to be migrated. From all the fields to be migrated, select the fields whose predicted importance is greater than the preset importance and use them as key fields; Based on the key fields, the first data classification result of the field to be migrated is determined; The determination of the first data classification result of the field to be migrated and the second data classification result of the field value of the field to be migrated further includes: Identify the current data type of the field value of the field to be migrated; The correspondence between data types and feature extraction models is queried to obtain the feature extraction model corresponding to the current data type, which is then used as the target feature extraction model for the field value. The field value is input into the target feature extraction model to obtain the data features corresponding to the field value; Based on the data characteristics, a second data classification result for the field value is determined.

2. The method according to claim 1, characterized in that, The step of determining the first data classification result of the field to be migrated based on the key field includes: If there is only one key field, query the correspondence between the key field and the business scenario to obtain the business scenario corresponding to the key field, which is used as the first target business scenario for the field to be migrated. Based on the first target business scenario, the first data classification result of the field to be migrated is obtained; or, When there are at least two key fields, the key fields are combined to obtain the key field combination corresponding to the field to be migrated; Query the correspondence between key field combinations and business scenarios to obtain the business scenarios corresponding to the key field combinations, which are used as the second target business scenarios for the fields to be migrated. Based on the second target business scenario, the first data classification result of the field to be migrated is obtained.

3. The method according to claim 1, characterized in that, The second data classification result for determining the field value based on the data characteristics includes: Identify the key data features in the data features; When the key data features meet the preset conditions, the data classification result corresponding to the key data features is determined as the second data classification result of the field value; or, If the key data features do not meet the preset conditions, the data features are input into the trained data classification prediction model to obtain the predicted probability of the field value under each preset data classification result. From the preset data classification results, the preset data classification results with a predicted probability greater than the preset probability are selected as the second data classification results of the field value.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Extract the first attachment address value of the attachment to be migrated in the nuclear safety supervision system corresponding to the data form to be migrated from the field values ​​of the field to be migrated; Extract the second attachment address value of the attachment to be migrated in the target nuclear safety monitoring system from the data migration parameters carried by the data migration instruction; Based on the first attachment address value and the second attachment address value, the attachment to be migrated is migrated from the nuclear safety regulatory system to the target nuclear safety regulatory system.

5. A nuclear safety regulatory data migration device, characterized in that, The device includes: The field determination module is used to determine the fields to be migrated corresponding to the data form to be migrated in response to the data migration instruction for the data form to be migrated corresponding to the nuclear safety regulatory system. The result determination module is used to determine the first data classification result of the field to be migrated, and the second data classification result of the field value of the field to be migrated; The target determination module is used to determine the target data classification result of the field to be migrated based on the first data classification result and the second data classification result. The template determination module is used to determine the migration classification template corresponding to the field to be migrated based on the target data classification result; the migration classification template is used to represent the mapping relationship between the field to be migrated in the nuclear safety regulatory system and the target nuclear safety regulatory system; The field migration module is used to migrate the field to be migrated from the nuclear safety supervision system to the target nuclear safety supervision system according to the migration classification template. The result determination module is further used to obtain the business scenario coverage, decision influence weight, and field sensitivity of the field to be migrated; input the business scenario coverage, decision influence weight, and field sensitivity into the importance prediction model to obtain the predicted importance of the field to be migrated; select the fields to be migrated with a predicted importance greater than a preset importance from the fields to be migrated as key fields; and determine the first data classification result of the field to be migrated based on the key fields. The result determination module is also used to identify the current data type of the field value of the field to be migrated; query the correspondence between the data type and the feature extraction model to obtain the feature extraction model corresponding to the current data type, which is used as the target feature extraction model for the field value; input the field value into the target feature extraction model to obtain the data features corresponding to the field value; and determine the second data classification result of the field value based on the data features.

6. The apparatus according to claim 5, characterized in that, The result determination module is also used to query the correspondence between the key field and the business scenario when there is only one key field, and obtain the business scenario corresponding to the key field as the first target business scenario of the field to be migrated. Based on the first target business scenario, a first data classification result of the field to be migrated is obtained; or, if there are at least two key fields, the key fields are combined to obtain a key field combination corresponding to the field to be migrated; the correspondence between the key field combination and the business scenario is queried to obtain the business scenario corresponding to the key field combination, which is used as the second target business scenario of the field to be migrated; based on the second target business scenario, a first data classification result of the field to be migrated is obtained.

7. The apparatus according to claim 5, characterized in that, The result determination module is further configured to identify key data features among the data features; if the key data features meet preset conditions, determine the data classification result corresponding to the key data features as the second data classification result of the field value; or, if the key data features do not meet the preset conditions, input the data features into the trained data classification prediction model to obtain the prediction probability of the field value under each preset data classification result; and select the preset data classification result whose prediction probability is greater than the preset probability from the preset data classification results as the second data classification result of the field value.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images