Air tightness data management method and system for air tightness detector

Abstract

The present invention discloses an airtightness data management method and system for an airtightness detector, and relates to the technical field of data management. An airtightness data management system for an airtightness detector includes: an airtightness data segmentation module, an airtightness data redundancy detection module, and an airtightness data compression management module. The present invention improves the efficiency of data processing and analysis by performing block processing on the target airtightness data set; by providing a summary of key information for each data block, it helps to quickly identify the base attributes and key features of the data; by identifying and marking redundant data, it provides a basis for data deduplication and compression; by dividing the data blocks with importance labels, it ensures that key data is retained and prioritized, and helps to apply customized compression strategies according to the different characteristics of the data blocks, thereby improving the pertinence and effect of data compression.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an airtightness data management method and system for an airtightness detector. Background Art

[0002] With the development of industrial automation and intelligent manufacturing, airtightness testing, as a key link in product quality control, has seen explosive growth in data volume. Due to the diversity of testing equipment and the time span, airtightness data management faces many challenges. Repeated testing of the same or similar products may lead to the generation of a large amount of redundant data, which not only increases the storage burden but also reduces the efficiency of data processing.

[0003] In the traditional data processing process, if the data cleaning method used is too simplified, important data may be mistakenly identified as redundant or erroneous data and deleted, resulting in the loss of valuable information; or similar data belonging to different devices may be cleared, resulting in data loss. Summary of the invention

[0004] The present invention aims to provide an airtightness data management method and system for an airtightness detector, so as to effectively manage the airtightness data and improve the efficiency and accuracy of the airtightness data management.

[0005] An airtightness data management method for an airtightness detector, comprising:

[0006] S1. Obtain the target airtightness data set, perform block processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n , n=1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ;

[0007] S2. Based on all target airtightness data block features T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n Performing data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set;

[0008] S3. Perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete data management of the target airtightness data set. The airtightness data compression strategy includes performing corresponding data compression operations on different data block sets.

[0009] As a preferred technical solution of the present invention, the specific steps of step S1 include:

[0010] S11. Obtain a target airtightness data set; perform a first division on the target airtightness data set according to the category segmentation standard to obtain a first target airtightness data set segmentation result; perform a second division on the first target airtightness data set segmentation result according to the time series sliding window segmentation method to obtain a second target airtightness data set segmentation result; perform a third division on the second target airtightness data set segmentation result according to the K-means clustering algorithm to obtain multiple target airtightness data blocks S12. n ;

[0011] S12. For each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n .

[0012] As a preferred technical solution of the present invention, the airtightness data block importance evaluation model in step S2 includes a data preprocessing layer, a feature matching layer and a structure output layer;

[0013] The data preprocessing layer is used to process the target airtightness data block features T n Perform preprocessing to obtain the preprocessing target airtightness data block feature U n ;

[0014] The feature matching layer is used to pre-process the target airtightness data block feature U n Perform importance matching to obtain the importance label B of the target airtightness data block n ;

[0015] The result output layer is used to output the importance label B of the target airtight data block. n ;

[0016] The specific steps for training the feature matching layer in the airtightness data block importance assessment model are:

[0017] Collecting several groups of airtight data block training samples, each group of airtight data block training samples contains a preprocessed airtight data block feature and a corresponding importance label; combining several groups of airtight data block training samples to obtain an airtight data block training set;

[0018] The feature matching layer is trained with the importance label as the target using the airtight data block training set to obtain the initial feature matching layer; the initial feature matching layer is evaluated to obtain the initial feature matching layer model evaluation result; if the initial feature matching layer model evaluation result is passed, the initial feature matching layer is used as the feature matching layer in the airtight data block importance evaluation model; otherwise, the model training is continued using the airtight data block training set.

[0019] As a preferred technical solution of the present invention, according to the characteristics T of all target airtightness data blocks, n The specific steps for data redundancy detection include:

[0020] For the target airtightness data block feature T n Calculate the approximate feature subset entropy and obtain the target airtightness data block subset entropy H n ; For all target airtightness data block subset entropy H n Calculate the mean and get the entropy mean J of the target airtightness data block subset n ; According to the target airtightness data block subset entropy mean J n Calculate the information gain and obtain the target airtightness data block subset entropy mean information gain value J n ';

[0021] For the target airtightness data block S n Calculate the entropy value in the target airtightness data set to obtain the entropy value D of the target airtightness data block n ; According to the target airtightness data block entropy value D n Calculate the information gain and obtain the information gain value Y of the target airtightness data block n ;

[0022] For the target airtightness data block S n Using the formula Calculate the corresponding information gain rate and obtain the information gain rate value P of the target airtightness data block n , γ is the balance coefficient;

[0023] If the information gain rate value P of the target airtightness data block n If the target airtightness data block is greater than or equal to the information gain threshold, the target airtightness data block is marked with a redundancy label R n is 1; if the information gain rate value of the target airtightness data block P n If the value is less than the information gain threshold, the target airtightness data block redundancy label R is marked. n is 0;

[0024] Traverse all target airtightness data blocks S n and the corresponding target airtightness data block feature Tn , for all target airtightness data block features T n Perform data redundancy detection.

[0025] As a preferred technical solution of the present invention, based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n The specific steps for data classification include:

[0026] For the target airtightness data block S n , using formula G n =R n *B n *F, calculate the target airtightness data block evaluation function value G n , F is the weight coefficient;

[0027] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the first redundancy range, n Dividing into a target airtight non-redundant data block set;

[0028] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the second redundancy range, n Dividing into target airtight redundant data block sets;

[0029] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the third redundancy range, n Divided into target airtightness special data block sets.

[0030] As a preferred technical solution of the present invention, the specific steps of performing similarity classification on the target airtightness data blocks in the target airtightness redundant data block set in step S3 include:

[0031] It is stipulated that the target airtightness redundant data block set contains I data blocks, which are represented as target airtightness data blocks S i , i=1,2,…,I;

[0032] For the target airtightness data block S i , the target airtightness data block S i Compare the similarity with the rest of the target airtightness data blocks in the target airtightness redundant data block set, and record the similarity with the target airtightness data block S i The similarity value V of the target airtightness data block corresponding to the maximum similarity i , the target airtightness data block similarity value V iCompared with the similarity threshold, if the target airtightness data block similarity value V i If the similarity is greater than the threshold, the target airtightness data block S i Divide into a redundant data block set of high-repetition target airtightness data; otherwise, the target airtightness data block S i Dividing into redundant data block sets with low duplication target airtightness data;

[0033] Traverse all target airtightness data blocks S i , until the target airtightness redundant data block set is divided into a high-repetition target airtightness redundant data block set and a low-repetition target airtightness redundant data block set.

[0034] As a preferred technical solution of the present invention, the specific steps of performing the compression operation according to the airtight data compression strategy in step S3 include:

[0035] Deduplication incremental compression operations are performed on redundant data block sets of highly repetitive target airtightness data, incremental compression operations are performed on redundant data block sets of low repetitive target airtightness data, general compression operations are performed on non-redundant data block sets of target airtightness data, and direct storage operations are performed on special target airtightness data block sets to complete data management of the target airtightness data set.

[0036] An airtightness data management system for an airtightness detector, comprising:

[0037] The airtightness data segmentation module is used to obtain the target airtightness data set, perform segmentation processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n , n=1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ;

[0038] The airtightness data redundancy detection module is used to deploy the airtightness data block importance assessment model based on the characteristics of all target airtightness data blocks T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S nPerforming data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set;

[0039] The airtightness data compression management module is used to perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete the data management of the target airtightness data set. The airtightness data compression strategy includes performing corresponding data compression operations on different data block sets.

[0040] The present invention has the following advantages:

[0041] 1. The present invention improves the efficiency of data processing and analysis by performing block processing on the target airtightness data set; by providing a summary of key information for each data block, it helps to quickly identify the basic attributes and key features of the data; by identifying and marking redundant data, it provides a basis for data deduplication and compression; by dividing the data blocks with importance labels, it ensures that key data is retained and prioritized, and helps to apply customized compression strategies according to the different characteristics of the data blocks, thereby improving the pertinence and effect of data compression.

[0042] 2. By implementing an airtight data redundancy detection process, the present invention can accurately quantify the uncertainty and complexity of data, effectively evaluate and distinguish the redundancy of data blocks, help optimize data storage efficiency, save storage space, and significantly improve data processing speed, ensure the simplicity and high quality of data sets, enhance data security, reduce the risk of leakage, and improve the consistency and accuracy of data processing through automated methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a structural schematic diagram of an airtightness data management system for an airtightness detector adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0045] Embodiment 1, an airtightness data management method for an airtightness detector, comprising:

[0046] S1. Obtain the target airtightness data set, perform block processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n, n=1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ;

[0047] The specific steps of step S1 include:

[0048] S11. Obtain a target airtightness data set; perform a first division on the target airtightness data set according to the category segmentation standard to obtain a first target airtightness data set segmentation result; perform a second division on the first target airtightness data set segmentation result according to the time series sliding window segmentation method to obtain a second target airtightness data set segmentation result; perform a third division on the second target airtightness data set segmentation result according to the K-means clustering algorithm to obtain multiple target airtightness data blocks S12. n ;

[0049] The category block standard is used to preliminarily classify the target airtightness data set, divide the data sources of the data in the target airtightness data set, and divide the airtightness data belonging to the same device into the same data block to ensure that the source of the data in the data block is unified and will not affect subsequent data queries; the time series sliding window block method is used to divide the time series of airtightness data from the same device, which can efficiently process and analyze airtightness data that changes over time, capture the time-sensitive characteristics of airtightness data, and identify data trends and periodic changes; compared with analyzing the entire time series, the sliding window can reduce the amount of data processed simultaneously and reduce computing resource consumption; the K-means clustering algorithm is used to further divide the data blocks based on features, and divide the data blocks belonging to the same time period again. Through clustering, data blocks with similar features can be identified, which helps to understand the internal structure of the data. In the same time period, data blocks may represent different events or states, and K-means clustering can further subdivide these data blocks;

[0050] S12. For each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ;

[0051] S2. Based on all target airtightness data block features T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B nand the target airtightness data block redundancy label R n For the target airtightness data block S n Performing data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set;

[0052] The airtightness data block importance evaluation model in step S2 includes a data preprocessing layer, a feature matching layer and a structure output layer;

[0053] The data preprocessing layer is used to process the target airtightness data block features T n Perform preprocessing to obtain the preprocessing target airtightness data block feature U n ;

[0054] The feature matching layer is used to pre-process the target airtightness data block feature U n Perform importance matching to obtain the importance label B of the target airtightness data block n ;

[0055] The result output layer is used to output the importance label B of the target airtight data block. n ;

[0056] The specific steps for training the feature matching layer in the airtightness data block importance assessment model are:

[0057] Collect several groups of airtightness data block training samples, each group of airtightness data block training samples contains a preprocessed airtightness data block feature and a corresponding importance label; combine several groups of airtightness data block training samples to obtain an airtightness data block training set; the importance labels are annotated by professional technicians according to actual conditions;

[0058] The feature matching layer is trained with the importance label as the target using the airtight data block training set to obtain the initial feature matching layer; the initial feature matching layer is evaluated to obtain the initial feature matching layer model evaluation result; if the initial feature matching layer model evaluation result is passed, the initial feature matching layer is used as the feature matching layer in the airtight data block importance evaluation model; otherwise, the model training is continued using the airtight data block training set;

[0059] The data preprocessing layer ensures the consistency and standardization of the data, providing clean and formatted data for further analysis; the feature matching layer identifies the most critical features for airtightness assessment through importance matching; the accuracy and reliability of the feature matching layer are ensured through initial evaluation and possible iterative training; the training process ensures that the model can accurately evaluate the importance of airtightness data blocks and provide decision support for data management;

[0060] According to all target airtightness data block features T nThe specific steps for data redundancy detection include:

[0061] For the target airtightness data block feature T n Calculate the approximate feature subset entropy and obtain the target airtightness data block subset entropy H n ; For all target airtightness data block subset entropy H n Calculate the mean and get the entropy mean J of the target airtightness data block subset n ; According to the target airtightness data block subset entropy mean J n Calculate the information gain and obtain the target airtightness data block subset entropy mean information gain value J n '; By calculating the feature subset entropy of each data block, the uncertainty and information complexity of the data block are quantified. This helps to identify the variability and information richness of the data block; the mean of the subset entropy provides a macro description of the information complexity of all data blocks in the dataset, which helps to evaluate the diversity of the data as a whole; the information gain based on the mean of the subset entropy reflects the measure of the information difference between data blocks, which helps to identify the discrimination of data blocks;

[0062] For the target airtightness data block S n Calculate the entropy value in the target airtightness data set to obtain the entropy value D of the target airtightness data block n ; According to the target airtightness data block entropy value D n Calculate the information gain and obtain the information gain value Y of the target airtightness data block n ; The entropy value is calculated for a single data block, which reflects the uncertainty and information distribution within the data block. The information gain value reflects the relative importance of the data block in the data set, which helps to evaluate the contribution of the data block to the overall data set;

[0063] For the target airtightness data block S n Using the formula Calculate the corresponding information gain rate and obtain the information gain rate value P of the target airtightness data block n , γ is the balance coefficient; the role of γ is to adjust the data to ensure the uniformity of the data; the value of γ is set by professional technicians according to actual conditions; the information gain rate combines the complexity within the data block and the differences between data blocks to provide a comprehensive evaluation index;

[0064] If the information gain rate value P of the target airtightness data block n If the target airtightness data block is greater than or equal to the information gain threshold, the target airtightness data block is marked with a redundancy label R n is 1; if the information gain rate value of the target airtightness data block P n If the value is less than the information gain threshold, the target airtightness data block redundancy label R is marked. n0; according to the comparison between the information gain rate and the preset threshold, the data block is marked with redundancy to clearly distinguish the redundant state of the data block. The information gain threshold is set by professional technicians according to the actual situation;

[0065] Traverse all target airtightness data blocks S n and the corresponding target airtightness data block feature T n , for all target airtightness data block features T n Perform data redundancy detection;

[0066] Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n The specific steps for data classification include:

[0067] For the target airtightness data block S n , using formula G n =R n *B n *F, calculate the target airtightness data block evaluation function value G n , F is the weight coefficient; the specific value of F is set by professional technicians according to actual conditions;

[0068] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the first redundancy range, n Dividing into a target airtight non-redundant data block set;

[0069] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the second redundancy range, n Dividing into target airtight redundant data block sets;

[0070] If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the third redundancy range, n Divide into target airtightness special data block sets;

[0071] The first redundant range, the second redundant range and the third redundant range are divided by professional technicians, based on the importance and redundancy labels of the target airtightness data block, combined with the dynamic evaluation function G of the weight coefficient F n Computing realizes the accurate classification of data blocks, optimizes the allocation of data storage resources, improves data processing efficiency and data set quality, and not only enhances the security and reuse value of data, but also meets the data management needs of different categories of data through flexibility and adaptability, thus reducing maintenance costs;

[0072] S3. Perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete data management of the target airtightness data set, and the airtightness data compression strategy includes performing corresponding data compression operations on different data block sets;

[0073] The specific steps of performing similarity classification on the target airtightness data blocks in the target airtightness redundant data block set in step S3 include:

[0074] It is stipulated that the target airtightness redundant data block set contains I data blocks, which are represented as target airtightness data blocks S i , i=1,2,…,I;

[0075] For the target airtightness data block S i , the target airtightness data block S i Compare the similarity with the rest of the target airtightness data blocks in the target airtightness redundant data block set, and record the similarity with the target airtightness data block S i The similarity value V of the target airtightness data block corresponding to the maximum similarity i , the target airtightness data block similarity value V i Compared with the similarity threshold, if the target airtightness data block similarity value V i If the similarity is greater than the threshold, the target airtightness data block S i Divide into a redundant data block set of high-repetition target airtightness data; otherwise, the target airtightness data block S i Dividing into redundant data block sets with low duplication target airtightness data;

[0076] The similarity threshold is determined by professional technicians based on actual conditions. Similarity classification enables more refined management of redundant data blocks and distinguishes redundant data of different degrees. The distinction between highly duplicated data block sets and low duplicated data block sets provides a basis for applying different compression strategies and optimizes the compression effect. Compressing data blocks with high similarity reduces storage space usage, improves storage efficiency, reduces the processing of redundant data, speeds up data processing, and improves overall performance.

[0077] Traverse all target airtightness data blocks S i , until the target airtightness redundant data block set is divided into a high-repetition target airtightness redundant data block set and a low-repetition target airtightness redundant data block set;

[0078] The specific steps of performing the compression operation according to the airtight data compression strategy in step S3 include:

[0079] Perform deduplication incremental compression operations on redundant data block sets with high duplication target tightness data, reducing storage space requirements while preserving data integrity by identifying and eliminating repeated patterns or sequences in the data;

[0080] Perform incremental compression operations on redundant data blocks with low duplication and airtightness targets, compressing only the changed parts of the data instead of the entire data set, which helps save storage resources and reduce processing time;

[0081] Performing a general compression operation on a non-redundant data block set of target airtightness data, and applying a general compression algorithm to reduce the volume of data to improve storage efficiency;

[0082] Direct storage operations are performed on the target airtightness special data block set to ensure instant access and use of special data and complete data management of the target airtightness data set.

[0083] Example 2, an airtightness data management system for an airtightness detector, see Figure 1 As shown, including:

[0084] The airtightness data segmentation module is used to obtain the target airtightness data set, perform segmentation processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n , n=1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ;

[0085] The airtightness data redundancy detection module is used to deploy the airtightness data block importance assessment model based on the characteristics of all target airtightness data blocks T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n Performing data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set;

[0086] The airtightness data compression management module is used to perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete the data management of the target airtightness data set. The airtightness data compression strategy includes performing corresponding data compression operations on different data block sets.

[0087] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. An airtightness data management method for an airtightness detector, characterized in that: include: S1. Obtain the target airtightness data set, perform block processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n , n = 1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ; S2. Based on all target airtightness data block features T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n Performing data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set; S3. Perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete data management of the target airtightness data set, and the airtightness data compression strategy includes performing corresponding data compression operations on different data block sets; According to all target airtightness data block features T n The specific steps for data redundancy detection include: For the target airtightness data block feature T n Calculate the approximate feature subset entropy and obtain the target airtightness data block subset entropy H n ; For all target airtightness data block subset entropy H n Calculate the mean and get the entropy mean J of the target airtightness data block subset n ; According to the target airtightness data block subset entropy mean J n Calculate the information gain and obtain the target airtightness data block subset entropy mean information gain value J n '; For the target airtightness data block S n Calculate the entropy value in the target airtightness data set to obtain the entropy value D of the target airtightness data block n ; According to the target airtightness data block entropy value D n Calculate the information gain and obtain the information gain value Y of the target airtightness data block n ; For the target airtightness data block S n Using the formula Calculate the corresponding information gain rate and obtain the information gain rate value P of the target airtightness data block n , γ is the balance coefficient; If the information gain rate value P of the target airtightness data block n If the target airtightness data block is greater than or equal to the information gain threshold, the target airtightness data block is marked with a redundancy label R n is 1; if the information gain rate value of the target airtightness data block P n If the value is less than the information gain threshold, the target airtightness data block redundancy label R is marked. n is 0; Traverse all target airtightness data blocks S n and the corresponding target airtightness data block feature T n , for all target airtightness data block features T n Perform data redundancy detection; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n The specific steps for data classification include: For the target airtightness data block S n , using formula G n =R n *B n *F, calculate the target airtightness data block evaluation function value G n , F is the weight coefficient; If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the first redundancy range, n Dividing into a target airtight non-redundant data block set; If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the second redundancy range, n Dividing into a target airtight redundant data block set; If the target airtightness data block evaluation function value G n If the target airtightness data block S is within the third redundancy range, n Divided into target airtightness special data block sets.

2. The airtightness data management method for an airtightness detector according to claim 1, characterized in that: step The specific steps of S1 include: S11. Obtain a target airtightness data set; perform a first division on the target airtightness data set according to the category segmentation standard to obtain a first target airtightness data set segmentation result; perform a second division on the first target airtightness data set segmentation result according to the time series sliding window segmentation method to obtain a second target airtightness data set segmentation result; perform a third division on the second target airtightness data set segmentation result according to the K-means clustering algorithm to obtain multiple target airtightness data blocks S12. n ; S12. For each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n .

3. The airtightness data management method for an airtightness detector according to claim 2, characterized in that: The airtightness data block importance evaluation model in step S2 includes a data preprocessing layer, a feature matching layer and a structure output layer; the data preprocessing layer is used to match the target airtightness data block feature T n Perform preprocessing to obtain the preprocessing target airtightness data block feature U n ; The feature matching layer is used to pre-process the target airtightness data block feature U n Perform importance matching to obtain the importance label B of the target airtightness data block n ; The result output layer is used to output the importance label B of the target airtight data block. n ; The specific steps for training the feature matching layer in the airtightness data block importance assessment model are: Collecting several groups of airtight data block training samples, each group of airtight data block training samples contains a preprocessed airtight data block feature and a corresponding importance label; combining several groups of airtight data block training samples to obtain an airtight data block training set; The feature matching layer is trained with the importance label as the target using the airtight data block training set to obtain the initial feature matching layer; the initial feature matching layer is evaluated to obtain the initial feature matching layer model evaluation result; if the initial feature matching layer model evaluation result is passed, the initial feature matching layer is used as the feature matching layer in the airtight data block importance evaluation model; otherwise, the model training is continued using the airtight data block training set.

4. The airtightness data management method for an airtightness detector according to claim 3, characterized in that: The specific steps of performing similarity classification on the target airtightness data blocks in the target airtightness redundant data block set in step S3 include: It is stipulated that the target airtightness redundant data block set contains I data blocks, which are represented as target airtightness data blocks S i , i=1,2,…,I; For the target airtightness data block S i , the target airtightness data block S i Compare the similarity with the rest of the target airtightness data blocks in the target airtightness redundant data block set, and record the similarity with the target airtightness data block S i The similarity value V of the target airtightness data block corresponding to the maximum similarity i , the target airtightness data block similarity value V i Compared with the similarity threshold, if the target airtightness data block similarity value V i If the similarity is greater than the threshold, the target airtightness data block S i Divide into a redundant data block set of high-repetition target airtightness data; otherwise, the target airtightness data block S i Dividing into redundant data block sets with low duplication target airtightness data; Traverse all target airtightness data blocks S i , until the target airtightness redundant data block set is divided into a high-repetition target airtightness redundant data block set and a low-repetition target airtightness redundant data block set.

5. The airtightness data management method for an airtightness detector according to claim 4, characterized in that: The specific steps of performing the compression operation according to the airtight data compression strategy in step S3 include: Deduplication incremental compression operations are performed on redundant data block sets of highly repetitive target airtightness data, incremental compression operations are performed on redundant data block sets of low repetitive target airtightness data, general compression operations are performed on non-redundant data block sets of target airtightness data, and direct storage operations are performed on special target airtightness data block sets to complete data management of the target airtightness data set.

6. An airtightness data management system for an airtightness detector, characterized in that: The system applies the airtightness data management method for an airtightness detector as described in any one of claims 1 to 5, including: The airtightness data segmentation module is used to obtain the target airtightness data set, perform segmentation processing on the target airtightness data set, and obtain multiple target airtightness data blocks S n , n = 1, 2, ..., N, N is the number of target airtightness data blocks; for each target airtightness data block S n Perform feature extraction to obtain the target airtightness data block feature T n ; The airtightness data redundancy detection module is used to deploy the airtightness data block importance assessment model based on the characteristics of all target airtightness data blocks T n The importance label is divided with the airtightness data block importance evaluation model to obtain the target airtightness data block importance label B n ; According to all target airtightness data block features T n Perform data redundancy detection to obtain the target airtightness data block redundancy label R n ; Based on the target airtightness data block importance label B n and the target airtightness data block redundancy label R n For the target airtightness data block S n Performing data classification to obtain a target airtightness redundant data block set, a target airtightness non-redundant data block set, and a target airtightness special data block set; The airtightness data compression management module is used to perform similarity classification on the target airtightness data blocks in the target airtightness redundant data block set to obtain a high-repetition target airtightness data redundant data block set and a low-repetition target airtightness data redundant data block set; perform compression operations according to the airtightness data compression strategy to complete the data management of the target airtightness data set. The airtightness data compression strategy includes performing corresponding data compression operations on different data block sets.

Images