Data classification method and device, equipment and storage medium

Abstract

The invention provides a data classification method and device, equipment and a storage medium. The method comprises the steps of obtaining to-be-processed data; inputting the to-be-processed data into a data classification model to obtain classified data and categories of the classified data; the data classification model is a deep learning model; and according to the category of the classification data, processing the classification data based on a natural language processing technology and a preset identification rule, and determining sensitive information. According to the method and the device, accurate classification of the data is realized, sensitive information can be identified and processed, and the data security is enhanced.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a data classification method, device, equipment and storage medium. Background Art

[0002] With the rapid development of modern information technology, the types of data stored in databases have become more and more diverse, including text, pictures, audio, video, compressed files and other formats, but traditional data management methods can hardly effectively cope with such diverse data types.

[0003] In addition, in the identification and classification of sensitive data, traditional methods often rely on manual operations, which is not only inefficient but also prone to misjudgment and omission. In addition, due to the differences in database versions and structures, traditional methods cannot adapt well to a variety of database systems, resulting in certain limitations in the analysis and classification of database content. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a data classification method, device, equipment and storage medium.

[0005] As one aspect of the present application, a data classification method is provided, comprising:

[0006] Get the data to be processed;

[0007] Inputting the data to be processed into a data classification model to obtain classified data and categories of the classified data; the data classification model is a deep learning model;

[0008] According to the category of the classified data, the classified data is processed based on natural language processing technology and preset recognition rules to determine sensitive information.

[0009] Optionally, the step of inputting the data to be processed into a data classification model to obtain classified data and categories of the classified data includes:

[0010] According to structured query language, determining that the category of the classified data is text data;

[0011] According to the binary large object field, it is determined that the category of the classified data is image data.

[0012] Optionally, the processing the classified data based on the category of the classified data and natural language processing technology and preset identification rules to determine the sensitive information includes:

[0013] Processing the text data based on regular expressions and a preset rule library to identify the sensitive information;

[0014] The image data is processed based on a picture recognition model to identify the sensitive information.

[0015] Optionally, the sensitive information is stored in encrypted form and access rights are assigned;

[0016] Based on the access operation and the access rights stated, access logs are recorded.

[0017] Optionally, in response to an abnormality in the data to be processed or the classified data, an error log is recorded;

[0018] In response to the number of occurrences of the abnormal situation being greater than a preset threshold, the error log is sent to an administrator.

[0019] Optionally, training data is obtained according to a multi-level data fusion technology; the training data at least includes: the data to be processed, the classified data and the access log;

[0020] The data classification model is updated according to the training data.

[0021] Optionally, obtaining the data to be processed includes:

[0022] Get the original data from the database;

[0023] In response to the original data being a compressed file, a decompression operation is performed on the compressed file to obtain the data to be processed.

[0024] As a second aspect of the present application, a data classification device is provided, comprising: an acquisition module and a processing module;

[0025] The acquisition module is used to acquire the data to be processed;

[0026] The processing module is used to input the data to be processed into a data classification model to obtain classified data and the category of the classified data; the data classification model is a deep learning model;

[0027] The processing module is also used to process the classified data according to the category of the classified data based on natural language processing technology and preset recognition rules to determine sensitive information.

[0028] Optionally, the processing module is specifically used to determine, according to a structured query language, that the category of the classified data is text data;

[0029] According to the binary large object field, it is determined that the category of the classified data is image data.

[0030] Optionally, the processing module is further configured to process the text data based on a regular expression and a preset rule base to identify the sensitive information;

[0031] The image data is processed based on a picture recognition model to identify the sensitive information.

[0032] Optionally, the processing module is further used to encrypt and store the sensitive information and assign access rights;

[0033] The data classification device also includes a recording module;

[0034] The recording module is used to record access logs according to the access operation and the access authority.

[0035] Optionally, the recording module is further used to record an error log in response to an abnormality in the data to be processed or the classified data;

[0036] The data classification device also includes a sending module;

[0037] The sending module is used to send the error log to an administrator in response to the number of occurrences of the abnormal situation being greater than a preset threshold.

[0038] Optionally, the acquisition module is further used to acquire training data according to a multi-level data fusion technology; the training data at least includes: the data to be processed, the classified data and the access log;

[0039] The data classification device also includes an updating module;

[0040] The updating module is used to update the data classification model according to the training data.

[0041] Optionally, the acquisition module is specifically used to acquire original data from a database;

[0042] In response to the original data being a compressed file, a decompression operation is performed on the compressed file to obtain the data to be processed.

[0043] As a third aspect of the present application, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned data classification method when executing the program.

[0044] As a fourth aspect of the present application, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data classification method provided in the present application.

[0045] As can be seen from the above, the data classification method, device, equipment and storage medium provided by the present application classify the data to be processed through the data classification model. Since the data classification model is a deep learning model, it can capture the complex features and patterns in the data, thereby achieving accurate classification of the data and obtaining the classification results and their categories. Furthermore, by combining natural language processing technology and preset recognition rules to process the classified data, sensitive information can be effectively identified and processed, thereby enhancing data security. By identifying and processing sensitive information, it helps to protect personal privacy and comply with data protection regulations, and reduce the risk of data leakage. In addition, by adjusting the training parameters and preset recognition rules of the deep learning model, this solution can adapt to data processing needs of different types and scales, help to enhance the performance when processing large-scale data sets, and at the same time, enhance the flexibility and adaptability of data classification, and significantly improve the speed and efficiency of data classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 A flowchart of a data classification method provided in an embodiment of the present application;

[0048] Figure 2 A flowchart of another data classification method provided in an embodiment of the present application;

[0049] Figure 3 A flowchart of another data classification method provided in an embodiment of the present application;

[0050] Figure 4 A flowchart of another data classification method provided in an embodiment of the present application;

[0051] Figure 5 A flowchart of another data classification method provided in an embodiment of the present application;

[0052] Figure 6 A flowchart of another data classification method provided in an embodiment of the present application;

[0053] Figure 7 A flowchart of another data classification method provided in an embodiment of the present application;

[0054] Figure 8 A schematic diagram of the composition of a data classification device provided in an embodiment of the present application;

[0055] Fig. 9 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0057] It should be noted that, in the embodiments of the present application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a concrete way. Unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meaning understood by people with ordinary skills in the field to which the present application belongs. SUMMARY OF THE INVENTION

[0059] In related technologies, the rapid development of artificial intelligence and machine learning technologies has driven a sharp increase in the amount of data. However, as the amount of data increases, the complexity and diversity of the data also increase. Traditional data analysis methods, such as statistical data analysis and simple data mining techniques, have been unable to meet the needs of modern enterprises for deep data mining and intelligent analysis. Especially for databases containing a large amount of unstructured data, traditional analysis methods often seem to be unable to effectively extract and utilize the valuable information therein.

[0060] The inventors of this application have found that traditional artificial intelligence and data analysis tools are difficult to cope with large and complex unstructured data sets and lack sufficient flexibility and intelligence. In addition, traditional data analysis methods often require a lot of manual preprocessing and feature extraction when processing these data, which is not only inefficient but also prone to subjectivity and errors. In addition, due to the diversity and complexity of data, traditional analysis methods often find it difficult to discover hidden patterns and correlations in the data, thereby limiting the full realization of the value of the data.

[0061] In order to solve the above problems, the present application provides a data classification method, which classifies the data to be processed through a data classification model. Since the data classification model is a deep learning model, it can capture the complex features and patterns in the data, thereby achieving accurate classification of the data and obtaining classification results and their categories. Furthermore, by combining natural language processing technology and preset recognition rules to process classified data, sensitive information can be effectively identified and processed, thereby enhancing data security. By identifying and processing sensitive information, it helps to protect personal privacy and comply with data protection regulations, and reduce the risk of data leakage. In addition, by adjusting the training parameters and preset recognition rules of the deep learning model, this solution can adapt to data processing needs of different types and scales, help to enhance the performance when processing large-scale data sets, and at the same time, enhance the flexibility and adaptability of data classification, significantly improving the speed and efficiency of data classification.

[0062] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application are described in detail below.

[0063] Figure 1 A flow chart of a data classification method provided in an embodiment of the present application. Figure 1 As shown, the data classification method provided by this application specifically includes the following steps:

[0064] S101. Obtain data to be processed.

[0065] In some embodiments, data of various types including text, images, audio, etc. are extracted from a database, and these data include structured data (such as tabular data) and unstructured data (such as text, images). Furthermore, these data are preprocessed, including data cleaning, format conversion, and semantic analysis. Data cleaning includes removing redundant data and correcting format errors; format conversion is to convert data into a unified format for further processing; semantic analysis is to perform preliminary semantic analysis on the data content and extract possible classification features.

[0066] The data sources may be a variety of database versions and complex data content environments, including but not limited to relational databases, non-relational databases, and cloud database platforms.

[0067] For example, for text data, operations such as word segmentation, stop word removal, and stem extraction are performed to make the text data more structured and facilitate subsequent analysis and processing. For image data, image scaling, cropping, and format conversion are performed to ensure that the image data meets system requirements.

[0068] In some embodiments, Figure 2 As shown, S101 can be specifically implemented as follows S1011-S1012:

[0069] S1011. Obtain original data from the database.

[0070] In some embodiments, a structured query language (SQL) query is executed on a relational database to retrieve data in a specific table or view. At the same time, the original data in the database can be automatically extracted through the application programming interface (API) provided by the database, such as Java Database Connectivity (JDBC), Open Database Connectivity (ODBC) or a software development kit (SDK) of a specific database.

[0071] The original data includes but is not limited to text, pictures, audio, video, compressed files and other formats. The database versions also include MySQL, Oracle, SQL Server, etc.

[0072] S1012: In response to the original data being a compressed file, decompress the compressed file to obtain data to be processed.

[0073] In some embodiments, by identifying compressed file header information in a binary large object (BLOB) field, such as ZIP, RAR, 7z and other compression formats, the data to be processed is automatically decompressed and extracted, including text, image, audio or other format files, and then each file is processed separately and classified by file type. In addition, for nested compressed files, recursive decompression is implemented until all non-compressed files are obtained.

[0074] S102: Input the data to be processed into a data classification model to obtain classified data and categories of the classified data.

[0075] Among them, the data classification model is a deep learning model.

[0076] In some embodiments, the data to be processed is input into a pre-trained deep learning model, which can classify the data into predefined categories, such as text data, image data, audio data, etc., based on the characteristics and context information of the data. The classification criteria can be customized according to actual business needs and application scenarios.

[0077] It should be understood that the data analysis model has been trained with a large amount of data and can process various data formats, including text, images and audio. The model also has dynamic learning capabilities and can automatically adjust classification rules based on new data to adapt to changing business needs.

[0078] In some embodiments, Figure 3 As shown, S102 can be specifically implemented as follows S1021-S1022:

[0079] S1021. According to the structured query language, determine that the category of the classified data is text data.

[0080] In some embodiments, text field data is extracted from a database table through an SQL query statement and formatted into a standard text form for further processing, for example, removing redundant spaces, line breaks, and special characters, unifying the case of the text, and converting the text into a specific encoding format, etc. When formatting the text field data, for the integrity and consistency of the data, default values ​​are filled for missing values, and records with abnormal values ​​are deleted, etc., to ensure the accuracy of subsequent processing and analysis.

[0081] S1022. Determine, according to the binary large object field, that the category of the classified data is image data.

[0082] In some embodiments, the image file is extracted from the BLOB field, and the binary data is converted into an image file format, such as JPEG, PNG, or GIF, or the specific type of the image is determined using file signatures (magic numbers) or file extensions. After the image is extracted, preliminary processing is automatically performed, such as scaling, cropping, etc.

[0083] S103. According to the category of the classified data, the classified data is processed based on natural language processing technology and preset recognition rules to determine sensitive information.

[0084] In some embodiments, natural language processing technology (NLP), a technology that performs deep semantic analysis on text data, can accurately understand the meaning of the text. The preset recognition rules can be sensitive information recognition rules formulated according to business needs and data characteristics, and are used to match and identify sensitive information in the data.

[0085] Among them, sensitive information includes unified social credit code, email address, MAC address, IPv6 address, IPv4 address, domain name, landline phone number, mobile phone number, postal code, license plate number, bank card number, passport number and ID card number.

[0086] Exemplarily, a convolutional neural network (CNN) is used to process image data to identify objects or scenes in the image; NLP is used to perform deep semantic analysis on the classified text to identify sensitive information such as keywords, phrases, and sentences; a recurrent neural network (RNN) is used to process audio data to recognize voice commands, etc.

[0087] In some embodiments, Figure 4 As shown, S103 can be specifically implemented as follows S1031-S1032:

[0088] S1031. Process text data based on regular expressions and a preset rule base to identify sensitive information.

[0089] In some embodiments, regular expressions are a powerful text pattern matching tool. A corresponding regular expression is written for each type of sensitive information, for example, to identify ID numbers, credit card numbers, phone numbers, etc. The regular expression is applied to the text data to scan and identify matching sensitive information. The preset rule library contains rules for identifying specific sensitive information (such as ID numbers, phone numbers, etc.). These rules can be based on keywords, phrases, specific formats or patterns, etc. By matching the text data with the preset rule library, sensitive information in the text can be quickly identified.

[0090] Exemplarily, text fields are automatically scanned to identify email addresses, mobile phone numbers, and social credit codes, and such sensitive information is marked and encrypted.

[0091] S1032. Process image data based on an image recognition model to identify sensitive information.

[0092] In some embodiments, a deep learning image recognition model is used to identify sensitive information in an image, detect whether the image contains information such as an ID card, bank card, confidential documents, etc., and classify it as sensitive data based on the image content. For example, for image data, the license plate number and ID card number in the image are identified and extracted, and encrypted to ensure the security of this information.

[0093] The data classification method provided in this application classifies the data to be processed through a data classification model. Since the data classification model is a deep learning model, it can capture the complex features and patterns in the data, thereby achieving accurate classification of the data and obtaining classification results and their categories. Furthermore, by combining natural language processing technology and preset recognition rules to process classified data, sensitive information can be effectively identified and processed, thereby enhancing data security. By identifying and processing sensitive information, it helps to protect personal privacy and comply with data protection regulations, and reduce the risk of data leakage. In addition, by adjusting the training parameters and preset recognition rules of the deep learning model, this solution can adapt to data processing needs of different types and scales, help to enhance the performance when processing large-scale data sets, and at the same time, enhance the flexibility and adaptability of data classification, significantly improving the speed and efficiency of data classification.

[0094] In some embodiments, Figure 5 As shown, the data classification method provided in the embodiment of the present application also includes the following S201-S202:

[0095] S201. Encrypt and store sensitive information, and assign access rights.

[0096] In some embodiments, sensitive information is encrypted by encryption algorithms such as symmetric encryption (AES), asymmetric encryption (RSA) or hybrid encryption. Further, access rights are assigned according to the user's role and responsibility, such as read-only permission, read-write permission or no permission, and user permissions are managed using an access control list (ACL) or role-based access control (RBAC) system to ensure that only authorized personnel can access sensitive data.

[0097] S202: Record access logs according to access operations and access permissions.

[0098] In some embodiments, access operations include reading, writing, deleting, etc., and access logs are recorded based on the access operations, including operation time, operation type, operation object, operation result, etc. At the same time, based on the operation permissions, whenever a user attempts to access sensitive information, the detailed information of this access is recorded and specially marked, and the sensitivity of the data is further confirmed by identifying abnormal operation modes or frequent access to sensitive data.

[0099] In some embodiments, the processed classified data will be output in a structured form for further analysis and application by the user. The user can view the classification results, sensitive data tags and access logs through the operation interface, and support the generation of reports in multiple formats to help users understand the data processing status and make business decisions based on the reports.

[0100] In some embodiments, Figure 6As shown, the data classification method provided in the embodiment of the present application also includes the following S301-S302:

[0101] S301: In response to an abnormality in the data to be processed or the classified data, an error log is recorded.

[0102] In some embodiments, the abnormal conditions include data format errors, classification failures, unrecognizable data types, etc. When an abnormal condition is detected in the data to be processed or the classified data, an error log is automatically recorded, and the error log includes a timestamp, error code, error description, abnormal type, affected data, etc., to facilitate subsequent analysis and problem solving.

[0103] S302: In response to the number of abnormal situations occurring being greater than a preset threshold, an error log is sent to an administrator.

[0104] In some embodiments, after an abnormality occurs in the data format, some abnormal data is automatically repaired, such as character encoding conversion, file reconstruction, etc. When the abnormality occurs frequently and exceeds a preset threshold, the error log and the attempted repair measures are sent to the administrator for further analysis and processing. During the data extraction process, if the extraction fails due to insufficient authority or network interruption, the retry mechanism is automatically triggered. After multiple failed retries, the error log is recorded and sent to the administrator for manual processing by the administrator. During the data analysis process, if an unrecognizable data type appears or the analysis result does not meet expectations, a re-analysis is performed using different models or algorithms. When the number of re-analysis is greater than the preset threshold, the error log and the attempted solutions are sent to the administrator so that the administrator can manually mark and correct the analysis results to improve the adaptability and accuracy of the model.

[0105] In some embodiments, Figure 7 As shown, the data classification method provided in the embodiment of the present application also includes the following S401-S402:

[0106] S401. Obtain training data based on multi-level data fusion technology.

[0107] The training data at least includes: data to be processed, classified data and access logs.

[0108] In some embodiments, the access log records detailed information about the user's interaction with the system, including the user's access time, access path, operation behavior, etc. This information is crucial for understanding user behavior patterns, contextual information, and historical access records, and helps the model better adapt to user needs and system environment. Multi-level data fusion technology can collect a variety of data including data to be processed, classified data, and access logs for training and optimizing data classification models to improve the accuracy and depth of data analysis.

[0109] S402: Update the data classification model according to the training data.

[0110] In some embodiments, the training data is preprocessed by cleaning, denoising, format conversion and other preprocessing operations to improve data quality and model training efficiency. Useful feature information is extracted from the training data, and these features can reflect the inherent laws and classification basis of the data. Feature extraction is one of the key steps in model training, which determines the model's recognition ability and classification accuracy of the data. The data classification model is trained using the preprocessed training data and the extracted feature information. During the training process, the parameters and structure of the model are continuously adjusted to minimize the classification error and improve the generalization ability of the model. Further, the trained model is evaluated and optimized to ensure its accuracy and stability in practical applications. The evaluation process can be carried out by cross-validation, precision evaluation, recall evaluation and other methods. According to the evaluation results, the model can be further adjusted and optimized to improve its classification performance and adaptability. At the same time, new training data is continuously collected, and the model is updated and retrained regularly to ensure that the model can adapt to the changing data environment and user needs.

[0111] In some embodiments, users can intuitively set or adjust classification rules and sensitive data identification standards through the system's graphical user interface (GUI). These rules and standards can include data types, data formats, data content characteristics, etc. to adapt to specific business needs and compliance requirements. In addition, dynamic learning capabilities ensure that classification and identification rules can be automatically updated based on new data to maintain the accuracy and timeliness of processing results.

[0112] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0113] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a data classification device.

[0115] refer to Figure 8 , the data classification device includes: an acquisition module 801 and a processing module 802;

[0116] The acquisition module 801 is used to acquire data to be processed;

[0117] The processing module 802 is used to input the data to be processed into a data classification model to obtain classified data and the category of the classified data; the data classification model is a deep learning model;

[0118] The processing module 802 is also used to process the classified data based on the category of the classified data based on natural language processing technology and preset recognition rules to determine sensitive information.

[0119] In some embodiments, the processing module 802 is specifically used to determine, according to a structured query language, that the category of the classified data is text data;

[0120] According to the binary large object field, it is determined that the category of the classified data is image data.

[0121] In some embodiments, the processing module 802 is further configured to process the text data based on a regular expression and a preset rule base to identify the sensitive information;

[0122] The image data is processed based on a picture recognition model to identify the sensitive information.

[0123] In some embodiments, the processing module 802 is further used to encrypt and store the sensitive information and assign access rights;

[0124] The data classification device also includes a recording module 803;

[0125] The recording module 803 is used to record access logs according to the access operation and the access authority.

[0126] In some embodiments, the recording module 803 is further used to record an error log in response to an abnormality in the data to be processed or the classified data;

[0127] The data classification device also includes a sending module 804;

[0128] The sending module 804 is used to send the error log to an administrator in response to the number of occurrences of the abnormal situation being greater than a preset threshold.

[0129] In some embodiments, the acquisition module 801 is further used to acquire training data according to a multi-level data fusion technology; the training data at least includes: the data to be processed, the classification data and the access log;

[0130] The data classification device also includes an updating module 805;

[0131] The updating module 805 is used to update the data classification model according to the training data.

[0132] In some embodiments, the acquisition module 801 is specifically used to acquire original data from a database;

[0133] In response to the original data being a compressed file, a decompression operation is performed on the compressed file to obtain the data to be processed.

[0134] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0135] The device of the above embodiment is used to implement the corresponding data classification method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0136] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the data classification method described in any of the above embodiments is implemented.

[0137] Fig. 9 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1060. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1060 in the device.

[0138] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0139] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0140] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0141] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0142] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0143] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0144] The electronic device of the above embodiment is used to implement the corresponding data classification method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0145] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data classification method described in any of the above embodiments.

[0146] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0147] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the data classification method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0148] Based on the same inventive concept, corresponding to the data classification method described in any of the above embodiments, the present disclosure also provides a computer program product, which includes a computer program. In some embodiments, the computer program is executable by one or more processors so that the processors perform the data classification method. Corresponding to the execution subject corresponding to each step in each embodiment of the data classification method, the processor that executes the corresponding step may belong to the corresponding execution subject.

[0149] The computer program product of the above embodiment is used to enable the processor to execute the data classification method described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0150] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0151] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0152] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0153] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A data classification method, characterized in that: The method comprises: Get the data to be processed; Inputting the data to be processed into a data classification model to obtain classified data and categories of the classified data; the data classification model is a deep learning model; According to the category of the classified data, the classified data is processed based on natural language processing technology and preset recognition rules to determine sensitive information.

2. The method according to claim 1, characterized in that The step of inputting the data to be processed into a data classification model to obtain classified data and categories of the classified data includes: According to structured query language, determining that the category of the classified data is text data; According to the binary large object field, it is determined that the category of the classified data is image data.

3. The method according to claim 2, characterized in that According to the category of the classified data, processing the classified data based on natural language processing technology and preset identification rules to determine sensitive information includes: Processing the text data based on regular expressions and a preset rule library to identify the sensitive information; The image data is processed based on a picture recognition model to identify the sensitive information.

4. The method according to claim 1, characterized in that: The method further comprises: Encrypting and storing the sensitive information and assigning access rights; Based on the access operation and the access rights stated, access logs are recorded.

5. The method according to claim 4, characterized in that The method further comprises: In response to an abnormality in the data to be processed or the classified data, recording an error log; In response to the number of occurrences of the abnormal situation being greater than a preset threshold, the error log is sent to an administrator.

6. The method according to claim 4, characterized in that The method further comprises: According to the multi-level data fusion technology, training data is obtained; the training data at least includes: the data to be processed, the classified data and the access log; The data classification model is updated according to the training data.

7. The method according to claim 1, characterized in that The obtaining of the data to be processed comprises: Get the original data from the database; In response to the original data being a compressed file, a decompression operation is performed on the compressed file to obtain the data to be processed.

8. A data classification device, characterized in that: The device comprises: an acquisition module and a processing module; The acquisition module is used to acquire the data to be processed; The processing module is used to input the data to be processed into a data classification model to obtain classified data and the category of the classified data; the data classification model is a deep learning model; The processing module is also used to process the classified data according to the category of the classified data based on natural language processing technology and preset recognition rules to determine sensitive information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program. 10 . A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to claim 1 .

Images