Secure encryption method and device for parameters and messages, equipment and storage medium

Abstract

The invention relates to the field of message encryption, in particular to a parameter and message security encryption method and device, equipment and a storage medium. The method comprises the following steps: acquiring a plaintext message to be encrypted; adaptive filtering noise reduction is carried out on the to-be-encrypted plaintext message, and abnormal value filtering elimination is carried out, so that a filtering optimization message is obtained; carrying out parameter information identification on the filtered and optimized message, and carrying out segment-by-segment parameter encryption to obtain a plurality of message segment encryption parameters; carrying out deep semantic feature analysis on the plurality of message data segments, and then carrying out segment-by-segment key field mining so as to extract a key semantic field of each segment; semantic feature sensitivity mining is carried out on each key semantic field, sensitivity judgment is carried out, and a plurality of high-sensitivity semantic fields are extracted; and performing segment-by-segment symmetric encryption on the plurality of high-sensitivity semantic fields, performing distributed encryption storage, and constructing a distributed encryption storage framework. According to the invention, high-security message encryption is realized.

Description

Technical Field

[0001] The present invention relates to the field of message encryption, and in particular to a method, device, equipment and storage medium for secure encryption of parameters and messages. Background Art

[0002] As an important carrier of data transmission, messages are widely used in various fields such as computer networks, communication systems, financial transactions, and the Internet of Things. In the process of information exchange, messages often contain sensitive data, such as user personal information, transaction records, passwords, etc. Once these data are stolen or tampered with, they may lead to serious privacy leakage, property loss, or system security issues. Therefore, ensuring the security and integrity of messages during transmission has become an important issue in modern information communication.

[0003] With the continuous development of network attack methods, traditional message security protection methods can guarantee the confidentiality and integrity of data to a certain extent. However, with the improvement of computing power and the increasing complexity of attack technology, these traditional methods are faced with problems such as insufficient encryption strength and complex key management. Especially in large-scale distributed systems, how to ensure that each message is not eavesdropped, tampered with or forged during transmission has become a more urgent challenge. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method, device, equipment and storage medium for secure encryption of parameters and messages to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a method for securely encrypting parameters and messages, comprising the following steps: Step S1: Obtain a plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and perform outlier filtering and elimination, so as to obtain a filtered optimized message; Step S2: Identify parameter information of the filtering optimization message, and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; Step S3: performing deep semantic feature analysis on multiple message data segments, and then mining key fields segment by segment, so as to extract key semantic fields of each segment; Step S4: Mining the semantic feature sensitivity of the key semantic fields of each segment, making sensitivity judgments, and extracting multiple highly sensitive semantic fields; Step S5: symmetrically encrypt multiple highly sensitive semantic fields piece by piece, and perform distributed encrypted storage to build a distributed encrypted storage framework; Step S6: Based on multiple message segment encryption parameters, the distributed encryption storage framework is randomly embedded and reconstructed to construct a randomly embedded distributed encryption framework to complete the secure encryption operation of parameters and messages.

[0006] The present invention also provides a parameter and message security encryption device, comprising: The filtering optimization module is used to obtain the plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and filter and remove outliers, so as to obtain the filtered optimized message; A parameter encryption module is used to identify parameter information of the filtering optimization message and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; The semantic feature analysis module is used to perform deep semantic feature analysis on multiple message data segments, and then mine the key fields segment by segment to extract the key semantic fields of each segment; The sensitivity judgment module is used to mine the semantic feature sensitivity of the key semantic fields of each segment, make sensitivity judgments, and extract multiple highly sensitive semantic fields; Distributed encryption module, used to perform segment-by-segment symmetrical encryption on multiple highly sensitive semantic fields, and perform distributed encrypted storage to build a distributed encrypted storage framework; The embedding and reconstruction module is used to randomly embed and reconstruct the distributed encryption storage framework based on multiple message segment encryption parameters, and build a randomly embedded distributed encryption framework to complete the secure encryption of parameters and messages.

[0007] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for securely encrypting parameters and messages described in any one of the above items are implemented.

[0008] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for securely encrypting parameters and messages described in any one of the above items are implemented.

[0009] The beneficial effects of the present invention are as follows: adaptive filtering noise reduction and outlier filtering can improve the quality and accuracy of plaintext messages and reduce errors that may occur after encryption; filtering and optimizing messages can reduce the noise of encrypted data and improve the efficiency and accuracy of subsequent encryption and decryption; parameter information recognition and segment-by-segment parameter encryption can ensure that sensitive information is effectively protected and improve data security; the generation of encryption parameters for multiple message segments can increase the difficulty of encryption and enhance data security; deep semantic feature analysis and key field mining can help identify important information in messages and provide an effective basis for subsequent encryption; extracting key semantic fields can ensure that encryption does not lose important information while protecting sensitive data; and the sensitivity of semantic features. Mining and extraction of highly sensitive fields can help identify and focus on protecting sensitive data and strengthen the targeted nature of encryption. Sensitivity judgment helps determine which fields require more stringent encryption measures and enhance data security. Symmetric encryption and distributed encryption storage of highly sensitive semantic fields can ensure the security of data during transmission and storage. Building a distributed encryption storage framework can improve data's anti-attack capabilities and reliability, avoid single point failures and data leakage risks, and random embedding reconstruction and building a randomly embedded distributed encryption framework can increase the complexity of the encryption algorithm and improve data security. Random embedding reconstruction based on message segment encryption parameters can customize encryption schemes and enhance data confidentiality and integrity. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the steps of a method for securely encrypting parameters and messages of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0011] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0012] The present application example provides a method, device, equipment and storage medium for secure encryption of parameters and messages. The execution subjects of the method, device, equipment and storage medium for secure encryption of parameters and messages include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0013] See also Figures 1 to 4The present invention provides a method for securely encrypting parameters and messages, the method comprising the following steps: Step S1: Obtain a plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and perform outlier filtering and elimination, so as to obtain a filtered optimized message; Step S2: Identify parameter information of the filtering optimization message, and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; Step S3: performing deep semantic feature analysis on multiple message data segments, and then mining key fields segment by segment, so as to extract key semantic fields of each segment; Step S4: Mining the semantic feature sensitivity of the key semantic fields of each segment, making sensitivity judgments, and extracting multiple highly sensitive semantic fields; Step S5: symmetrically encrypt multiple highly sensitive semantic fields piece by piece, and perform distributed encrypted storage to build a distributed encrypted storage framework; Step S6: Based on multiple message segment encryption parameters, the distributed encryption storage framework is randomly embedded and reconstructed to construct a randomly embedded distributed encryption framework to complete the secure encryption operation of parameters and messages.

[0014] The present invention can improve the quality and accuracy of plaintext messages through adaptive filtering noise reduction and outlier filtering, reduce the errors that may occur after encryption, filter and optimize messages to reduce the noise of encrypted data, improve the efficiency and accuracy of subsequent encryption and decryption, parameter information identification and segment-by-segment parameter encryption can ensure that sensitive information is effectively protected and improve data security, the generation of encryption parameters for multiple message segments can increase the difficulty of encryption and enhance data security, deep semantic feature analysis and key field mining can help identify important information in messages and provide an effective basis for subsequent encryption, extract key semantic fields can ensure that encryption does not lose important information while protecting sensitive data, semantic feature sensitivity mining and high Sensitivity field extraction can help identify and focus on protecting sensitive data and strengthen the targetedness of encryption. Sensitivity judgment helps determine which fields require more stringent encryption measures and enhance data security. Segment-by-segment symmetric encryption and distributed encryption storage of highly sensitive semantic fields can ensure the security of data during transmission and storage. Building a distributed encryption storage framework can improve data's anti-attack capabilities and reliability and avoid single point failures and data leakage risks. Random embedding reconstruction and building a random embedding distributed encryption framework can increase the complexity of the encryption algorithm and improve data security. Random embedding reconstruction based on message segment encryption parameters can customize encryption schemes and enhance data confidentiality and integrity.

[0015] In the embodiment of the present invention, refer to Figure 1, is a flow chart of steps of a method for securely encrypting parameters and messages of the present invention. In this example, the steps of the method for securely encrypting parameters and messages include: Step S1: Obtain a plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and perform outlier filtering and elimination, so as to obtain a filtered optimized message; In this embodiment, the original message data to be encrypted is read from the business system or other data sources, and the message data is cached in the memory for subsequent processing and analysis. The statistical characteristics of the message data, such as amplitude distribution, frequency characteristics, etc., are analyzed. According to the characteristics of the message noise, a suitable adaptive filtering algorithm, such as Wiener filtering, Kalman filtering, etc., is selected, and the parameters of the filter are dynamically adjusted so that it can effectively suppress interference components such as random noise and impulse noise in the message. Through adaptive filtering processing, the signal-to-noise ratio of the message is greatly improved, and the reliability of subsequent processing is enhanced. The method of statistical distribution analysis is used to identify outliers and burr data in the message. According to the normal distribution characteristics of the message data, an adaptive outlier detection threshold is set. For abnormal data points exceeding the threshold, interpolation, smoothing and other methods are used for repair processing, and outliers in the message are eliminated to ensure the continuity and smoothness of the data, and provide high-quality input for subsequent semantic analysis. After adaptive filtering noise reduction and outlier filtering, a high-quality optimized message is obtained. The noise component of the message data has been greatly reduced, and the outliers have been effectively eliminated. This pre-processed optimized message will be used as input data for subsequent semantic analysis and encryption processing.

[0016] Step S2: Identify parameter information of the filtering optimization message, and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; In this embodiment, the optimized message data is deeply analyzed to identify various types of parameter information contained therein. Natural language processing techniques, such as named entity recognition and keyword extraction, are used to detect numerical parameters, code parameters, etc. in the message. According to the semantic characteristics and contextual relationships of the parameters, various types of parameters are classified and labeled in a fine-grained manner to establish a structured representation of the message parameter information, providing a clear target for subsequent encryption processing. Different encryption algorithms and keys are used to encrypt the identified parameter information. For different types of parameters, appropriate encryption methods, such as symmetric encryption and asymmetric encryption, are selected. The encrypted parameter information is dynamically combined with the original message segments to form encrypted message segments. When combining, random embedding, segmented encryption, etc. can be used to increase the complexity of the final message. After the above parameter identification and segment-by-segment encryption processing, a group of encrypted message segments are obtained. Each message segment contains encrypted key parameter information. These encrypted message segments will be used as input data of the subsequent comprehensive encryption scheme for further processing.

[0017] Step S3: performing deep semantic feature analysis on multiple message data segments, and then mining key fields segment by segment, so as to extract key semantic fields of each segment; In this embodiment, a pre-trained deep learning semantic analysis model is used to perform fine-grained semantic analysis on each message data segment, and advanced natural language processing models such as BERT and GPT are used to extract features at the vocabulary, syntax, and semantic levels of the message, and identify rich semantic feature information such as keywords, named entities, and sentiment tendencies from the message. These semantic features will provide an important basis for subsequent key field mining and message association analysis. Based on the semantic features extracted in the previous step, key fields are mined for each message data segment, and corresponding rules and algorithms are designed in combination with domain knowledge and business rules to identify the core semantic information in the message. For example, key fields related to personal privacy, sensitive transactions, etc. can be focused on. Through this targeted key field mining, the key semantic information in the message is highly focused. After deep semantic feature analysis and key field mining, the key semantic fields of each message segment are finally obtained. These key semantic fields contain the most core and sensitive information content in the message. These key fields will be the focus of subsequent encryption processing to ensure their security.

[0018] Step S4: Mining the semantic feature sensitivity of the key semantic fields of each segment, making sensitivity judgments, and extracting multiple highly sensitive semantic fields; In this embodiment, the key semantic fields of each message segment extracted need to further explore their sensitivity characteristics, and a set of sensitivity assessment index systems for semantic features are designed in combination with domain knowledge and security requirements. These indicators include: the sensitivity level involving privacy, the importance of key business, the necessity of regulatory compliance, etc. By comparing these sensitivity indicators, each key semantic field is scored and evaluated. Based on the above sensitivity evaluation, a dynamically adjustable sensitivity threshold is set for each key semantic field. This sensitivity threshold can be adjusted according to different business scenarios, security requirements and other factors. For key semantic fields exceeding the sensitivity threshold, they are marked as high-sensitivity fields and need to be encrypted and protected. Through this adaptive sensitivity judgment mechanism, the encryption strategy can be flexibly controlled to be consistent with actual needs. After the above sensitivity analysis and adaptive judgment, a set of high-sensitivity key semantic fields are finally extracted. These high-sensitivity fields contain the most critical and private core information content in the message. These high-sensitivity fields will be the main target of subsequent encryption processing to ensure that they are effectively protected.

[0019] Step S5: symmetrically encrypt multiple highly sensitive semantic fields piece by piece, and perform distributed encrypted storage to build a distributed encrypted storage framework; In this embodiment, the highly sensitive semantic fields extracted in step S4 are encrypted segment by segment, and an efficient symmetric encryption algorithm such as AES, ChaCha20, etc. is used to encrypt each semantic field. An independent encryption key is generated for each semantic field to ensure the independence and isolation of encryption. The encrypted semantic fields are reassembled back into the original message data segment structure, and the encrypted message data segments are dispersedly stored in multiple independent encryption storage units. Each encryption storage unit is an independent computing node, which can be a physical machine, a virtual machine or a container. In order to achieve heterogeneous encryption, each storage unit is equipped with a different encryption algorithm and key, and redundant backup, sharding reconstruction and other fault-tolerant technologies are used to ensure that even if some storage units fail, integrity damage will not be caused. Based on the above-mentioned distributed storage and heterogeneous encryption design, a distributed encryption storage framework is constructed, which includes multiple independent encryption storage units and a central control system for coordinating and managing these units. The central control system is responsible for dynamically scheduling storage strategies, monitoring fault-tolerant status, coordinating encryption keys and other functions. Through this distributed architecture, the security and availability of the entire encryption system are greatly improved.

[0020] Step S6: Based on multiple message segment encryption parameters, the distributed encryption storage framework is randomly embedded and reconstructed to construct a randomly embedded distributed encryption framework to complete the secure encryption operation of parameters and messages.

[0021] In this embodiment, a coding index table of message data segments and encryption parameters is established. The index table records the corresponding relationship between each message data segment and the corresponding encryption parameter. Through this index table, it can be ensured that the original message can be correctly restored during decryption. On the basis of establishing the coding index, it is necessary to adopt a random embedding method to dynamically reorganize the encoded parameters and the message. Each time encryption is performed, a different embedding position and order are randomly selected, so that the final encrypted message presents a high degree of uncertainty. This random reconstruction method increases the difficulty for attackers to crack the encrypted message. In order to further increase the uncertainty of the encrypted message, more complex reconstruction rules are designed. In addition to simple random embedding, other coding transformations can also be introduced, such as segmented encryption, multi-level nesting, etc. Through the superposition of multiple complex transformations, the encrypted message finally generated will present extremely high uncertainty and confusion. For the receiver, only through the coding index table established in advance can the encrypted message be correctly decrypted and restored. The receiver first identifies the corresponding relationship between the message data segment and the encryption parameter according to the index table, and then gradually disassembles and restores the encrypted message according to the correct reconstruction rule to finally obtain a clear original message.

[0022] In this embodiment, refer to Figure 2, is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Obtain the plaintext message to be encrypted; Step S12: performing multi-band wavelet transform decomposition on the encrypted plaintext message, thereby obtaining message data of multiple frequencies; Step S13: Analyze the noise characteristics of the message data of multiple frequencies one by one, and extract the message noise characteristics of each frequency; Step S14: Adaptively filter and reduce noise based on the message noise characteristics of each frequency, thereby obtaining a filtered and reduced noise message; Step S15: Detect abnormal burst points of the filtered and denoised messages and mark abnormal burst values; Step S16: Filter and remove abnormal burst values, thereby obtaining a filtering optimized message.

[0023] In this embodiment, the source of the plaintext message to be encrypted is determined, such as network transmission, database extraction or user input, to ensure the reliability and integrity of the data source so that the subsequent encryption process can proceed smoothly, use an appropriate interface or protocol (such as HTTP, TCP / IP) to obtain the plaintext message from the data source, and store it in a memory or file, perform a preliminary verification on the obtained data to ensure that its format and content meet expectations, format the plaintext message into a standard format suitable for subsequent processing (such as JSON, XML or binary format) to facilitate the processing of subsequent steps, select an appropriate wavelet basis (such as Haar, Daubechies, Coiflet, etc.) for wavelet transform, so as to extract message features in different frequency ranges, and finally obtain the plaintext message from the data source. Characteristic, use wavelet transform function (such as wavedec in PyWavelets library) to perform multi-band decomposition on encrypted plaintext message, decompose message data into multiple frequency sub-bands, obtain high-frequency and low-frequency components, store message data of multiple frequencies in data structure for subsequent processing, ensure that sub-band data of each frequency can be accessed and analyzed separately, calculate relevant noise characteristics for message data of each frequency, such as signal-to-noise ratio (SNR), root mean square value (RMS), peak factor, etc., and use statistical analysis methods (such as standard deviation, mean value) to evaluate the noise level in each frequency sub-band, compare the extracted noise characteristics with predefined thresholds to identify the significance of noise, and record the noise characteristics of each frequency Data is collected to facilitate the implementation of subsequent adaptive filtering. According to the analyzed noise characteristics, a suitable adaptive filter (such as Kalman filter, adaptive mean filter, etc.) is selected. The filter parameters are dynamically adjusted according to the noise characteristics of each frequency to ensure that it can effectively remove noise and retain the signal. The adaptive filter is applied to the message data of each frequency to obtain the filtered denoised message. The filtering effect of each frequency is recorded during the filtering process for subsequent evaluation. The definition criteria of abnormal protrusion points are clarified, such as instantaneous values ​​exceeding a certain threshold or sharp changes within a certain frequency range. The abnormal detection algorithm (such as Z-score method, moving average method) is used to analyze the filtered denoised message, detect abnormal protrusion values, and record the detected All abnormal protrusion points and their related information (such as timestamp, amplitude, frequency, etc.), mark the detected abnormal protrusion values ​​to ensure that these abnormal values ​​can be identified and processed in the subsequent processing stage, determine the criteria for filtering outliers, such as setting a threshold range or using statistical methods (such as the quartile method) to determine the filtering conditions, traverse the marked abnormal protrusion values, filter them according to the set criteria, and eliminate those message data identified as abnormal, ensure that the eliminated abnormal values ​​are recorded during the filtering process for subsequent analysis and verification, save the message data that has been filtered out as a filtered optimized message, ensure that its format is consistent with the original data, and add metadata (such as processing time, filtering criteria) to the optimized message for subsequent access and use.

[0024] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing semantic structure analysis on the filtering optimization message and extracting message semantic structure data; Step S22: performing complete semantic multi-segment decomposition of the filtering optimization message according to the message semantic structure data, thereby obtaining multiple message data segments; Step S23: Identify parameter information of multiple message data segments and extract parameter information of each message segment; Step S24: Encrypt the parameter information of each message segment segment by segment, so as to obtain multiple message segment encryption parameters.

[0025] In this embodiment, a suitable semantic analysis tool or library (such as NLTK, spaCy or a custom regular expression) is selected to process and analyze the content of the filtering optimization message, and the filtering optimization message is preprocessed, including removing redundant spaces, punctuation marks and special characters, converting the message into a unified format (such as lowercase) to improve the accuracy of subsequent analysis, applying natural language processing (NLP) technology to the message to perform word segmentation, part-of-speech tagging and syntactic analysis to extract semantic structure data, identify key components in the message (such as subject, verb, object, etc.), and record their positions and relationships in the message, and store the extracted semantic structure data in a data structure for subsequent processing, such as using a dictionary or a data frame (such as PandasDataFrame), defining decomposition rules according to the extracted semantic structure data, such as dividing the message segments according to specific keywords, sentence structures or logic, and using the decomposition rules to decompose the filtering optimization message into multiple segments to generate multiple message data segments, ensuring that each data segment retains complete semantic information, which is convenient for subsequent analysis and processing, and verifying the decomposed message segments to confirm Ensure that it conforms to the expected semantic structure, store multiple message data segments in a list or array for subsequent processing, determine the type of parameter information that needs to be extracted, such as timestamp, user ID, operation code, status code, etc., use regular expressions, NLP technology or custom parsers to extract the required parameter information from each message segment, traverse each message segment, apply parameter extraction methods, identify and extract parameter information for each segment, record the extracted parameter information, including its name, value and source segment, select a suitable encryption algorithm (such as AES, RSA or other symmetric / asymmetric encryption algorithms), formulate an encryption scheme based on security requirements, generate or obtain the keys required for encryption, and ensure the secure storage and management of the keys to prevent unauthorized access, encrypt the parameter information of each message segment one by one, ensure the security of each parameter, apply the selected encryption algorithm, encrypt the parameters, generate encrypted parameter data, store the encrypted parameter data in a secure location, ensure its availability and integrity, and generate an encryption result report containing the encrypted parameters and their original values ​​for each segment for subsequent verification and auditing.

[0026] The specific section-by-section parameter encryption is as follows: Extract parameter information of the first message segment; Convert the parameter information of the first message segment into a JSON string to obtain multiple JSON strings; Perform MD5 encryption on multiple JSON strings to generate multiple encrypted strings; Generate a 16-bit random character code and a current user identification data; Using the 16-bit random character code to symmetrically encrypt multiple encrypted character strings to obtain symmetrically encrypted character strings; Encapsulate the current user identity authentication data in a request header to obtain a user identity request header unit; The symmetric encryption string is embedded into the header by using the user identity request header unit, thereby obtaining the message segment encryption parameter; All message segment encryption parameters are iteratively encrypted to obtain multiple message segment encryption parameters.

[0027] In this embodiment, the first message segment is traversed to identify and extract the required parameter information, such as timestamp, user ID, operation code, etc. The extracted parameter information is stored in a dictionary or a similar data structure for subsequent processing. An applicable JSON processing library (such as the json module in Python) is introduced. The function of the JSON library is used to convert the extracted parameter information dictionary into a JSON string, format the output, and ensure that the structure of the JSON string is clear and meets the standard. If there are multiple message segments, the above process is repeated to generate corresponding JSON strings and store them in a list. An applicable hash library (such as hashlib in Python) is introduced to traverse the stored multiple JSON strings, encrypt each JSON string using the MD5 algorithm, generate an encrypted string using a hash function, record each encryption result, and store all MD5 encrypted strings in a list for subsequent use. A random number generation library (such as the random or secrets library in Python) is introduced to generate a 16 16-bit string, the characters can include letters and numbers, ensure the uniqueness and unpredictability of the random character code, obtain the current user's identification data (such as user ID or session token) from the user authentication system or session, ensure that the obtained data is valid and up-to-date, select a suitable symmetric encryption algorithm (such as AES), and define the key generation and padding method, use the generated 16-bit random character code as the key, symmetric encrypt multiple MD5 encrypted strings one by one, record each encryption result, form a list of symmetric encrypted strings, determine the structure of the request header, which usually includes content type, user identification information, etc., encapsulate the obtained user identification data into the request header to form a complete request header unit, combine the user identity request header unit with the symmetric encryption string to form the final message segment encryption parameters, ensure that the embedding process does not destroy the integrity of the encrypted string, repeat the above encryption steps for all extracted message segments, process the parameter information of each message segment one by one, and store all message segment encryption parameters in an appropriate data structure, such as a list or dictionary, for subsequent use or sending.

[0028] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: performing deep semantic feature analysis on multiple message data segments to extract message semantic features of each segment; Step S32: performing contextual logic association analysis on the message semantic features of each segment to obtain message semantic logic association data; Step S33: performing intelligent semantic smoothing on multiple message data segments based on message semantic logic association data, thereby generating multiple semantically smoothed message segments; Step S34: mining the key fields of multiple semantically smooth message segments segment by segment, thereby extracting the key semantic fields of each segment.

[0029] In this embodiment, a suitable natural language processing tool or library (such as spaCy, NLTK, Transformers, etc.) is selected to perform deep semantic feature analysis, and multiple message data segments are preprocessed, including removing redundant spaces, punctuation marks, converting to lowercase, etc., to improve the accuracy of the analysis. Each message segment is analyzed using the selected semantic analysis tool to extract semantic features, such as keywords, entity recognition (such as names, places, dates), word meanings, and dependencies, etc. The extracted semantic features are stored in a data structure (such as a dictionary or a data frame) for subsequent processing, and the criteria for contextual logic analysis are determined to clarify which features or fields have logical associations, which may include time, causal relationships, topic relevance, etc. A logistic regression model, a Bayesian network, or a graph theory-related method is used to perform contextual logic analysis on the extracted semantic features, identify and record the logical relationship between each message feature segment, and form message semantic logic association data. The analyzed logical association data is stored in an appropriate data structure for subsequent use (such as a list, a dictionary, or a data frame). ), select a suitable semantic smoothing algorithm (such as conditional generative adversarial network (CGAN), variational autoencoder (VAE), etc.) to achieve semantic smoothing, use the previously extracted semantic features and logical association data to train the selected model to ensure that the model can understand and generate natural language that conforms to the context, input multiple message segments into the trained semantic smoothing model to generate smoothed semantic message segments, ensure that the generated message segments are more semantically coherent and logical, determine the types of key fields that need to be extracted, such as keywords, important parameters, specific entities, etc., use TF-IDF, LDA topic model, text similarity calculation and other methods to identify the key fields in each semantic smooth message segment, mine the key fields of each semantic smooth message segment one by one, extract the content that matches the defined key field type, store the extracted key fields in a structured data format (such as a dictionary, list) for subsequent use, verify the extracted key fields to ensure their accuracy and relevance, summarize all the extracted key fields to form the final data set for subsequent analysis and use.

[0030] In this embodiment, step S4 includes the following steps: Step S41: performing application scenario analysis on the plaintext message to be encrypted to obtain message application scenario data; Step S42: Identify the security requirements of the message application scenario data, thereby obtaining the current message security requirement data; Step S43: Calculate the dynamic security sensitivity threshold according to the current message security requirement data to generate the current scenario security sensitivity threshold; Step S44: performing semantic feature sensitivity mining on the key semantic fields of each segment, thereby generating the sensitivity of the key semantic fields; Step S45: Perform a sensitivity judgment on the sensitivity of the key semantic field based on the current scenario security sensitivity threshold. When the sensitivity of the key semantic field is greater than or equal to the current scenario security sensitivity threshold, it is judged as a high-sensitivity semantic field. All key semantic fields are traversed to extract multiple high-sensitivity semantic fields.

[0031] In this embodiment, the message application scenarios that need to be analyzed are clearly defined, such as financial transactions, medical information, user authentication, etc., and context data related to the plaintext message to be encrypted is collected, including the usage environment, data type, user needs, etc. Information can be obtained through questionnaires, user interviews or historical data analysis, and the collected data is classified and organized to extract key features of the application scenarios, such as data sensitivity, usage frequency, legal and regulatory requirements, etc. The extracted features are recorded in a data structure (such as a dictionary or a data frame) to form message application scenario data, and standards for security demand identification are formulated to clarify which features and factors will affect the security requirements of the message (such as data confidentiality, integrity, and availability). According to the collected message application scenario data, the security requirements in the current environment are analyzed, including exposed risks, potential attack surfaces, etc. The analysis results are compared with the security demand standards, the security demand data of the current message is identified and recorded in the data structure, and a suitable model or algorithm (such as fuzzy logic, machine learning algorithm) is selected to calculate the dynamic security sensitivity threshold, and the security requirements data is collected. Parameter data that affects security sensitivity, such as application scenario characteristics, security requirement levels, historical event data, etc., perform dynamic security sensitivity threshold calculation based on input parameters, generate the security sensitivity threshold of the current scenario, record the calculation results for subsequent use, determine the indicators used to evaluate the sensitivity of key semantic fields, such as data type, privacy level, legal compliance, etc., select appropriate analysis tools or algorithms (such as decision trees, feature importance analysis) to evaluate the sensitivity of each key semantic field, analyze each segment of key semantic fields, calculate and generate their sensitivity values, store the sensitivity results in a data structure to ensure its traceability, compare the sensitivity of each key semantic field with the security sensitivity threshold of the current scenario, and based on the comparison results, determine that when the sensitivity of the key semantic field is greater than or equal to the security sensitivity threshold of the current scenario, it is determined to be a high-sensitivity semantic field, traverse all key semantic fields, extract multiple high-sensitivity semantic fields, and store them in appropriate data structures (such as lists or dictionaries) for subsequent security processing.

[0032] In this embodiment, step S5 includes the following steps: Step S51: symmetrically encrypting multiple highly sensitive semantic fields segment by segment to obtain multiple encrypted semantic fields; Step S52: performing independent encapsulation processing on multiple encryption semantic fields to generate multiple independent encryption units; Step S53: Perform distributed encryption storage on multiple independent encryption units to build a distributed encryption storage framework.

[0033] In this embodiment, the symmetric encryption algorithm used is determined, such as AES, DES, or ChaCha20, and an appropriate mode (such as CBC, GCM) is selected to improve security. The key required for encryption is generated to ensure that its length and complexity meet security standards. The key is securely stored to avoid unauthorized access. Each highly sensitive semantic field is traversed and encrypted using the selected symmetric encryption algorithm. The encrypted result is stored in a list or array to form multiple encrypted semantic fields. The encryption result is checked for integrity to ensure that no errors occur during the encryption process. The encapsulation structure of the independent encryption unit is designed, including metadata such as field name, encrypted value, and timestamp for subsequent use. Each encrypted semantic field is encapsulated to create an independent encryption unit. The encapsulation format can be JSON, XML, or other structured formats to ensure that each independent encryption unit is complete and self-contained for easy access and management. The encryption unit is stored in a data structure (such as a list or dictionary) to ensure that it is easy to access and manage. Select a suitable distributed storage system (such as Apache Cassandra, MongoDB, Amazon S3, etc.) to ensure that it supports high availability and data redundancy. Design a distributed encryption storage framework, determine the data sharding strategy and access control mechanism to achieve efficient storage and secure management of data, distribute and store multiple independent encryption units in the designed distributed storage system to ensure that data is evenly distributed among multiple nodes to improve access speed and fault tolerance. Develop a data backup and recovery strategy to prevent data loss or damage, ensure that the stored data is backed up regularly, and test the effectiveness of the recovery process. Configure access rights to the storage system to ensure that only authorized users can access and manage the stored data. Implement monitoring and auditing mechanisms to track all access and modification operations to stored data.

[0034] In this embodiment, step S6 includes the following steps: Step S61: performing unencrypted data identification on the filtered optimized message based on multiple highly sensitive semantic fields and parameter information of each message segment, and extracting all unencrypted data in the message; Step S62: performing data segmentation processing on all unencrypted data in the message, thereby obtaining unencrypted data segments; Step S63: sequentially encode the unencrypted data slices and the encryption parameters of the multiple message segments to obtain encoded unencrypted data slices and encoded encryption parameters; Step S64: performing obfuscated serialization integration on the encoded unencrypted data slices and the encoded encryption parameters, thereby obtaining an obfuscated data sequence; Step S65: randomly embed and reconstruct the obfuscated data sequence into the distributed encryption storage framework, and construct a randomly embedded distributed encryption framework to complete the secure encryption of parameters and messages.

[0035] In this embodiment, the message is traversed and filtered to optimize, and the unencrypted data matching the message is identified by using the highly sensitive semantic field as a keyword, and the location information (such as the number of lines and the character position) of all the unencrypted data is recorded for subsequent processing, and the extracted unencrypted data is stored in a list or a dictionary for subsequent data slicing processing, and the rules and sizes of the slicing are determined, for example, based on the number of bytes, the number of lines or the length of a specific character to ensure the rationality and effectiveness of the slicing, and the stored unencrypted data is traversed and slicing is performed on it according to the set rules to generate multiple unencrypted data slices, and it is ensured that each data slice contains sufficient information for subsequent processing, and all the generated unencrypted data slices are stored in a list to facilitate subsequent encoding processing, and a sequential encoding method is determined, such as UTF-8 encoding, Base64 encoding or a custom encoding scheme to improve data security and transmission efficiency, and each unencrypted data slice and the corresponding message segment encryption parameter are sequentially encoded to ensure that the encoded data can retain the original information structure for subsequent obfuscation processing, and the encoded unencrypted data slice and the encoded data are separated. The encrypted parameters after encoding are stored in an appropriate data structure to facilitate subsequent operations. Appropriate obfuscation algorithms (such as AES obfuscation, XOR obfuscation, etc.) are selected to improve data security and prevent unauthorized access. The encoded unencrypted data pieces and the encoded encryption parameters are obfuscated and serialized to generate an obfuscated data sequence. This ensures that the obfuscation process can effectively mix the data and increase the complexity and incomprehensibility of the data. The generated obfuscated data sequence is stored in an appropriate data structure for subsequent random embedding processing. The strategy of random embedding reconstruction is determined to ensure that the data can be randomly distributed in the distributed storage framework to avoid the risks brought by centralized storage. The obfuscated data sequence is randomly embedded and reconstructed in the distributed encryption storage framework to ensure that each data piece and encryption parameter are stored in a dispersed manner during the storage process. A load balancing algorithm is used to ensure that the data is evenly distributed among the nodes. The integrity of the embedded data is verified to ensure that all data pieces and encryption parameters are successfully embedded and accessible. A monitoring mechanism is implemented to track the health status and access status of the storage system to ensure data security and availability.

[0036] In this embodiment, the present invention further provides a parameter and message security encryption device, including: The filtering optimization module is used to obtain the plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and filter and remove outliers, so as to obtain the filtered optimized message; A parameter encryption module is used to identify parameter information of the filtering optimization message and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; The semantic feature analysis module is used to perform deep semantic feature analysis on multiple message data segments, and then mine the key fields segment by segment to extract the key semantic fields of each segment; The sensitivity judgment module is used to mine the semantic feature sensitivity of the key semantic fields of each segment, make sensitivity judgments, and extract multiple highly sensitive semantic fields; Distributed encryption module, used to perform segment-by-segment symmetrical encryption on multiple highly sensitive semantic fields, and perform distributed encrypted storage to build a distributed encrypted storage framework; The embedding and reconstruction module is used to randomly embed and reconstruct the distributed encryption storage framework based on multiple message segment encryption parameters, and build a randomly embedded distributed encryption framework to complete the secure encryption of parameters and messages.

[0037] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above-mentioned methods for securely encrypting parameters and messages when executing the computer program.

[0038] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for securely encrypting parameters and messages described in any one of the above items are implemented.

[0039] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0040] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks.

[0041] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0042] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for secure encryption of parameters and messages, characterized in that: The following steps are involved: Step S1: Obtain a plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and perform outlier filtering and elimination, so as to obtain a filtered optimized message; Step S2: Identify parameter information of the filtering optimization message, and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; Step S3: performing deep semantic feature analysis on multiple message data segments, and then mining key fields segment by segment, so as to extract key semantic fields of each segment; Step S4: Mining the semantic feature sensitivity of the key semantic fields of each segment, making sensitivity judgments, and extracting multiple highly sensitive semantic fields; Step S5: symmetrically encrypt multiple highly sensitive semantic fields piece by piece, and perform distributed encrypted storage to build a distributed encrypted storage framework; Step S6: Based on multiple message segment encryption parameters, the distributed encryption storage framework is randomly embedded and reconstructed to construct a randomly embedded distributed encryption framework to complete the secure encryption operation of parameters and messages.

2. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Obtain the plaintext message to be encrypted; Step S12: performing multi-band wavelet transform decomposition on the plaintext message to be encrypted, thereby obtaining message data of multiple frequencies; Step S13: Analyze the noise characteristics of the message data of multiple frequencies one by one, and extract the message noise characteristics of each frequency; Step S14: Adaptively filter and reduce noise based on the message noise characteristics of each frequency, thereby obtaining a filtered and reduced noise message; Step S15: Detect abnormal burst points of the filtered and denoised messages and mark abnormal burst values; Step S16: Filter and remove abnormal burst values, thereby obtaining a filtering optimized message.

3. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing semantic structure analysis on the filtering optimization message and extracting message semantic structure data; Step S22: performing complete semantic multi-segment decomposition of the filtering optimization message according to the message semantic structure data, thereby obtaining multiple message data segments; Step S23: Identify parameter information of multiple message data segments and extract parameter information of each message segment; Step S24: encrypt the parameter information of each message segment segment by segment, thereby obtaining multiple message segment encryption parameters; The specific section-by-section parameter encryption is as follows: Extract parameter information of the first message segment; Convert the parameter information of the first message segment into a JSON string to obtain multiple JSON strings; Perform MD5 encryption on multiple JSON strings to generate multiple encrypted strings; Generate a 16-bit random character code and a current user identification data; Using the 16-bit random character code to symmetrically encrypt multiple encrypted character strings to obtain symmetrically encrypted character strings; Encapsulate the current user identity authentication data in a request header to obtain a user identity request header unit; The symmetric encryption string is embedded into the header by using the user identity request header unit, thereby obtaining the message segment encryption parameter; All message segment encryption parameters are iteratively encrypted to obtain multiple message segment encryption parameters.

4. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing deep semantic feature analysis on multiple message data segments to extract message semantic features of each segment; Step S32: performing contextual logic association analysis on the message semantic features of each segment to obtain message semantic logic association data; Step S33: performing intelligent semantic smoothing on multiple message data segments based on message semantic logic association data, thereby generating multiple semantically smoothed message segments; Step S34: mining the key fields of multiple semantically smooth message segments segment by segment, thereby extracting the key semantic fields of each segment.

5. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing application scenario analysis on the plaintext message to be encrypted to obtain message application scenario data; Step S42: Identify the security requirements of the message application scenario data, thereby obtaining the current message security requirement data; Step S43: Calculate the dynamic security sensitivity threshold according to the current message security requirement data to generate the current scenario security sensitivity threshold; Step S44: performing semantic feature sensitivity mining on the key semantic fields of each segment, thereby generating the sensitivity of the key semantic fields; Step S45: Perform a sensitivity judgment on the sensitivity of the key semantic field based on the current scenario security sensitivity threshold. When the sensitivity of the key semantic field is greater than or equal to the current scenario security sensitivity threshold, it is judged as a high-sensitivity semantic field. All key semantic fields are traversed to extract multiple high-sensitivity semantic fields.

6. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: symmetrically encrypting multiple highly sensitive semantic fields segment by segment to obtain multiple encrypted semantic fields; Step S52: performing independent encapsulation processing on multiple encryption semantic fields to generate multiple independent encryption units; Step S53: Perform distributed encryption storage on multiple independent encryption units to build a distributed encryption storage framework.

7. The method for secure encryption of parameters and messages according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing unencrypted data identification on the filtered optimized message based on multiple highly sensitive semantic fields and parameter information of each message segment, and extracting all unencrypted data in the message; Step S62: performing data segmentation processing on all unencrypted data in the message, thereby obtaining unencrypted data segments; Step S63: sequentially encode the unencrypted data slices and the encryption parameters of the multiple message segments to obtain encoded unencrypted data slices and encoded encryption parameters; Step S64: performing obfuscated serialization integration on the encoded unencrypted data slices and the encoded encryption parameters, thereby obtaining an obfuscated data sequence; Step S65: randomly embed and reconstruct the obfuscated data sequence into the distributed encryption storage framework, and construct a randomly embedded distributed encryption framework to complete the secure encryption of parameters and messages.

8. A device for securely encrypting parameters and messages, characterized in that: The method for performing abnormality monitoring of a transformer according to claim 1 comprises: The filtering optimization module is used to obtain the plaintext message to be encrypted; perform adaptive filtering and noise reduction on the plaintext message to be encrypted, and filter and remove outliers, so as to obtain the filtered optimized message; A parameter encryption module is used to identify parameter information of the filtering optimization message and encrypt the parameters segment by segment, thereby obtaining encryption parameters of multiple message segments; The semantic feature analysis module is used to perform deep semantic feature analysis on multiple message data segments, and then mine the key fields segment by segment to extract the key semantic fields of each segment; The sensitivity judgment module is used to mine the semantic feature sensitivity of the key semantic fields of each segment, make sensitivity judgments, and extract multiple highly sensitive semantic fields; Distributed encryption module, used to perform segment-by-segment symmetrical encryption on multiple highly sensitive semantic fields, and perform distributed encrypted storage to build a distributed encrypted storage framework; The embedding and reconstruction module is used to randomly embed and reconstruct the distributed encryption storage framework based on multiple message segment encryption parameters, and build a randomly embedded distributed encryption framework to complete the secure encryption of parameters and messages.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method for securely encrypting parameters and messages described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for securely encrypting parameters and messages described in any one of claims 1 to 7 are implemented.

Images