Encryption-based text visualization method, data processing method, system and device
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHONGXIN KUANWEI MEDIA TECH CO LTD
- Filing Date
- 2023-02-10
- Publication Date
- 2026-06-02
Smart Images
Figure CN116167064B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and more specifically, to an encryption-based text visualization method, data processing method, system, and apparatus. Background Technology
[0002] Human memory and information processing capabilities are limited. A picture is worth a thousand words, and visualizing book texts can more easily help people digest or understand large amounts of textual information within a limited time. However, in the current process of visualizing the original book's textual information, there is a possibility of leakage of the original textual information, leading to a large number of pirated books and posing a significant risk to the data security of the original books.
[0003] There is currently no effective solution to the above problems. Summary of the Invention
[0004] This invention provides an encrypted text visualization method, data processing method, system, and apparatus that can process encrypted text information and improve the data security of the original book.
[0005] According to one aspect of the present invention, an encryption-based text visualization method is provided, applied to a terminal device, the method comprising:
[0006] The obtained text information of the original book is encrypted to obtain encrypted text information;
[0007] The encrypted text information is sent to the data processing platform, so that the data processing platform can extract events from the encrypted text information to obtain a ciphertext result; and the ciphertext result is fed back to the terminal device.
[0008] The encrypted result is decrypted to obtain the event extraction result; wherein the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element;
[0009] Construct a knowledge graph of events based on the event extraction results;
[0010] The element image corresponding to the event element is embedded into the event knowledge graph to obtain a visualized image of the text information.
[0011] As an optional implementation, encrypting the text information of the acquired original book to obtain encrypted text information includes:
[0012] Word embedding is performed on the obtained text information of the original book to obtain the text embedding vector;
[0013] The text embedding vector is homomorphically encrypted using a homomorphic encryption library to obtain encrypted text information.
[0014] As an optional implementation, after obtaining the visualized image of the text information, the method further includes:
[0015] The visualization image is calculated according to a preset hash algorithm to obtain the hash value of the visualization image;
[0016] Obtain the public and private keys corresponding to the visualized image;
[0017] The hash value is encrypted using the private key to obtain the digital signature of the visualized image;
[0018] The digital fingerprint of the visualized image is obtained based on the digital signature and the public key;
[0019] The digital fingerprint and the obtained current timestamp are added to the visualization image to obtain a visualized digital collection.
[0020] As an optional implementation, embedding the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information includes:
[0021] The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role;
[0022] Obtain the element image corresponding to the event element;
[0023] The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
[0024] According to another aspect of the present invention, an encrypted text data processing method is also provided, applied to a data processing platform, the method comprising:
[0025] Event extraction is performed on the encrypted text information sent by the terminal device to obtain the ciphertext result;
[0026] The noise error of the encrypted text information is determined based on the ciphertext result;
[0027] If the noise error is less than or equal to a preset threshold, the encrypted result is fed back to the terminal device.
[0028] As an optional implementation, the step of extracting events from the encrypted text information sent by the terminal device to obtain the ciphertext result includes:
[0029] Trigger word detection is performed on the encrypted text information to obtain the trigger words included in the encrypted text information;
[0030] The encrypted text information is subjected to event type detection to obtain the event types included in the encrypted text information;
[0031] Event arguments are extracted from the encrypted text information to obtain the event arguments included in the encrypted text information;
[0032] Argument role identification is performed on the encrypted text information to obtain the argument roles included in the encrypted text information;
[0033] The trigger word, the event type, the event argument, and the argument role are determined as the ciphertext result.
[0034] As an optional implementation, if the noise error is greater than the preset threshold, the method further includes:
[0035] The encrypted result is determined as the result to be decrypted;
[0036] The process involves sending the result to be restored to the terminal device, enabling the terminal device to decrypt the result and obtain the text information to be restored; denoising the text information to be restored to obtain denoised text information; homomorphically encrypting the denoised text information to obtain encrypted text information; sending the encrypted text information to the data processing platform; and performing the step of extracting events from the encrypted text information sent by the terminal device to obtain a ciphertext result.
[0037] According to another aspect of the present invention, an encrypted text visualization system is also provided, including a terminal device, a data processing platform, and a server, wherein:
[0038] The server is used to train an event extraction model based on pre-acquired training data and deploy the event extraction model to the data processing platform.
[0039] The terminal device is used to encrypt the text information of the acquired original book to obtain encrypted text information, and send the encrypted text information to the data processing platform.
[0040] The data processing platform is used to extract events from the encrypted text information based on the event extraction model to obtain ciphertext results; and to determine the noise error of the encrypted text information based on the ciphertext results; if the noise error is less than or equal to a preset threshold, the ciphertext results are fed back to the terminal device.
[0041] The terminal device is further configured to decrypt the encrypted result to obtain an event extraction result; wherein the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element; and constructs an event knowledge graph based on the event extraction result; and embeds the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information.
[0042] According to another aspect of the present invention, an encryption-based text visualization device is also provided, comprising:
[0043] The encryption module is used to encrypt the text information of the original book to obtain encrypted text information;
[0044] The sending module is used to send the encrypted text information to the data processing platform, so that the data processing platform can extract events from the encrypted text information to obtain a ciphertext result; and to feed back the ciphertext result to the terminal device.
[0045] The decryption module is used to decrypt the ciphertext result to obtain the event extraction result; wherein, the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element;
[0046] The construction module is used to construct a knowledge graph of events based on the event extraction results;
[0047] An embedding module is used to embed the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information.
[0048] According to another aspect of the present invention, an encrypted text data processing apparatus is also provided, comprising:
[0049] The extraction module is used to extract events from the encrypted text information sent by the terminal device to obtain the ciphertext result;
[0050] The determination module is used to determine the noise error of the encrypted text information based on the ciphertext result;
[0051] The feedback module is used to feed back the encrypted result to the terminal device if the noise error is less than or equal to a preset threshold.
[0052] According to another aspect of the present invention, a computing device is also provided, the computing device comprising: at least one processor, a memory, and an input / output unit; wherein the memory is used to store a computer program, and the processor is used to invoke the computer program stored in the memory to execute the above-described encryption-based text visualization method or encryption-based text data processing method.
[0053] According to another aspect of the present invention, a computer-readable storage medium is also provided, which includes instructions that, when executed on a computer, cause the computer to perform the above-described encryption-based text visualization method or encryption-based text data processing method.
[0054] In this embodiment of the invention, the encrypted text information of the original book can be sent to a data processing platform, enabling the platform to extract events from the encrypted text information while it is in an encrypted state and return the extracted ciphertext results. Decrypting the ciphertext results yields the event extraction results. Analyzing these results generates a knowledge graph of events, and embedding the element images corresponding to the event elements into the knowledge graph creates a visualized image of the text information. Therefore, this embodiment of the invention can obtain a visualized image of the original book's text information while encrypting it, thus improving the data security of the original book. Attached Figure Description
[0055] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:
[0056] Figure 1 This is a flowchart illustrating an optional encryption-based text visualization method according to an embodiment of the present invention;
[0057] Figure 2 This is a flowchart illustrating an optional encrypted text data method according to an embodiment of the present invention;
[0058] Figure 3 This is a schematic diagram of the structure of an optional encryption-based text visualization system according to an embodiment of the present invention;
[0059] Figure 4 This is a schematic diagram of the structure of an optional encryption-based text visualization device according to an embodiment of the present invention;
[0060] Figure 5 This is a schematic diagram of the structure of an optional encrypted text data device according to an embodiment of the present invention;
[0061] Figure 6A schematic diagram of the structure of a medium according to an embodiment of the present invention is shown.
[0062] Figure 7 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. Detailed Implementation
[0063] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0064] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0065] The following is for reference. Figure 1 , Figure 1 This is a flowchart illustrating an encryption-based text visualization method according to an embodiment of the present invention. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.
[0066] Figure 1 The flowchart of an embodiment of the present invention, which provides an encrypted text visualization method, is applied to a terminal device and includes:
[0067] Step S101: Encrypt the text information of the original book to obtain encrypted text information.
[0068] In this embodiment of the invention, the original book can be an electronic book or a paper book; the text information of the original book can be obtained by acquiring an image containing the original book through an image acquisition device set on the terminal device, and by performing text recognition on the image to be recognized, the text information of the original image can be obtained from the image to be recognized. Alternatively, the text information of the original book can be directly read from the memory.
[0069] As an optional implementation, step S101 encrypts the text information of the acquired original book, and the specific method for obtaining the encrypted text information is as follows:
[0070] Word embedding is performed on the obtained text information of the original book to obtain the text embedding vector;
[0071] The text embedding vector is homomorphically encrypted using a homomorphic encryption library to obtain encrypted text information.
[0072] This implementation method allows for word embedding of text information, reducing the dimensionality of the text information and improving the encryption efficiency of the text information.
[0073] In this embodiment of the invention, since homomorphic encryption mechanisms cannot efficiently perform embedding representation, the terminal device needs to first convert the original data into an embedding vector through an embedding layer and then encrypt it into a ciphertext result. The terminal device and the data processing platform share a pre-trained model, such as the BERT model.
[0074] In this embodiment of the invention, the method for encrypting text information can be homomorphic encryption. Homomorphic encryption is a type of encryption method with special natural properties. Compared with general encryption algorithms, homomorphic encryption can not only perform basic encryption operations, but also perform various computational functions between ciphertexts. That is, calculating before decryption is equivalent to decrypting before calculating. Homomorphic encryption of text information can be performed using the homomorphic encryption library HElib.
[0075] Step S102: Send the encrypted text information to the data processing platform so that the data processing platform can extract events from the encrypted text information to obtain ciphertext results; and feed back the ciphertext results to the terminal device.
[0076] In this embodiment of the invention, the data processing platform can be built based on the MLaaS (Machine Learning as a Service) model. The server collects training data from various sources such as the Internet and the edge computing, then trains a model based on the training data, and finally deploys the model to the data processing platform to provide inference services to customers. However, when customers send plaintext data to the server for processing, there is a risk of privacy leakage. Therefore, homomorphically encrypted text information can be sent to the data processing platform to ensure the security of the original text.
[0077] Step S103: Decrypt the ciphertext result to obtain the event extraction result.
[0078] In this embodiment of the invention, the event extraction result includes at least trigger words, event types, event arguments, and argument roles; the event arguments contain event elements. Event extraction can be performed using an event extraction model that integrates external knowledge and based on privacy-preserving natural language processing techniques. The event extraction methods can include trigger word detection, event type detection, event argument extraction, and argument role recognition.
[0079] Step S104: Construct a knowledge graph of events based on the event extraction results.
[0080] Step S105: Embed the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information.
[0081] In this embodiment of the invention, event elements can be transformed into element images using a pre-trained text-to-image model, which can be constructed using a generative adversarial network. Text-to-image technology generates an image corresponding to the content of a descriptive text.
[0082] As an optional implementation, step S105 embeds the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information in the following specific way:
[0083] The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role;
[0084] Obtain the element image corresponding to the event element;
[0085] The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
[0086] In this implementation method, the knowledge graph of events can be converted into a knowledge image of events, and the position of the text information of the event element in the knowledge image of events can be determined. Then, the element image corresponding to the event element can be embedded into the position of the text information of the event element in the knowledge image of events to obtain a visualization image. The obtained visualization image is a multimodal image, which ensures the amount of information in the visualization image.
[0087] As an optional implementation, after step S105, the following steps may also be included:
[0088] The visualization image is calculated according to a preset hash algorithm to obtain the hash value of the visualization image;
[0089] Obtain the public and private keys corresponding to the visualized image;
[0090] The hash value is encrypted using the private key to obtain the digital signature of the visualized image;
[0091] The digital fingerprint of the visualized image is obtained based on the digital signature and the public key;
[0092] The digital fingerprint and the obtained current timestamp are added to the visualization image to obtain a visualized digital collection.
[0093] This implementation method allows for the acquisition of digital fingerprints and current timestamps based on visualized images. These fingerprints and timestamps are then added to the visualized image to create visualized digital collections, thereby enhancing the security of the visualized image.
[0094] The following is for reference. Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of an encrypted text data processing method provided by the present invention. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.
[0095] Figure 2 The flowchart of an embodiment of the present invention, which provides an encrypted text data processing method, is applied to a data processing platform and includes:
[0096] Step S201: Extract events from the encrypted text information sent by the terminal device to obtain the ciphertext result.
[0097] In this embodiment of the invention, an event extraction model can be trained based on plaintext data. To ensure compatibility with homomorphic encryption algorithms, the Chebyshev polynomial approximation activation function Tanh can be used. Experiments show that Tanh = −0.00163574303018748x³ + 0.249476365628036x yields the best results (Tanh performs better than other activation functions in training). After the training phase is completed, the event extraction model is deployed on a data processing platform.
[0098] As an optional implementation, step S201 involves extracting events from the encrypted text information sent by the terminal device to obtain the ciphertext result, specifically in the following manner:
[0099] Trigger word detection is performed on the encrypted text information to obtain the trigger words included in the encrypted text information;
[0100] The encrypted text information is subjected to event type detection to obtain the event types included in the encrypted text information;
[0101] Event arguments are extracted from the encrypted text information to obtain the event arguments included in the encrypted text information;
[0102] Argument role identification is performed on the encrypted text information to obtain the argument roles included in the encrypted text information;
[0103] The trigger word, the event type, the event argument, and the argument role are determined as the ciphertext result.
[0104] This implementation method allows for the sequential detection of trigger words, event types, extraction of event arguments, and identification of argument roles in encrypted text information, ensuring the comprehensiveness of the encrypted results.
[0105] In this embodiment of the invention, information extraction is a text processing technique that extracts factual information such as entities, relationships, and events of a specified type from natural language text and outputs it as structured data; event extraction is a technique that extracts events of interest to the user from unstructured information and presents them to the user in a structured manner. The event extraction task can be decomposed into four sub-tasks: trigger word recognition, event type classification, argument recognition, and role classification.
[0106] Step S202: Determine the noise error of the encrypted text information based on the encrypted result.
[0107] Step S203: If the noise error is less than or equal to a preset threshold, the encrypted result is fed back to the terminal device.
[0108] In this embodiment of the invention, the preset threshold can be 1. When the accumulated noise error exceeds 1 after the encrypted text information is sent to the data processing platform for inference calculation, the intermediate result is returned to the terminal device for restoration. The noise is removed and the encrypted text information is re-encrypted and sent to the data processing platform. This process is repeated multiple times until the intermediate result converges, which is the final ciphertext result. After decryption, the event extraction result (trigger word, event type, event argument, argument role) is returned.
[0109] As an optional implementation, if the noise error is greater than the preset threshold, the following steps may also be included:
[0110] The encrypted result is determined as the result to be decrypted;
[0111] The process involves sending the result to be restored to the terminal device, enabling the terminal device to decrypt the result and obtain the text information to be restored; denoising the text information to be restored to obtain denoised text information; homomorphically encrypting the denoised text information to obtain encrypted text information; sending the encrypted text information to the data processing platform; and executing step S201.
[0112] This implementation method allows the ciphertext result to be restored when the noise error of the ciphertext result exceeds a preset threshold. Denoising the restored text information reduces the noise error of the obtained ciphertext result, thereby improving the accuracy of the ciphertext result.
[0113] This invention can obtain a visualized image corresponding to the text information of the original book while encrypting the text information, thus improving the data security of the original book. Furthermore, this invention can improve the encryption efficiency of text information. Furthermore, this invention can ensure the amount of information in the visualized image. Furthermore, this invention can improve the security of the visualized image. Furthermore, this invention can ensure the comprehensiveness of the encrypted result. Furthermore, this invention can improve the accuracy of the encrypted result.
[0114] After introducing the method of exemplary embodiments of the present invention, the following references are made. Figure 3 An exemplary embodiment of the present invention provides a text visualization system based on encryption, comprising a terminal device 301, a data processing platform 302, and a server 303, wherein:
[0115] The server 303 is used to train an event extraction model based on pre-acquired training data and deploy the event extraction model to the data processing platform 302.
[0116] The terminal device 301 is used to encrypt the text information of the acquired original book to obtain encrypted text information, and send the encrypted text information to the data processing platform 302.
[0117] The data processing platform 302 is used to extract events from the encrypted text information based on the event extraction model to obtain ciphertext results; and to determine the noise error of the encrypted text information based on the ciphertext results; if the noise error is less than or equal to a preset threshold, the ciphertext results are fed back to the terminal device 301.
[0118] The terminal device 301 is further configured to decrypt the encrypted result to obtain an event extraction result; wherein the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element; and constructs an event knowledge graph based on the event extraction result; and embeds the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information.
[0119] As an optional implementation, the terminal device 301 encrypts the text information of the acquired original book, and the specific method for obtaining the encrypted text information is as follows:
[0120] Word embedding is performed on the obtained text information of the original book to obtain the text embedding vector;
[0121] The text embedding vector is homomorphically encrypted using a homomorphic encryption library to obtain encrypted text information.
[0122] This implementation method allows for word embedding of text information, reducing the dimensionality of the text information and improving the encryption efficiency of the text information.
[0123] As an optional implementation, the terminal device 301 is further configured to:
[0124] After obtaining the visualized image of the text information, the visualized image is calculated according to a preset hash algorithm to obtain the hash value of the visualized image;
[0125] Obtain the public and private keys corresponding to the visualized image;
[0126] The hash value is encrypted using the private key to obtain the digital signature of the visualized image;
[0127] The digital fingerprint of the visualized image is obtained based on the digital signature and the public key;
[0128] The digital fingerprint and the obtained current timestamp are added to the visualization image to obtain a visualized digital collection.
[0129] This implementation method allows for the acquisition of digital fingerprints and current timestamps based on visualized images. These fingerprints and timestamps are then added to the visualized image to create visualized digital collections, thereby enhancing the security of the visualized image.
[0130] As an optional implementation, the terminal device 301 embeds the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information in the following specific way:
[0131] The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role;
[0132] Obtain the element image corresponding to the event element;
[0133] The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
[0134] In this implementation method, the knowledge graph of events can be converted into a knowledge image of events, and the position of the text information of the event element in the knowledge image of events can be determined. Then, the element image corresponding to the event element can be embedded into the position of the text information of the event element in the knowledge image of events to obtain a visualization image. The obtained visualization image is a multimodal image, which ensures the amount of information in the visualization image.
[0135] As an optional implementation, the data processing platform 302 extracts events from the encrypted text information based on the event extraction model to obtain the ciphertext result in the following specific manner:
[0136] Trigger word detection is performed on the encrypted text information to obtain the trigger words included in the encrypted text information;
[0137] The encrypted text information is subjected to event type detection to obtain the event types included in the encrypted text information;
[0138] Event arguments are extracted from the encrypted text information to obtain the event arguments included in the encrypted text information;
[0139] Argument role identification is performed on the encrypted text information to obtain the argument roles included in the encrypted text information;
[0140] The trigger word, the event type, the event argument, and the argument role are determined as the ciphertext result.
[0141] This implementation method allows for the sequential detection of trigger words, event types, extraction of event arguments, and identification of argument roles in encrypted text information, ensuring the comprehensiveness of the encrypted results.
[0142] As an optional implementation, the data processing platform 302 is further used for:
[0143] If the noise error is greater than the preset threshold, the ciphertext result is determined as the result to be decrypted;
[0144] The process involves sending the result to be restored to the terminal device, enabling the terminal device to decrypt the result and obtain the text information to be restored; denoising the text information to be restored to obtain denoised text information; homomorphically encrypting the denoised text information to obtain encrypted text information; sending the encrypted text information to the data processing platform; and extracting events from the encrypted text information sent by the terminal device to obtain a ciphertext result.
[0145] This implementation method allows the ciphertext result to be restored when the noise error of the ciphertext result exceeds a preset threshold. Denoising the restored text information reduces the noise error of the obtained ciphertext result, thereby improving the accuracy of the ciphertext result.
[0146] After introducing the methods and systems of exemplary embodiments of the present invention, the following references are made. Figure 4 An exemplary embodiment of the present invention provides a text visualization device based on encryption, which includes:
[0147] Encryption module 401 is used to encrypt the text information of the acquired original book to obtain encrypted text information;
[0148] The sending module 402 is used to send the encrypted text information obtained by the encryption module 401 to the data processing platform, so that the data processing platform can perform event extraction on the encrypted text information to obtain the ciphertext result; and feed back the ciphertext result to the terminal device.
[0149] The decryption module 403 is used to decrypt the ciphertext result to obtain the event extraction result; wherein, the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element;
[0150] Construction module 404 is used to construct a knowledge graph of events based on the event extraction results obtained by decryption module 403;
[0151] The embedding module 405 is used to embed the element image corresponding to the event element into the event knowledge graph obtained by the construction module 404 to obtain a visualized image of the text information.
[0152] As an optional implementation, the encryption module 401 encrypts the text information of the acquired original book, and the specific method for obtaining the encrypted text information is as follows:
[0153] Word embedding is performed on the obtained text information of the original book to obtain the text embedding vector;
[0154] The text embedding vector is homomorphically encrypted using a homomorphic encryption library to obtain encrypted text information.
[0155] This implementation method allows for word embedding of text information, reducing the dimensionality of the text information and improving the encryption efficiency of the text information.
[0156] As an optional implementation, the embedded module 405 is also used for:
[0157] After obtaining the visualized image of the text information, the visualized image is calculated according to a preset hash algorithm to obtain the hash value of the visualized image;
[0158] Obtain the public and private keys corresponding to the visualized image;
[0159] The hash value is encrypted using the private key to obtain the digital signature of the visualized image;
[0160] The digital fingerprint of the visualized image is obtained based on the digital signature and the public key;
[0161] The digital fingerprint and the obtained current timestamp are added to the visualization image to obtain a visualized digital collection.
[0162] This implementation method allows for the acquisition of digital fingerprints and current timestamps based on visualized images. These fingerprints and timestamps are then added to the visualized image to create visualized digital collections, thereby enhancing the security of the visualized image.
[0163] As an optional implementation, the embedding module 405 embeds the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information in the following specific way:
[0164] The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role;
[0165] Obtain the element image corresponding to the event element;
[0166] The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
[0167] In this implementation method, the knowledge graph of events can be converted into a knowledge image of events, and the position of the text information of the event element in the knowledge image of events can be determined. Then, the element image corresponding to the event element can be embedded into the position of the text information of the event element in the knowledge image of events to obtain a visualization image. The obtained visualization image is a multimodal image, which ensures the amount of information in the visualization image.
[0168] Next, refer to Figure 5 An exemplary embodiment of the present invention will be described, comprising:
[0169] The extraction module 501 is used to extract events from the encrypted text information sent by the terminal device to obtain the ciphertext result;
[0170] The determining module 502 is used to determine the noise error of the encrypted text information based on the ciphertext result obtained by the extraction module 501.
[0171] The feedback module 503 is used to feed back the encrypted result to the terminal device if the noise error obtained by the determination module 502 is less than or equal to a preset threshold.
[0172] As an optional implementation, the extraction module 501 performs event extraction on the encrypted text information sent by the terminal device to obtain the ciphertext result in the following specific manner:
[0173] Trigger word detection is performed on the encrypted text information to obtain the trigger words included in the encrypted text information;
[0174] The encrypted text information is subjected to event type detection to obtain the event types included in the encrypted text information;
[0175] Event arguments are extracted from the encrypted text information to obtain the event arguments included in the encrypted text information;
[0176] Argument role identification is performed on the encrypted text information to obtain the argument roles included in the encrypted text information;
[0177] The trigger word, the event type, the event argument, and the argument role are determined as the ciphertext result.
[0178] This implementation method allows for the sequential detection of trigger words, event types, extraction of event arguments, and identification of argument roles in encrypted text information, ensuring the comprehensiveness of the encrypted results.
[0179] As an optional implementation, the feedback module 503 is also used for:
[0180] If the noise error is greater than the preset threshold, the ciphertext result is determined as the result to be decrypted;
[0181] The process involves sending the result to be restored to the terminal device, enabling the terminal device to decrypt the result and obtain the text information to be restored; denoising the text information to be restored to obtain denoised text information; homomorphically encrypting the denoised text information to obtain encrypted text information; sending the encrypted text information to the data processing platform; and extracting events from the encrypted text information sent by the terminal device to obtain a ciphertext result.
[0182] This implementation method allows the ciphertext result to be restored when the noise error of the ciphertext result exceeds a preset threshold. Denoising the restored text information reduces the noise error of the obtained ciphertext result, thereby improving the accuracy of the ciphertext result.
[0183] After introducing the methods, systems, and apparatus of exemplary embodiments of the present invention, the following references are made. Figure 6 A computer-readable storage medium according to exemplary embodiments of the present invention will be described, please refer to... Figure 6 The computer-readable storage medium shown is an optical disc 60, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it implements the steps described in the above method implementation, such as encrypting the text information of the original book to obtain encrypted text information; sending the encrypted text information to a data processing platform so that the data processing platform can extract events from the encrypted text information to obtain ciphertext results; feeding back the ciphertext results to the terminal device; decrypting the ciphertext results to obtain event extraction results; wherein, the event extraction results include at least trigger words, event types, event arguments, and argument roles; the event arguments contain event elements; constructing a knowledge graph of events based on the event extraction results; embedding the element images corresponding to the event elements into the knowledge graph of events to obtain a visualized image of the text information; the specific implementation methods of each step will not be repeated here.
[0184] It should be noted that examples of the computer-readable storage medium may also 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 optical and magnetic storage media, which will not be elaborated here.
[0185] After introducing the methods, media, and apparatus of exemplary embodiments of the present invention, the following references are made. Figure 7 A computing device for encrypted text visualization or encrypted text data processing according to an exemplary embodiment of the present invention.
[0186] Figure 7 A block diagram is shown of an exemplary computing device 70 suitable for implementing embodiments of the present invention. The computing device 70 may be a computer system or a server. Figure 7 The computing device 70 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.
[0187] like Figure 7As shown, the components of the computing device 70 may include, but are not limited to: one or more processors or processing units 701, system memory 702, and bus 703 connecting different system components (including system memory 702 and processing unit 701).
[0188] The computing device 70 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 70, including volatile and non-volatile media, removable and non-removable media.
[0189] System memory 702 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 7021 and / or cache memory 7022. Computing device 70 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 7023 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 7 Not shown in the image (usually referred to as a "hard drive"). Although not shown in Figure 7 The diagram illustrates that disk drives for reading and writing to removable non-volatile disks (e.g., "floppy disks") and optical disc drives for reading and writing to removable non-volatile optical discs (e.g., CD-ROMs, DVD-ROMs, or other optical media) can be provided. In these cases, each drive can be connected to bus 703 via one or more data media interfaces. System memory 702 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.
[0190] A program / utility 7025 having a set (at least one) of program modules 7024 may be stored, for example, in system memory 702, and such program modules 7024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 7024 typically perform the functions and / or methods described in the embodiments of the present invention.
[0191] The computing device 70 can also communicate with one or more external devices 704 (such as a keyboard, pointing device, display, etc.). This communication can be performed through the input / output (I / O) interface 705. Furthermore, the computing device 70 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 706. Figure 7 As shown, network adapter 706 communicates with other modules of computing device 70 (such as processing unit 701) via bus 703. It should be understood that, although... Figure 7 As not shown, it can be used in conjunction with computing device 70 with other hardware and / or software modules.
[0192] The processing unit 701 executes various functional applications and data processing by running programs stored in the system memory 702. For example, it encrypts the acquired text information of the original book to obtain encrypted text information; sends the encrypted text information to the data processing platform so that the platform can extract events from the encrypted text information to obtain ciphertext results; and feeds back the ciphertext results to the terminal device; decrypts the ciphertext results to obtain event extraction results. The event extraction results include at least trigger words, event types, event arguments, and argument roles; the event arguments contain event elements; a knowledge graph is constructed based on the event extraction results; and the element images corresponding to the event elements are embedded into the knowledge graph to obtain a visualized image of the text information. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of an encrypted text visualization device or an encrypted text data processing device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of a unit / module described above can be further divided into multiple units / modules for specificity.
[0193] In the description of this invention, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0194] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0195] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0196] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0197] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0198] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0199] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
[0200] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.
Claims
1. A method for encryption-based text visualization applied to a terminal device, characterized by, The method includes: The obtained text information of the original book is encrypted to obtain encrypted text information; The encrypted text information is sent to the data processing platform, so that the data processing platform can extract events from the encrypted text information to obtain a ciphertext result; and the ciphertext result is fed back to the terminal device. The encrypted result is decrypted to obtain the event extraction result; wherein the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element; Construct a knowledge graph of events based on the event extraction results; Embedding the element image corresponding to the event element into the event knowledge graph yields a visualized image of the text information, including: The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role; Obtain the element image corresponding to the event element; The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
2. The encryption-based text visualization method of claim 1, wherein, The process of encrypting the text information of the original book to obtain encrypted text information includes: Word embedding is performed on the obtained text information of the original book to obtain the text embedding vector; The text embedding vector is homomorphically encrypted using a homomorphic encryption library to obtain encrypted text information.
3. The encryption-based text visualization method of claim 1, wherein, After obtaining the visualized image of the text information, the method further includes: The visualization image is calculated according to a preset hash algorithm to obtain the hash value of the visualization image; Obtain the public and private keys corresponding to the visualized image; The hash value is encrypted using the private key to obtain the digital signature of the visualized image; The digital fingerprint of the visualized image is obtained based on the digital signature and the public key; The digital fingerprint and the obtained current timestamp are added to the visualization image to obtain a visualized digital collection.
4. A method for processing encrypted text data, applied to a data processing platform, based on the method for visualizing encrypted text according to any one of claims 1-3, characterized in that, The method includes: Event extraction is performed on the encrypted text information sent by the terminal device to obtain the ciphertext result; The noise error of the encrypted text information is determined based on the ciphertext result; If the noise error is less than or equal to a preset threshold, the encrypted result is fed back to the terminal device.
5. The encryption-based text data processing method according to claim 4, characterized by, The process of extracting events from the encrypted text information sent by the terminal device to obtain the ciphertext result includes: Trigger word detection is performed on the encrypted text information to obtain the trigger words included in the encrypted text information; The encrypted text information is subjected to event type detection to obtain the event types included in the encrypted text information; Event arguments are extracted from the encrypted text information to obtain the event arguments included in the encrypted text information; Argument role identification is performed on the encrypted text information to obtain the argument roles included in the encrypted text information; The trigger word, the event type, the event argument, and the argument role are determined as the ciphertext result.
6. The encryption-based text data processing method according to claim 5, characterized by, If the noise error is greater than the preset threshold, the method further includes: The encrypted result is determined as the result to be decrypted; The process involves sending the result to be restored to the terminal device, enabling the terminal device to decrypt the result and obtain the text information to be restored; denoising the text information to be restored to obtain denoised text information; homomorphically encrypting the denoised text information to obtain encrypted text information; sending the encrypted text information to the data processing platform; and performing the step of extracting events from the encrypted text information sent by the terminal device to obtain a ciphertext result.
7. A system for encryption-based text visualization, characterized in that, This includes terminal equipment, data processing platforms, and servers, among which: The server is used to train an event extraction model based on pre-acquired training data and deploy the event extraction model to the data processing platform. The terminal device is used to encrypt the text information of the acquired original book to obtain encrypted text information, and send the encrypted text information to the data processing platform. The data processing platform is used to extract events from the encrypted text information based on the event extraction model to obtain ciphertext results; and to determine the noise error of the encrypted text information based on the ciphertext results; if the noise error is less than or equal to a preset threshold, the ciphertext results are fed back to the terminal device. The terminal device is further configured to decrypt the encrypted result to obtain an event extraction result; wherein the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element; and a knowledge graph of events is constructed based on the event extraction result; and the element image corresponding to the event element is embedded into the knowledge graph of events to obtain a visualized image of the text information, including: The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role; Obtain the element image corresponding to the event element; The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
8. An encryption-based text visualization device, characterized by include: The encryption module is used to encrypt the text information of the original book to obtain encrypted text information; The sending module is used to send the encrypted text information to the data processing platform so that the data processing platform can extract events from the encrypted text information and obtain the ciphertext result. And feed back the encrypted result to the terminal device; The decryption module is used to decrypt the ciphertext result to obtain the event extraction result; wherein, the event extraction result includes at least a trigger word, an event type, an event argument, and an argument role; the event argument contains an event element; The construction module is used to construct a knowledge graph of events based on the event extraction results; The embedding module is used to embed the element image corresponding to the event element into the event knowledge graph to obtain a visualized image of the text information, including: The knowledge graph is transformed into a knowledge image; wherein the knowledge image includes textual information of the event elements and the argument roles, as well as relationship information between one event element and another event element / argument role; Obtain the element image corresponding to the event element; The element image is embedded into the position of the text information of the corresponding event element in the knowledge image to obtain a visualized image of the text information.
9. An encryption-based text data processing apparatus based on the encryption-based text visualization method according to any one of claims 1 to 3, characterized by, include: The extraction module is used to extract events from the encrypted text information sent by the terminal device to obtain the ciphertext result; The determination module is used to determine the noise error of the encrypted text information based on the ciphertext result; The feedback module is used to feed back the encrypted result to the terminal device if the noise error is less than or equal to a preset threshold.
10. A computing device, the computing device comprising: At least one processor, memory, and input / output unit; The memory is used to store computer programs, and the processor is used to call the computer programs stored in the memory to execute the method as described in claim 6.
11. A computer-readable storage medium comprising instructions, wherein: When it is run on a computer, it causes the computer to perform the method as described in claim 6.