505 results about "Plain text" patented technology

The invention discloses a contract risk assessment and compliance check method, system and device based on a large language model and a medium, belongs to the cross technical field of artificial intelligence and natural language processing, and aims to solve the technical problem of how to automatically, quickly and accurately identify potential risks and compliance in a contract. According to the technical scheme, the method comprises the steps of data preprocessing, wherein non-plain text format files of various sources are subjected to data preprocessing and converted into plain text format files; constructing a knowledge performing semantic understanding and relation extraction on industrial standards, internal regulations of enterprises and a plain text format file obtained after preprocessing by utilizing a big language, and constructing a structured and queriable knowledge base; training a large language model: optimizing parameters of the large language model in combination with pre-training and supervised training; and risk assessment and compliance check: based on the trained large language model and the compliance rule base, performing identification and analysis of potential risk points and compliance check on the input contract text.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of medical health, financial science and technology and the like, and discloses a voice generation method which comprises the following steps: constructing a multi-language voice synthesis model, obtaining plain text data and paired voice text data, and constructing an expansion vocabulary; updating a language perception embedding layer and model parameters, and converting an input text into a mark sequence; and the encoder extracts context semantic features, extracts pronunciation rule features, and the decoder fuses the features to generate an acoustic feature sequence, and converts the acoustic feature sequence into target voice data. According to the invention, the multi-language speech synthesis model is combined with the language perception embedding layer, so that the speech generation capability of a low-resource language is improved; the text conversion accuracy is improved by expanding the vocabulary, the target language learning ability is enhanced by unsupervised training, the low data environment adaptability is optimized by supervised training, and the speech naturalness and fluency are improved by feature fusion.

Systems or techniques are provided for facilitating retrieval augmented generative question and answer boosting. In various embodiments, a system can access a plain text question regarding a scientific instrument. In various aspects, the system can generate, via a large language model that references a document-graph repository, a structured or unstructured answer for the plain text question. In various instances, the document-graph repository can comprise a plurality of document-graphs that respectively correspond to a plurality of technical documents. In various cases, for a first document-graph that corresponds to a first technical document, leaf nodes of the first document-graph can represent respective text blocks written in the first technical document, and non-leaf nodes of the first document-graph can respectively represent a document title, one or more section headings, and one or more scientific instrument identifiers written in the first technical document and beneath which the respective text blocks are nested.

The invention relates to an engineering document index consistency proofreading method and system based on a multi-modal large model, and the method comprises the steps: Q1. OCR detection and recognition: carrying out the optical character recognition and format analysis of a source document, converting an uploaded PDF document into a processable text message in a Markdown format, and carrying out the format discrimination of a table, a formula and a plain text; and Q2, table and formula processing: adopting a hierarchical processing strategy, intelligently selecting an optimal processing mode according to the complexity of the table, and converting table information into a descriptive long text through a language large model and cue words. According to the method, accurate, reliable and efficient document index checking service can be provided for a user, the quality and efficiency of professional document processing are remarkably improved, the efficiency and quality of knowledge graph construction are remarkably improved, a knowledge verification system capable of being evolved continuously is established, and the method is suitable for popularization and application. And a reliable technical support is provided for knowledge management and professional decision-making in a complex field.

The present application discloses a method, device, storage medium and equipment for structured extraction of document information, the method comprising: first obtaining a target image where the target document is located; and extracting target visual features of the target image; then inputting the target visual features into a semantic information extraction model for OCR information extraction to obtain target OCR information, and encoding it to obtain a target semantic encoding vector; then inputting the target visual features and the target semantic encoding vector into a pre-built multimodal large language model to predict the structured information extraction result corresponding to the target document. It can be seen that since the present application adopts a general structured information extraction method combining OCR information with a multimodal large language model, and uses visual features and OCR information as the extraction basis for spatial and textual semantics respectively, it solves the problem of lack of spatial information when performing structured extraction through pure text, thereby effectively improving the accuracy of structured extraction of document information.

The invention discloses a multi-modal classification method fusing a graph convolutional neural network and a capsule graph neural network, and solves the problem of how to apply an artificial intelligence technology to an appearance patent. The method comprises the following steps: coding a patent text sequence by utilizing BERT, segmenting semantic graph convolution by utilizing PCNN, constructing a dependency tree by utilizing grammar graph convolution, carrying out interactive attention and relationship classification, and finally carrying out image feature extraction through a capsule network. According to the method, the appearance patent classification technology fusing heterogeneous multi-modal information is researched, the feature extraction and fusion problems of multi-modal information such as characters, images and networks are solved, a heterogeneous multi-modal appearance design patent classification model is constructed, and the classification accuracy is greatly improved relative to pure text content. And meanwhile, an appearance design patent AI standard data set is constructed on the basis of the intellectual property hypergraph network, so that the blank of patent types in a traditional Lankyo classification system is filled, and the bottleneck of a traditional appearance patent classification method is broken through.

A multi-modal retrieval system based on the similarity between image and text feature vectors, which system belongs to the technical field of information retrieval. In the present invention, advanced deep learning technology is used to extract high-dimensional feature vectors of image data and text data, and the similarity between these feature vectors is computed by means of a specific similarity algorithm. The system can process various types of query inputs, which take the form of plain text, plain images and a combination thereof, thereby providing a flexible search mode.

The invention discloses a data circulation trusted system and device based on a block chain and privacy calculation, and relates to the technical field of trusted data. Comprising a data supply end, a data demand end and a credible supervision end, the data supply end comprises a digital identity identification module which is used for generating a dynamic digital identity according to an enterprise unified social credit code and an ISO industry classification code and submitting the dynamic digital identity to a first block chain of the credible supervision end for authentication; the mixed desensitization module is used for carrying out first 3-bit plaintext reservation and hash replacement on the sensitive field by adopting an AES-256 algorithm, binding a UTC timestamp to generate a desensitization record and uploading the desensitization record to a first block chain; and the zero-knowledge proof generation module is used for converting the privacy calculation result into a zero-knowledge proof voucher and pushing verification parameters to a sandbox environment of the data demand end. According to the invention, the security and privacy of data in a circulation link and the credibility of transactions are guaranteed, and the problems of privacy leakage, uncredible transactions, difficult supervision and the like possibly existing in data circulation are solved.

Systems or techniques that facilitate electronic acquisition of troubleshooting knowledge for medical imaging scanners are provided. In various embodiments, a system can access a plain text service manual and a service complaint that are associated with a medical imaging scanner. In various aspects, the system can identify, via named-entity recognition or natural language processing, a semantic hierarchy of the plain text service manual. In various instances, the system can record, via graphical user interface tracking, how a service technician that is troubleshooting the service complaint sequentially navigates through the semantic hierarchy, thereby yielding a troubleshooting trace that corresponds to the service complaint.

The invention discloses a cultural heritage file multi-dimensional storage system, which relates to the field of cultural heritage digital protection and intelligent storage and comprises a data acquisition and processing module, a double-library management module, a multi-dimensional index retrieval engine, a security and convergence module and a backup and disaster recovery module. According to the method, structured texts and unstructured files are uniformly accessed through various interfaces, a special tool chain is adopted for format standardization, audios and videos are transcoded into an H.264 / AAC format through FFmpeg, images are subjected to resolution adjustment and compression through ImageMagick, plain texts are extracted from texts through ApacheTika and are converted into UTF-8 codes, standardized data are uniformly converted into an intermediate format, and the format of the intermediate format is converted into the intermediate format. According to the technical scheme, the method comprises the following steps of: standardizing input data by adopting a three-layer duplicate removal strategy, facilitating other modules to receive data, performing refined redundancy processing on the standardized input data by adopting a three-layer duplicate removal strategy, remarkably reducing storage redundancy, partitioning a cultural heritage data main library according to three layers of ''project type-medium type-age'', and partitioning an inheritor information library according to two levels of ''province-inheritor number prefix''.

The invention discloses a multilingual speech recognition model training method and a related device, and relates to the technical field of speech recognition, and the method comprises the steps: constructing a multilingual speech recognition model training model comprising a first training branch and a second training branch in advance, the first training branch and the second training branch are each composed of an encoder and a decoder, the first training branch and the second training branch share a decoder and a partial encoder; and performing multi-task joint training on the first training branch and the second training branch through the voice text supervised training data and the plain text training data to obtain the trained first training branch as a multilingual voice recognition model. According to the scheme, the calculation overhead of model training can be reduced, and the utilization rate of the training data is improved, so that an efficient and accurate multilingual speech recognition model is obtained through training under the condition that the training period is effectively shortened and supervised training data is reduced, and the multilingual speech recognition effect is improved.

Certain aspects of the disclosure provide a method for verifiable key rotation of an encryption key. The method includes generating a ciphertext by encrypting a plaintext with a homomorphic probabilistic encryption scheme based on a first key. The method further includes generating an updating token based on a difference between the homomorphic probabilistic encryption scheme based on a second key and generating a second ciphertext by encrypting the first ciphertext with the updating token. The method further includes validating the key rotation by selecting a set of second ciphertext blocks from the second ciphertext; reverting the set of second ciphertext blocks with the updating token to a set of third ciphertext blocks; and computing a Hamming distance between blocks of the set of second ciphertext blocks and the corresponding set of third ciphertext blocks.

The invention discloses a complex text OCR (Optical Character Recognition) error recognition and repair method based on a large language model, and relates to the technical field of text processing, the method comprises the following steps: step 1, a text preprocessing module recognizes and excludes a non-text area in a preliminary text result generated by OCR to ensure that residual content is pure text input, and a text preprocessing module is used for preprocessing the residual content; obtaining a text result of the plain text data; step 2, an error recognition module performs entity recognition on a text result of the plain text data by using a large language model, and provides revision suggestions for recognized suspected errors; 3, the database provides knowledge recall for the recognized entities and errors, and supplementation is provided for follow-up repair; and 4, correcting errors in a text result of the plain text data by an error repairing module through the acquired context information and supplementary data provided by the database, and outputting a document.

The invention provides an updatable attribute condition proxy re-encryption method with forward security and capable of resisting quantum attacks. The method comprises the steps that an authorization manager generates and publishes public parameters; the entrusting party and the entrusted party generate a public and private key pair of the entrusting party and the entrusted party according to the public parameters; the entrusting party encrypts the plaintext to generate an encrypted ciphertext and sends the encrypted ciphertext to the cloud server; the entrusting party generates an updated public key for the entrusting party according to the public key of the entrusting party, and the updated public key is used for updating the ciphertext of the private key of the entrusting party; the entrusting party generates a re-encryption key associated with the control strategy; the cloud server re-encrypts the encrypted ciphertext, generates a re-encrypted ciphertext and sends the re-encrypted ciphertext to the trusted party; the trusted party generates an updated private key; and the trusted party decrypts the re-encrypted ciphertext by using the updated private key. According to the updatable attribute condition proxy re-encryption method, public and private keys of a receiver are allowed to be periodically alternated based on a key asynchronous updating mechanism, so that forward security is realized; and fine-grained control of ciphertext conversion is realized through an attribute control structure.

The invention discloses an urban governance multi-modal large model evaluation method and device based on text tagging, and relates to the technical field of data processing and smart cities. Sample data are obtained, sample pictures and corresponding text tags are obtained, the sample pictures are input into a model, an output text corresponding to the model is obtained, and the output text corresponding to the model is obtained; extracting object existence, classification labels and target position information in the output text to obtain a structured dictionary list, and obtaining an accuracy index of the model in a single sample picture according to data in the structured dictionary list and the text labels corresponding to the sample pictures; and obtaining a comprehensive evaluation index of the model on the sample data according to the accuracy indexes of the plurality of single sample pictures. According to the method, the object judgment capability, the label classification capability and the target positioning capability of the multi-modal urban governance multi-modal large model are fully considered, the problem that plain text similarity evaluation indexes are unreliable is solved, and the accuracy of urban governance multi-modal large model evaluation is improved.

Various examples of improving an in-memory graph query engine using a persisted storage component are provided. The method includes updating data stored in an in-memory graph query engine and, based on updating the data, converting the data to a plain text form that may be more efficiently stored in the persistent storage component. The method further includes updates to additional in-memory graph query engines from the persistent storage component such that in-memory data stored in the graph query engines is synchronized.

The invention discloses a PDF (Portable Document Format) element extraction method based on a rendering process and suitable for RAG (Random Access Gateway). According to the method, the PDF content is decomposed into a plurality of blocks, and the blocks are subjected to type judgment and processing. Marking the image data in the form of text placeholders, and retaining the position and reference value of the image in the document; and for the table data, the table data is converted into an HTML format so as to maintain the structural integrity, and the consistency and readability of the table data in a plain text environment are ensured. And finally converting all extracted contents into a Markdown format to be output. According to the method, text input which is uniform in format and easy to process is provided for an RAG system, information loss is greatly reduced, the problem that an existing PDF analysis tool is difficult to process complex content is solved, and system performance and data processing reliability are improved.

The invention relates to the technical field of image processing and secret communication, in particular to a remote sensing image encryption algorithm based on a novel spatiotemporal chaotic system. Comprising the following steps: constructing a spatiotemporal chaotic system based on a coupling mapping lattice CML model, scrambling a plaintext by using a point-taking blocking Arnold periodic scrambling algorithm, eliminating a boundary generated by a blocking effect by using a bit-level arrangement algorithm, and designing a diffusion algorithm based on the spatiotemporal chaotic system and a Hash index chain. The method has the advantages that more complex behaviors of the spatiotemporal chaotic system can be described, and the spatiotemporal chaotic system not only has a larger parameter range, but also has more chaotic sequences; from the perspective of anti-decoding capability of an encryption algorithm, the dynamic characteristic of the spatio-temporal chaotic system is very suitable for image encryption; on the basis of a spatiotemporal chaotic system, the remote sensing image encryption algorithm is designed in combination with a point-taking partitioning algorithm, so that the spatial features of the remote sensing image can be processed more comprehensively, and the encryption algorithm has relatively high capability of resisting cracking.

Systems or techniques that facilitate systems and methods for providing explainability of natural language processing are provided. In various embodiments, a system can access a plain text clinical sentence. In various aspects, the system can generate, via execution of a first machine learning model, an assertion status classification label for a word of interest in the plain text clinical sentence. In various instances, the system can extract, from a hidden attention layer of the first machine learning model, word-wise attention scores corresponding to the plain text clinical sentence and render, on an electronic display, both the assertion status classification label and a graphical representation of the word-wise attention scores. In various cases, the system can determine, via execution of a second machine learning model, a reliability score for the assertion status classification label, based on the word-wise attention scores, and can render the reliability score on the electronic display.

The embodiment of the invention discloses a debugging port safety access method and device, vehicle-mounted electronic equipment and a storage medium, the debugging port safety access method is applied to the vehicle-mounted electronic equipment, the vehicle-mounted electronic equipment comprises at least one debugging port, and the debugging port safety access method comprises the steps that when a debugging port access password input by a user is received, the debugging port access password is sent to the vehicle-mounted electronic equipment; calling a preset encryption algorithm; the algorithm key is used for encrypting the original password through an encryption algorithm to obtain a debugging port target password, and the algorithm key and the original password are both obtained by calculating a unique identifier UID of the vehicle-mounted electronic equipment; and when confirming that the debugging port access password is consistent with the debugging port target password, allowing the user to access the debugging port. According to the technical means, the technical problem that the password leakage is easily caused when the password plaintext of the debugging port is stored in the vehicle-mounted electronic equipment in the related technology is solved.

The invention relates to a threshold homomorphic password federated gradient secure aggregation method, system and device, and the method comprises the steps: obtaining an aggregation gradient plaintext based on an online participant set, a threshold value and a network connection time limit; obtaining an online participant set and a threshold value, inputting the online participant set and the threshold value into a T-N threshold homomorphic encryption model, and then encrypting and collecting the online participant set and the threshold value to an aggregation party to generate ciphertext data; an aggregation party collects encryption parameters through an aggregation algorithm in combination with ciphertext data and aggregation gradient plaintext, and a T-N threshold homomorphic encryption model can expand a new private key with a threshold access characteristic on the basis of multi-party homomorphic encryption, so that under the condition that a certain proportion of participants are offline, a new private key with a threshold access characteristic can be expanded, and the encryption efficiency is improved. And the rest participants can still decrypt the ciphertext by using the new private key with the threshold access characteristic, and then the aggregation gradient plaintext is obtained by cooperating with calculation for aggregation, so that the time of iterative convergence to an expected value is shortened.

Customers of a software platform, such as a unified communications as a service platform, are enabled to control their own encryption keys used to encrypt and decrypt data from various communication services in the software platform. A key connector service is used to coordinate communications with a key management server for generating plaintext keys for data encryption and encrypted keys based on the plain text keys, and with a key broker server for storing and retrieving copies of the encrypted keys. A context identifier may be associated with an encrypted key and used to track which data has been encrypted with an underlying plaintext key. Examples of data encrypted may include conference recordings, webinar recordings, phone call recordings, voicemails, emails, and calendar tokens.

The present application relates to a test paper composition grading method, device and storage medium provided by the present application, and belongs to the field of artificial intelligence technology. The present application obtains the test paper composition image to be graded, the test paper composition title text, the writing text to be graded, and the composition scoring standard text; the test paper composition image, the test paper composition title text, the writing text, and the composition scoring standard text are input into a multimodal large model in combination with prompt information, and the evaluation result of the test paper composition to be graded is output. The present application not only has the plain text of the test paper composition as input, but also sets an evaluation dimension for the overall content of the test paper for the test paper composition image, so as to avoid certain limitations on the accuracy of the scoring result. In addition, an alignment mechanism for the test paper composition scoring process is added to alleviate the problem of hallucinations in the existing test paper composition grading method based on a large model, thereby greatly improving the overall effect of the test paper composition grading task.

The present application discloses a method, device, medium and program product for data auditing in federated learning, wherein the method for data auditing in federated learning comprises: obtaining communication data flow information of a federated learning device, wherein the communication data flow information comprises at least one of plaintext data and secret data; if the communication data flow information comprises plaintext data, performing a basic feature audit on the plaintext data, and when the basic feature audit of the plaintext data passes, performing a content feature audit on the plaintext data; if the communication data flow information comprises secret data, performing a basic feature audit on the secret data, and when the basic feature audit of the secret data passes, selectively performing a content feature audit on the secret data based on whether the secret data has the decryption authority; when the audit is completed or an abnormal state is found during the audit process, an audit result is generated. The present application solves the technical problem of low efficiency of federated learning due to the presence of malicious data in the communication of federated devices.

The invention belongs to the technical field of artificial intelligence and multi-modal large models, and particularly relates to a large visual language model illusion relieving method and device. The method comprises the following steps of: acquiring a complete visual token of an original image and a text token of a text prompt, connecting the tokens and jointly inputting the tokens into a large language model decoder; calculating an attention score matrix of the text token and all the visual tokens based on a cross-modal dynamic sampling strategy so as to sample key visual tokens; obtaining classification tokens of the original image, and screening significant visual tokens based on the classification tokens and attention scores of the visual tokens in the complete visual tokens; and carrying out adaptive attention enhancement on the significant visual token and the key visual token, and subtracting the logs distribution influence of plain text input from the logs distribution with enhanced visual information by comparing decoding strategies so as to obtain final target text output. The objective of the invention is to alleviate illusion problems in large-scale visual language models.

The invention discloses a trusted execution environment-based trusted federal learning system and method. The system comprises a server and a plurality of clients, the server and the plurality of clients are respectively provided with a domain virtual machine, an encryption module and a decryption module, the domain virtual machine is used as a trusted execution environment, and a remote secure connection module is configured in the domain virtual machine. According to the method, the local training and central aggregation process of the whole federated learning is protected based on the trusted execution environment, the global model, the local model and the updated data only exist in the trusted execution environment in a plaintext mode, the data is encrypted when the data is out of the trusted execution environment, the completeness of a federated learning protocol and the confidentiality of parameters are protected, and the reliability of the federated learning is improved. Only small calculation overhead is introduced while poisoning attacks and privacy attacks are effectively resisted, the precision and safety of the trained model are improved while user data privacy is effectively guaranteed, and privacy and safety attacks faced by a current federal learning system are comprehensively solved.

The present invention belongs to the technical field of text processing, and relates to an intelligent extraction method and system for an input text containing a mathematical formula. The method comprises: 1) performing format determination, conversion and preprocessing on an input text; 2) performing angle correction on the preprocessed image-formatted text; 3) performing formula detection; 4) performing layout analysis; 5) for inline formulas, according to a formula detection box, determining whether a corrected OCR detection box contains an inline formula, and splitting the OCR detection box containing the inline formula, so as to obtain a text-only OCR detection box; 6) performing formula recognition to obtain a formula recognition result; 7) performing text recognition to obtain a text recognition result; and 8) on the basis of a layout analysis box and a layout category thereof, performing same-line detection box determination and merging on the formula recognition result and the text recognition result, so as to obtain an extraction result for the input text. The present invention can effectively improve the extraction efficiency and accuracy for input texts containing mathematical formulas.

The disclosure provides a system / method / scheme to securely send data from a cloud, or cloud service provider, to users via a secure connectionless system, referred to herein as a C-VPN communication infrastructure (C-VPN CI). In one example a method of communicating from a cloud service provider to a user via a C-VPN CI includes: (1) obtaining, by a cloud service provider, security parameters from a SDE Cloud server operating on a computing system of the cloud service provider, wherein the security parameters include a set of mathematical rules and values for converting plain text to ciphertext, (2) creating a secure communication using the security parameters received from the SDE Cloud server, wherein the secure communication includes a secure header and secure data, and (3) sending the secure communication to the user via a generic electronic message delivery system.

The invention relates to the field of artificial intelligence, and particularly provides a contract risk auditing method and device, and the method comprises the following steps: S1, splitting a contract content paragraph, and decomposing a contract text into a plurality of independent paragraph units with a logic relation; s2, converting the contract text into a structured data unit, and performing text analysis and risk factor extraction; s3, table textualization: converting table data in the contract into a plain text format which can be processed by a large model; s4, constructing a list table to systematically organize key information in the contract; s5, performing text semantic analysis to deeply understand the contract text; s6, element checking: carefully reviewing and verifying key elements in the contract text; and S7, risk information summarization: summarizing and analyzing potential risks in the contract text. Compared with the prior art, the method has the advantages that potential risks in the text can be recognized and predicted through learning of a large amount of text data, and therefore the efficiency and accuracy of contract risk auditing are remarkably improved.

Systems, apparatuses, methods, and computer program products are disclosed for classical-quantum encryption and decryption. An example method for classical-quantum encryption includes receiving, by communications hardware, a symmetric key and a plaintext message, generating, by a function generator, an analytic function using the symmetric key and the plaintext message, computing, by a cryptography unit, a ciphertext based on a Taylor series expansion of the analytic function, and outputting the ciphertext. An example method for classical-quantum decryption, the method includes receiving, by communications hardware, a symmetric key and a ciphertext, deriving, by a cryptography unit and using a quantum computer, an analytic function using the ciphertext, generating, by a function generator, a plaintext message using the analytic function and the symmetric key, and outputting the plaintext message.