3518 results about "Conversion method" patented technology

The invention provides a natural language SQL (Structured Query Language) conversion method based on a data platform and a large language model, which relates to the technical field of data processing and comprises the following steps of: performing vectorization storage on metadata, blood relationship, indexes and historical query information, performing intention judgment and vector matching on a user query request, and determining a query condition based on a matching result. An association path is constructed according to data consanguinity, and an optimal SQL statement is generated by utilizing a historical query optimization table connection sequence and combining index matching. According to the method, intelligent conversion from the natural language to the efficient SQL can be realized, the query efficiency is improved, and the use threshold of a user is reduced.

The invention relates to the technical field of coordinate conversion, in particular to a CAD and BIM model coordinate automatic conversion method and system based on coordinate mapping, and the method comprises the following steps: extracting CAD building two-dimensional coordinates input by reference to a building drawing, constructing an initial two-dimensional triangular mesh, extracting key geometric feature points of a building, and combining the floor height parameter and corner information of the building to obtain a CAD and BIM model coordinate automatic conversion model; and mapping the two-dimensional grid to a three-dimensional coordinate space to generate initial building three-dimensional point cloud data. According to the method, a high-quality initial triangular mesh is constructed through a Delaunay triangulation algorithm, coordinate information of a sparse position is accurately captured, a Poisson surface reconstruction technology is combined, global curved surface fitting and smoothing processing are performed on point clouds of a sparse region, and density compensation and precision improvement of coordinate point distribution are realized. According to the optimization mode, the problem of model precision loss is effectively relieved in complex scenes such as building corners, special-shaped spaces and floor height changes.

A text-to-structured query language conversion method based on a large language model comprises the steps that database outline information is cut, and tables and columns needed by query of a non-target structured query language SQL are eliminated through correlation scoring and Steiner tree problem solving; screening context samples, predicting a similarity score from a text to a structured query language Text-to-SQL by using a cross encoder language model, and selecting a sample most related to a query problem; and injecting the cut database table and column information and the screened context sample into a cue word template, and generating an SQL query statement by using a large language model. The method can be used for optimizing the automatic conversion process from the natural language to the SQL and improving the conversion accuracy, and is used for providing a quick and convenient database retrieval mechanism for a non-SQL user and providing applications such as a data access mode in a wider form for mechanisms such as big language model retrieval enhancement generation RAG and the like.

The invention provides a query statement conversion method and device based on a natural language and a storage medium. The method comprises the steps that a natural language query statement input by a user is received, a pre-trained large language model is used for decomposing the natural language query statement into a plurality of subtasks, and each subtask corresponds to one query operation; analyzing each subtask, and performing step-by-step reasoning based on a mode knowledge base and a large language model in a database to generate an intermediate representation corresponding to each subtask; and summarizing the intermediate representation corresponding to each subtask, and converting the summarized intermediate representation into a complete target query statement by utilizing a large language model. According to the method, the accuracy of semantic understanding can be improved, the reliable target query statement is generated, the conversion efficiency is improved, and system debugging and optimization are facilitated.

The embodiment of the invention provides a cross-chip platform instruction conversion method, which comprises the following steps: collecting instruction set information of a source chip platform and a target chip platform, establishing an instruction feature analysis model, and calculating a semantic similarity matrix between instructions in a feature vector space by adopting a kernel function; training a multilayer graph attention neural network based on the semantic similarity matrix, mapping feature vectors of a source platform instruction and a target platform instruction to a shared embedding space, and performing iterative optimization on a mapping relation graph by applying a reinforcement learning method to obtain an instruction equivalent conversion rule; the instruction equivalent conversion rule is loaded in the instruction conversion engine, the input source platform instruction is decoded and analyzed, and a converted target platform instruction sequence is output to an instruction execution unit of a target chip platform; the resource overhead in the conversion process can be optimized, and the overall efficiency of the system is improved on the basis of ensuring the conversion correctness.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses an emotional speech conversion method based on rhythm prediction, which comprises the following steps: extracting phoneme sequences, acoustic features and emotional dimension representations in input text data and source audio data, and extracting language information by using a text encoder; frame-level rhythm changes and textual rhythm representations are generated based on the language information and the sentiment dimension representations. The method comprises the following steps: generating acoustic rhythm representation in combination with speaker characteristics and emotional dimension representation, calculating alignment loss by aligning text rhythm representation and acoustic rhythm representation, jointly training a rhythm prediction module and an acoustic modeling module to generate comprehensive rhythm representation, and finally generating converted voice waveforms and evaluating the converted voice waveforms through a discriminator. And optimizing each module parameter based on the comprehensive loss, and generating a target emotional voice. According to the method, accurate control of rhythm fine granularity is realized through implicit modeling, and the problem of mismatching during training and operation is avoided, so that the naturalness and emotion richness of voice are greatly improved.

The invention discloses a method and device for automatically converting a cross-format document into a Markdown document and a form enhancement method and system. The Markdown document conversion method comprises the following steps: firstly, obtaining a document image; mining hidden structure information from the document image, wherein the hidden structure information comprises target elements and hierarchical relationships among the target elements; performing semantic content analysis on the document image based on the structure information to obtain a semantic content analysis result; extracting key information in the document image according to an analysis result; the key information is converted into a Markdown format, preliminary formatting is carried out in a form or list mode, and a preliminary Markdown form is obtained; and finally, optimizing the preliminary Markdown form to form a target Markdown form, so that the cross-format document is automatically converted into the Markdown. According to the method, a complex nested structure and a form with irregular layout in the document can be effectively identified and converted, and the integrity and readability of form information when the form is converted into the Markdown format are ensured.

The invention discloses a query statement conversion method and device based on a large model, equipment and a medium, and relates to the field of computer science, and the method comprises the steps: obtaining a natural language query statement sent by a user side, comparing the natural language query statement with a high-frequency problem in a target knowledge base, and obtaining a query statement conversion result; whether a high-frequency problem with the similarity with the natural language query statement exceeding a preset similarity threshold value exists in the target knowledge base or not is judged; if the high-frequency problem that the similarity with the natural language query statement exceeds a preset similarity threshold does not exist, determining a target database table corresponding to the natural language query statement based on the target knowledge graph, and extracting a creation statement corresponding to the target database table, so as to determine target information corresponding to the target database table according to the creation statement; and analyzing the target information by using a preset large model to generate an SQL statement corresponding to the natural language query statement. According to the method and the device, the natural language query statement can be efficiently and accurately converted into the structured SQL statement.

In the field of document processing, format conversion is a common demand, for example, a PDF (Portable Document Format) or a scanning copy is converted into an editable format such as Word, Excel and the like, a traditional method generally adopts an OCR (Optical Character Recognition) technology to directly recognize document content and output a target format, and the method has the defects that the recognition accuracy is insufficient, errors can only be checked and corrected item by item after the target format is converted, and the efficiency is high. In order to solve the problems of lack of visual comparison with an original manuscript, easiness in omission, incapability of adjusting an identification result in real time in a format conversion process and high subsequent editing workload, the invention provides a brand-new document format conversion method, and provides a visual interactive interface by introducing a three-column visual interface and a real-time team correction mechanism. According to the method, the user can check and adjust the recognition result in real time in the conversion process, the accuracy of document conversion is remarkably improved, the flexibility of document conversion is achieved, the user is supported to carry out secondary editing on the content before formal output, visual comparison between the recognized content and an original manuscript is achieved, and the check difficulty is reduced.

The invention relates to the technical field of artificial intelligence, can be applied to the field of medical health, and discloses a timbre conversion method, device, equipment and medium based on cultural semanteme, the method comprises the following steps: constructing a cultural semantic timbre library comprising a semantic label and timbre characteristic parameter mapping relationship, the semantic label characterizing emotional semanteme of a target timbre, and the timbre characteristic parameter mapping relationship between the semantic label and the timbre characteristic parameter; the timbre characteristic parameters comprise a pitch range, rhythm rhythm and a harmonic structure; performing feature extraction based on text, image and audio multi-mode information to obtain semantic keywords, visual emotion features and audio acoustic features; performing attention weight fusion on the features through a multi-modal fusion deep learning model, and dynamically adjusting model parameters in combination with a semantic timbre library to generate a target timbre; and finally, intelligent conversion from the multi-mode information to the adaptive tone is realized. Through semantic-driven multi-modal feature collaborative optimization, the defect that timbre conversion machinery is stiff and lacks emotional expression is overcome, and the integrating degree of timbre expression and semantic scenes is improved.

The invention discloses a conversion method and system based on SysML and Modelica model semantic mapping. The method comprises the following steps that S1, a Modelica standard model library is imported into a SysML modeling tool; s2, completing the definition of behavior elements, and forming an SysML model instance; s3, exporting a Modelica model which can be executed by the Modelica simulator; s4, establishing a mapping relation table between SysML model elements and Modelica model elements; s5, when a change event occurs in the SysML model, updating the content of the corresponding Modelica model; s6, the Modelica model is imported into the SysML model, and a corresponding SysML model instance is generated; s7, simulation result mapping and behavior modeling generation are executed, a state transition diagram structure is formed, and structure updating of internal block diagrams in the system model is completed. According to the method, bidirectional conversion and joint simulation optimization between models are realized, and the method is suitable for cross-platform modeling, collaborative design and functional verification scenes of a complex system.

The invention relates to the technical field of Internet of Things, in particular to a multi-protocol conversion Internet of Things terminal communication method. Comprising the following steps: monitoring a communication data packet sent by Internet of Things terminal equipment in real time through a protocol sniffing module, and extracting a protocol feature field; matching the protocol feature field based on a dynamic protocol library, and identifying a native protocol type of the equipment; generating a protocol conversion strategy according to a target platform protocol demand, and calling a corresponding protocol analysis engine to perform semantic analysis on the data packet; the analyzed data content is reconstructed according to a target protocol format, and a unified communication interface packaging layer is added; and an optimal communication link is selected through an adaptive routing algorithm, and cross-protocol data transparent transmission is completed. The invention provides an integrated communication method capable of realizing efficient protocol dynamic identification, high-reliability semantic conversion, intelligent link optimization and safe packaging, so as to break through the technical barrier of multi-protocol Internet of Things terminal interconnection.

The invention discloses an intelligent data acquisition and conversion method based on a visual rule model, which comprises the following steps: S1, converting a configured rule chain into a data body in a JSON format by a visual rule modeling layer, analyzing the data body into an AST abstract syntax tree, and performing field mapping on the AST abstract syntax tree, the mapping fields are converted into executable codes through an intelligent conversion engine, and an execution plan is generated; s2, the intelligent acquisition layer pulls data from the heterogeneous data source, cleans the data and then allocates the data to an intelligent conversion engine for parallel processing; and S3, the intelligent conversion engine monitors the data consanguinity map and the field-level conversion path in real time, and sends a signal to the visual rule modeling layer or the intelligent acquisition layer according to the abnormal condition type so as to realize rule chain reconfiguration or data reacquisition. The method has the advantages that non-coding docking and real-time supervision of heterogeneous system data are realized, and the problems of dynamic adaptation, semantic understanding and data blood relationship interpretability in financial fund management are solved.

An inference method for encrypted deep neural network model is executed by a computing device and includes: encoding a message according to a quantization parameter to generate a plaintext, encrypting the plaintext according to a private key to generate a ciphertext, sending the ciphertext to a deep neural network model to generate a ciphertext result, decrypting the ciphertext result according to the private key to generate a plaintext result, and decoding the plaintext result according to the quantization parameter to generate an inference result.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a text-to-video method based on deep semantic analysis, which comprises the following steps of: extracting keywords and named entities from a to-be-converted text, analyzing a core theme and a text structure of the text, and performing semantic analysis to generate a semantic analysis result; retrieving matched images, video clips, sound effects and background music according to a semantic analysis result, and performing spatial layout to generate a preliminary visual layout framework; and constructing a video timeline, integrating the layout scheme, the background music and the sound effect to generate a complete video content, and finally outputting the video content as a video file. Keywords, named entities, core topics and text structures in texts are accurately extracted through semantic analysis, images, video clips, sound effects and background music conforming to semantics are intelligently matched, and the problem that a large amount of manual intervention is needed is avoided. An adaptive animation effect is generated through a deep learning model, and dynamic presentation of video content and continuity of a visual effect are ensured.

The invention provides a file conversion method and device, equipment and a program product, and the method comprises the steps: obtaining a to-be-converted file which is an image file or a portable document format file, i.e., a PDF file; identifying elements in the to-be-converted file, determining attributes of the identified elements based on an identification result, and performing logic layering on the identified elements; the elements comprise texts; generating a structured document based on the logical layering result and the attributes of the identification elements; and converting the structured document or the edited structured document into an editable file in a portable document format, so that the PDF can be edited. According to the method and the device, the automatic conversion from the image or the PDF to the editable PDF is realized, and in the conversion process, through the structured document generated in the middle, while the logic level of the document is improved, a user is supported to carry out instant editing, and the editing efficiency and convenience are improved.

The invention relates to the technical field of voice processing, in particular to a real-time voice synthesis and conversion method in an intelligent voice call system, which comprises the following steps of: acquiring voice data input by a user through a voice recognition module, preprocessing the voice data, performing semantic analysis through a bidirectional recurrent neural network and an attention mechanism, and obtaining a semantic analysis result; the method comprises the following steps: extracting a key semantic unit, selecting a proper voice template based on user historical interaction data and an adaptive template matching algorithm, performing voice synthesis by using a generative adversarial network, realizing cross-language or dialect real-time voice conversion through a multi-task learning algorithm, and combining phoneme-level optimization processing to ensure the naturalness and continuity of the voice, so as to improve the voice conversion efficiency. And through real-time analysis and a self-adaptive adjustment mechanism fed back by the user, the voice output quality is optimized, and the user experience is improved. According to the invention, efficient and natural speech synthesis and conversion services can be provided in various intelligent devices and application scenarios, and complex requirements in different language environments can be met.

The invention discloses an MRI-PET mode conversion method and system based on a generative adversarial network, and belongs to the technical field of artificial intelligence medical image generation. And the multi-scale structure representation injection module injects multi-scale anatomical prior information at different stages of the encoder, and overcomes the limitations of insufficient utilization of prior information and single injection scale. And the adaptive semantic residual fusion module adopts semantic attention guidance and double-branch attention weighting, adaptively fuses fine-grained local features and global context information, harmonizes the difference between the fine-grained local features and the global context information in an abstract level and a semantic category, and solves the problems of feature conflict and semantic fuzziness in a bottleneck region. The direction sensing space-frequency discriminator realizes multi-dimensional and fine-grained adversarial supervision through a space, frequency and local image block multi-branch collaborative discrimination mechanism, and improves the structural fidelity and spectrum authenticity of a synthetic image. And the generated image is superior to the existing method in indexes such as structural similarity and peak signal-to-noise ratio, and has higher clinical practical value.

The invention discloses a language transformation method and device based on retrieval enhancement and a storage medium, and relates to the technical field of language transformation.The method comprises the steps that in response to a query request, query information is determined based on the query request; performing intention recognition on the query information, and determining a target cue word template from a preset cue word template library; performing question recall on the query information to obtain target data; and performing language conversion through the target data and the target cue word template to generate a target structured query language. The problem that an original technical scheme is insufficient in generalization in a specific field is solved by retrieving business knowledge and industry common knowledge related to the problem through intention recognition, and the problem that the model effect cannot be improved by performing fine adjustment in the specific field due to the limitation of computing resources is solved through problem recall. And the language conversion efficiency and accuracy are improved.

Embodiments of the present application provide a speech conversion method and apparatus, a storage medium, and an electronic device. The method includes: acquiring a source speech to be converted and a target speech sample of a target speaker; recognizing a style category of the target speech sample, and extracting a target audio feature from the target speech sample according to the style category; extracting a source audio feature from the source speech; acquiring a first style feature of the target speech sample and determining a second style feature of the target speech sample according to the first style feature; fusing and mapping the source audio feature, the target audio feature, and the second style feature to obtain a joint encoding feature; and decoding the joint encoding feature, to obtain a target speech feature, and converting the source speech based on the target speech feature to obtain a target speech.

The invention relates to the technical field of vehicle-mounted communication, and discloses an intelligent identification and conversion method for a heterogeneous vehicle-mounted connector protocol. According to the method, after a vehicle-mounted connector is connected, preset disturbance signal sequences are sequentially injected, response behaviors of the preset disturbance signal sequences in a signal channel are recorded, and a corresponding response sample set is constructed by analyzing response level, time delay and feedback data. The system further archives and encodes the sample set, generates a disturbance response behavior track containing state jump characteristics, and reasones a communication protocol type and a corresponding state driving factor through track comparison. On the basis, a field stable region and a boundary change mode are extracted, a protocol adaptive sampling rule is generated, then real-time segmentation and extraction are carried out on subsequent communication data, and a standardized data frame is constructed. Finally, data format reconstruction and semantic conversion among heterogeneous vehicle-mounted protocols are realized, and communication compatibility and data intercommunication capability among various connectors are improved.

The invention provides a method for converting an SAR image into an optical image based on a multi-mode conditional diffusion model. The method comprises the following steps: firstly, collecting SAR image and optical image data with a pairing relationship, and ensuring that a sample has diversity in the aspects of scene types, target structures and image styles; secondly, an image-language multi-modal model is adopted to generate text descriptions of SAR and optical images respectively, unified language descriptions are constructed through semantic analysis and fusion, and a light-SAR-text three-modal training sample set containing structure, semantic and style information is formed; according to the method, a denoising diffusion model guided by a multi-modal condition is designed and trained, a noise adding-denoising reconstruction process of an original optical image is taken as an optimization target, an SAR image, language description and a style image are introduced as multi-modal prompt conditions, and the expression of the generated image in the aspects of structure reduction, semantic alignment and style presentation is comprehensively guided.

The invention discloses a Tibetan language multi-dialect real-time semantic conversion method based on a cross-language BERT model, and the method comprises the following steps: S1, collecting original text corpora of each dialect of the Tibetan language, and constructing a standardized training corpus set; s2, performing parameter initialization on the mBERT model, and preliminarily training the mBERT model; s3, constructing a semantic modeling model, and performing fine adjustment on the semantic modeling model; s4, receiving to-be-converted text input, and encoding; s5, obtaining an intermediate semantic representation vector of the text through a semantic coding sub-module; s6, inputting the intermediate semantic representation vector into a semantic generation sub-module, and generating target text output; and S7, executing syntactic consistency correction and language fluency correction. According to the method, mBERT modeling and an adversarial optimization mechanism are fused, real-time semantic consistency conversion of multiple dialects of the Tibetan language is achieved, and the method has the advantages of being high in accuracy, high in robustness and low in response delay.

The invention relates to the technical field of model deployment, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a model service cross-framework request conversion method, device, equipment and medium, and the method comprises the steps: receiving a reasoning request based on a first model service framework, analyzing input data and a request path, and extracting input parameters and model identification information; determining a target request path of the second model service framework according to the model identification information, and converting the input parameters into a target input format; sending the converted input data to a target reasoning service, receiving a reasoning result and extracting an output parameter; and converting the output parameter into an output format of the first model service framework and returning the output format to the client. According to the method, an adaptation mechanism is introduced between the client and the target model service, so that calling logic which originally depends on a specific reasoning framework can be accessed to heterogeneous reasoning service without changing, and structural compatibility and communication unification of cross-platform deployment and calling of the model service are realized.

The invention relates to the technical field of natural language processing, in particular to a novel-script intelligent conversion method and system, and the method comprises the steps: obtaining an input novel text, and splitting the novel text to obtain divided volumes; processing each chapter to obtain a chapter mark and a chapter outline, and selecting roles appearing in each chapter to obtain an outgoing figure list; acquiring role labeling information based on the outline of each chapter and section, and acquiring roll-dividing outline information based on the outline of each chapter and section; combining the role labeling information and the roll division outline information corresponding to each roll division to obtain a combined set; distributing plot volume information and role distribution information corresponding to each set based on the set number request; merging based on the plot volume information and the role allocation information to obtain a set outline, and studying, judging and adjusting the content of the set outline; generating the script content corresponding to each set based on the set outline, and combining the script content to output a complete script of the novel text. The method and the device are used for improving the conversion effect from a large volume of novel to a script.

The invention provides a cross-time-space conversion method with a Fourier filtering operator for multivariable time sequence classification. The cross-time-space conversion method comprises the following steps: mapping an input time sequence to a target variable; mapping a time sequence data set to a group of C category labels Y; after training, the CSTFormer model outputs a vector containing C values so as to estimate the probability that the time sequence belongs to each category; in the CSTFormer model, data input by a multivariable time sequence firstly passes through a LayerNorm layer and then enters a global adaptive Fourier neural operator module, noise is adaptively filtered, and important frequency information is enhanced; the output passes through a LayerNorm layer and then enters a time-space consistency learning module; the time-space consistency learning module is composed of three sub-modules, namely a dynamic multi-scale time attention module, a dynamic space attention module and a dynamic cross-distribution fusion module; respectively learning a time context and a space context, and fusing to obtain a learned time-space consistency context; and finally, outputting a classification result by the classification head.

The invention belongs to the technical field of aviation equipment system modeling and analysis, and particularly relates to an aviation equipment system reliability analysis method and system based on MBSE model conversion, and the method comprises the steps: S1, building the function model reliability of an aviation equipment system through an MBSE model mapping conversion technology; s2, establishing a fault logic model of the aeronautical equipment system, and completing key fault identification and analysis evaluation of the aeronautical equipment system; s3, determining reliability index parameters of the aeronautical equipment system according to key fault identification and analysis results of the aeronautical equipment system; and S4, determining an aviation equipment system reliability analysis result according to the aviation equipment system reliability index parameters, and completing reliability analysis. According to the method, the model conversion method is adopted to analyze the reliability related indexes of the aeronautical equipment system, the situation that reliability analysis results of the same system are greatly differentiated due to manual intervention and do not conform to the actual system state can be avoided, and comprehensiveness and accuracy of fault logic relation analysis of the aeronautical equipment system are guaranteed.

The invention discloses an industrial communication protocol conversion system and conversion method. The method comprises the following steps: acquiring data of an industrial communication source protocol; protocol conversion: converting the source protocol data into target protocol data according to a sequence of protocol analysis, standardized modeling and protocol repackaging; according to protocol analysis, original data transmitted from different hardware interfaces are analyzed according to corresponding industrial protocols; the standardized modeling parses the data into a data model in a unified format; protocol repackaging: recoding the data model into a data frame conforming to a communication specification according to a target protocol rule; and data output: pushing the obtained target protocol data to a third-party server through an MQTT protocol or directly storing the target protocol data in a database for a third-party system to access. Through three core technologies of protocol analysis, unified data modeling and protocol packaging, lossless conversion among different industrial protocols is realized, and an efficient and reliable data communication infrastructure is provided for an industrial automation system.

The invention belongs to the technical field of multi-modal intelligent data management, and discloses a multi-modal business data co-processing and intelligent conversion method, which comprises the steps of fusing multi-source data, coupling cross-modal time sequence association, detecting image-text semantic conflicts, and generating an RAG semantic unit and a space-time alignment semantic packet. Constructing a four-dimensional priority label to divide resource pool categories, dynamically allocating resource pool computing resources, generating a low-redundancy feature set, triggering a forced preemption strategy during resource competition, and synchronously generating a resource arbitration log; injecting a dynamic rule node according to a data type, executing confidence arbitration in combination with a conflict arbitration identifier, generating business decision content and generating a rule correction decision packet; constructing a full-link semantic thinking chain, synchronously capturing a system operation track, and aligning to generate a dual-channel tracing report; identifying residual sensitive fields, triggering hot update to load corresponding rules, quantizing effectiveness to generate compliance reports, reversely updating an industry rule base, and optimizing a resource allocation strategy.

The invention relates to the technical field of computers, and discloses a method for converting a C + + code into a CUDA-C code, and the method comprises the steps: receiving a C + + source code, carrying out lexical analysis and grammatical analysis, generating an abstract syntax tree, and carrying out semantic analysis to ensure that the source code is correct semantically; analyzing the abstract syntax tree, identifying a data dependency relationship among the calculation tasks, and determining loop statements and conditional statements in the source code; and converting a loop statement and a conditional statement in the source code into a kernel function, a thread block and a thread management code corresponding to the CUDA, and further generating a corresponding compilable source file. According to the method, the abstract syntax tree of the C + + code is analyzed, the parallelism in the abstract syntax tree is analyzed, the code is optimized, the CUDA-C efficient code is generated, then efficient automatic conversion of the code is achieved, and the method has great significance in accelerating program performance and shortening the development period.