181results about How to "Improve generation effect" patented technology

The invention relates to a power log intelligent analysis system based on a knowledge graph and a large language model. The power log intelligent analysis system comprises a data collection and preprocessing module, a knowledge graph construction and management module, a context understanding and correlation analysis module, a personalized report generation module and a multi-modal data integration module. According to the method, information such as equipment, events and operations in the power logs is structured through the knowledge graph and is associated with domain knowledge, so that deep understanding and association analysis of log contents are realized, and the problem of insufficient context understanding in a traditional method is solved. By utilizing the strong generation capability of a large language model and based on context information provided by a knowledge graph, a personalized report meeting roles and requirements of a user can be automatically generated, and the user experience and practicability of log analysis are improved; log data in various formats are integrated into the knowledge graph, a comprehensive summary report containing information such as charts and timelines is generated through a large language model, and the problem that heterogeneous data are difficult to integrate is solved.

The invention belongs to the technical field of artificial intelligence and big data analysis, and particularly relates to a scenic spot passenger flow trend prediction analysis method based on an AI big language model. According to the method, big data and artificial intelligence technologies are utilized, LBS data, scenic spot data, holiday and festival information, third-party maps, weather data and other multi-source data are comprehensively applied, a comprehensive multi-dimensional knowledge base is constructed, and meanwhile, the knowledge search and generation capability is improved by utilizing an RAG technology; through model pre-training and fine tuning, the universal model capability is developed, and a multi-agent system is further constructed; based on the natural language processing capability of the AI large language model, the LLM can intelligently analyze the text input of the scenic region administrator, drive the cooperative work among multiple agents, and achieve the intelligent prediction and analysis of the scenic region passenger flow trend. The method can more accurately predict the passenger flow trend of the scenic area.

The invention discloses an Internet of Things equipment access protocol component development method, which is used for quickly developing an Internet of Things equipment access protocol analysis and processing component at an Internet of Things platform side, and comprises the following steps: S1, constructing a protocol analysis and processing general framework according to the protocol analysis and processing component of an Internet of Things platform; s2, abstracting a specific logic processing part of a protocol in the general framework into a method / function interface; s3, constructing a protocol expert AI knowledge base for data learning; s4, constructing an AI large model and a multi-agent processing flow, selecting a specified large model, configuring related parameters, extracting required parameter extraction / coding logic, and generating an interface implementation code; s5, integrating each generated interface implementation code with the universal framework; and S6, testing, adjusting and optimizing the integrated access protocol analysis and processing component. According to the method, the unified development template can be provided, so that the development technical threshold is reduced, and the development efficiency is greatly improved.

The invention discloses a text generation method, electronic equipment and a storage medium, and relates to the field of large model technology and text processing. The method comprises the following steps: acquiring to-be-processed data; based on the data structure information of the to-be-processed data, a target map of the to-be-processed data is constructed, and the target map is used for describing different entities in the to-be-processed data and the incidence relation between the different entities; generating a target problem of the to-be-processed data based on the target map, and identifying a problem type of the target problem; and generating a reply text of the target question based on the target question and the question type. The technical problem that the text generation effect is poor in the prior art is solved.

The invention provides a large model text generation method and system based on self-adaptive cue words, and belongs to the technical field of large model text generation. The technical problem to be solved is that the current large language model text generation has the defects of selection deviation and uncertainty. According to the technical scheme, hierarchical clustering processing is carried out on problems contained in a large-scale multi-task language understanding MMLU data set, a text embedding and similarity calculation matrix is adopted, and a plurality of problem clusters containing similar features are constructed and obtained; randomly extracting representative problem examples from each problem cluster, and constructing excellent cue words with remarkable guide effects for each problem based on domain knowledge and potential semantic association; a Qwen model is adopted to generate candidate cue words with diversity and pertinence for various question clusters divided in advance, a cue word bank is constructed, and each question and cue word pair in the cue word bank is manually scored; the method is applied to text generation.

The invention relates to a transformer voiceprint anomaly detection method based on a generative adversarial network, and the method comprises the steps: obtaining voiceprint data, and carrying out the preprocessing of the voiceprint data, and obtaining the preprocessed spectrum data; constructing an abnormal voiceprint detection model; inputting the preprocessed spectrum data into an abnormal voiceprint detection model for training; and obtaining voiceprint data to be detected and preprocessing the voiceprint data to be detected, inputting the preprocessed voiceprint data to be detected into the trained abnormal voiceprint detection model, and outputting a detection result. According to the method, unbalanced distribution of normal voiceprint data and abnormal voiceprint data can be balanced, the generalization ability of the model is enhanced, and the model can keep high detection performance when processing a small amount of abnormal data; according to the method, the distinguishing capability of the abnormal voiceprint is enhanced, the abnormal voiceprint can be effectively recognized in a complex noise environment, the influence of noise and interference factors is reduced, and the detection accuracy is improved; fine-grained features in the voiceprint signals can be captured, extraction of the features is further optimized, and therefore abnormal voiceprints can be recognized more accurately.

The invention relates to the technical field of novel power system optimization operation, in particular to a new energy high-uncertainty scene generation method and device based on a CWGAN-GP model, and the method comprises the steps: correcting an initial generative adversarial network through employing a Wasserstein distance and a gradient penalty term, so as to obtain a final generative adversarial network, and the target convolutional neural network is introduced into the final generative adversarial network to obtain a conditional deep convolutional generative adversarial network of improved deep convolution, so that WGAN-GP is introduced into the conditional deep convolutional generative adversarial network of improved deep convolution to obtain a CWGAN-GP model of improved deep convolution. And a target L-ISODATA clustering algorithm is applied to cluster the generated wind and light scenes so as to generate a high-uncertainty new energy power generation output scene. Therefore, the problems that in the related technology, when the GAN processes high-dimensional data, complex space-time characteristics are difficult to effectively capture, and due to lack of prior information, the training direction is prone to deviation, and the scene generation effect and stability are affected are solved.

The invention provides a database knowledge body construction method and a structured query language generation method, a relational database knowledge body comprises a plurality of knowledge body units, and the plurality of knowledge body units are mutually connected through associated fields to form a knowledge network; each knowledge body unit corresponds to one data table, each knowledge body unit comprises multi-layer node data, and the multi-layer node data comprises table information, field information, field vectors, field enumeration value information and field enumeration value vector representation of the data tables. The construction method comprises the steps of obtaining first data table information based on data table metadata; reasoning and extracting the text code pairing data set through a large language model to obtain second data table information; and fusing the first data table information and the second data table information to construct a relational database knowledge body. Refined, low-redundancy, accurate, comprehensive and rich dependency data is provided for the TEXT2SQL task of the large language model, and the TEXT2SQL generation capacity of the large language model is improved.

The invention relates to a defect image generation method and device, equipment and a storage medium, and is applied to the field of artificial intelligence, and the method comprises the steps: obtaining a pure noise image, a defect object image, an original defect image, a defect text description and a template mask image; utilizing a ControlNet model and a diffusion model to generate a defect latent space image expressed by a latent space based on the pure noise image according to the original defect image, the defect text description and the template mask image; according to the defect submerged space image and the defect real object image, defect target features and background features represented by the submerged space are obtained by using the template mask image, and the defect target features and the background features are fused to generate submerged space fusion features represented by the submerged space; and processing the submerged space fusion features by adopting a diffusion model, and decoding to generate a final defect image. The method has the technical effects that the problem of long tail distribution of the industrial defect image is solved, and the quality of the defect image is improved.

The invention provides a generative adversarial network architecture search method and system based on hybrid convolution operation, and the method comprises the steps: firstly designing a wide search space, then constructing a super-net integrating all candidate operations, enabling the training process of the super-net to be completely differentiable through a continuous relaxation method, and enabling the training process of the super-net to be completely differentiable; therefore, efficient training is carried out by using a gradient descent method, and finally, the optimal operation on each position is selected to obtain the optimal architecture. Different from a traditional architecture search method, the method introduces a novel hybrid convolution operation into a search space, and optimizes a search process by integrating a partial channel attention mechanism. According to the generative adversarial network architecture search based on hybrid convolution operation, the long-distance information capturing capability and architecture search speed of the network are enhanced, and compared with a traditional search method, the method has higher efficiency and better performance, and the optimal neural network architecture suitable for tasks can be found more quickly.

The invention relates to the technical field of high-speed train bogie fault detection, and discloses a bogie unknown fault diagnosis method based on a generative model zero sample learning strategy, and the method comprises the steps: carrying out a bogie mechanical fault simulation experiment on an electric locomotive through employing multi-body dynamics analysis software SIMPACK, and collecting normal and fault data; establishing a fault attribute semantic matrix for the train operation influence factors; performing feature extraction according to the data attributes and the fault data; building an unknown fault data feature sample generation model based on a diffusion model, and performing unknown fault data feature generation by using random noise and unknown fault attribute combination; and a fault diagnosis classification model is constructed, and mapping from data features to fault attributes and then to fault categories is realized. According to the method, diagnosis of known faults and unknown faults of the high-speed train bogie is completed, the accuracy and generalization of fault diagnosis are improved, and comprehensive guarantee is provided for safe use of the high-speed train bogie.

The invention relates to a multi-modal large model scene understanding method based on scene graph enhancement, and belongs to the field of cross-modal information fusion and generation. The method comprises the following steps: firstly, preprocessing an input image, transmitting the preprocessed image into an open vocabulary target detection model to obtain entity information in the image, and generating an image with an entity bounding box and an entity category; secondly, transmitting the image with the bounding box and the entity category into a scene graph generation model, generating a preliminary entity relationship, and transmitting the preliminary entity relationship into a logic large model for correction to obtain a corrected entity relationship; thirdly, constructing a scene graph according to the entity in the image and the corrected entity relationship, transmitting the scene graph into a prompt large model, and generating a prompt text based on the scene graph; and finally, inputting the prompt text and the preprocessed image into a multi-modal large model, understanding image information by the multi-modal large model according to the prompt text, and generating description of a scene in the image. According to the method, the scene understanding capability of the multi-modal large model image can be effectively enhanced.

The invention discloses an image generation method and device, equipment, a medium and a product, and relates to the field of image processing. The method comprises the following steps: acquiring a first image and a gray level change graph, and acquiring a noise image; in the process of carrying out iterative noise reduction on the noise image by taking modification of the first image as a noise reduction condition, obtaining the ith noise image corresponding to the ith iteration noise reduction stage; when i = 1, performing noise reduction on the first noise image to obtain a first noise reduction stage image output in a first iteration noise reduction stage; when i is greater than 1, based on a fusion proportion indicated by a second pixel value in the gray level change graph, fusing the i-th noise image and the (i-1)-th noise reduction stage image output in the (i-1)-th iteration noise reduction stage to obtain an i-th fused image; and carrying out noise reduction on the ith fusion image to obtain an ith noise reduction stage image output in the ith iteration noise reduction stage until the iteration noise reduction requirement is met, and obtaining a generated image as a modification result of the first image. The method can improve the generation effect of the image modification result.

The invention discloses a tree coding-based long video generation optimization method, which comprises the following steps of: constructing a video frame sequence, and obtaining frame features; clustering the frame features to obtain a correlation score between the key frame and the video query; calculating the number of high-correlation clusters, and outputting a corresponding frame feature set and a correlation score; key frames of all the high-correlation clusters serve as first-layer nodes of a video feature tree, the high-correlation clusters are clustered into w sub-clusters respectively, a second layer is constructed based on the sub-cluster key frames, the correlation score of the second-layer nodes is obtained by subtracting one from the correlation score of the first-layer nodes, each layer is constructed according to the method, and the first-layer nodes and the second-layer nodes are obtained; the relevance score of the last layer of nodes is 1; the large language model outputs an optimization reasoning result based on the speculation sampling principle and the draft model; and inputting the optimized reasoning result and the video frame sequence into a preset video generation model to obtain an answer video. According to the method, the reasoning accuracy and efficiency are improved by inquiring self-adaptive and hierarchical long video understanding.

The invention provides a video generation method and device, and relates to the technical field of computers, in particular to the technical fields of large models, deep learning, image processing, voice recognition and the like. According to the specific implementation scheme, semantic partitioning and position marking are conducted on a to-be-processed material, and a semantic text block set comprising at least one semantic text block is obtained; based on the key event information, classifying semantic text blocks in the semantic text block set to obtain a key text block set and a non-key text block set; generating a key image sequence based on the key text block set, the to-be-processed material and a video material library; generating a non-key image sequence based on the non-key text block set and a video material library; the target video is generated based on the key image sequence and the non-key image sequence, and the video generation effect is improved.

The invention relates to the field of financial science and technology speech conversion, and discloses a speech synthesis method, device and equipment based on a conditional matching stream and a medium, and the method comprises the steps: preprocessing an input text, and converting the input text into an embedded vector; based on a stream matching model, the input text is combined with the embedded vector and mapped to the intermediate representation space, and the input text in the intermediate representation space gradually generates speech spectrum features; on the basis of a zero sample learning mechanism, generating a voice spectrum meeting requirements from the voice spectrum features; and restoring the voice spectrum into a voice signal and outputting the voice signal. By introducing a stream matching model and a zero sample learning mechanism, speech with emotions or a specific style can be directly generated without emotional data training, the dependence of a traditional speech technology on large-scale data with emotional labels is broken through, and the application range of the speech technology is greatly expanded. The method is applied to application scenes such as financial science and technology voice conversion.

The invention relates to the technical field of artificial intelligence, in particular to a large model retrieval enhancement generation method and system.The method comprises the following steps that corpus knowledge is segmented according to paragraphs, and entities and keywords are extracted to serve as information nodes of the paragraphs; adjacent nodes among the information nodes are extracted to serve as expansion information of the current node; calculating a communication relationship of nodes among different paragraphs, and supplementing context information of the paragraphs by utilizing expansion information of the nodes to form word granularity description of the paragraphs; performing knowledge retrieval by using a retrieval mode of two granularities of words and sentences, and performing knowledge recall questions and answers; the large model retrieval enhancement generation method and system have the advantages that context information of knowledge fragments is supplemented through the communication relation of key information between paragraphs, and a multi-scale retrieval algorithm of word and sentence granularity is matched, so that the accuracy rate of recalled knowledge is increased, and the large model generation effect is improved.

The invention discloses a large-scale embedded index data desensitization method suitable for a forestry database, and belongs to the technical field of data desensitization, and the method comprises the steps: obtaining a forestry data description document D1, splitting the document D1 into sentences, and processing the sentences into embedded vectors; a user customizes a query sentence containing the desensitization word, and a query vector is generated; performing hash coding on the embedded vector and the query vector to obtain a corresponding hash function cluster; searching data to be desensitized through cosine similarity calculation; and inputting to-be-desensitized data and the selected desensitization method into the large language model to generate desensitized data, and replacing the corresponding sentences in the D1 to obtain a desensitized forestry data description document D2. According to the method, the input data is converted into the high-dimensional vector through the embedding layer, so that the semantic features of the data can be effectively expressed in the vector space, the retrieval speed and accuracy of large-scale data are improved by means of the locality sensitive hashing technology, the calculation overhead is reduced, and a technical guarantee is provided for real-time desensitization processing of a large-scale data set.

The invention discloses an image generation model construction method and a three-dimensional digital model determination method. The method comprises the following steps: firstly, obtaining a first object description image, a first description text corresponding to the first object description image, and a first attitude image corresponding to the first object description image; and constructing an image generation model by using the first object description image, the first description text and the first attitude image, so that the constructed image generation model can generate image data with relatively high quality according to the first description text and the first attitude image. Therefore, the image generation model can achieve the purpose of generating the image data according to the text information and the posture information, the image generation effect of the image generation model is improved, and a three-dimensional digital model determined by means of the image generation model can also conform to natural posture constraints. And the determination effect of the three-dimensional digital model can be improved.

The invention provides a graph-to-text model training method and device, relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like, and can be applied to scenes such as content generation of artificial intelligence. According to the specific implementation scheme, an image sample set is obtained, wherein the image sample set comprises at least one image sample; obtaining an initial graph-to-text model, wherein the graph-to-text model comprises an image coding sub-network, a connection sub-network and a multi-modal large language model; training an image coding sub-network and a connection sub-network based on the image sample set and the image generator to obtain a trained image coding sub-network and a trained connection sub-network; and based on the image sample set, training the multi-modal large language model, the trained image coding sub-network and the trained connection sub-network to obtain a trained graph-to-text model.

The invention discloses a news customization-oriented multi-modal abstract generation method, which comprises the following steps of: firstly, inputting pictures and text data into a BART-based multi-modal code, realizing multi-modal interaction in a coding process, meanwhile, adding an image-text matching module to select a sentence corresponding to each picture, and adding a cross attention layer in a decoder; then, constructing an abstract scoring model, and selecting an optimal abstract by calculating the similarity between the candidate abstract and the news text as a score; and calculating a ROUGE score between the sentence corresponding to the picture and the optimal abstract as a text similarity score, obtaining an image-text similarity score in combination with the picture features after multi-modal interaction, obtaining a picture selection probability, selecting the picture with the highest probability as a model selection picture, and generating a multi-modal news abstract. According to the system, a B / S framework is adopted, a lightweight Web framework Flask is used for building, and a Layui open source framework is used for building an interactive interface. According to the method, the accuracy and richness of news multi-modal abstract generation are effectively improved, and the robustness is high.

The invention discloses a battlefield semantic situation rapid generation method based on image analysis, and belongs to the technical field of battlefield situation generation. The method comprises the following steps: dividing a battlefield area into a plurality of local battlefields; reconnaissance is carried out on each local battlefield area; generating a multi-source heterogeneous image database; performing time-space relationship unification on the multi-source heterogeneous image database; constructing a battlefield situation element composition system; constructing a battlefield situation element extraction technology system; carrying out adaptive extraction on battlefield situation elements; generating a local battlefield situation; a global battlefield situation is generated based on the local battlefield situation. The invention provides a battlefield situation element extraction framework based on deep learning, designs a battlefield situation generation method based on deep learning, and provides a conflict situation fusion method and a battlefield region division method based on an attention mechanism and a complete space-time relationship unification mode. A whole set of battlefield semantic situation adaptive generation method is constructed, and decision-making assistance can be provided for direct commanders and fighters.

The invention designs and synthesizes a tetraphenyl ethylene covalent molecular cage with pyridine functionalization, and an AIE supermolecule photosensitizer is obtained through coordination and the synergistic effect of a subject and an object. The TPE unit enhances the photophysical properties of the photosensitizer and endows the photosensitizer with the AIE characteristic; the molecular cage and tetraphenylporphyrin are combined through a host and a guest, so that self-aggregation of porphyrin in water is further inhibited, ROS generation is promoted, and cancer cells are effectively killed through photocatalysis NADH oxidation assistance.

The invention discloses an image generation method and system, electronic equipment and a computer program product, and relates to the field of large model technology and image processing. The method can comprise the steps that an initial scene image to be processed is determined, and the image content of the initial scene image comprises at least one display object; determining an auxiliary object image to be drawn at a target position in the initial scene image; based on the auxiliary object image, the target position and the initial scene image, a posture image and an object mask image of the auxiliary display object are determined, the posture image is used for representing the posture of the auxiliary display object, the object mask image is used for representing an image area where the auxiliary display object is located in the initial scene image, and the image area comprises the target position; and analyzing the attitude image, the object mask image and the initial scene image by using the redrawing model to obtain a target scene image. The technical problem of low image generation accuracy is solved.

The invention relates to the technical field of anomaly detection, and discloses an industrial equipment time sequence anomaly detection method and device. The method comprises the following steps: preprocessing collected time series data of industrial equipment to obtain preprocessed time series data; encoding and decoding the preprocessed time sequence data to obtain reconstructed time sequence data; carrying out loss value calculation according to the reconstructed time sequence data to obtain total loss; performing optimization processing on preset anomaly detection model parameters according to the total loss to obtain an anomaly detection model; and performing anomaly detection on the real-time test data according to the anomaly detection model to obtain an anomaly detection result. According to the invention, the accuracy of the time sequence anomaly detection of the industrial equipment is improved.

The present application discloses a method for generating a virtual image and related equipment thereof, the method comprising: after acquiring voice data to be processed, firstly extracting voice features of the voice data to be processed to obtain voice features to be used, so that the voice features to be used can represent the voice information carried by the voice data to be processed; then determining virtual image display data corresponding to the voice data to be processed according to the voice features to be used, facial parameters to be used, and a pre-constructed virtual image generation model, so that the virtual image display data can represent a virtual image that matches the voice data to be processed, so that the virtual image can display the facial state presented by the character when the voice data to be processed is emitted, thereby achieving the purpose of automatically generating a virtual image.

The invention provides an intelligent generation method, system and device for game images and animations and a medium, and the method specifically comprises the steps: obtaining user design demand data, carrying out the feature extraction and style recognition of the user design demand data through a deep learning algorithm, and obtaining the key feature data of the game images and animations; obtaining specified style parameters, and based on the specified style parameters, analyzing the game image and animation key feature data according to a pre-trained GAN model to generate a target game image and animation; acquiring user equipment data of current user equipment, and adaptively displaying the target game image and animation on the current user equipment according to the user equipment data. According to the method, the process of game development and animation production is simplified, the technical threshold is reduced, and the creation efficiency and quality are improved.

The invention relates to an automatic prediction method for dose distribution in a brachytherapy plan. Comprising the following steps: acquiring a structure image and a real dose distribution diagram; constructing an improved DiT model and a noise predictor; preprocessing the structure image and the real dose distribution diagram, and inputting the preprocessed structure image and the preprocessed real dose distribution diagram into an improved DiT model for model training; and preprocessing a noise image and a to-be-predicted structure image, inputting the preprocessed noise image and the to-be-predicted structure image into the trained improved DiT model, carrying out reverse denoising on the improved DiT model under the guidance of the feature information of the structure image, and finally decoding to obtain a predicted dose distribution diagram. The improved DiT model is a diffusion model using a Diffusion Transform architecture, the prediction precision is maintained, the consumption of computing resources is reduced, the efficiency of the radiotherapy plan is improved, and the controllability of model generation is further improved by combining the semantic features of the structural image.

The invention discloses a radio frequency simulation complex electromagnetic signal generation device and method based on pulse multi-channel dynamic distribution, which break through a traditional method for improving environmental simulation complexity by increasing the number of feed channels in radio frequency simulation and fully utilize effective system radio frequency channel hardware resources. Priority configuration is carried out on complex battlefield radiation source signals according to actual combat requirements, pulse-level parameter calculation is carried out according to a space-time relation, and high-density signal pulse sequences are dynamically distributed among different channels through real-time calculation. A final pulse sequence and a corresponding antenna array synchronous control code which can be generated in multiple radio frequency channels are formed through recursive sorting, and the maximum utilization of radio frequency channel time resources is realized, so that a multi-radiation-source and high-pulse-density complex signal environment is realized under the condition of limited channel quantity, and the complex electromagnetic environment generation capability of a system is greatly improved.

The invention discloses an interior design rendering graph generation method and device based on a diffusion model, and the method comprises the steps: collecting the data of a historical interior design decoration rendering graph, carrying out the style classification, and carrying out the fine adjustment of a LoRA adapter of each style; extracting Canny operator features and depth image features of the indoor blank image, and generating control conditions; identifying a fixed structure in the indoor blank image by using the image segmentation model, and marking mask data; a control condition, mask data and prompt are input, and a decoration rendering graph fitting the indoor structure is generated; setting a selectable decoration style according to the LoRA adapter, and inserting the LoRA in the workflow to adjust the style of the rendering graph; and setting and adjusting hyper-parameters to ensure that the structural layout of the rendered image is consistent with the indoor blank image and improve the detail information and the image quality of the rendered image. The method can improve the generation effect and practicability of the interior design rendering graph, and can be widely applied to the technical field of computers.