491results about How to "Improve build quality" patented technology

The invention provides a large language model optimization generation method based on optimal cue word selection, and belongs to the technical field of large language model optimization generation. The technical problem to be solved is to provide the improvement of the large language model optimization generation method based on optimal cue word selection. According to the technical scheme, a selected data set is preprocessed, a sequence is formed by splicing questions and answers, and a spectral clustering algorithm is adopted to divide the sequence into multiple groups of question and answer pairs with similar characteristics; sampling representative samples from each cluster, and based on professional knowledge, language logic and semantic association, constructing high-quality cue words which can guide and generate a large model aiming at a specific problem; a large-parameter online model is used, a diversified and targeted cue word set is generated for each cluster with reference to the created high-quality cue words, generated questions, candidate cue words and answers of the candidate cue words are integrated, and a data set used for fine tuning of the cue evaluation model is constructed; the method is used for generating the language model.

The invention relates to an unmanned aerial vehicle knowledge graph construction method based on multi-modal large model recognition, and the method comprises the steps: carrying out the data fusion of texts, images, videos and sensor data related to an unmanned aerial vehicle, and constructing an unmanned aerial vehicle multi-modal data set; constructing a multi-modal large model integrated with a Transform architecture and a self-attention mechanism for extracting structured information from input data, and training the multi-modal large model by using a multi-modal data set of the unmanned aerial vehicle; structured information is extracted from unmanned aerial vehicle data input in real time by using the trained multi-modal large model to construct a knowledge graph, knowledge graph data is updated regularly through an online learning mechanism, and the quality and consistency of the knowledge graph are ensured by adopting an automatic verification and error correction mechanism. According to the method, the defects of low accuracy and low efficiency in unmanned aerial vehicle knowledge graph construction in the prior art are overcome, and the construction quality of the knowledge graph is improved.

The invention discloses a radiology report generation method based on semantic alignment, and belongs to the technical field of radiology report generation. The radiology report generation network constructed by the invention comprises a multi-scale feature extraction module, a cross-modal semantic alignment module and a Transform report generation module which are connected in sequence; the multi-scale feature extraction module comprises a convolutional neural network and a multi-scale local sparse attention module which are connected in sequence; the cross-modal semantic alignment module comprises an embedded layer, a multi-head attention module and a gating fusion module, wherein the multi-head attention module and the gating fusion module are connected with the embedded layer. The input end of the multi-head attention module and the input end of the gating fusion module are connected with the output end of the multi-scale local sparse attention module. The predicted radiology report generated by the radiology report generation method is good in quality.

The invention discloses a context learning-based database query generation method and system and a storage medium, and the method comprises the steps: extracting keywords and phrases from a natural language query, retrieving values similar to the keywords in a database, and returning values most related to the keywords and corresponding columns thereof, retrieving description information related to the keywords and the phrases in a database directory; performing mode selection aiming at the most relevant value of each keyword and the corresponding column, namely screening out the column irrelevant to the natural language query, further selecting a table necessary for generating the SQL query, and finally reducing the mode to a minimum column set necessary for generating the SQL query; and correcting logic and grammar errors of the method model through the database mode, the natural language query, the generated candidate SQL query and the execution result thereof. According to the method, the efficient SQL query statement is generated by intelligently understanding the data context and the query requirement.

The invention discloses a face image super-resolution method and device of a diffusion model based on residual prediction, and relates to the field of image super-resolution, and the method comprises the steps: obtaining a to-be-reconstructed low-resolution image; a diffusion model based on residual prediction and a conditional noise predictor are constructed and trained, and a trained diffusion model and a trained conditional noise predictor are obtained; gaussian noise is sampled from standard Gaussian distribution to serve as residual noise images, a to-be-reconstructed low-resolution image, the residual noise image of each step and the corresponding step length are input into a trained conditional noise predictor, prediction noise of each step is obtained through prediction, and the low-resolution image is reconstructed. Iteratively executing a de-noising process of T steps through a reverse de-noising network in the trained diffusion model to obtain a restored residual image; and adding the restored residual image and the up-sampled low-resolution image to be reconstructed to obtain a restored high-resolution image. The image super-resolution method solves the problems that an existing image super-resolution method is complex in generation process and limited in detail recovery.

The invention discloses an image generation method and system based on diffusion model adaptive reasoning. The method comprises the following steps: constructing a next noise intensity prediction module TPM; improving an original diffusion model, and adding a TPM; the improved diffusion model is trained by using a reinforcement learning method, the whole denoising process is expanded for multiple times, the next time step is predicted in each iteration, an award is calculated according to the quality of a finally generated image and the number of steps, and TPM parameters are updated by using a PPO loss function; in the actual reasoning process, noise is randomly sampled from Gaussian noise and input into the trained diffusion model, the diffusion model is used for predicting a denoising result, meanwhile, the TPM is used for outputting distribution of time steps based on next denoising, and a distribution mode is used as the next time step used in actual reasoning; and when the predicted time step is smaller than a set threshold value, a final image generation result is obtained based on model output. According to the method, the image generation process can be dynamically adjusted, and a reasoning result with both efficiency and quality is realized.

The invention discloses a method for converting a two-dimensional image of a building component into a three-dimensional model, which relates to the technical field of image processing, and comprises the following steps of: comparing the size of the three-dimensional model of the component with the size of an actual building component to obtain error data between the two, and generating corresponding accuracy through a model error data set; if the accuracy of the component three-dimensional model does not exceed the expectation, carrying out coincidence analysis on the component three-dimensional model and the building component and obtaining the coincidence degree, generating a complete coefficient according to the coincidence degree, screening out defect areas in the component three-dimensional model according to the complete coefficient, and associating to obtain the optimization priority of each defect area; and after a model optimization scheme is given for the defect areas by the building component model optimization knowledge graph, optimizing the defect areas in sequence according to optimization priorities. A corresponding model optimization scheme is provided for the defect area through the building component model optimization knowledge graph, and the optimization pertinence is higher when all the defect areas are optimized.

The invention relates to the technical field of computers, in particular to a mathematical physics explanation video generation method and device based on multi-agent collaboration, and the method comprises the steps: obtaining the actual task demand information of a mathematical physics explanation video; based on the actual task demand information, controlling a scriptor agent to generate an animation frame script, so that the cartoon agent generates an animation video corresponding to the animation frame script, and generating a synchronous subtitle and an explanation audio corresponding to the animation video through an interpreter agent; and synchronously integrating the animation frame script, the animation video, the synchronous subtitles and the explanation audio to construct an initial explanation video, carrying out picture analysis on the initial explanation video through a quality inspector agent to obtain a picture analysis result, correcting the initial explanation video, and generating a final mathematical physics explanation video. Therefore, the problems that an existing teaching video making technology is poor in content accuracy and visual expression effect, high in video making cost, difficult to meet actual teaching requirements and the like are solved.

The invention relates to a catalyst for ethylene oxide ring-opening polymerization and a preparation method thereof, and belongs to the technical field of high polymer material synthesis, and the catalyst is a composite structure based on a silicon dioxide nanoparticle loaded bimetal organic complex; a modified nitrogen-containing polydentate ligand is prepared by adopting a special method, is coordinated with metal ions through covalent bonds and is loaded on silicon dioxide nanoparticles; by utilizing the high dispersity and stability of the silicon dioxide nanoparticles and the synergistic catalytic effect of the bimetal organic complex, the catalytic effect is effectively improved, the polymerization process is accelerated, the polymerization stability is enhanced, the polymerization molecular weight is improved, and the distribution is narrow.

The invention provides a large language model vertical field multi-task objective question evaluation set automatic generation method, and relates to the technical field of artificial intelligence, and the method comprises the steps: for each text in a vertical field plain text data set, according to a plurality of preset task types, calling a problem solver to carry out task suitability discrimination on the text, and obtaining a task suitability discrimination result; when the judgment result is appropriate, generating at least one initial objective question stem of the task type; performing ambiguity detection on the initial objective question stem, and calling a question solver to rewrite the ambiguous initial objective question stem to obtain a rewritten objective question stem; and finally, calling a question solver to generate corresponding objective question options, objective question answers and objective question answer analyses for each rewritten objective question stem, and taking the objective question options, objective question answers and objective question answer analyses as an objective question evaluation set of a corresponding task type. By means of the method and device, the problems that in the prior art, time and labor are consumed in the large model evaluation dataset construction process, and automatic generation of the evaluation dataset in the specific vertical field cannot be achieved are solved.

The invention discloses a cross-modal medical image registration method based on a submerged space diffusion model, relates to the technical field of medical image processing, and solves the technical problem that an existing registration method is not suitable for multi-modal medical image registration. The method comprises the steps of obtaining a first modal original medical image and a second modal original medical image, and performing preprocessing operation to obtain a floating image and a target image; constructing a cross-modal conversion network, compressing a target image to a submerged space for representation by using a pre-trained auto-encoder, inputting the target image into a diffusion model, and performing training through forward noise addition and reverse noise reduction; inputting the floating image into a diffusion model of a cross-modal conversion network to generate a second modal conversion image; inputting the floating image and the target image into a registration network, and obtaining respective registered images for the floating image and the second modal conversion image; and training the registration network to obtain an image after floating image registration. The method is wide in application field, and is suitable for registration among medical images in various modes.

The invention discloses a thinking chain-based software vulnerability automatic repair method and a storage medium. The method comprises the following steps of S1, preprocessing training data; constructing input and output of the model, including a vulnerability program, a repair position and a repair program; s2, model training; taking a vulnerability program as the input of the model, and constructing a sequence of {a repair position + a repair program} as the expected output; step S3, vulnerability restoration; and S2, inputting a given bug program to be repaired into the trained model obtained in the step S2 after utilizing the input in the step S1, searching possible outputs by utilizing a cluster search technology, and arranging the outputs from high to low according to the possibility to obtain candidate repair programs generated by CotRepair. The storage medium is used for storing a computer program for executing the method. The method has the advantages of simple principle, wide application range, high automation degree, high repairing efficiency and precision and the like.

The invention discloses a diffusion model self-guiding-based image or video generation method and system. The method comprises the steps that the input content is a noise potential variable and a future offset step length of a current time step; the diffusion model predicts the score network twice based on the input content to obtain a conditional score network of the current time step and the future offset time step; carrying out linear combination on the two conditional score networks to generate a combined conditional score network; denoising the noise potential variable of the current time step by using a combined condition score network; calculating and updating a potential variable of the previous time step according to a denoising result; in each time step, the self-guiding strategy is adopted to carry out denoising processing on the noise, and noise prediction is optimized; and after de-noising processing of all time steps, a de-noising potential variable is finally output as a final model generation result, and an image or a video is obtained. According to the invention, the quality of the generated image or video can be obviously improved.

The invention discloses a miniature sawtooth generation method based on an artificial intelligence optimization algorithm, and the method comprises the following steps: S1, initializing a generation parameter, and mapping the generation parameter to a high-dimensional complex field; s2, selecting and configuring an algorithm, and optimizing parameters by constructing a target function in a high-dimensional complex field; s3, constructing a neural morphology calculation system, processing the optimized parameters through a neural network and a complex modulation activation function, and generating a preliminary miniature sawtooth waveform; s4, error evaluation is carried out, an error signal is converted from a time domain to a frequency domain for weighted analysis and optimization, and key frequency band parameters are identified and adjusted; s5, adaptively adjusting the issuing frequency and synaptic weight of the neural network, generating parameters through continuous optimization, and circularly adjusting the waveform; and S6, outputting the optimized micro sawtooth waveform. According to the invention, high-precision and high-stability micro sawtooth waveform generation is realized, and the method is suitable for signal processing and application in a complex environment.

The invention discloses a home scene image generation method based on Stable Diffusion. The method comprises the following steps: firstly collecting a multi-style home scene image-text data set for a home scene generation task; then, on the basis of the data set, a Stable Diffusion model of the text graph is trained by adopting a LoRA training strategy; meanwhile, the content structure of the generated home scene image is controlled in combination with a ControlNet network, so that a Stable Diffusion model which effectively meets a home scene image generation task is obtained; the method comprises the following steps: combining a Stable Diffusion model network with a home scene generation problem, taking a multi-style home scene graph as initial noise, and taking a design constraint as a condition for generating a structural scene graph; according to the invention, a small sample training set is adopted, so that various home scene designs can be generated; meanwhile, the skill requirement for model training of the user is low, and common users can also be well trained and applied.

The invention relates to a test case generation method and device, equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the steps of obtaining a test requirement document and a target code of an application program; the test demand document is used for indicating the test demand of a tester for the application program; the target code comprises at least one of a newly added code and a modified code; obtaining a prompt statement based on the test requirement document of the application program and the target code; the prompt statement is used for indicating to generate a test case matched with the test requirement document and the target code by taking a specified database as background knowledge; the specified database is a database composed of knowledge related to the test of the application program; and inputting the prompt statement into the generative language model to obtain a test case output by the generative language model. According to the scheme, the generation quality of the test case can be improved.

The invention discloses a stable diffusion model-based generation method for a traffic vehicle image generation task, and the method can improve the similarity between text semantics and generated image semantics, enables a generated image to meet the actual road vehicle style in China, improves the authenticity and diversity of the generated image, and improves the image generation efficiency. And the generation efficiency of the text generated image is optimized. The method comprises the following steps: firstly, modeling a semantic consistency problem of a text and an image, and establishing a semantic alignment enhancement algorithm process according to the semantic consistency problem; making a model scheme through multi-stage training; and finally training the model until convergence and determining a scheduling scheme. The method has excellent performance in the task of generating the image through the text, and the performance in all aspects of the evaluation generation task is improved to a certain extent compared with a baseline method.

The invention discloses an automatic README document generation method for a code repository, which comprises the following steps of: firstly, carrying out importance sorting on code files in the code repository by adopting a pre-trained machine learning model, and automatically screening out the most critical code files, so that the problems of inaccuracy and low efficiency caused by manual screening are avoided; therefore, pertinence and accuracy of document generation are improved. Secondly, the key code file is subjected to function-level splitting, and the function abstract is generated based on the control flow and the data flow, so that the document content not only covers the function of the code, but also embodies the complexity of the code logic and structure, and the document is ensured to comprehensively and accurately describe the core function of the code. And finally, the README document is generated by utilizing the large language model, so that the automatic writing of the document is further realized, the workload of manual intervention is reduced, and meanwhile, the generated document is ensured to have natural and smooth language expression and consistency.

The invention discloses a video virtual fitting framework in a real scene based on a controllable image diffusion model. The video virtual fitting framework comprises a data preprocessing module used for constructing feature expressions of figures and clothes; the single-stage image fitting network is used for generating a virtual fitting image based on the preprocessed data and performing implicit deformation and fusion of clothes by using a cross attention mechanism; the diffusion guiding module is used for enhancing the time sequence consistency of the generated video, a self-supervision model Video MAE and a self-supervision image model DINO-V2 are introduced, the video is masked by the self-supervision model Video MAE, and a complete video is reconstructed through inter-frame information; and the long video generation module is used for generating a long video and keeping the consistency of the video, splitting the complete video into a plurality of short video clips, and reducing the jitter at the clip joints by using a time sequence common noise reduction strategy. The diffusion guiding module is designed, efficient time sequence consistent video virtual fitting is achieved through self-supervised learning, and the method has the advantages of being excellent in shielding processing, stable in long video generation and the like.

The invention relates to a laser radar-inertial navigation tight coupling SLAM (Simultaneous Localization and Mapping) method using ground constraint, belongs to the field of mapping of autonomous mobile equipment, and aims to solve the problems of relatively large Z-axis height positioning error, inaccurate point cloud map construction and low rear-end matching speed existing in long-time operation of a laser inertial SLAM method in the prior art. The method comprises the following steps: S100, constructing a laser inertial navigation SLAM system, wherein the construction is divided into IMU pre-integration, laser radar odometer and rear-end sliding window optimization; and S200, adding a functional module for simulating and extracting ground point cloud in the laser radar odometer, and using the functional module to restrain the posture of the robot / unmanned vehicle. And S300, constructing a self-adaptive voxel map by using the pose optimized and output by the rear end. According to the method, pose estimation is optimized by adopting a cloth simulation technology, Z-axis errors are reduced, an adaptive voxel map is introduced, and the matching efficiency and precision of the SLAM rear end are improved in combination with a hash table and a K-D tree.

The invention discloses a photovoltaic power station supervised data generation method based on a generative adversarial network, which is used in the technical field of data augmentation, and comprises the following steps: initializing a generator and a discriminator, and randomly extracting training samples; training a generator and a discriminator by using the training sample, and generating a synthetic data set conforming to photovoltaic power station data set distribution through the generator; and clustering the features of the synthetic data set and the photovoltaic power station data set through a K-means clustering algorithm, observing a clustering center and feature distribution, evaluating the feature distribution difference between the generated data set and the real photovoltaic power station data set through an unsupervised clustering method, and evaluating the quality of the generated data set. According to the method, through the steps of density value sorting, initial center selection and the like, fine division of clustering is achieved, and initial center selection deviation in the clustering process is effectively avoided by combining density value calculation and a grid division method.

The invention provides an intelligent bidding and tendering file generation system and method, and belongs to the technical field of information processing, and the system comprises a demand obtaining module which obtains user input data and carries out the analysis, and further determines the demands of a user; the candidate determination module is used for determining an initial attribute value of the bidding project based on the demand of the user, and determining a bidding file candidate template in a preset bidding file template library based on the initial attribute value; the template screening module is used for analyzing the bidding and tendering file candidate templates based on a plurality of preset index types so as to determine a plurality of first templates; the combination determining module is used for determining an optimal template combination based on all the first templates and further generating a dynamic template file; and the file generation module is used for performing split analysis on the data input by the user and the dynamic template file, generating bidding and tendering file configuration information based on a split analysis result, and further generating an optimized and integrated bidding and tendering file in combination with the dynamic template file. And the efficiency of the bidding and tendering process and the accuracy of the file are improved.

The invention belongs to the technical field of image processing, and discloses an improved DCGAN-based pipeline magnetic flux leakage defect image generation model, which comprises the following steps: S1, acquiring a magnetic flux leakage signal in a pipeline through a magnetic flux leakage detector; s2, carrying out image enhancement by adopting a pseudo-color processing technology, and carrying out pseudo-color enhancement by adopting density segmentation; s3, a residual network and an attention mechanism are embedded into the DCGAN model, and the extraction capability of model features is improved; and S4, generating a pipeline magnetic flux leakage defect image through the improved model. The algorithm proposed by the pipeline magnetic flux leakage defect image generation model based on the improved DCGAN can stably generate a pipeline magnetic flux leakage defect image with better quality, an effective way is provided for expansion of a pipeline magnetic flux leakage defect sample data set, and the problem of small samples faced by development of deep learning in the field of defect detection can be effectively solved.

The invention belongs to the technical field of medical images and deep learning, and particularly relates to a non-paired cross-modal medical image conversion method based on contour guide path regularization, which comprises the following specific steps: constructing a conversion path from a source domain to a target domain; a path regularization method is applied to smooth path transition and ensure the stability in the image conversion process; according to a path regularization technology based on contour guidance, the model can be focused on a key anatomical region, the structural consistency and accuracy of the generated CT image are further improved, and the training time can be remarkably shortened by reducing additional training steps. The invention aims to simplify the unsupervised training normal form and overcome the defects of the traditional GAN-based single-step generation method in the aspect of capturing the complex anatomical structure of the medical image. While the training time and the sampling time are considered, the problem that the quality of the generated medical image is limited is overcome.

The invention discloses a code abstract generation method oriented to semantic structure feature joint enhancement. According to the method, an encoder-decoder architecture is followed, and a multi-form combined semantic feature enhancement method is adopted to automatically generate a code abstract. Wherein the encoder learns code semantics at token and statement levels, and the decoder receives code embedding and generates a code abstract in combination with an attention mechanism. Unlike a single tree or graph coding process, the method uses graph representation to enhance the interval divided tree structure. The joint decoder aggregates the text sequence information and the structure sequence information containing the location node features, and predicts and generates a model understood code summary text. According to the method, the problems of repetition and redundancy of code texts with different lengths caused by disordered code text features are relieved. In a relatively complex code text data set, a word ambiguity phenomenon caused by insufficient knowledge information understanding is reduced, and a code abstract with relatively high quality is generated. Meanwhile, the method has good convergence performance.

The invention relates to a physical and data driving combined fluid animation generation method and device, and the method comprises the steps: S1, building a transparent fluid motion field, applying consistency constraint to the optical flow of a bidirectional video sequence, carrying out the self-supervision training through the real fluid video data in an original video data set S, and obtaining a transparent fluid motion field; generating average optical flow data F and constructing training data; s2, an animation generation model training stage: inputting the training data into a multi-scale double-flow texture feature learning network based on self-attention driving, and performing training in combination with an original video data set S and average optical flow data F; and S3, a fluid animation generation stage: simulating an input image by using a physical model to obtain a motion field M, and guiding actual natural fluid animation generation. According to the method provided by the invention, the physical authenticity of fluid animation generation is improved, and a new solution is provided for simulation and visualization of a complex fluid phenomenon.

The invention relates to the technical field of 3D action generation, and particularly provides a 3D human body action generation method and device, a storage medium, electronic equipment and a product, and the method can comprise the steps: obtaining a text feature vector corresponding to the text description of a human body action; layering and quantifying the text feature vector to obtain a basic action mark sequence and a residual action mark; acquiring a basic action sequence corresponding to the basic action mark sequence, and acquiring a residual action sequence corresponding to the residual action mark; and generating a 3D human body action sequence based on the basic action sequence and the residual action sequence. Some embodiments of the present application can improve the accuracy of 3D human motion generation.

The invention discloses a data blood relationship analysis method based on knowledge graph expansion, relates to the technical field of knowledge graphs, and solves the problem that new information cannot be explored and added through an automatic means because the content of the knowledge graph is limited in a data range on which the knowledge graph depends when the knowledge graph is initially constructed. The method comprises the following steps: collecting metadata related to data consanguinity and constructing a knowledge graph; obtaining an expanded knowledge graph by using an inference engine according to a structure and a relationship in the power grid knowledge graph; based on the expanded knowledge graph, data consanguinity extraction and data consanguinity analysis are carried out, and the data consanguinity extraction specifically refers to query of data consanguinity information in the knowledge graph; the data consanguinity analysis specifically determines whether data loss or conversion errors occur. Through continuous expansion and optimization, the knowledge graph can better serve stable operation of the power grid and optimal configuration of resources, and powerful data support is provided for intelligent management and decision making of the power grid.

The invention discloses a method for generating a multi-modal 3D object through mixed diffusion supervision, and the method comprises the following steps: S1, employing modal similarity loss to align modal prompt and rendering image coding, better injecting semantic information of multiple modals into the generation process of the 3D object, the 3D object generation module is used for enabling a generated 3D object to better meet the requirements of each modal prompt; s2, mixed diffusion supervision is adopted, priori knowledge of a 2D diffusion model and a 3D diffusion model is utilized, and the advantages of the two pre-training diffusion models are combined, so that the generation effect and consistency of a 3D object are improved; S3, a three-stage optimization method is utilized, mixed diffusion supervision is combined in each stage, and the 3D object is generated; according to the method, by adopting modal similarity loss, mixed diffusion supervision and three-stage optimization methods, the generation quality of the 3D object can be effectively improved, and the method has remarkable practical value and application prospect.

The invention discloses an assembly type multi-layer lightweight concrete sandwich wallboard structure system, which relates to an assembly type multi-layer building and comprises lightweight concrete sandwich prefabricated wallboards, vertical corner prefabricated members and fully prefabricated hollow floor slabs, the lightweight concrete sandwich prefabricated wall panel and the vertical corner prefabricated part are connected in an anchoring mode through a vertical anchoring connecting section, a prefabricated bracket is arranged on one side of the lightweight concrete sandwich prefabricated wall panel, and the full-prefabricated hollow floor slab is arranged on the prefabricated bracket. The fully-prefabricated hollow floor slabs and the lightweight concrete sandwich prefabricated wallboards are anchored and connected through the horizontal cast-in-place sections of the fully-prefabricated hollow floor slabs, and every two adjacent layers of lightweight concrete sandwich prefabricated wallboards and vertical corner prefabricated parts are fixedly clamped through buckle type connecting parts. The invention further discloses a construction method of the fabricated multi-layer lightweight concrete sandwich wallboard structure system. Connection joints are simple and convenient, grouting connection is not needed, the prefabricated horizontal members do not need temporary supports, the on-site pouring amount is small, and the stress performance is good.