340 results about "Classification treatment" patented technology

The invention relates to the technical field of computer processing, in particular to a software architecture code generation method and system based on a large language model, and provides the following scheme: obtaining demand information input by a user, analyzing demands by using a natural language processing technology, and extracting functional elements; performing classification processing on the functional elements through a clustering algorithm to generate a functional module group; mapping the function module group to a system architecture layer, and generating an architecture diagram represented by UML (Unified Modeling Language); and generating a corresponding source code according to the UML graph, and optimizing the source code. The optimization strategy comprises static analysis of format problems and potential vulnerabilities in identification codes and performance optimization of complex functions. Through combination of the large language model and the automatic code generation and optimization technology, the software development efficiency is improved, manual intervention is reduced, and the correctness and maintainability of the generated code are ensured.

The invention discloses a classification processing method and device for target characteristic data. The method comprises the steps that a target characteristic data set is acquired; the target characteristic data set comprises target characteristic data; preprocessing the target characteristic data set to obtain a preprocessed data set; and carrying out classification identification processing on the preprocessed data set to obtain category information. According to the method, effective classification processing and service of complex multi-source heterogeneous target characteristic data are realized, correct extraction of target characteristics is realized, and the production efficiency and competitiveness of equipment are effectively improved.

The invention discloses an expensive constrained multi-objective optimization method and system based on constrained hyper-volume expectation. The method comprises the following steps: firstly, initializing a population and training an agent model; then calculating a correlation coefficient between the solution with the best population convergence and the constraint violation degree of the solution, and performing classification processing; then, optimization is carried out on the agent model, and a new solution is selected by utilizing a filling criterion based on constraint hyper-volume expectation to carry out evaluation and is filled into a file; further selecting and screening individuals by using an improved environment to enter a next-generation population; and finally, judging whether a stop condition is reached or not, if so, outputting a final population, otherwise, turning to execute an iteration process. According to the method, the optimization efficiency is remarkably improved, local optimum is avoided, constraint conditions are precisely processed, and the population can be more effectively converged to a better feasible region.

The invention discloses an enhanced contrast learning method and device for highly unbalanced text classification, and the method comprises the steps: carrying out the preprocessing of text data in a training data set and a test data set, and obtaining corresponding original training texts and test texts; respectively inputting the original training text and the test text into the RoBERTa model to obtain corresponding text embedding representations; constructing a text classification model based on data enhancement and comparative learning, wherein the text classification model comprises a text enhancement module, a text representation module, a comparative learning module and a text classification module; and applying the trained and tested text classification model to classification processing of to-be-processed text data, and outputting a classification result. The invention provides a new self-constrained stacked data enhancement method and a new double-weighted contrast loss function, the characterization problem caused by data imbalance and data lack can be solved, and a better text classification effect is achieved.

The invention relates to a futures content generation method and system based on a large language model, and the method comprises the steps: obtaining real-time market data, macroscopic industry chain supply and demand data and futures event information data generated by futures content, carrying out the preprocessing of the real-time market data, the macroscopic industry chain supply and demand data and the futures event information data, and carrying out the processing of the preprocessing data; obtaining basic index data; retrieving the basic index data based on the user statement to obtain corresponding target index data; and processing the target index data through a big language model by utilizing a CoT cue word based on a thinking chain CoT so as to generate futures content corresponding to the user statement. Through the method and the device, classification processing of different futures data is realized to improve the data quality, and on this basis, the thinking chain CoT cue word is utilized to guide the large language model to convert the high-quality futures data into the futures content meeting the statement requirements of the user, so that the problem of how to improve the content generation quality in the futures field is solved.

To efficiently and effectively classify a large amount of document and text data by an LLM.SOLUTION: The present invention relates to a text classification system 1 which classifies documents accumulated in a document DB 14 by categories, and the text classification system has a classification processing part 12 which lets an LLM 2 proposes one or more categories based upon a classification policy specified by a user, a search processing part 13 which searches the document DB 14 for documents belonging to the respective proposed categories, and a UI processing part 11 which presents the respective categories and the numbers of documents belonging to the respective categories to the user.SELECTED DRAWING: Figure 1

The invention discloses an intelligent express parcel automatic sorting method based on deep learning, and the method comprises the steps: collecting a multi-view image, carrying out the standardization enhancement processing, carrying out the bidirectional space sequence coding through a Vision Mama structured state space model, obtaining a fusion visual feature map, inputting a preliminary classification network, and carrying out the primary classification processing, and according to the initial classification category, dynamically selecting expert sub-networks of the MoE-Mama hybrid expert network to complete deep feature reconstruction and fine classification, and finally, according to the final classification category, generating a control instruction to realize automatic guide positioning and accurate sorting. According to the method, the parcel sorting accuracy and efficiency are remarkably improved, and the method is suitable for intelligent logistics sorting operation in a complex environment.

The invention discloses a thesis generation method and device based on a large model. The method comprises the following steps: collecting original thesis data through network acquisition and official purchase channels; preprocessing the original paper data to obtain preprocessed data; based on a preset classification system and a metadata table, carrying out classification processing on the preprocessed data to obtain classification processing data; constructing a training sample based on the classification processing data, and outputting a corresponding bar content; a multi-task learning framework is adopted to carry out fine tuning on the pre-trained large language model, the multi-task learning framework comprises an outline generation task and a text generation task, and task types are distinguished through system prompt; and receiving a paper title and a keyword input by a user, sequentially generating a paper outline through the fine-tuned model, and generating text contents of each chapter in parallel based on the paper outline. According to the invention, the paper generation quality and efficiency can be improved, so that the user experience is improved.

The invention discloses a multi-granularity financial text noise open classification method based on a large model, and belongs to the technical field of text noise classification. Performing clustering processing on the semantic features to obtain a plurality of balls with different labels, and calculating attributes of the plurality of balls with different labels; according to the positions of the samples in the pellets and the attributes of the pellets, the samples in the pellets are classified into clean samples, internal noise is distributed, and external noise is distributed. A plurality of pellets with different labels are obtained through clustering processing, the attribute of each pellet is calculated, at the moment, each category is finally represented by a plurality of pellets with the same label but different attributes, the multi-granularity prototype and the distribution range of the category can be effectively reflected, and the representation learning effect is improved. Meanwhile, classification processing is carried out according to the positions of the samples in the pellets and the attributes of the pellets, and the method can be suitable for data environments of various distribution types.

The invention relates to the technical field of medical information systems, in particular to an intelligent classification treatment system and method for medical waste in an operating room, and the system comprises a waste recognition module which is used for recognizing the medical waste through a computer vision algorithm; determining a waste category based on the recognition result; the electronic guiding module is in communication connection with the waste identification module and is used for receiving the waste category information sent by the waste identification module; based on the waste category information, generating an electronic guide for guiding the medical staff to store the waste; the waste weighing and recording module is in communication connection with the electronic guiding module and is used for calculating and recording the weight and the capacity of the waste; waste weight and volume data are generated; the RFID reading module is in communication connection with the waste weighing and recording module and is used for automatically reading RFID electronic tag information; the source tracing of the waste is realized based on the RFID electronic tag information; the system can automatically complete the whole process from waste identification, classification guidance, weight recording to information tracking.

The invention relates to the technical field of data classification, and discloses a data classification method and system based on an improved TSK fuzzy classification model, and the method comprises the steps: obtaining a to-be-classified data set, and dividing the to-be-classified data set into a training set and a test set; based on the training set, utilizing a supervised enhanced soft subspace clustering algorithm and a deep learning algorithm to respectively optimize a fuzzy rule consequent and a fuzzy rule consequent of a fuzzy rule of a pre-constructed TSK fuzzy classification model; and inputting the test set into the optimized TSK fuzzy classifier model for classification processing to obtain a data classification result. According to the method, the fuzzy rule consequent and fuzzy rule consequent parameters of the TSK fuzzy classification model are optimized respectively, so that the adaptability of the model to high-dimensional data and complex data sets is improved, and the precision and efficiency of the model in data classification are further improved.

The invention relates to a cue word generation method of a large language model and a question answering method of the large language model, and relates to the technical field of natural languages. The cue word generation method of the large language model comprises the following steps: obtaining an initial cue word, and carrying out semantic classification processing on the initial cue word to obtain classification information of the initial cue word; judging that the dialogue intention of the initial cue word is a preset dialogue intention needing cue word generation; obtaining a cue word template bound with the dialogue intention needing to generate the cue word in advance; initial entity words in the initial cue words are extracted, and target entity words are determined in the initial entity words according to a first entity word type in the cue word template; and replacing the vacant cue word in the cue word template with the target entity word, and taking the replaced cue word template as the target cue word. According to the method and the device, knowledge enhancement can be performed on the initial cue word related to the preset dialogue intention needing to generate the cue word, so that the use of computing resources is reduced.

The invention relates to the technical field of enterprise analysis, in particular to an enterprise information processing method and device based on a large language model, equipment and a storage medium, and the method comprises the steps: obtaining a target page group of a to-be-analyzed enterprise; performing data cleaning on a parent page and a child page of the same target page group to obtain a page source code group; performing classification processing on the page source code block through a first preset model to obtain a first classification source code block and a second classification source code block; constructing a basic product tree based on the first classification source code group through a second preset model; performing supplementary construction on the basic product tree based on the second classification source code group through a third preset model to obtain an enterprise product tree; and obtaining enterprise product information of the to-be-analyzed enterprise based on the enterprise product tree. The problem that enterprise product information is difficult to obtain can be solved, so that the blank of enterprise product library resources on the market is filled, and the beneficial effects of enabling enterprises, industries and industry analysis are achieved.

The invention provides a large language model generation code detection method and system, which is applied to the technical field of artificial intelligence, and comprises the following steps: obtaining a to-be-detected code; a to-be-detected code is input to a trained shared encoder, a code feature vector is obtained, the shared encoder is obtained through multi-target joint training, and the multi-target joint training is used for optimizing classification loss, domain confrontation loss, comparison loss and difficult sample loss at the same time; l2 normalization is carried out on the code feature vector, and the code feature vector is mapped to a hyperspherical space to obtain spherical embedding; the sphere is embedded and input into a sphere category classifier based on sphere logistic regression for classification processing, a detection result of the to-be-detected code output by the sphere category classifier is obtained, the detection result comprises AI generation and human writing, and a decision boundary of the sphere category classifier is an intersection line of a hyperplane and a hypersphere for classification. According to the invention, the AI generation code and the human compiled code can be accurately distinguished.

A multi-class classification system performs multi-class classification using an adapted, multi-level binary classification model in conjunction with pre-classification and post-classification processing. Original, multi-class training data is transformed into coarse-level adapted training data and fine-level adapted training data. In the coarse-level adapted training data, objects from the original training set are classified into either a majority classification set (representing the largest original classification set) or a non-majority classification set representing a combination of the remaining classification sets from the original training data. In the fine-level adapted training data, objects from the non-majority classification set retain their original classifications from the original training data. The adapted training data is used to train coarse-level and fine-level instances of the binary classification model, which are used to generate coarse-level and fine-level binary classifications of objects with respect to an input data set. The binary classifications are transformed into a multi-class classification.

The invention provides an intelligent mining production management and control method based on an ADP algorithm, and relates to the technical field of intelligent mining, and the method comprises the steps: firstly obtaining vehicle data and wrong vehicle point data, carrying out the road division of a two-way single lane with a wrong vehicle point as the end points of the two ends of a road section, and carrying out the position judgment and display of a running vehicle in the two-way single lane; judging passing priorities of the vehicles, and checking whether vehicles running in opposite directions exist in adjacent road sections of the current vehicle or not; carrying out data preprocessing on the collected mine car scheduling data, dividing the data into a training data set and a test data set, carrying out classification processing on the preprocessed data, and establishing a classification model; identifying and dividing a naturally formed area of the underground mining area operation area by adopting a clustering algorithm; establishing a nonlinear system model, establishing a performance index, comprehensively considering transportation efficiency, cost saving and time benefit, measuring the effect of a scheduling strategy, and setting an optimization target; and establishing an ADP algorithm, and outputting an optimal scheduling scheme.

The invention relates to the technical field of data search, and particularly discloses a search question and answer method combining ElasticSearch and AI. Comprising the steps of classifying questions in advance, then obtaining the questions input by a user, preprocessing the questions to obtain question text feature data, then calculating the question text feature data to obtain question classification values, and judging whether the question classification values are within a preset threshold interval or not; according to the method, the BERT model and the internal neural network structure thereof can be utilized to calculate the question classification probability and determine the final classification result, and compared with a relatively simple question classification mode in an RAG technology, the method has obvious advantages; the deep semantic relationship of the question cannot be fully considered during classification by the RAG technology, so that the classification is inaccurate, and the phenomenon that the question is difficult to answer or is not answered can occur, so that the user experience can be effectively improved, and the user stickiness is improved.

The invention discloses an anti-unmanned aerial vehicle interference effect evaluation method and system, and belongs to the technical field of anti-unmanned aerial vehicle interference effect evaluation, and the method comprises the following steps: collecting two types of anti-unmanned aerial vehicle scheme cases, carrying out the standardization and classification processing of cases which are good in evaluation but failing in off-site simulation, and building a failure case library; cases which are both good in evaluation and off-site simulation are classified, then the economic benefit range of each type of evaluation method is determined, and a successful case library is established. According to the method, a failure case library containing structured data and a success case library with a clear economic benefit range are established, a to-be-evaluated scheme is evaluated, then three-dimensional data are extracted from the failure case library to construct a multi-dimensional association model, and an evaluation blind area is positioned; and finally, three evaluation methods are generated in combination with a success case library, economic benefits are calculated and sorted, the difference between evaluation and off-site simulation can be effectively reduced, the evaluation accuracy is improved, and off-site simulation failure conditions are reduced.

The invention discloses a micro-control unit fault classification processing method and system, belongs to the technical field of micro-control unit fault processing, and aims to solve the problems that in the prior art, a fault processing mode is relatively single, different faults cannot be properly processed, the fault processing efficiency is relatively poor, and the fault processing efficiency is relatively high. And the fault processing cost is high. The method comprises the following steps: in response to received fault information, determining a fault type according to the fault information; determining a corresponding processing mode according to the fault category; and executing a corresponding processing mode to realize fault classification processing. The fault type is determined according to the fault information, and effective measures are taken for solving the faults of different types, so that the fault processing efficiency is improved, the fault processing cost is reduced, the stability and reliability of the micro-control unit during fault processing are improved, and the fault processing effect of the micro-control unit is ensured.

The invention relates to the technical field of natural language processing, and discloses a short text classification processing method utilizing a graph attention network, which comprises the following steps of: cleaning short text data, performing word segmentation and part-of-speech tagging, removing redundant words, converting each word into a vector representation with a fixed length by utilizing a word embedding technology, and extracting the vector representation by utilizing a graph attention network; obtaining a text vector matrix; constructing a text graph based on the text vector matrix, and constructing a tag graph according to a known tag relationship; a graph attention mechanism is applied to nodes in the text graph and the label graph, attention coefficients between the nodes are calculated, feature weighted summation is carried out, and updated node embedding representation is obtained. The short text classification processing method using the graph attention network aims at solving the problem that in an existing short text classification processing method, due to the fact that sparsity and characteristics of short texts are insufficient, labels are difficult to predict accurately through a traditional classification method.

The invention provides a text classification method and device, electronic equipment and a storage medium, and relates to the technical field of natural language process.The method comprises the steps that a training sample set is obtained, and the training sample set comprises sample texts and sample classification labels and sample reasoning reasons corresponding to the sample texts; performing fine tuning on a first pre-trained large language model through the training sample set to obtain a text classification model; in response to a text classification request, through the text classification model, based on a preset reasoning constraint parameter, only performing classification processing on a to-be-classified text to obtain a prediction classification label; wherein the preset reasoning constraint parameters comprise an output length limiting parameter and a logit probability intervention parameter. According to the method, the text classification efficiency can be improved while the accuracy and the reliability of a text classification result are improved.

The invention provides a work order processing method based on a large model, 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 work order processing scenes. The method comprises the steps of obtaining a to-be-processed work order, wherein the to-be-processed work order comprises problem information; determining cue words of the to-be-processed work order, wherein the cue words comprise preset cue words or cue words obtained by updating the preset cue words according to the service category information; and performing work order classification processing on the cue word and the problem information by using the large model to obtain a work order category for the to-be-processed work order so as to process the to-be-processed work order according to the work order category. The invention further provides a work order processing device based on the large model, the intelligent agent, equipment and a medium.

The invention discloses a voice deception detection method based on double attention and multi-scale feature fusion, and belongs to the technical field of voice deception detection. The method comprises the steps that training corpora are acquired and preprocessed; inputting the preprocessed training corpus into a detection model for model training; adjusting hyper-parameters to minimize the target loss function to obtain a trained detection model; obtaining a test corpus and preprocessing the test corpus; inputting the preprocessed test corpus into the trained detection model, and outputting a voice deception detection result; the detection module comprises a Sinc module, a feature extraction module, a feature fusion module and a classification processing module; the Sinc module is used for extracting a preliminary feature X in an input voice segment, the feature extraction module further extracts a multi-scale feature Yi from the preliminary feature X, the feature fusion module aligns and splices the multi-scale feature Yi and then outputs a fusion feature Y, and the classification processing module processes the fusion feature to obtain a classification result.

The invention discloses a label classification method and device for a long text, equipment, a storage medium and a product, relates to the technical field of computers, and discloses a label classification method for the long text, which comprises the following steps: obtaining a to-be-classified text; and based on the to-be-classified text, performing label classification processing through a preset large language model to obtain a label classification result. According to the method, the to-be-classified texts are converted into the text sequence vectors by the large language model through position coding, and then correlation among the text sequence vectors is calculated in parallel by utilizing a multi-head self-attention mechanism, that is, the large language model can process the text sequence vectors in parallel, so that the video memory utilization rate of the large language model is improved, and the classification efficiency is improved. Due to the improvement of the utilization rate of the video memory, the large language model can process the long text with more characters, namely, the large language model does not need to segment the long text, so that semantic loss caused by segmentation is avoided, and the tag classification accuracy of the long text is improved.

The invention relates to a natural resource asset management and territorial space planning system fusion method and system. The method comprises the following steps: encoding territorial space planning vector data and natural resource asset registration data to generate a space-time binding code; constructing a spatial topological graph and a time sequence diagram based on the codes, respectively extracting planning constraint feature vectors and asset dynamic feature vectors, and fusing the vectors to generate a planning asset coupling scoring matrix; recognizing a conflict unit set based on the planning asset coupling scoring matrix; based on the conflict unit set and a preset business rule base, performing classification processing on each conflict unit in the conflict unit set to obtain a conflict type; and based on the conflict type, generating a service execution instruction set through a preset reinforcement learning decision model. According to the method, through space-time unified coding and feature fusion processing, the accuracy of data association and the scientificity of decision making are improved, so that collaborative governance of territorial space planning and natural resource asset management is realized.

The invention discloses an intelligent classification processing system and method for building solid waste, and relates to the technical field of intelligent classification, and the method comprises the steps: traversing a target region, collecting multi-dimensional data of the building solid waste, and determining a to-be-classified data set; determining a plurality of classification labels to construct an intelligent classification model, and synchronizing the to-be-classified data set to the intelligent classification model to obtain a classification decision; the classification decision is simulated and executed to conduct classification processing monitoring on the building solid waste, and operation feedback data is generated; optimizing the intelligent classification model based on the operation feedback data to obtain an intelligent optimization classification model, and synchronizing the to-be-classified data set to the intelligent optimization classification model to obtain a classification optimization decision; and intelligent classification treatment is conducted on the building solid waste. The technical problems that in the prior art, when the building solid waste is classified and treated, efficiency is low, and accuracy is not high are solved, and the technical effect of improving the accuracy and efficiency of building solid waste classification is achieved.

The invention discloses a three-stage differential garbage classification treatment system, and relates to the technical field of energy conservation and environmental protection. A throwing opening is formed in the top of a shell, a classification mechanism is arranged in the shell, and the classification mechanism comprises a three-stage differential separation module, a throwing module and a visual recognition module; the three-stage differential separation module comprises a first conveying belt, a second conveying belt and a third conveying belt which are sequentially arranged from top to bottom, a dispersing roller is arranged below the throwing opening and is in transmission connection with the first conveying belt through a belt, a throwing module is arranged at one end of the third conveying belt, and a visual recognition module is arranged above the throwing module; more than two garbage cans are arranged at the bottom in the shell, and a compression mechanism is arranged in one garbage can. According to the three-stage differential garbage classification treatment system, the three-stage differential separation module is utilized, multiple kinds of garbage can be thrown at a time and accurately recognized and sorted, compared with manual throwing, the error rate is greatly reduced, and the recognition accuracy rate reaches up to 97.3%.

The invention relates to a Json file parallel analysis and data writing method and device based on DataX. The method comprises the following steps: acquiring a source end Json file set, and dividing the source end Json file set into small file subsets and large file subsets according to file sizes; the small file aggregation path is configured with a json reader of the DataX, and parallel reading and analysis are carried out; splitting a root array of the large file into a plurality of independent small Json files through a Python script, aggregating paths, and reading and analyzing by using a DataX parallel channel; and finally executing the DataX Job to write the data into a target end. Through a classification processing strategy, the large-scale Json data analysis writing efficiency is remarkably improved, the large file memory occupation risk is reduced, the file scale is automatically adapted, a mature DataX frame and a Python script are reused, high performance and low maintenance cost are both considered, multi-type target end storage is supported, and the problems that a traditional tool is weak in parallel, high in resource consumption, poor in flexibility and the like are effectively solved.

The invention discloses a charging pile operation and maintenance optimization method and system based on intelligent prediction and scheduling, and belongs to the technical field of charging pile operation and maintenance. The method comprises the steps of designing a deep learning model, dividing a data set for training, and outputting a fault emergency degree; dividing candidate task groups, setting radiation range constraints of operation and maintenance sites, and combining the candidate task groups to perform priority ranking and task combination to obtain task groups; in combination with the state and skill of the operation and maintenance personnel, distributing a corresponding task group; calculating the passing time of the operation and maintenance route, optimizing the route based on the task group to obtain an optimized route, and combining the optimized route with the task group to obtain an operation and maintenance task; environment safety detection is carried out on the fault charging pile, and visual verification is carried out on the equipment state; defining an execution condition, judging whether the execution condition of the operation and maintenance task is met or not, and executing the operation and maintenance task when the execution condition is met; and if not, running the classification processing rule, carrying out time window replanning, and executing a conflict resolution strategy to obtain a new operation and maintenance task.

The invention relates to the technical field of code classification processing, and discloses a waste code cleaning method and device based on reachability analysis, equipment and a medium, and the method comprises the steps: scanning static codes in a preset program, and collecting and analyzing a dependency relationship and a reference relationship between the static codes; analyzing the reachability of the dependency relationship and the reference relationship between the codes, and determining static codes without the reference relationship; marking the static code without the reference relationship as a waste code according to the reachability analysis result; according to the marked abandoned codes, clearing suggestions and clearing operation steps of the abandoned codes are made, output and displayed. The method can be applied to development of business systems such as financial science and technology, medical treatment, health and pension and the like, waste codes in projects are accurately recognized and cleared through combination of control flow analysis and data flow analysis, and code quality and maintenance efficiency are improved.