357 results about "Model application" patented technology

The invention discloses a territorial space planning index dynamic evaluation model, and particularly relates to the field of territorial planning, and the model comprises a multi-source heterogeneous data fusion module, an index system construction module, a dynamic adjustment model construction module, a scheme evaluation and optimization module, and a model application and dynamic updating module. According to the method, various spatial data are integrated through a multi-source heterogeneous data fusion technology, and the data quality is ensured by adopting a three-stage cleaning assembly line and an intelligent correction algorithm; the method comprises the following steps: constructing an index system based on six core contents of territorial space planning, and determining an index weight by applying a Delphi method and an analytic hierarchy process to realize adaptive adjustment of an index threshold; the model adopts time sequence analysis, regression analysis and a machine learning algorithm to predict a development trend, a dynamic feedback mechanism is established in combination with a system dynamics method, and an evaluation scheme is quantified through an analytic hierarchy process; the model performance is evaluated by adopting indexes such as accuracy rate and precision rate, and parameters are continuously optimized based on an evaluation result; finally, the model is integrated to a service system to realize real-time monitoring, and dynamic updating is realized through three mechanisms of data driving, performance triggering and regular maintenance.

The invention relates to the technical field of computers, in particular to a model fine-tuning training method based on dynamic low-rank tensor adaptation, a model application method and a related device. The model fine-tuning training method based on dynamic low-rank tensor adaptation in one embodiment comprises the following steps: acquiring a pre-training model; adding fine tuning parameters to model parameters of the pre-training model to obtain fine tuning parameter matrixes of different layers, combining the fine tuning parameter matrixes of multiple layers into a fine tuning parameter tensor and decomposing the fine tuning parameter tensor into a core tensor and two low-rank factor matrixes to obtain to-be-fine-tuned parameters; and performing fine tuning on the pre-training model through the sample data, freezing original parameters of the pre-training model in the fine tuning process, updating the core tensor and the two low-rank factor matrixes in sequence, and performing low-rank adjustment on the slice matrix of the updated core tensor to obtain updated fine tuning parameters. By adopting the scheme of the embodiment, the performance of the obtained model can be further improved while the parameter fine tuning cost is reduced.

The invention relates to the technical field of power converters, in particular to a power converter control method and device based on physical information machine learning and a storage medium. Comprising the following steps: setting up a control system; collecting, storing and preprocessing data; building and evaluating a model; model deployment; applying the model; and selecting a prediction model of the operation mode of the power converter. According to the design, physical constraint information is embedded into a loss function, a machine learning algorithm is used for mining the relation between the duty ratio, the frequency and the number of hopping pulses of a control signal and input voltage, input current, output voltage, output current and temperature, and a machine learning control model is deployed on an FPGA. The duty ratio, the frequency and the pulse hopping number of the control signal are predicted and controlled in real time; accurate modeling is performed through the nonlinear capability of a machine learning model, so that a large amount of cost can be saved, and the accuracy of the model is improved.

The invention relates to an AI-based meteorological disaster prediction method, which belongs to the field of marine meteorological data analysis and prediction, and comprises the following steps: (1) data acquisition and preprocessing; (2) constructing a time sequence data set; (3) designing and constructing a model; (4) model training; (5) model verification; and (6) model application: applying the trained model to an actual marine meteorological disaster prediction task. The method has the advantages that (1) the prediction precision is improved, and the prediction precision of the marine meteorological data is effectively improved by combining the Bi-LSTM and the MLP model; and (2) the robustness and stability of the model are enhanced, and the robustness of the model in different data environments is enhanced through the synergistic effect of Bi-LSTM and MLP. And (3) the flexibility and application universality of the model are improved, and the flexible structure enables the model to be widely applied to a plurality of fields such as marine meteorology, environmental monitoring, meteorological disaster early warning and the like, and has good adaptability.

The invention provides an automatic vending device replenishment prediction method, which comprises a model training process and a model application process, and is characterized in that the model training process comprises the steps of obtaining historical operation data of different automatic vending devices and establishing a data set, and the historical operation data at least comprises time data, environment data, geographic data and commodity data; constructing a model, processing the historical operation data, and inputting the processed historical operation data into the model for training to obtain a trained model; the model application process comprises the following steps: predicting sales volume of each inventory unit in different automatic vending devices at different time points according to the trained model, and calculating predicted inventory amount of each inventory unit at different time points; and calculating replenishment priorities of different automatic vending devices at least according to the predicted inventory amount of each inventory unit.

A service processing method executed by a computer device. The service processing method comprises: acquiring prompt information of a target item which is recalled for a service user, wherein the prompt information of the target item comprises information of the service user, features of at least one associated item which is associated with the service user, and features of the target item (S301); calling an item processing model under a model application inference framework, and on the basis of the prompt information of the target item, predicting the degree of association of the service user with the target item, wherein the item processing model is obtained by means of training under a model training inference framework, and is reused in the model application inference framework (S302), and the processing speed of the item processing model in the model application inference framework is higher than the processing speed of the item processing model in the model training inference framework; and performing service processing on the target item on the basis of the degree of association of the service user with the target item (S303).

The invention provides an artificial intelligence auxiliary judgment method, system and device, a storage medium and a product. The system comprises a scene application layer, a model application layer and a model service layer. And the scene application layer is used for acquiring case information and business scene information of the task. And the model application layer is used for acquiring task configuration parameters of the tasks according to the business scene information. The model service layer is used for acquiring operation state information of a model instance and acquiring case information and task configuration parameters of a task; obtaining case information of the task, an input text vector of task configuration parameters and model capability vectors of different types of service models; according to the input text vector and the model capability vector, obtaining a matching degree between the task and different types of service models; and according to the matching degree and the model instance operation state information, distributing the case information and the task configuration parameters of the task to the corresponding model instance of the service model of the corresponding type for processing, and obtaining a reasoning result of the task.

The invention belongs to the technical field of computers, and particularly discloses a medical dialogue service device and system based on a large language model, and the device comprises a data set construction module, a model training module and a model application module. The data set construction module comprises a dialogue sample reconstruction unit, a knowledge graph question and answer pair generation unit and a dialogue sample rewriting unit; the model training module is used for training a large language model based on the reconstructed dialogue sample, the knowledge graph question and answer pair and the rewritten dialogue sample to obtain a trained large language model; and the model application module is used for inputting the question content carried by the dialogue request to the trained large language model to obtain the answer content. According to the method and the device, high-quality medical dialogue service can be provided for the user in an end-to-end dialogue mode aiming at an actual medical consultation scene.

The invention provides a preference learning method which can be applied to the technical field of artificial intelligence. The preference learning method comprises the steps that sample questions matched with preset standards are determined from a text document pre-trained by a large model, the preset standards comprise a forward standard and a reverse standard, and the sample questions are used for representing questions generated when a user interacts with the large model; inputting the plurality of sample questions into a large model to generate a plurality of question and answer pairs according to answers corresponding to the sample questions output by the large model; evaluating answers in each question and answer pair based on a forward standard by using a plurality of evaluation models to obtain an evaluation label corresponding to each question and answer pair; and training the large model by using preference data generated based on the evaluation label to obtain a target model aligned with the forward standard. The invention further provides a model application method, a preference learning device, equipment, a storage medium and a program product.

The invention discloses a multi-level detail automatic simplification method for an oblique photography live-action three-dimensional model, and relates to the technical field of three-dimensional model simplification and computer graphics, and the method comprises the steps: obtaining oblique photography original data and three-dimensional model basic information; preprocessing the model, performing adaptive Gaussian filtering denoising, improving RANSAC to remove outer points, compressing textures in a blocking manner, correcting mapping coordinates, and repairing a topological structure; extracting multi-scale features; constructing a simplified decision model, and determining a simplification rate and a priority by combining an observation distance, scene precision and hardware performance; performing hierarchical simplification, vertex hierarchical improved edge folding, patch hierarchical adaptive deletion and regional hierarchical grid reconstruction; performing multi-dimensional quality evaluation, and if the requirements are not met, performing backtracking adjustment; and outputting a simplified model stored according to the LOD hierarchy, wherein the simplified model comprises transition information and a simplified log. According to the method, the data quality is improved through refined preprocessing, the simplification pertinence is enhanced through multi-dimensional feature extraction and intelligent decision, and the application value of the model is improved.

Various embodiments include a system. The system comprises processing circuitry. The processing circuitry obtains an Application Programming Interface (API) call that is associated with a Large Language Model (LLM). The processing circuitry generates a feature vector that numerically represents data included in the API call associated with the LLM. The processing circuitry provides the feature vector to a security LLM trained to detect security threats to the LLM. The processing circuitry obtains an output from the security LLM that indicates a security threat to the LLM. The processing circuitry determines a security policy based on the security threat. The processing circuitry provides the security policy to a security proxy that screens the API call.

The invention provides a method and a system for predicting the wear life of an overflow surface of a release structure, and is suitable for the technical field of hydraulic engineering monitoring. The prediction method comprises the steps of data acquisition equipment arrangement, model training, actual measurement data acquisition, model application and result display and maintenance, and a prediction system is designed based on the method. A sensor is arranged to collect relevant abrasion data of the flow passing surface of the release structure, and an abrasion depth prediction model is designed based on a double-channel structure; static data features are extracted through full connection layer coding, long-term dependence features are extracted through LSTM and an attention mechanism and fused to obtain a comprehensive feature vector, and finally the wear depth is predicted; dynamic prediction of the wear life is achieved through model deployment and periodic actual measurement data input, the model is updated in combination with nondestructive testing data, and the prediction precision is improved; the method effectively solves the problem that the service life of the overflow face of the water drainage building is abraded in the complex water flow environment.

The invention provides a large model fine tuning method, and relates to the technical field of artificial intelligence, in particular to the technical field of large models and the technical field of deep learning. According to the specific implementation scheme, a to-be-deployed large model is determined from a plurality of large models of different types according to a model application scene; inputting the initial prompt data into the to-be-deployed large model to obtain a first output result; according to at least one of a preset database corresponding to the model application scene and the first output result, adjusting the initial prompt data to obtain adjusted prompt data; according to the training sample data corresponding to the model application scene, finely adjusting the to-be-deployed large model to obtain a target large model; according to the adjusted prompt data and the target large model, a first performance evaluation value of the target large model is determined, and the first performance evaluation value is used for representing the performance of the target large model. The invention further provides a large model fine adjustment device, electronic equipment and a storage medium.

The invention discloses a deep learning-based mechanical multi-joint mechanical property prediction method, which comprises the following steps of: performing fine model simulation of a plurality of joints of SPR, FDS and welding spots, creating a plurality of fine models of mechanical connection joints, and realizing data construction; collecting layout feature information of the CAE fine model or the experimental material sheet; performing feature selection on the joint database based on a random forest method; a strength feature model is constructed based on a convolutional neural network, feature information data selected through a random forest method is used as a training set, corresponding joint strength feature information is used as a label, and the strength feature model of multiple joints is trained; a plurality of convolutional neural network models are integrated, predicted multi-joint strength feature information, model evaluation and model application are comprehensively obtained, historical data and simulation results are used as training data, and the deep learning model can efficiently predict mechanical properties when the number of joints and positions change.

The invention provides a code generation method based on an artificial intelligence low-code system. The code generation method can be applied to the technical field of artificial intelligence. The method comprises the following steps: packaging a pre-trained artificial intelligence large model into an artificial intelligence model service to obtain a model application program interface; according to the model application program interface, deploying an artificial intelligence model service into a production environment; based on a production environment, integrating an artificial intelligence model service into a workflow engine of a low-code platform by utilizing a model application program interface so as to obtain an artificial intelligence low-code system; and automatically generating application program codes based on user application requirements by utilizing an artificial intelligence low-code system. According to the artificial intelligence low-code system, automatic decision support is provided, and a more intelligent, user-friendly, efficient and safe low-code application development platform is provided. The invention further provides a code generation device and equipment based on the artificial intelligence low-code system, a storage medium and a program product.

The invention discloses a construction site monitoring arrangement method based on deep reinforcement learning, and relates to the technical field of model application. Monitoring arrangement modeling is design of a multi-agent reinforcement learning model, through deep reinforcement learning of multiple agents and guidance of a common target, all the agents are promoted to act in a cooperative and self-adaptive mode, and finally intelligent arrangement of construction site monitoring is achieved. According to the construction site monitoring intelligent arrangement method based on deep reinforcement learning, monitoring arrangement design can be efficiently and automatically carried out, compared with a traditional artificial experience and fixed rule method, the arrangement efficiency and precision can be remarkably improved, the monitoring equipment is regarded as an intelligent agent for joint optimization, and the construction site monitoring intelligent arrangement method based on deep reinforcement learning has the advantages that the arrangement efficiency and precision are greatly improved. Global coordination and self-adaptive arrangement can be realized, the problems of inflexibility and low efficiency caused by a manual method are avoided, and the monitoring arrangement efficiency and precision are improved.

The invention relates to a method and apparatus for generating a project-specific network architecture. The invention relates to a method for generating a project-specific network architecture, said method comprising the steps of:-providing (S1) a base model, in particular a large language model, with LoRa network adaptation; providing (S2) a model library having training data pairs, each of which consists of input data having a model application and / or model and / or hardware and / or software specification, and output data having at least one network architecture belonging to the respective input data; -selecting (S3) item-specific training pairs on the basis of said library of models; and-training (S4) the LoRa network of the base model on the basis of the item-specific training pair for generating the item-specific network architecture.

The invention provides a communication method and device, and relates to the technical field of communication. In the method, after the model application equipment indicates the first state of one or more first models to the model management equipment, the first state can be maintained in the first time window, so that the condition that the model application equipment frequently reports the first state of one or more first models to the model management equipment is avoided; and information interaction between the model application equipment and the model management equipment is reduced.

The invention provides a model application-oriented multi-modal data set annotation management method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining a processed data set; obtaining a basic index of the processed data set; determining a labeling quality coefficient according to the basic index; obtaining a trained application model of the ith time period; obtaining process diagnosis parameters; determining a process normal coefficient; obtaining model performance parameters of the trained application model; determining a result normal coefficient; determining whether the data set processing model needs to be trained; under the condition that the data set processing model needs to be trained, determining a loss function of the data set processing model in the ith time period according to the labeling quality coefficient, the process normal coefficient and the result normal coefficient; and training the data set processing model according to the loss function to obtain the data set processing model of the (i + 1) th time period. According to the method and the device, the accuracy and the applicability of multi-modal data set labeling management can be improved.

The invention discloses a heterogeneity causal effect quantitative evaluation system and method for electric vehicle charging behaviors, and relates to the field of electric vehicle big data analysis, artificial intelligence and causal inference. The system comprises a data preparation and variable system construction module, a heterogeneity causal effect quantitative evaluation model construction module and a model application and result interpretation module. A dual machine learning framework is adopted, systematic deviation of high-dimensional hybrid factors is eliminated by calculating orthogonalization residual errors, a causal forest model is constructed on this basis, a conditional average processing effect is accurately and stably quantified based on a splitting criterion of maximizing effect heterogeneity, and a high-precision and high-precision effect is obtained. The problem of causal effect estimation deviation of a traditional method under the forms of high-dimensional data and complex functions is solved. In order to enhance the interpretability, an agent model based on a single decision tree is further constructed, and a complex causal forest conclusion is extracted into a group of visual and operable If-Then decision rules, so that a complete closed loop from data to robust and interpretable decisions is realized.

The invention belongs to the technical field of water quality model packaging, and particularly relates to a river basin water quality prediction model packaging display method and system, and the method comprises the steps: firstly carrying out the multi-thread digitalization of a water quality prediction model, and outputting water quality prediction result analysis; the data template is used for storing water quality prediction result analysis data, and a storage result is output; then configuring a visual rendering basic map service, and calling a data source of the visual rendering basic map service to perform real-time dynamic rendering of water quality evolution according to a prediction result of the water quality prediction model; and finally configuring resource data of a two-dimensional scene and a three-dimensional scene of the target river basin, superposing a water quality evolution real-time dynamic rendering service in the resource data of the two-dimensional scene and the three-dimensional scene, and generating a river basin two-dimensional scene model application and a river basin three-dimensional scene model application. According to the invention, the problem of poor effect in the packaging and displaying process of the water quality prediction model in the prior art can be solved.

The invention relates to the technical field of model automatic training, and discloses a small model automatic training method based on multi-modal large model cognition intelligent driving, and the method comprises the steps: obtaining each training sample generation task received in a target time period and a task execution state of each model driving end; judging whether the model driving group meets a deadline requirement for executing an exclusive sample labeling strategy or not, and selecting the exclusive sample labeling strategy or a shared sample labeling strategy to execute distribution and automatic labeling actions for all multi-modal training data in each training sample generation task, and sending the training sample set obtained by automatic labeling to a model application end to carry out small model training aiming at the corresponding detection scene. Therefore, by performing selective annotation image proportion sharing on the training sample generation task and establishing a dual-behavior judgment system of the model application end and the model driving end, the task processing amount is reduced, and meanwhile, the influence on the annotation data quality and the training model recognition accuracy is reduced as much as possible.

The invention discloses a river total phosphorus concentration prediction method based on an XGBOOST model. The method comprises the following steps: obtaining river basin water quality data provided by an online water quality monitoring station; preprocessing the water quality data of the river basin; constructing a data set; performing total phosphorus concentration prediction by using an XGBoost regression model; basic parameters of the prediction model are initialized and trained, and SHAP analysis is introduced; and inputting real-time data to be measured into the trained prediction model, and outputting a prediction result. The system comprises a data set construction module, a model construction module, a model training module and a model application module. By using the method, high-precision prediction of the total phosphorus concentration of the river basin is realized. The method can be widely applied to the field of water quality monitoring.

The invention provides an evaluation method of data elements in a model application, related hardware and a program product. The method comprises the following steps: acquiring metadata knowledge and content knowledge of target data elements from a metadata knowledge base and a content knowledge base set by a big language model hitching data platform, and storing the target data elements in the data platform. Setting the metadata knowledge and the content knowledge of the target data element as cue words to be imported into a large language model so as to execute the following steps through the large language model: generating a query language order based on the metadata knowledge of the target business document, and querying a data platform according to the query language order to obtain a query result; and determining a matching degree between the query result and the content knowledge of the target data element. And based on the matching degree between the query result and the content knowledge of the target data element and the cost of applying the target data element to the large language model, determining the efficiency of applying the target data element to the large language model.

The invention relates to the technical field of prefabricated part modeling, in particular to an interaction system for prefabricated part steel bar parameter driving design and a modularization implementation method. Incrementally updating the engine; the model application module is used for acting the change patch sequence on the three-dimensional reinforcement model in a transaction mode and driving display refreshing; the system further comprises a rule base module and an interpretable verification module. The rule base module stores a steel bar arrangement rule and / or a standard verification rule in a constraint declaration form; the interpretable verification module is used for performing compliance verification on the three-dimensional reinforcement model or the derived quantity thereof based on the evidence data field, and outputting a violation item list; the interactive interface comprises parameter panels and a violation interactive area, and the parameter panels are displayed in groups according to component type parameters, geometric parameters, steel bar parameters and specification options and support interactive modification. According to the method, the script dependency is reduced, the dependency graph increment patch is updated in real time, the automatic specification matching and positioning are realized, and the low-cost expansion is governed by the plug-in.

A signal identification method based on priori knowledge integration and result self-adaption comprises a model construction step, a model application step and a knowledge updating step, a Bayesian network is constructed to realize preliminary pre-sorting of a large number of radio signals, and the identification efficiency is improved; a Bayesian neural network is constructed, and the cognition degree and range of signal modulation recognition are enriched; and finally, updating the Bayesian network by using a result after modulation identification, and realizing iterative integration of priori knowledge and result-adaptive signal identification in a multi-dimensional environment. According to the method, a two-stage network structure is formed, the Bayesian network is used for integrating and updating knowledge and playing a preliminary screening role, the Bayesian neural network is used for calculating a signal recognition result and the confidence coefficient of the signal recognition result, the non-binary conclusion of traditional signal recognition is broken through, and the screening speed and robustness are improved while the signal screening precision is guaranteed.

The invention relates to the technical field of data processing, in particular to a BERT and BiLSTM fusion technology-based power customer service customer appeal classification prediction method. The prediction method comprises the following steps: model training; the method specifically comprises the following steps: data preprocessing; labeling the data; judging validity; semantic enhancement; classifying business scenes; and model application: outputting a business scene classification result. According to the method, deep analysis of data of a plurality of links such as 95598 customer appeals and electricity utilization is realized, key risk points are identified, and a data basis and technical support are provided for subsequent active services.

The invention relates to the field of deep learning model application testing, in particular to an automatic driving model robustness testing method and device. Through a module-level noise injection technology, various interference factors in a real environment are simulated, and the performance of the automatic driving model is comprehensively evaluated. According to the method, the disturbance of input data is considered, the intelligent task performance of the model in key stages such as perception and prediction is further deeply analyzed, and targeted anti-noise is designed to maximize the influence on the model performance. And the anti-noise is optimized by adopting a target-based optimization method, so that the robustness of the automatic driving model is accurately evaluated. In addition, the performance of the automatic driving model in a complex environment and under noise interference can be accurately evaluated, and an important guarantee is provided for safety application of the automatic driving technology. Through the implementation of the invention, the robustness and safety of the automatic driving system can be remarkably improved, and a solid foundation is laid for the future development of an intelligent traffic system.

The invention relates to a man-machine cooperation mine ventilation intelligent control method which comprises the steps that a state space S is defined as a set of finite states, and each state is composed of carbon dioxide concentration C, gas concentration D and dust concentration E, namely S = (C, D, E); performing normalization processing on each state attribute; constructing an action space; executing an action according to the state transition probability to perform state transition; setting a reward function based on the carbon dioxide concentration, the gas concentration and the dust concentration; setting a reward weight matrix, and providing additional rewards according to expert guidance feedback; setting a discount factor; making a simulation scene which is scaled down in equal proportion, and simulating a real mine environment; initializing a simulation environment and intelligent agent neural network parameters; the fan is automatically controlled to adjust parameters through a random-greedy exploration mechanism, and the state, action and reward data are recorded; and further performing data set construction, model training, man-machine collaborative decision making and model application.

The present application discloses a text reasoning model training method, a digital human text reasoning method and related equipment, which belong to the field of artificial intelligence technology. Among them, the method includes: responding to a model training request initiated by a first terminal, obtaining a training file and a training instance identifier corresponding to the model training request; preprocessing the training file according to a pre-configured model training preprocessing tool to obtain model training data; assigning the model training data to a model learning service instance corresponding to the training instance identifier, obtaining a text reasoning model obtained by the model learning service instance training a pre-trained language model according to the model training data. In this way, the fine-tuning and training process of the pre-trained language model can be simplified, reducing the complexity of the operation, thereby making the model application easier to promote.