45results about How to "Raise the importance" patented technology

The invention relates to the field of chlorophyll a concentration prediction, and discloses a 1D-DSCAM-based subsurface chlorophyll a concentration inversion method, which comprises the following steps of: obtaining sea surface temperature and sea surface chlorophyll a concentration data of satellite remote sensing and subsurface chlorophyll a concentration, subsurface temperature and salinity profile data of a biogeochemical buoy; carrying out preprocessing, constructing a data set, and inputting a training set into a 1D-DSCAM-GRU deep learning model to carry out model training; the model comprises an Embedding module, a 1D-DSCAM module and a multi-layer GRU module; and preprocessing sea surface temperature and sea surface chlorophyll a concentration data obtained by satellite remote sensing of a sea area to be predicted and subsurface layer temperature and salinity profile data obtained by a biogeochemical buoy, and inputting the data into the qualified model for subsurface layer chlorophyll a concentration prediction. According to the method disclosed by the invention, the prediction precision can be improved.

The invention provides an evolutionary neural architecture searching method and system based on similarity agent assistance, and the method comprises the steps: 1, initializing an architecture population, and selecting an architecture with the best performance as an initial reference architecture; 2, constructing a graph neural network variant as a feature extractor; 3, constructing an agent model, and training the agent model through a joint loss function; 4, the high-potential architecture is reserved according to the fitness value, authenticity performance evaluation is carried out on the high-potential architecture, and an evaluation result is added into the training set; combining the current population with the high-performance architecture predicted and screened by the proxy model, and updating the population through an environment selection strategy; and step 5, repeating the step 3 and the step 4 until the population performance converges, and finally outputting a global optimal architecture. According to the method, the high-performance neural network architecture can be quickly searched under limited computing resources, and an efficient and intelligent novel solution is provided for automatic design and optimization of the neural network.

The invention relates to an underwater image detection system and method based on a YOLOv8s model, and the system comprises an underwater image collection and preprocessing subsystem which is used for collecting underwater image data and carrying out the preprocessing; the target detection subsystem is used for carrying out target detection by adopting an improved YOLOv8s model, and the improved YOLOv8s model is used for obtaining a feature map by adopting a mode of combining a denoising mechanism and a dynamic adjustment receptive field mechanism based on the preprocessed underwater image data, carrying out feature enhancement by adopting a dual attention mechanism based on the feature map, and carrying out target detection by adopting an improved YOLOv8s model; performing feature fusion and detection to obtain a target detection result; the performance monitoring and evaluation subsystem is used for monitoring and evaluating the target detection result; and the detection result display and output subsystem is used for outputting and displaying the target detection result. Compared with the prior art, the method has the advantages of improving the depth and precision of feature extraction, improving the underwater image detection performance and the like.

The invention discloses a user learning behavior analysis system and method based on a knowledge graph, and relates to the technical field of data analysis, the system comprises an evaluation test question labeling module, a knowledge graph construction module, a user investigation evaluation unit and a learning recommendation module; the evaluation test question labeling module is used for performing knowledge point division on all evaluation test questions and labeling the investigation proportion of each knowledge point in the evaluation test questions; the knowledge graph construction module is used for screening all knowledge points involved in user learning contents, constructing a knowledge graph and analyzing a pre-repair relationship between the knowledge points; the user investigation and evaluation unit is used for investigating and evaluating the mastering degree of a user on each knowledge point in the knowledge graph; and the learning recommendation module is used for screening recommended learning knowledge points according to the mastery degree of the user on each knowledge point in the knowledge graph, calculating and analyzing the recommendation priority of each recommended learning knowledge point and the adaptation degree of each evaluation test question, and synchronously recommending the knowledge points and the evaluation test questions to the user.

The invention discloses a thermal generator set load prediction system based on machine learning, and the system overcomes the defects of a conventional load prediction method through an end-to-end solution composed of a comprehensive data collection module, a multi-level feature engineering module, a multi-model integration module, a self-adaptive optimization module and the like. The system collects multi-dimensional data from a thermal generator set control system, an environment monitoring system, a fuel detection system and a historical database, wherein the multi-dimensional data comprises load data, environment data, fuel characteristics and equipment operation data. According to the multi-dimensional data integration mode, the model not only depends on single historical load data, but combines multiple influence factors such as environment, fuel and equipment states, the problem that a traditional method depends on a single data source is solved, the load prediction precision is effectively improved, and the load prediction efficiency is improved. And the adaptive capacity of the prediction model to different environment conditions and equipment states is stronger.

The invention discloses a new energy data entry method, system and device and a storage medium, and relates to the technical field of data entry, and the method comprises the steps: obtaining machine account data, and obtaining a proportion emphasis parameter; acquiring a period consumption curve, and acquiring a data entry period; recording machine account data of the new energy based on the data recording period; the method is used for solving the problems that in an existing new energy machine account data input method, when machine account data of multiple kinds of new energy is continuously input for a long time, the input period of each machine account data cannot be controlled based on the consumption cost and the consumption proportion of each kind of new energy, and therefore after the machine account data is input, the machine account data cannot be continuously input. The problems that the data processing time is increased and the data efficiency is reduced due to the fact that workers are assisted to carry out effective data analysis are solved.

The invention relates to the technical field of large language model processing, in particular to a keyword extraction method based on the understanding ability of a large language model. According to the patent, the TF-IDF value of the vocabulary is taken as a starting point, the TF-IDF value is continuously adjusted by means of a large language model, at the moment, the TF-IDF value does not belong to an original TF-IDF definition, but is a value reflecting the importance of the vocabulary after being optimized by the large language model, and the patent is recorded as an importance weight; the method mainly aims at forming a method for continuously correcting the importance of vocabularies by means of a large language model, continuously expanding the vocabularies, forming a keyword extraction method driven by a large model technology, fully utilizing the semantic comprehension ability of the large language model, and fully utilizing the characteristic of high speed of traditional keyword extraction. The user finally deploys the keyword extraction capability based on the dictionary word weight, the keyword extraction capability is provided for the user to use, the speed is far higher than the keyword extraction capability of a large language model by means of a prompt instruction, and the effect is stable.

The invention provides a carbonate rock lithology identification method based on machine learning, and the method comprises the steps: obtaining the hyperspectral data of a carbonate rock sample through an ASD spectrometer, and carrying out the preprocessing of the hyperspectral data; a mixed feature selection method is adopted, firstly, feature wavebands in the hyperspectral data are selected, then a random forest method is adopted for feature importance sorting, and features with high importance are selected; constructing a carbonate rock lithology identification model based on the selected features, wherein model parameters are determined by a machine learning algorithm; and predicting the mineral content in the carbonate rock according to the lithology identification model so as to identify the lithology of the carbonate rock. According to the method, on the basis of carbonate rock hyperspectral data, feature selection is carried out by adopting a mixed feature selection method after preprocessing, a lithology identification model is established on the basis, model parameters are determined through a machine learning mode, mineral component content is predicted, and therefore carbonate rock lithology identification and classification are achieved. And the identification precision and efficiency are greatly improved.

The embodiment of the invention provides a communication method and device, communication equipment, a communication system and a storage medium. The communication method comprises: sending first information, the first information being used for reporting a data volume related to a data category in at least one LCG. According to the embodiment of the invention, reporting of data volumes with different importance can be realized.

The invention relates to image data processing, and discloses a non-motor vehicle illegal behavior efficient monitoring method and system based on deep learning, so as to improve the overall performance of recognition. The method comprises the following steps: carrying out feature extraction in a down-sampling process step by step by using a bcheck module of MobileNetV3; in a Neck network layer, a DFSM unit is added in a branch for feature fusion of a C3 module; the DFSM unit comprises an AFA Conv subunit and a CSA Conv subunit; based on an AFA Conv subunit, introducing double attention of a space and a channel as a time domain to enable a local modeling part to have global information; the DFSM is added on the basis of a C3 module, the importance of time domain and frequency domain features in a learning feature graph can be effectively enhanced, key features of a target are better captured by enhancing features with higher distinction degree, and the performance and robustness of the model are improved.

The invention discloses a series-parallel robot kinematics calibration method for working area optimization. The method comprises the following steps: analyzing a geometric error source influencing the tail end precision of the hybrid robot, and establishing a kinematic model containing error terms; a laser tracker is used for collecting the difference value between the real coordinates of the tail end point and the output coordinates of the error model in the reachable range of the hybrid robot to generate a residual function; according to the distribution of the measurement points in the working area in the maximum reachable range of the hybrid robot, weighting operation is carried out on the residual function, and an improved particle swarm algorithm fitness function is generated; using an improved particle swarm algorithm to iteratively identify geometric errors of the hybrid robot; the identified error is compensated to a controller, and kinematics calibration of the robot is completed; the kinematics calibration method provided by the invention is simple and efficient, and can be applied to most parallel and hybrid robots.

The invention discloses a P-glycoprotein inhibitor and substrate prediction method based on multi-modal contrast learning. The method comprises the following steps: constructing a data set of a P-glycoprotein inhibitor and a substrate; constructing a P-glycoprotein inhibitor and substrate prediction model by using a deep learning method; inputting the comparison loss and the classification loss into the constructed P-glycoprotein inhibitor and substrate prediction model, combining the comparison loss and the classification loss to obtain a total loss function, and training and optimizing parameters of the P-glycoprotein inhibitor and substrate prediction model through the total loss function; and inputting data of a compound to be predicted into the optimized P-glycoprotein inhibitor and substrate prediction model, outputting a final classification result, and judging whether the compound is the P-glycoprotein inhibitor and the substrate or not. According to the method, the prediction precision and generalization performance of the model are improved, the interpretability of the model is realized, and a reliable scientific basis is provided for molecular design in drug development.

The embodiment of the invention provides a data processing method and device, electronic equipment and a storage medium, and the data processing method comprises the steps: obtaining seat recording data; if the seat recording data corresponds to at least two speakers and the at least two speakers comprise a seat user and a non-seat user, determining a target time period corresponding to the non-seat user in the seat recording data; acquiring client recording data; and according to the coincidence rate of the target time period and the speaking time period of the customer and the similarity between the voiceprint of the non-seat user and the voiceprint of the customer, determining whether audio data of the customer is serially connected into the seat recording data. Therefore, the detection accuracy can be improved when the crosstalk source in the seat recording data is detected.

The invention relates to the technical field of archive management, and discloses an archive management method and system.The method comprises the steps that archive basic data are obtained, and the archive basic data comprise archive forming time, archive content and archive confidentiality deadline; performing classification score calculation according to the archive basic data to obtain archive classification scores; based on the archive classification score and a preset classification scoring standard, obtaining an archive archiving category; calculating an importance rating factor according to the archive basic data and the archive archiving category; performing importance score calculation based on the importance rating factor to obtain an archive importance score; and according to the archive importance score and a preset storage period standard, selecting a storage period for archiving. According to the method, the file storage efficiency can be improved, and the retrieval speed is increased.

The invention discloses a no-reference light field image quality evaluation method based on a visual converter, and the method comprises the steps: extracting a sub-aperture image array of a distorted light field image, and extracting a central sub-aperture image and a sub-aperture image array of which the central angle resolution is a * a; inputting a central sub-aperture image of the distorted light field image into a space blocking module to obtain a distorted light field image space block rich in space information, and inputting a sub-aperture image array of which the central angle resolution is a * a of the distorted light field image into an angle blocking module to obtain a distorted light field image angle block; obtaining multi-layer features on a spatial domain of the distorted light field image, obtaining multi-layer features on an angle domain of the distorted light field image, and splicing the multi-layer features to obtain fusion features rich in spatial features and angle features; and carrying out regression on the fusion features by utilizing a quality score prediction network to obtain a quality score of the distorted light field image, and training the network by utilizing gradient back propagation according to a configured related network model and training parameters.

The invention relates to a sensor system, a sleep space and a method of optimizing sleep quality and comfort in a sleep space. The sensor system is used for monitoring and optimizing personal sleep quality, comfort, health and welfare and comprises a radar sensor, a processor, a communication device and a control component of environmental equipment. Configuring a sleep space with the sensor system; a sensor system is employed to perform a method of optimizing sleep quality and comfort in a sleep space. Adjustment of the environmental device to facilitate returning of the individual to a calm and deep sleep state is initiated by controlling the environmental device control component based on data collected by the radar sensor and / or data and / or control signals processed by the processor.

The embodiment of the present invention discloses a feature extraction method, device, vehicle orientation determination method, and vehicle-mounted terminal. The method includes: determining the width-to-height ratio of the vehicle to be detected according to the relative position relationship between the vehicle area and the license plate area; extracting a feature map of the vehicle area through a feature extraction layer in a vehicle structure line detection model; regressing the feature map according to the width-to-height ratio through a regression layer in the vehicle structure line detection model to determine the structure line information of the vehicle to be detected in the vehicle area; determining the orientation information corresponding to the structure line information according to the correspondence between the preset orientation information and the structure line information as the orientation information of the vehicle to be detected; wherein each feature vector of the feature map is obtained by superimposing an attention factor; the attention factor is determined according to the similarity between the feature vector and the global semantic features of all feature vectors in the semantic group. Applying the solution provided by the embodiment of the present invention can more accurately determine the orientation information of the vehicle.

The invention relates to a port storage yard container storage time prediction method and device based on a self-attention mechanism, and the method comprises the steps: calculating the correlation degree between each characteristic variable and the storage time through gray correlation degree analysis; feature variables with high correlation are screened out based on the correlation degree to serve as prediction input, a complex dependency relationship and long program column features among modeling variables of the multi-head self-attention network are introduced, nonlinear mapping and fitting are achieved in combination with a full-connection network, and therefore the accuracy of a prediction result is effectively improved; in the model training process, a loss function with measurement monotonous consistency is designed, a constraint model keeps monotonous sequence consistency of output results on the premise that prediction precision is not lost, and the container turnover and secondary transfer risks caused by prediction sequence deviation in storage yard operation are reduced. And the model prediction performance is comprehensively evaluated from two dimensions of prediction precision and monotone consistency. According to the method, prediction precision and application practicability are both considered, and reliable time information can be provided for storage optimization of the container in the storage yard.

The present invention relates to the field of chlorophyll a concentration prediction, and discloses a subsurface chlorophyll a concentration inversion method based on 1D-DSCAM, comprising the following steps: obtaining satellite remote sensing sea surface temperature and sea surface chlorophyll a concentration data and subsurface chlorophyll a concentration, subsurface temperature and salinity profile data of biogeochemical buoys, and preprocessing, constructing a data set, and inputting the training set into a 1D-DSCAM-GRU deep learning model for model training; the model comprises an Embedding module, a 1D-DSCAM module and a multi-layer GRU module; after preprocessing the sea surface temperature and sea surface chlorophyll a concentration data obtained by satellite remote sensing of the sea area to be predicted and the subsurface temperature and salinity profile data obtained by the biogeochemical buoys, the data are input into a qualified model for subsurface chlorophyll a concentration prediction. The method disclosed by the present invention can improve the accuracy of prediction.

This application discloses a resource processing method, apparatus, device, medium, and program product for virtual characters. By triggering an operation on a first virtual building to consume a first resource and generate a second resource, and triggering an operation on a second virtual building to consume the second resource and generate a third resource, the total amount of the third virtual resource meets the conditions to trigger the activation of the upgrade control of the second virtual building. By triggering an operation on the upgrade control of the second virtual building, the second virtual building is upgraded, thereby increasing the number of interactions between the player and the system during the game and improving the interactivity between the game and the player.

The invention provides an automatic testing method and device based on multiple intelligent algorithms and electronic equipment. The method comprises the following steps: arranging each single intelligent algorithm in a multi-intelligent algorithm into a plurality of test cases for testing the corresponding algorithm according to a preset protocol; according to a preset association degree table, determining the association degree between any two single intelligence algorithms in the multi-intelligence algorithm; according to the correlation degree, calculating the correlation degree quantity of each single intelligence algorithm in the multi-intelligence algorithm; the correlation degree quantity of any single intelligent algorithm is a comprehensive index obtained through comprehensive calculation based on the correlation degree between any single intelligent algorithm and other single intelligent algorithms except the single intelligent algorithm; and according to the association degree quantity, determining a scheduling sequence of cooperative work of each single intelligent algorithm in the multi-intelligent algorithm, and according to the scheduling sequence, scheduling the test case of each single intelligent algorithm to test the corresponding algorithm to obtain a test result of the cooperative work of the multi-intelligent algorithm.

The invention relates to an intelligent driving simulation data storage method and device oriented to a hybrid memory and a medium, and belongs to the technical field of intelligent driving. The method comprises the steps that simulation data are graded based on attributes of the simulation data, and grades corresponding to the simulation data are obtained; classifying the simulation data based on the access frequency of the simulation data to obtain types corresponding to the simulation data; and storing the simulation data in the DRAM or the NVM based on the preset weight, the grade and the type. According to the intelligent driving simulation data storage method oriented to the hybrid memory provided by the invention, the limitation on intelligent driving simulation under a single memory can be made up by utilizing a hybrid memory architecture formed by two storage media, namely, the DRAM and the NVM, and utilizing respective advantages of different storage media, so that the intelligent driving simulation can be realized. By optimizing the data storage strategy, the data processing capability of intelligent driving simulation is improved, so that the performance and efficiency of the simulation system are improved.

The invention discloses an intelligent power supply station work order scheduling method and system, a storage medium and an electronic terminal. The method comprises the following steps: collecting electric energy data, load data and renewable energy data in a power system in real time; pre-processing the electric energy data and the load data, wherein the pre-processing comprises data interpolation and abnormal data elimination; screening out electric energy data and load data with high attention weight from the preprocessed electric energy data and load data by adopting an attention mechanism; predicting work order data to be scheduled by using a recurrent neural network (RNN) based on the attention mechanism, and outputting a first prediction result; predicting the renewable energy source data by adopting a Benders decomposition algorithm, and outputting a second prediction result; and making a power supply station work order scheduling strategy by referring to the first prediction result and the second prediction result. By utilizing the method, the importance and the processing efficiency of the data are improved.

The invention belongs to but is not limited to the technical field of artificial intelligence, and discloses an Alzheimer's disease diagnosis method based on electroencephalogram signal channel selection and a gating circulation unit, which selects an electroencephalogram channel through a particle swarm algorithm, reduces redundant information in electroencephalogram signal data, and improves the accuracy of electroencephalogram data analysis; feature extraction is carried out on the electroencephalogram signal data through principal component analysis, and the importance and distinction degree of features are improved; and finally, inputting the electroencephalogram signals into a gated circulation unit neural network for classification prediction, thereby reducing the number of electroencephalogram channels and reducing the dimension of data input. And the calculation efficiency is improved while the classification performance is ensured. According to the method, the classification performance of the Alzheimer's disease patients and the healthy subjects is improved, and accurate and efficient classification of the Alzheimer's disease patients and the healthy subjects is achieved.

This invention discloses a heuristic dynamic memory weighting and recall reordering method, comprising six steps: initial impression value calculation, Ebbinghaus forgetting curve modeling, recall depth parameterization, multi-dimensional independent sorting, multi-dimensional result fusion, and recall-triggered impression value inversely proportional increment. This invention simulates the natural decay of memory through an 8-stage Ebbinghaus forgetting curve, achieves a recall-as-reinforcement effect through an inverse impression value increment mechanism, comprehensively considers semantic similarity, temporal freshness, and memory importance through multi-dimensional reordering, and flexibly adjusts the breadth and depth of recall through recall depth parameterization. This invention provides two forgetting curve implementation methods: discrete-stage lookup table method and continuous curve calculation method (including exponential decay type and power-law decay type), suitable for different application scenarios. This invention significantly improves the intelligence level and anthropomorphism of AI long-term memory systems, enabling AI to perform natural memory recall like humans.

The invention discloses a business data caching method and device, equipment and a medium. The method comprises the following steps: regularly obtaining related data of each business data access event within a preset duration before a current moment from an access log of each cache database, and determining a popularity value ranking of each business data content identifier; the method comprises the following steps: after to-be-cached business data is received, determining a target cache database corresponding to the to-be-cached business data in each cache database according to business data content identifiers of the to-be-cached business data and popularity value ranking of each business data content identifier, and caching the business data to be cached into the target cache database. According to the embodiment of the invention, the importance and reading requirements of the business data needing to be stored can be measured based on the business data content identifiers of the business data needing to be stored and the popularity value ranking of each business data content identifier, and the business data needing to be cached is cached.

The embodiments of this specification relate to the field of artificial intelligence, and specifically disclose a method, device and storage medium for object type identification of a business object, the method comprising: receiving business data of a target business object; obtaining a pre-constructed object type identification model, the object type identification model comprising two or more classifiers associated in sequence; wherein the classifier is constructed based on an unbalanced sample set configured with sample weights; the sample weights corresponding to the training of other classifiers except the first classifier are determined based on the prediction results of the previous classifier of the corresponding classifier; the business data are processed by each classifier of the object type identification model to obtain the processing results of the business data by each classifier; based on the processing results of the business data by each classifier, the object type of the target business object is determined, thereby further improving the accuracy of object type identification of the business object.

A feature vector dimension compression method and apparatus, and a device and a medium. The method comprises: acquiring a training sample; training a pre-built classification model by using the training sample, so as to obtain a false positive sample and a positive sample; respectively determining a first important feature dimension of the false positive sample and a second important feature dimension of the positive sample; and determining a dimension-compressed training sample by using the first important feature dimension, the second important feature dimension and the training sample. Therefore, redundant features can be deleted, such that the processing speed of feature vectors is increased. In addition, after an interference feature is deleted, a classification model is trained by using a compressed feature vector, such that the false positive probability of the classification model can be reduced and the importance of a key feature can be improved, thereby improving the sensitivity of the classification model to a black sample and improving the detection rate of malicious files by the classification model.

The invention discloses an energy storage system safety monitoring and control system for a comprehensive energy station, and relates to the technical field of system safety monitoring. In order to solve the technical problems of battery thermal runaway, low intelligent degree and insufficient integrated management of the application of the existing energy storage system in a micro-grid in the prior art, the invention provides the technical scheme that the energy storage system safety monitoring and control system for the comprehensive energy station. The system comprises an operation monitoring and integrated management module which is used for monitoring power input and output of an energy storage system, power grid interaction parameters, capacity and energy utilization rate; the safety monitoring and early warning module is used for monitoring preset parameters in the energy storage equipment and in the operation environment; and the data analysis and optimization control module is used for acquiring data of operation parameters of the load system and carrying out scheduling and optimization control on load behaviors of the load system according to real-time data. The method is suitable for safety monitoring and control of an energy storage system of a comprehensive energy station.

The invention belongs to the technical field of market information visualization analysis, and discloses a market information visualization and analysis system based on a self-adaptive equivalent amplitude reference. The system comprises a data preprocessing fluctuation calculation module, a dynamic equivalence amplitude reference generation module, an equivalence line generation maintenance module, a chip distribution dynamic calculation module and a market form analysis module, and is characterized in that based on an original market data set, an equivalence line amplitude is adjusted to carry out adaptive calculation on an object market volatility to obtain a volatility data set; the method comprises the following steps: calculating and adjusting an equivalent amplitude reference value based on a volatility data set to obtain a multi-amplitude equivalent line sequence data set, obtaining an equivalent line sequence data set and a chip distribution data set according to a multi-amplitude equivalent line, and comprehensively analyzing data and visually displaying. The method has the remarkable advantages of high market analysis accuracy, high chip distribution timeliness and good market noise data filtering effect.