901results about How to "Easy to adapt" patented technology

The invention relates to the technical field of logistics transportation, in particular to a logistics transportation route optimization method and system based on digital twinning. The method comprises the following steps: constructing a digital twin logistics base through multi-source heterogeneous data fusion and dynamic logistics network modeling; carrying out regional logistics distribution feature extraction and dynamic time sequence prediction based on a digital twinborn substrate to obtain a predicted regional transportation demand; performing real-time state evaluation on the line, generating a dynamic line performance matrix, and performing vehicle resource allocation in combination with the order task priority; and carrying out multi-objective solution and dynamic adjustment on the transportation scheduling scheme to finally obtain an optimal transportation scheduling scheme. And performing iterative optimization on the digital twin model through real-time deviation analysis and a feedback mechanism, and dynamically adjusting a transportation plan to form a closed-loop optimization process. Through the logistics transportation route optimization technology, the logistics transportation efficiency is remarkably improved, the cost is reduced, and the toughness of the system is enhanced.

The invention relates to the technical field of communication optimization, in particular to a wireless communication method and system of a vehicle diagnosis system. The method comprises the following steps: identifying a plurality of signal sources in an environment and three-dimensional space data of a current position of a vehicle; performing scene interference intensity comprehensive evaluation on the plurality of signal sources in the environment to obtain a current scene interference intensity evaluation value of the vehicle; environment obstacle space layout analysis is carried out on the three-dimensional space data of the current position of the vehicle, environment three-dimensional modeling is carried out, and a vehicle environment three-dimensional point cloud model is constructed; signal multi-path propagation evolution is carried out according to the current scene interference intensity evaluation value of the vehicle and the vehicle environment three-dimensional point cloud model, and optimal signal frequency band analysis is carried out, so that optimal signal frequency band parameters are extracted; and carrying out dynamic transmission frequency modulation and signal adaptive coding based on the optimal signal frequency band parameter, and constructing a dynamic signal transmission strategy. According to the invention, efficient and stable wireless communication is realized, and the vehicle-mounted communication performance is improved.

The invention relates to the field of robot attitude control, in particular to a robot attitude control method and system based on intelligent recognition. The method comprises the following steps: continuously acquiring a real-time sandbox scene video stream based on a high-definition camera; and carrying out time sequence frame segmentation on the real-time sandbox scene video stream, and carrying out global contrast enhancement processing to obtain a global contrast optimization image sequence. Carrying out dynamic object identification on the global contrast optimization image sequence, and carrying out continuous frame optical flow motion tracking to generate a dynamic object optical flow change track; optimizing the image sequence according to the global contrast to extract scene ground and scene obstacle data; performing dynamic trajectory rendering on the scene ground and scene obstacle data based on the dynamic object optical flow change trajectory so as to construct a dynamic scene twinborn model; robot position posture parameters and user operation instructions are recognized. According to the invention, timely attitude adjustment response and accurate movement position control are realized.

The invention discloses a computing task scheduling method and device in a multivariate heterogeneous environment and a medium, and relates to the technical field of parallel computing. The method comprises the following steps: monitoring resource states of various computing resources in a multivariate heterogeneous environment in real time, and quantifying the resource states to obtain corresponding resource information; under the condition that the to-be-processed calculation task is generated in the scheduling task list, performing demand analysis on the to-be-processed calculation task to determine a task demand report; calculating the task demand report and the resource information by using a preset scheduling strategy generation model to generate an intelligent scheduling strategy; according to the intelligent scheduling strategy, various computing resources are called to execute the to-be-processed computing task; and continuously monitoring the scheduling task list and the resource state so as to update the intelligent scheduling strategy corresponding to the to-be-processed calculation task based on the scheduling strategy strategy optimization logic.

The invention discloses a knowledge graph-based nursing corpus automatic creation method, and relates to the field of artificial intelligence technology and medical information processing, and the method comprises a multi-dimensional data acquisition stage, a knowledge graph construction stage, a corpus automatic generation and updating stage, and a corpus quality control and evaluation stage. According to the automatic corpus generation method driven by the knowledge graph, dynamic generation and real-time updating of corpora are achieved by constructing an ontology structure, a corpus generation template and an updating algorithm in the nursing field; through a deep learning model and a transfer learning technology, new nursing knowledge and a diversified information structure are continuously introduced into the corpus, and the diversity of corpus content is increased.

The present invention relates to the field of medical equipment, and in particular to a body position reversal device and a method of using the same. The body position reversal device comprises a support structure and a retaining device for fixing a human body, wherein the retaining device is rotatably mounted on the support structure, and the retaining device comprises a front support mechanism for supporting the front side of the human body and a rear support mechanism for supporting the rear side of the human body, wherein a retaining space for accommodating the human body is formed between the rear support mechanism and the front support mechanism; the body position reversal device also comprises an operating mechanism or a driving device for driving the retaining device to reverse so that the human body can switch between a supine position and a prone position. The beneficial effects of the present invention are: it is convenient for the reversal and adjustment of the human body position, the device has a simple structure, the reversal is flexible and labor-saving, and the safety of the human body during the reversal process is ensured.

The invention belongs to the technical field of intelligent weighing, and more particularly relates to an intelligent self-adaptive electronic scale system based on machine learning and a data processing method, and the system comprises a composite sensor module which is used for collecting gravity, volume and shape information; the automatic calibration module is connected with the composite sensor module and is used for carrying out regular calibration and calibration according to the data of the composite sensor module; the wireless networking module is connected with the automatic calibration module and is used for wirelessly transmitting and interacting the calibrated data; the intelligent operation and maintenance module is connected with the wireless networking module and is used for receiving the transmitted data and realizing equipment state monitoring and anomaly detection; the environment adaptation module is connected with the intelligent operation and maintenance module and is used for realizing adaptive compensation in a severe environment according to a detection result; and the man-machine interaction module is connected with the environment adaptation module and is used for displaying a compensated result and realizing a user-friendly operation interface, so that high-precision and all-around weighing perception is realized.

The invention discloses a quantum dot enhanced dynamic power consumption management method, a quantum dot enhanced dynamic power consumption management system and related equipment. Aiming at the problem of insufficient optimization caused by difficulty in comprehensively, accurately and dynamically sensing the internal energy distribution and conversion process of a chip by a traditional method, the method comprises the following steps of: acquiring the quantum state of the chip in real time by utilizing a quantum dot sensing array, and constructing an adaptive power consumption prediction model by combining multi-source data fusion and feature extraction; and an optimal management strategy is generated based on a multi-objective optimization framework, an execution feedback and self-learning mechanism is introduced, and finally a complete closed-loop control system is formed. The method can be widely applied to various processor chips in the fields of high-performance calculation, the Internet of Things, artificial intelligence and the like, dynamic power consumption management of the chips is achieved through the quantum dot enhancement technology, the performance is guaranteed, meanwhile, energy consumption is minimized, the battery endurance time is prolonged, the heat dissipation cost is reduced, and the energy efficiency of the chips can be remarkably improved.

The invention discloses an energy-saving illumination control system and method for an urban illumination LED lamp group, and relates to the technical field of illumination control, and the system comprises an ambient light detection module, a traffic flow monitoring module, a time period division module, a weather information acquisition module, a weather information control module, an LED lamp group driving module, a wireless communication module, a high-precision photosensitive sensor for the ambient light detection module, a filtering and temperature compensation module, and an intensity measurement accurate data transmission module. The traffic flow monitoring module depends on geomagnetism or camera shooting, is high in precision and strong in recognition, and facilitates regulation and control through data; the time period division module accurately times and corrects time according to a clock chip, and sets illumination measures according to the time; the weather information acquisition module is networked to acquire meteorological data, and lamps are adjusted according to day conditions; and the control module multi-core microprocessor calculates illumination levels and brightness according to multi-source data to control lamp groups. According to multi-factor intelligent lamp control, energy saving is remarkable, lighting quality is good, comfort and safety are improved, remote monitoring and management can be achieved, troubleshooting is accurate and efficient, maintenance is convenient and fast, intelligent and green development of urban lighting is promoted, and the intelligent city construction requirement is met.

The invention discloses a blind person auxiliary interaction method and system based on a multi-modal large model and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a user voice instruction and an external environment image, and carrying out the preprocessing of the obtained data; inputting the preprocessed data into a pre-trained multi-modal large model to obtain an environment understanding result; integrating the environment understanding result into feedback information for voice output, and adjusting output intonations according to environment characteristics; the acquisition method of the pre-trained multi-modal large model comprises the following steps: acquiring historical multi-modal data; and inputting the historical multi-modal data into a pre-constructed multi-modal large model, carrying out fine tuning on the trained multi-modal large model through a base layer in a frozen model to obtain a trained multi-modal large model, fusing multi-modal information through the multi-modal large model, accurately identifying a user intention and a corresponding object in a complex environment, and carrying out real-time identification on the user intention and the corresponding object in the complex environment. Therefore, accurate scene description is fed back.

The invention discloses an intelligent agent control method and device and an intelligent agent, and belongs to the field of intelligent agents. The intelligent agent control method comprises the steps of generating a target task execution plan based on a three-dimensional scene graph corresponding to a target scene and a target scene graph; controlling the intelligent agent based on the target task execution plan; wherein the three-dimensional scene graph is dynamically updated based on a feedback result of the intelligent agent in the process of executing the target task execution planning, and the target scene graph is determined based on the target task. According to the intelligent agent control method, the dynamic target task plan is generated by the three-dimensional scene graph dynamically updated based on the feedback result of the intelligent agent in the process of executing the target task plan, and the intelligent agent is controlled to execute the related task based on the dynamic target task plan. Target task planning is optimized in reverse based on the actual sensing condition of the intelligent agent in the task execution process, the unknown environment is better adapted, and the task execution effect in the unknown environment is improved.

The invention relates to the technical field of unmanned aerial vehicle flight planning, and discloses an unmanned aerial vehicle cluster optimal path planning method and system, and the method comprises the steps: firstly constructing an unmanned aerial vehicle flight state prediction model and a path planning decision model, predicting the future state of an unmanned aerial vehicle, and making a decision of an optimal path; the two models are trained innovatively by adopting a dual machine learning algorithm, the accuracy of model prediction and decision making is improved, the path planning result is effectively corrected and optimized by constructing a residual error fitting model, and the planning robustness is enhanced. According to the method, the dynamic flight state, the environment uncertainty and the task target diversity of the unmanned aerial vehicle are comprehensively considered, and the unmanned aerial vehicle cluster optimal path planning instruction conforming to the actual flight condition can be generated in real time. The method improves the task execution efficiency and safety of the unmanned aerial vehicle cluster, is suitable for multiple fields of military reconnaissance, disaster rescue, logistics distribution and the like, and has a wide application prospect and an important practical value.

The invention discloses an iterative learning control optimization method for a direct current motor with non-repetitive disturbance, and relates to the technical field of direct current motor control, and the method comprises the steps: lifting a nominal model of a nonlinear system to a high-dimensional linear space through a deep Koopman operator, and obtaining the description of a high-dimensional state space model of the nonlinear system; converting the state space model into a linear repetition process model, and obtaining a linear matrix inequality condition of system convergence in a high-dimensional space by using a two-dimensional iterative learning control method; further, the intelligent agent is trained in a high-dimensional state space model iterative learning control system with model mismatch and a non-repetitive uncertainty nonlinear system, and finally the intelligent agent is applied to an actual system. The control law gain obtained by the method can better adapt to an original nonlinear system, a deep reinforcement learning algorithm is designed to compensate non-repetitive disturbance, and zero-error tracking of expected output is basically achieved.

The invention discloses a resource allocation method based on a game theory and a genetic algorithm. The method comprises the following steps: constructing a communication model of communication equipment and obtaining channel capacity from a base station to user communication equipment; constructing a game model of an optimal channel access strategy according to the channel capacity from the base station to the user communication equipment; and obtaining an optimal solution of the game model based on a genetic algorithm, and taking the optimal solution as a resource allocation result. According to the method, the interference and the user communication equipment are used as two parties of the game for modeling, so that the method can dynamically cope with a complex and changeable electromagnetic environment. Compared with a traditional algorithm which is poor in performance under the conditions of high load and multiple devices, the resource allocation method can better adapt to complex scenes, and therefore the efficiency and reliability of spectrum management are improved.

The invention discloses a path optimization method and system for unmanned aerial vehicle logistics distribution, and relates to the technical field of unmanned aerial vehicle logistics distribution, and the method comprises the following steps: obtaining all executable distribution paths, screening an unmanned aerial vehicle logistics distribution default execution path, obtaining unmanned aerial vehicle distribution state parameters, and analyzing unmanned aerial vehicle logistics distribution state characterization parameters. Path influence parameters of default distribution sub-paths are collected, unmanned aerial vehicle default distribution sub-path optimization label information is judged, all standby sub-paths are counted, logistics adaptation execution priority values of all the standby sub-paths are analyzed, and therefore unmanned aerial vehicle logistics distribution optimal sub-paths are screened and optimized execution is carried out. The unmanned aerial vehicle distribution efficiency and safety can be improved, complex and changeable meteorological conditions and obstacle conditions can be effectively handled, the distribution time and energy consumption are reduced, the adaptability of the unmanned aerial vehicle in a complex environment is enhanced, and smooth completion of a distribution task is ensured.

The invention discloses an active learning-based electric power knowledge graph construction method and system, and relates to the technical field of electric power market transaction data analysis, and the method comprises the steps: collecting data, cleaning the collected data, generating word prediction task data of an electric power transaction scene, and training an electric power field word embedding model; generating an entity relationship training sample, inputting a word embedding model, performing entity relationship label prediction through an entity relationship joint extraction model, extracting a high-quality sample based on active learning to perform part-of-speech tagging, and training the model based on a tagged sample; and applying the trained entity relationship joint extraction model to power transaction data to construct a knowledge graph, performing manual correction and entity unification, and storing the knowledge graph into a Neo4j database. According to the method, active learning and deep learning are combined, so that the sample labeling cost is effectively reduced, and meanwhile, the model performance is ensured.

The utility model discloses a flexible dexterous hand touch sensing electronic skin based on an FPC (Flexible Printed Circuit), which comprises a palm FPC carrier plate, and a palm longitudinal electrode and a palm transverse electrode which are arranged on the palm FPC carrier plate, and the staggered points of the palm longitudinal electrode and the palm transverse electrode form a palm touch sensing capacitor unit. The finger longitudinal electrodes and the finger transverse electrodes are arranged on the finger FPC carrier plate, staggered points of the finger longitudinal electrodes and the finger transverse electrodes form a finger touch sensing capacitor unit, the electronic skin has a touch sensing function and can simulate the touch of a human body, so that the mechanical arm has more intelligent and flexible operation capability, and the mechanical arm is more flexible to operate. The external environment and object characteristics can be sensed more accurately, the operation of the manipulator can be controlled more accurately, and the operation precision and safety are improved.

The invention relates to the technical field of video source switching, and discloses an intelligent video source switching system and method for a director switching station. The method comprises the following steps: acquiring an input video stream of a current video source through a director switching station, and performing N-gram feature vector calculation and inter-frame difference analysis to obtain video frame segmentation data; performing scene analysis on the video frame segmentation data to obtain a scene feature signature; performing spatial-temporal feature extraction and fusion on each video frame in the input video stream according to the scene feature signature to obtain a scene spatial-temporal fusion feature set; inputting the scene space-time fusion feature set into an LSTM-based lightweight time sequence convolutional network model to carry out video switching behavior prediction so as to obtain video switching behavior prediction data; and inputting the video switching behavior prediction data into a double-depth Q learning model based on a Markov decision process to carry out video source switching decision to obtain a video source switching decision result, thereby improving the intelligent video source switching accuracy of the director switching station.

The invention provides a sewer internal defect detection method and system based on YOLOv11 improvement, and the method achieves the dynamic weight fusion of multi-level features through a self-adaptive feature fusion module, and improves the detection capability of a model for small targets and complex backgrounds. The selectivity of channel characteristics is improved through an SENet attention mechanism, and background interference is reduced; and introducing an MPDIOU loss function to improve bounding box regression loss. The performance of the improved model in detection tasks of sewer defects such as cracks, obstacles, corrosion, deformation and the like is remarkably superior to that of original YOLOv11, and particularly key indexes such as mAP50 (average precision), Box precision (P), recall rate (R) and the like are remarkably improved. According to the invention, efficient and accurate detection of multiple types of defects in the sewer can be realized, and a better solution is provided for maintenance and management of the sewer.

The invention relates to the technical field of artificial intelligence, and discloses a multi-modal model training fine-tuning optimization method based on artificial intelligence, which comprises the following specific steps: preparing and preprocessing data, collecting a large-scale multi-modal data set, constructing an image text data set containing one million high-quality images and text description accurately corresponding to the images, and performing fine-tuning optimization on the image text data set. According to the method, data are subjected to comprehensive and meticulous cleaning operation, noise data and mistakenly labeled data in the data are strictly removed, so that the accuracy and reliability of the data are ensured, and the effective utilization rate of the data can be increased by at least 20% through data cleaning; wherein the image data is screened, blurred, low-resolution and unclear-content images are removed, it is ensured that each image can clearly convey specific visual information, and text description, grammar error checking, spelling error and semantic ambiguity parts are corrected or deleted.

The invention relates to the technical field of agricultural microbial agents, in particular to bacillus velezensis as well as a separation method and application thereof. The bacillus velezensis is preserved in the China General Microbiological Culture Collection Center, the preservation date is May 17, 2024, the preservation number is CGMCC No.30687, the preservation address is No.3, Yard 1, Beichen West Road, Chaoyang District, Beijing, the postcode is 100101, and the bacillus velezensis is classified and named as bacillus velezensis. The bacillus velezensis separated from the soil of the Ningboo garden of the Academy of Agricultural Sciences in Yitai City of Shandong Province or the fermentation inoculant thereof can be simultaneously used as a preparation raw material of a growth promoting agent, a yield increasing agent, a soil conditioner and a bio-organic fertilizer, and has multiple application scenes.

The invention belongs to the technical field of mariculture, and particularly relates to a flexible deep sea truss aquaculture net cage which comprises a flexible net cage system, a stock bin barrel system is arranged in the middle of the flexible net cage system, and an overwater suspension corridor assembly is arranged between the top end of the flexible net cage system and the top end of the stock bin barrel system. An anchor cable system is arranged on the outer side of the circumference of the flexible net cage system. By designing the flexible net cage system, the weight of the culture net cage is increased by filling viscoplastic filling materials through the bottom annular thick supporting pipes and the stand columns, the gravity center of the net cage is reduced, and the safety of the culture net cage in the putting process and the stability in actual operation are improved; other supporting pipes, supporting pieces, stand columns in the stock bin barrel system and transverse annular supporting pipes are filled with seawater, net cage throwing is assisted, and balance weight is simple; due to the integral structural design, the net cage has seawater corrosion resistance, is firm in structure, can bear the impact of large waves and seawater, has certain water permeability and can keep the circulation of seawater.

The invention discloses a time series anomaly detection method based on a neural network, and the method comprises the steps: obtaining to-be-detected multivariable time series data, and inputting the multivariable time series data into a spatial-temporal feature fusion unit, performing time domain information and attribute information analysis on the multivariable time sequence data by a time domain convolutional network and a graph attention influence network in the spatial-temporal feature fusion unit, and obtaining spatial-temporal fusion features through feature fusion; decomposing the multivariable time sequence data by adopting a self-adaptive time sequence decomposition algorithm to obtain a trend sequence and a periodic sequence; inputting the space-time fusion feature, the trend sequence and the periodic sequence into a time sequence reconstruction unit to obtain a decoding feature; performing anomaly detection on the decoding features through an anomaly detection unit to obtain an abnormal state of the multivariable time series data; according to the method, the reconstruction deviation between the potential abnormal data and the reconstruction data can be expanded, and the potential abnormal data in the multi-dimensional time sequence can be rapidly and accurately detected.

The invention provides a real-time rendering method for an augmented reality game, and relates to the field of three-dimensional reconstruction, and the method comprises the steps: obtaining the rendering scene description of a game object in a three-dimensional model; generating a rendering fusion feature of the game object according to the rendering scene description, and performing subdivision detection on the rendering fusion feature to obtain a texture element index of the game object in the virtual object model; determining a target scene rendering image of the game object in the rendering coloring model, and determining a rendering embedding identifier corresponding to the target rendering range according to the target scene rendering image; determining a rendering structure level of the game object in the target rendering area according to the reference pose information, and determining a rendering interaction attribute of the game object during rendering task distribution according to the rendering structure level and the texture element index; the game object is rendered in real time according to the rendering embedded identifier and the rendering interaction attribute, and the game scene is generated, and the real-time rendering performance of the augmented reality game can be improved under the influence of visual dislocation generated by the compatible rendering effect.

The invention belongs to ocean engineering, and discloses a seabed multifunctional freely-adjustable crawler belt which comprises a main frame, at least one pair of telescopic oil cylinders, at least one pair of outer supporting legs, at least one pair of inner supporting legs, at least one connecting rod, at least one overturning oil cylinder and at least one overturning oil cylinder connecting weldment. Wherein the main frame is hinged with the telescopic oil cylinder, the outer supporting leg and the inner supporting leg through pin shafts; the connecting rod is provided with at least three reamed holes which are respectively connected with the crawler belt assembly, the outer supporting leg and the inner supporting leg through bolts; the overturning oil cylinder is mounted on the crawler beam through the overturning oil cylinder connecting weldment and is connected with the connecting rod through the bolt; according to the invention, flexible adjustment of the crawler belt in multiple directions is realized. Particularly, due to the synergistic effect of the telescopic oil cylinder and the overturning oil cylinder, the width and height of the crawler belt can be adjusted under different terrain conditions, obstacles can be overcome through the rotating action, meanwhile, the equipment can better adapt to the complex and changeable seabed environment, and the operation efficiency and safety are improved.

The invention belongs to the field of artificial intelligence and deep learning, and provides a small sample continuous learning method and system based on adaptive adaptation layer selection. The small sample continuous learning method based on adaptive adaptation layer selection comprises the following steps: pre-training a singular value of a linear weight; freezing a pre-training linear weight matrix corresponding to the knowledge sensitive component; adaptively determining an adaptation layer; multiplying the adapter matrix based on the adaptation layer by the training sample features of the current incremental adaptation training stage to obtain redundancy capacity features; and the small sample playback data is obtained again, singular value decomposition, adaptive layer adaptive determination and incremental adaptive training operation are performed in sequence based on the updated pre-training linear weight matrix, and learning is stopped until the continuous learning model reaches a set requirement, so that the trained continuous learning model is utilized to execute a classification task. According to the method, dynamic adapter selection for minimizing old knowledge interference is realized, and the classification accuracy of a small sample continuous learning model is guaranteed.

The invention discloses a visual positioning method and system based on multi-modal information fusion, and belongs to the field of computer vision. The method comprises the following steps: acquiring an RGB image and a depth image in the same scene, extracting semantic features from the RGB image through a multi-modal feature extraction network, and extracting structural features from the depth image; performing weight distribution and deep fusion on the semantic features through a feature balance module to obtain final multi-modal fusion features; predicting three-dimensional scene coordinates of each two-dimensional pixel point and uncertainty corresponding to the three-dimensional scene coordinates on the basis of the final multi-modal fusion features; and calculating the six-degree-of-freedom pose of the camera based on the predicted coordinates. According to the method, the problems of texture dependence and structure fuzziness in the existing single-mode visual positioning method are solved.

The invention discloses a named entity recognition method and system based on a knowledge enhancement pre-training model, relates to the technical field of named entity recognition, and aims to solve the problem that an existing training model cannot perform named entity recognition more accurately. According to the method, the knowledge enhancement pre-training model is introduced, so that the model can learn more priori knowledge and semantic information, the generalization ability of unseen text data is improved, the interpretability of the model is enhanced through the detailed performance evaluation and optimization process, the working mechanism of the model is beneficially understood, and the working efficiency of the model is improved. Therefore, the model is better adjusted and optimized, the generalization ability of the optimized model is also improved, the model can better adapt to different application scenes and data sets, the generation of the monitoring log enables performance analysis and problem tracking to be more convenient, the continuous optimization of the model performance is facilitated, and the optimization efficiency is improved. A standard knowledge enhancement training model can be improved according to user feedback on a target application terminal.