160results about How to "Improve real-time response performance" patented technology

The invention relates to the technical field of electric power design, in particular to an intelligent dispatching system of a transformer area power supply grid. According to the method, a self-adaptive sampling strategy of real-time load fluctuation and distributed energy output characteristics is adopted; when the system detects the rapid change or abnormal fluctuation of the load, the data acquisition frequency is automatically improved, so that the capture of key information is ensured; when the load is stable, the sampling frequency is reduced, and the collection of redundant data is reduced; adaptive sampling can dynamically adjust the acquisition frequency, it is guaranteed that important data are not lost at the critical moment, and meanwhile the system burden is reduced; a hierarchical data processing architecture is adopted, data processing is divided into an edge layer and a cloud layer, the edge layer is responsible for conducting primary processing on data collected in a transformer area, including denoising, feature extraction and the like, and the data quality is guaranteed; only the key data subjected to primary processing is uploaded to a cloud end for data analysis and decision optimization; therefore, the burden of data transmission and processing is reduced, and the real-time response capability of the scheduling system is improved.

The invention discloses a hydropower station gate detection method and system, and relates to the technical field of hydropower station gate detection, and the method comprises the steps: collecting environment parameters, building a dynamic environment model, and determining a real-time impact factor on a gate state; synchronously collecting gate vibration and sound wave data to obtain a composite signal; constructing a short-term and long-term trend model, and identifying a potential abnormal trend; automatically adjusting the sampling frequency of the sensor according to an abnormal detection result; performing fault classification on the multi-parameter signals by using an event pattern recognition algorithm; and generating an automatic response strategy according to a fault classification result. According to the hydropower station gate detection method provided by the invention, the accuracy and efficiency of hydropower station gate detection are improved through multi-dimensional parameter fusion and adaptive sampling adjustment. Through monitoring of various parameters, the system can comprehensively analyze the state of the gate, the misjudgment risk caused by a single signal is reduced, and comprehensive recognition of faults is enhanced.

The invention discloses an intelligent security and protection monitoring method and system based on image recognition. The method comprises the following steps: S1, acquiring multi-modal data; s2, performing preprocessing to generate complete target information; s3, performing real-time detection on the generated complete target information, and performing primary processing on a conventional scene; s4, based on an improved visual SLAM technology, obtaining three-dimensional information of multiple cameras; s5, when the edge device detects a potential abnormal condition, performing abnormal behavior analysis on the data by using a Swin Transform model, and optimizing a detection result in combination with the three-dimensional information of the multiple cameras; s6, performing adaptive learning on historical data by using a depth deterministic strategy gradient algorithm, and dynamically adjusting a threshold value of abnormal behavior detection; and S7, after an abnormal condition is detected, processing data through differential privacy protection and an end-to-end encryption technology, automatically controlling security and protection equipment, and giving a real-time alarm. According to the invention, image recognition and deep learning technologies are fully utilized, and accurate real-time monitoring in a complex scene is realized.

The invention provides a multi-agent cooperation system, which comprises a multi-agent cooperation engine module, a task decomposition and distribution module and a tool calling normal form module, and is characterized in that the task decomposition and distribution module is used for decomposing tasks and distributing decomposed sub-tasks to agents; the multi-agent cooperation engine module is used for managing cooperation and communication between agents; and the tool calling module enables the intelligent agent to dynamically call different tools. According to the multi-agent collaboration system, the collaboration efficiency among the agents, the flexibility of task decomposition, the adaptivity of tool calling and the intelligent level of user interaction are remarkably improved, and remarkable technical advantages and effects are shown in complex task processing and dynamic environment processing.

The invention discloses a motion control method for a redundant mechanical arm, computer equipment and a storage medium, and the motion control method comprises the steps: presetting an expected motion trajectory of an end effector, deducing a trajectory tracking model, and introducing a generalized inverse of a Jacobian matrix of the redundant mechanical arm to rewrite the trajectory tracking model. A joint angular velocity expression of the redundant mechanical arm is obtained, a position error is set, a joint angular velocity model of the redundant mechanical arm is derived, discretization processing is conducted on the joint angular velocity expression of the redundant mechanical arm, generalized inverse of a Jacobian matrix of the redundant mechanical arm is estimated, and therefore a motion control model of the redundant mechanical arm is obtained. And joint angle information and position information when the end effector tracks the expected movement track are obtained and input into a movement control model of the redundant mechanical arm to be processed, the joint angular speed of the redundant mechanical arm is obtained, and therefore the redundant mechanical arm is driven to move, and tracking of a preset target track is completed by the redundant mechanical arm. According to the method, the redundant mechanical arm can be effectively controlled.

The invention discloses a power grid safety enhanced intelligent scheduling method and device based on twinborn adversarial imitation learning and a storage medium, and belongs to the technical field of power scheduling. The method comprises the following steps: acquiring current real-time state information of a power grid system; inputting the real-time state information into a pre-trained scheduling strategy agent to generate a corresponding real-time scheduling action; and judging whether the real-time scheduling action in the current state is an expert-level action or not based on a state action data pair pool formed by the scheduling strategy agent in a training stage, and outputting a final scheduling strategy to a real environment according to a judgment result. Through real-time data analysis, intelligent decision and expert verification, the method can automatically adapt to the complexity and dynamic nature of the power grid, not only realizes efficient, safe and stable operation of the power grid, but also provides powerful support for intelligent management of the power grid.

The invention discloses a network security threat monitoring method and system based on artificial intelligence, and relates to the technical field of digital information transmission, and the method comprises the steps: obtaining data of a plurality of data sources in a network environment, carrying out the multi-level data fusion of the data through an artificial intelligence model, and forming unified data representation; the artificial intelligence model comprises at least one selective fusion layer, and features are extracted from different data sources and are jointly expressed; based on a data fusion result, performing anomaly detection by adopting an unsupervised learning method; and modeling the network flow data into a graph structure according to the detected abnormal behavior, and analyzing the graph structure by adopting a graph neural network GNN. According to the method, the technical problems of difficulty in multi-dimensional data fusion, delay in threat detection, insufficient response capability and the like in the existing network security protection technology are solved.

The invention relates to the technical field of network security, and discloses an industrial log noise reduction processing method and system based on an artificial intelligence algorithm, and the method comprises the steps: collecting historical alarm data of a device / application, carrying out the preprocessing, and dividing the preprocessed data into a training set and a test set; constructing a convolutional neural network model, and training and testing the convolutional neural network model based on the training set and the test set to obtain an alarm log noise reduction model; operating parameters of the alarm log noise reduction model are configured and integrated with a dynamic sensing system; receiving real-time alarm data of the equipment / application, and inputting the real-time alarm data into the alarm log noise reduction model to obtain alarm features; classifying according to the alarm features, and determining the category of the real-time alarm data; and carrying out storage and visual analysis based on the alarm features and categories. According to the invention, repeated or irrelevant alarm information can be accurately identified from a large number of alarms, and noise reduction processing is carried out, so that the system burden is reduced.

The invention relates to the technical field of digital factories, in particular to a smart factory real-time safety monitoring method and system based on edge computing. Firstly, an edge computing device, a camera and a sensor group are deployed in each production area; then, acquiring image data through a camera; acquiring sensor data through the sensor group; and finally, constructing a safety monitoring model, and operating the safety monitoring model on the edge computing device. Inputting image data and sensor data into the safety monitoring model, and obtaining a safety monitoring result through a data preprocessing layer, a feature analysis layer, a feature fusion layer and a monitoring result prediction layer in sequence; the image data and the sensor data are finely analyzed through the safety equipment wearing feature analysis network and the dangerous behavior feature analysis network, the finally obtained safety monitoring result can accurately reflect the real-time safety state of the smart factory, and efficient and dynamic safety management is ensured.

The invention belongs to the technical field of power equipment, and particularly relates to a multi-modal deep learning edge computing platform for power equipment. The edge computing platform comprises a data acquisition module, a data fusion module, a dynamic model updating module, an edge computing optimization module, an intelligent alarm and prediction module, an upstream and downstream data link integration module, an edge device resource management module, a security enhancement module and a simulation and emulation module. And the data fusion module performs splicing, weighted fusion or PCA mathematical transformation on the features of different modalities in the feature extraction stage to form a comprehensive feature vector, and performs fusion according to model output results of different modalities in the model decision-making layer, including use of a voting mechanism, weighted scoring or logistic regression. According to the invention, by integrating a multi-modal deep learning technology and an edge computing architecture, comprehensive performance improvement and cost saving are brought to power equipment monitoring and management.

The invention provides a quadruped robot control method and system based on reinforcement learning and a composite model, relates to the technical field of robot automatic control, and introduces multiple control modes (a wheel type mode, a foot type mode and a wheel-foot composite mode) to realize efficient passing of multiple terrains. A reinforcement learning method is used for replacing traditional model prediction control, the complexity of a control system is greatly simplified, the real-time response capability to a dynamic environment is enhanced, a composite model optimization controller further optimizes speed distribution through quadratic programming so as to ensure the optimal speed and stability performance, a user can manually switch a control mode, and the control efficiency is improved. The requirements of different task scenes, such as patrol, rescue and transportation tasks of complex terrains, are met; the invention shows excellent passing efficiency and energy consumption performance in experiments, especially in the aspect of smoothness of terrain transition and multi-mode switching.

The invention relates to an agricultural data interaction method and platform based on multi-source information, and belongs to the technical field of agricultural data processing. Comprising the following steps: processing collected data through a corresponding edge calculation module to generate a dynamic label; analyzing and processing the agricultural information data to obtain a supervision label and corresponding supervision data; all the tags and the corresponding data are imported into a geographic information system, matching is carried out according to the corresponding areas and the respective tags, and meanwhile, the monitoring tags are recognized and updated through a cloud platform computing center. The real-time data is fused and sent to the cloud computing platform through the edge computing module, the interaction prompt is generated through association with the supervision data, so that the real-time performance and the high efficiency of data processing are improved, meanwhile, the monitoring data and the supervision data are associated through the interaction prompt, and the interactivity of visual display is improved.

The invention provides an abnormal street lamp detection system and method based on a YOLOv8 model, the system comprises an image acquisition module, a target detection module and an abnormal street lamp identification module, the image acquisition module is used for acquiring a monitoring image on a road in real time, the target detection module adopts the YOLOv8 model to carry out target detection on image data, and the abnormal street lamp identification module is used for identifying the abnormal street lamp. Identifying a street lamp area in the image, positioning a street lamp in the image and marking the position of the street lamp; and the abnormal street lamp identification module analyzes the detected street lamp state by using image features, performs multiple times of abnormal detection on multiple street lamp images collected in the same time period by adopting a multiple-time identification strategy, and judges a final result through a voting mechanism, thereby identifying the abnormal street lamp. According to the invention, automatic detection and state analysis are carried out on the street lamps by using the YOLOv8 model, so that real-time monitoring and identification of abnormal street lamps are realized, and the intelligent management level of an urban road illumination system is improved.

The invention discloses a vehicle path planning method in a V2X environment, and particularly relates to an improved RRT path planning method based on a dynamic search step size of tabu search. The method mainly comprises the following steps: initializing a starting point and an ending point, taking the starting point as a root node of a tree, and generating a search map according to real-time road and obstacle information by using a V2X technology; randomly generating points within a limited angle, generating a new node according to a dynamic search step length, detecting whether the new node intersects with an obstacle in the map, and if so, abandoning the node; if the current node is not intersected with the new node, adding the new node into the RRT spanning tree, adding a path between the current node and the new node into the path RRT spanning tree, and adding the accessed nodes into a taboo list to avoid re-accessing the nodes in subsequent search; checking whether the new node is close to the target point, if so, stopping searching, and finishing path planning; and repeating the above steps until the path connecting the starting point and the target point is found or the maximum number of iterations is reached.

The invention discloses an industrial scene-oriented intelligent Agent system and an implementation method thereof, and the system comprises a user interaction layer which is used for providing a diversified interface and carrying out the communication with a back-end service through an API gateway; the intelligent layer is used for realizing task management, task planning and resource scheduling functions by adopting a micro-service architecture arranged based on a container; the physical equipment layer is used for being integrated with an upper-layer system through an industrial Internet of Things protocol and processing time-sensitive applications by adopting an edge computing technology; wherein the user interaction layer is bidirectionally connected with the body intelligent layer, and the body intelligent layer is bidirectionally connected with the physical equipment layer. According to the invention, a series of operations such as order analysis, material planning, production planning, task distribution, material preparation, production execution, quality control and exception handling can be autonomously carried out, manual intervention is greatly reduced, and the production efficiency is improved.

The embodiment of the invention provides a traffic attack detection method and device and electronic equipment, and the method comprises the steps: determining a first feature vector corresponding to a to-be-detected data stream based on a feature value, corresponding to a target feature, of each data packet in the to-be-detected data stream; inputting the first feature vector into an attack detection model, and determining a first category of the to-be-detected data stream through the attack detection model; wherein the attack detection model comprises a symmetric tree structure, and the first category represents whether the to-be-detected data stream is normal or not; determining a second category of the first data stream through an attack recognition model; wherein the attack recognition model is a deep learning model, the first data stream is an abnormal to-be-detected data stream, and the second category comprises a preset attack type. A two-stage recognition architecture of the attack detection model and the attack recognition model is adopted, the detection speed is increased, the real-time response capability of detection is improved, fine recognition of network attacks is achieved, and the precision and reliability of detection are improved.

The invention discloses a portrait video generation method and system supporting a user-defined text. The system comprises a text analysis module, a semantic alignment module, a video generation module, a real-time processing module, a feedback adjustment module and an early warning display module. The problems of semantic mismatching of text and image generation, inaccurate multi-language support and poor real-time response are solved. Through a multi-level text analysis and semantic alignment module, the scheme combines a culture background and multi-language characteristics in a text analysis stage to generate accurate structured data, and behavior instructions and expression descriptions in a text are accurately mapped through a deep learning algorithm to ensure that generated videos are consistent with text semantics. Meanwhile, the translation processing unit is combined with a language model and an algorithm, efficient and accurate multi-language translation is achieved, and ambiguity is avoided. The real-time processing module improves the response performance of the system in high-load environments such as transportation hubs through time monitoring and speed control, dynamically adjusts and generates strategies, and ensures that the system is stable and efficient.

The invention relates to an intelligent fund routing system based on an AI large model and an optimization method thereof, and belongs to the field of finance, and the system comprises a data processing module which is used for automatically collecting financial market data, and carrying out the preprocessing and feature extraction; the decision forming module is used for analyzing the processed data and performing fund routing decision based on an AI model architecture; the fund routing optimization module is used for optimizing a fund routing path according to market and user behavior prediction results; the risk assessment module is used for monitoring transactions and fund flow directions in real time and assessing potential risks; and the risk management integration module is used for carrying out early warning and decision support according to the risk assessment result. The method has the advantages that the efficiency is improved; the safety is enhanced; the precision is improved, and the deep learning model can better predict the market trend and the user behavior.

The invention discloses a trusted DCS implementation method and system fusing point-to-point and server architectures, and relates to the technical field of industrial control systems, and the method comprises the steps: building a data link of a calculation part and a protection part on a terminal of a trusted DCS; establishing a data link between the trusted upper computer and the trusted management platform on the trusted upper computer; releasing trusted data of the trusted DCS in the point-to-point architecture of the DCS; and credible state prompting and alarming functions are added in a diagnosis page of the DCS, and credible item starting and stopping, credible abnormity alarming and alarming processing are carried out. According to the invention, by establishing a trusted data link, realizing data intercommunication and introducing a dynamic credibility evaluation mechanism, real-time data release and transmission of trusted information are realized in a point-to-point architecture of the DCS, so that the DCS system can know trusted state change in real time and give an alarm, the ability of the system to resist security threats is remarkably improved, and the reliability of the system is improved. And meanwhile, the compatibility with the existing DCS architecture is kept.

The invention discloses a karst area foundation pit water inrush early warning system and method, and relates to the technical field of artificial intelligence. Data of groundwater dynamic, geological stress and soil water content of a karst area are monitored in real time through a data acquisition module, and data cleaning, noise filtering and complementing are performed in a data processing module; a multi-dimensional interpolation algorithm is used for compensating data missing, and the data integrity and accuracy are improved; in the region division and analysis module, a karst region is divided into independent karst sub-regions, geological characteristic data is monitored in real time, and the fracture expansion trend and the water level change are analyzed through a model of the chain reaction early warning module, so that the water inrush time and region are predicted, and the dependence of the system on a historical data mode is reduced; and the feedback control module evaluates the associated risk index Tsyz, so that the water inrush risk of adjacent areas is prevented in advance, and the real-time response and construction safety of the system are ensured.

The invention discloses a vehicle path planning method in a V2X environment, and particularly relates to an RRT vehicle path planning method based on vehicle trajectory prediction in the V2X environment. The method mainly comprises the following steps of initializing a starting point and an ending point of an algorithm, acquiring driving information of surrounding vehicles by using a V2X technology, generating an initial sampling area, predicting tracks of the surrounding vehicles in a period of time in the future according to a vehicle track prediction algorithm, and taking the predicted tracks as predicted virtual obstacles. Adjusting the initially generated sampling area, adopting an optimized sampling area strategy to obtain an optimized sampling area, taking a starting point as a root node of the tree, randomly generating a new node in a fan-shaped area with a specified direction angle at a fixed step length, and checking whether the new node intersects with an obstacle or not. And if no collision exists, adding the node and the path into the RRT tree. And if the new node is close to the terminal point, stopping searching. Otherwise, continuing iteration until the path is found or the maximum number of iterations is reached.

The invention relates to the technical field of intelligent positioning, in particular to an intelligent positioning system and positioning method applied to a spraying robot, and the positioning system comprises a light field data acquisition module, a particle tracking calculation module, a sound wave precision distance measurement module and a dynamic verification execution module. According to the method, the operation environment of the spraying robot is sensed in an all-around mode through synthesis of a multi-sensing technology, the accurate position of the spraying head is updated through a strategy of capturing light field data in real time and accurately calculating particle dynamics, the spraying precision is ensured, the real-time response capacity to environment changes and the dynamic adjusting capacity of the spraying process can be greatly improved, and the spraying quality is improved. The material waste is reduced, the coating quality and the production efficiency are improved, sound wave precise distance measurement is added, the robustness and reliability of the system in a complex industrial environment are enhanced through sound wave and light field information fusion, precise tracking is combined with real-time position adjustment, and it is ensured that the spraying quality reaches the optimal quality every time.

The invention relates to the technical field of platform door control, in particular to a communication-based SIL4 platform door system, which comprises a domain controller, a DCU (Data Control Unit), an external interface and other subsystem equipment, the platform door system realizes interconnection and intercommunication with a signal system and other subsystem equipment through bus connection and hard wire connection, high safety and high reliability of the system are ensured, a dual-CPU architecture is adopted in a domain controller and a door control unit, dual processing and cross verification can be carried out on data by utilizing a dual-CPU design, and the system is convenient to use. The accuracy and consistency of data are ensured, so that an existing relay circuit is replaced to reach an SIL4 security level; a data transparent transmission mechanism is carried out by using a single CPU, so that the data transmission delay is reduced, and the real-time response capability is improved.

The invention discloses a metro crew scheduling plan compilation optimization method and system based on an algorithm, relates to the technical field of metro scheduling, and is used for solving the problem that a conventional metro crew scheduling system is not timely in peak allocation. In the prior art, traffic roads are directly matched with aircrafts one by one, but the adaptability between the traffic roads and the aircrafts is not fully considered, and optimization is not carried out aiming at special requirements in peak hours. In the peak period, the demand is far greater than that in the low peak period, more aircraft shifts are possibly needed for support, and in the peak period, the important demand is that the route and the aircraft shifts with high matching degree need to be preferentially matched. According to the method, through matching optimization of the route and the locomotive crew and combination of historical passenger flow data, efficient subway team scheduling is achieved, and it is ensured that the shift demand in the peak period is preferentially met.

The invention discloses a cloud edge collaboration method based on container technology edge computing, and relates to the technical field of edge computing, the method comprises the following steps: utilizing a cloud edge collaboration module built in an edge gateway to carry out container life cycle management on a software container, and utilizing a cloud mirror image management platform to carry out mirror image life cycle management on a container mirror image; communication between the edge gateway and the cloud mirror image management platform is completed by using a cloud edge cooperation module, a regulation and control strategy of the edge gateway is predicted and optimized in the cloud mirror image management platform, and the predicted and optimized regulation and control strategy is deployed to the edge gateway and acts on related equipment; and performing anomaly detection on the monitoring data of each software container collected in real time by utilizing a pre-constructed machine learning model and a preset anomaly rule, identifying and feeding back an anomaly result to a management party. The method has the advantages that data processing efficiency is improved, delay is reduced, expansion is easy, deployment is flexible, regulation and control are finer, and operation and maintenance are carried out in advance.

The invention provides an intracranial pressure real-time monitoring and drainage adaptive control optimization system. The intracranial pressure real-time monitoring and drainage self-adaptive control optimization system comprises a hardware module, a software module and a mathematical model, the intracranial pressure is monitored in real time through a high-precision sensor, self-adaptive adjustment is carried out based on individual characteristics of a patient to optimize drainage control, and the hardware module comprises the high-precision pressure sensor used for monitoring the intracranial pressure in real time, and the software module is used for monitoring the intracranial pressure in real time; the drainage pipeline is connected into the patient valine and used for adjusting drainage of cerebrospinal fluid. By combining the high-precision pressure sensor, the artificial intelligence algorithm, the neural network and the fuzzy control strategy, the real-time response capability of the system to the intracranial pressure change is remarkably improved. The preferably adopted micro electro mechanical system sensor has the advantages of being high in precision and low in delay, intracranial pressure changes as small as 0.01 mmHg can be detected, and the drifting phenomenon of the sensor in long-term monitoring is reduced through the self-calibration function.

The invention relates to the field of power systems, and discloses a DMMoEQN-based power system parameter identification method, which comprises the following steps: acquiring an initial observation value # imgabs0 # and a target observation value # imgabs1 # of a power system, and selecting an optimal parameter adjustment action # imgabs3 # by an intelligent agent according to a current observation value # imgabs2 # through an online network; an action # imgabs4 # is executed, the electric power system updates a parameter state # imgabs6 # of the electric power system according to the action # imgabs5 #, and a new observation value # imgabs7 # is obtained; calculating a step reward according to an error between the new observation value # imgabs8 # and the target observation value # imgabs9 #, and obtaining a total reward according to the step reward; judging whether the observation value # imgabs10 # of the electric power system is within the error range of the target observation value # imgabs11 #, if so, performing initialization, and continuing training; when the epoch number is larger than the preset maximum epoch number, training is ended, a power system parameter set # imgabs12 # is obtained through the trained power system parameter identification model, and the power system is adjusted according to the parameter set # imgabs13 #. According to the invention, efficient and accurate parameter identification and dynamic adjustment of the power system can be realized.

The invention discloses an airborne multi-source integrity monitoring method and device for an aviation navigation operation network, and belongs to the field of satellite navigation, and the method comprises the steps: constructing an overall design architecture of an airborne multi-source high-performance navigation receiver; an ionosphere gradient monitoring algorithm based on carrier phase difference is provided, IGM detection statistical error characteristics of the carrier phase are researched, an ionosphere gradient monitoring threshold is established, and a switching mechanism from an airborne DFree mode to an IFree mode is realized; an aviation navigation multipath mitigation suppression algorithm is researched, multivariate feature extraction of observation data is combined, an observation data feature matrix is established, a parallel time convolutional neural network architecture is designed, and the weight is updated through a stochastic gradient descent method. According to the airborne multi-source integrity monitoring method and device for the aviation navigation operation network provided by the invention, accurate monitoring of the ionosphere gradient is realized, a switching mechanism between a DFree mode and an IFree mode is optimized, and the integrity monitoring capability and the system availability of the aviation navigation operation network are improved.

The invention relates to the technical field of torque calculation, in particular to a torque adaptability regulation and control method and system for an electric power-assisted bicycle, and the method comprises the steps: receiving a torque regulation instruction, starting a system regulation unit based on the torque regulation instruction, collecting a side-sway angle and a side-sway angular velocity, calculating transmission delay, and if the transmission delay is not in a delay range, starting the system regulation unit; if the transmission delay is within the delay range, screening the transmission data packet set to obtain a standard data packet set and an over-limit data packet set, adjusting the over-limit data packet set to obtain an adjusted data packet set, and obtaining an integrated data packet set based on the standard data packet set and the adjusted data packet set; and if not, calculating an external interference estimated value, calculating a side-sway angular acceleration by using the external interference estimated value, calculating a side-sway torque and an offset torque, calculating a regulation and control torque according to the side-sway torque and the offset torque, and completing torque adaptive regulation and control according to the regulation and control torque. According to the invention, the regulation and control speed and accuracy of torque adaptive regulation and control can be improved.

The invention relates to the technical field of forest total production value estimation, and discloses a forest ecosystem total production value automatic accurate estimation method based on a remote sensing technology, which comprises the following steps: acquiring a real-time positioning signal of remote sensing acquisition equipment, acquiring a to-be-estimated forest map from a geographic information database, and displaying the real-time positioning signal on the map; meteorological parameters and forest characteristic parameters of a to-be-estimated forest are acquired through remote sensing acquisition equipment, and the ground estimation model performs preliminary estimation on the total production value of the forest ecosystem through the meteorological parameters and the forest characteristic parameters; collecting landform characteristics of the map, judging whether the preliminary estimation result is corrected or not according to the landform characteristics, and adjusting the preliminary estimation result according to the landform characteristics if the preliminary estimation result needs to be corrected; and storing the adjusted estimation result, and displaying a dynamic fluctuation graph of the adjusted estimation result on a visual device. The method is accurate and reliable in estimation of the total production value of the forest ecosystem.