545results about How to "Cope well" patented technology

The invention provides a cross-domain network security policy automatic generation and protection policy collaboration method and system, and relates to the technical field of network security, and the method comprises the steps: collecting multi-domain security event data; constructing a security threat map; generating a cross-domain security risk score by using a deep learning algorithm; determining an inter-domain access control rule set and an intra-domain protection strategy according to the score; forming a cross-domain collaborative protection strategy; deploying a strategy on the multi-domain security device; establishing an inter-domain information sharing channel; monitoring the strategy effect; optimizing the strategy by using a reinforcement learning algorithm; and updating to each domain security device. According to the method, the effectiveness of cross-domain network security protection is improved.

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 provides a multi-level low-altitude air route network construction method in a complex urban environment, and relates to the technical field of low-altitude air route construction, and the method comprises the steps: building a low-altitude flight rule base; performing three-dimensional discretization on the urban space, and dividing the airspace into three-dimensional grids; designing a risk assessment function R; dividing a plurality of height layers, and distributing the height layers for different types of aircrafts; constructing a multi-stage air route network; constructing an airspace three-dimensional airway model; based on the airspace three-dimensional air route model, adopting a hybrid iterative algorithm to optimize the air route planning of each height layer; performing path smoothing on the discrete path points generated by the hybrid iterative algorithm by adopting a B spline curve, and performing flight performance verification on the smoothed path to obtain a continuous flight path; and generating a low-altitude air route network according to the continuous flight path. According to the method, the defects in the aspects of complex urban environment processing, multi-source data integration, multi-level airspace division, path optimization and the like in the prior art can be overcome, so that safe, efficient and flexible low-altitude flight management is realized.

The invention discloses a multi-task collaborative robot scheduling method and system oriented to an intelligent factory, and the method comprises the steps: receiving the input data of a plurality of tasks to be executed by the intelligent factory, the input data comprising the task type, the dependency relationship between the tasks, the task priority, the resource demand of each task, and the expected completion time of each task; determining an initial task execution sequence of the tasks according to the task types, the dependency relationships and the task priorities; obtaining current resource state data of all available robots in the intelligent factory; according to the resource demand of each task, the expected completion time of each task, the initial task execution sequence and the current resource state data of all available robots, a scheduling algorithm is adopted to generate a multi-task cooperative scheduling rule; and controlling the plurality of target robots to execute the plurality of tasks according to the multi-task cooperative scheduling rule. According to the method, the resource utilization rate of the robot in the intelligent factory can be effectively improved, and the task execution efficiency is optimized.

The invention discloses a self-evolution network security defense strategy generation and dynamic deployment method, which comprises the following steps of: acquiring multi-dimensional data such as original network flow data, and generating an optimized feature matrix through adaptive interval division and symbolization conversion; constructing a feature graph structure based on the optimized feature matrix, extracting threat features by using a graph neural network and an attention mechanism, and generating a threat mode set; analyzing threat propagation characteristics according to the threat evaluation index set and the threat incidence matrix, and generating a threat propagation graph; and generating an initial defense strategy set based on a threat assessment result, and generating an optimized defense strategy set through dependency analysis and conflict elimination. According to the invention, through adaptive feature extraction and dynamic strategy optimization, the intelligent level and protection effect of network security defense are improved.

The invention discloses a power distribution network overhead line risk refined early warning method and system. The method comprises the following steps: collecting meteorological time sequence data and power distribution network topology and line parameter data; and preprocessing the data, and constructing a prediction data set. And establishing a fault probability prediction model based on the meteorological data and the line parameters. Calculating the fault probability by using the mathematical model, correcting the model, training in combination with static topology and dynamic meteorological data, and constructing a fault probability network model. And analyzing the importance of the nodes and lines of the power distribution network, and evaluating the load loss proportion of the nodes. And carrying out normalization processing on the importance indexes. And comprehensively calculating the predicted fault probability, the node loss load and the importance index to obtain a branch risk parameter. Fine early warning is carried out according to a set early warning threshold value, and dynamic adjustment is carried out to adapt to the actual operation condition. The method has the advantages that comprehensive risk assessment is provided, and the accuracy of fault prediction and the timeliness of risk early warning are improved.

The invention belongs to the technical field of condensation prevention of power equipment, and discloses an intelligent induction type condensation prevention system and method for the power equipment, and the system comprises a multivariate data collection unit, an intelligent control unit and an execution unit, and achieves the comprehensive real-time monitoring of the internal and external environments of the equipment through the integration of the multivariate data collection unit; the intelligent control unit can accurately predict the condensation risk based on real-time and historical data by using a pre-trained machine learning model, and dynamically adjust the condensation prevention strategy according to the condensation risk, thereby ensuring that condensation can be effectively prevented under various complex environmental conditions; the accurate execution of the execution unit further guarantees the condensation prevention effect, the operation stability and safety of the power equipment are integrally improved, the equipment fault risk caused by condensation is reduced, the service life of the equipment is prolonged, and the unnecessary maintenance cost is reduced; the system has self-learning and self-adaptive capabilities, can continuously optimize a control strategy to adapt to different environmental conditions, and ensures an optimal anti-condensation effect.

The invention discloses a pipe production task management method and system, and belongs to the technical field of pipe production, and in the pipe production task management method and system, factors such as order priority, equipment state and raw material supply are analyzed through an intelligent algorithm, and the production schedule is automatically optimized, so that production resources are utilized more reasonably and efficiently. Resource waste can be avoided, idle time in the production process is shortened, and therefore production efficiency and the productivity utilization rate are improved. The urgency degree and the delivery date of the order are analyzed through an intelligent algorithm, and the enterprise can preferentially arrange the production of the urgent order to ensure that the customer demand is met in time. Meanwhile, production tasks are reasonably distributed according to the running state of the equipment and the raw material supply condition, and the use efficiency of the equipment and the utilization rate of raw materials are improved. The dynamic adjustment mechanism monitors the production progress in real time and automatically adjusts the production plan according to the actual situation, so that the system can rapidly adjust the production plan and distribute the tasks to other devices, and continuity and on-time delivery of the production tasks are ensured.

The invention belongs to the field of fault diagnosis, and particularly relates to a main shaft bending common characteristic diagnosis system based on a stacking integration method, and the system comprises the following modules: a sensor module which is used for collecting a vibration signal of a main shaft in real time; the data acquisition and processing module is used for converting an analog signal into a digital signal and preprocessing the signal acquired by the sensor; the feature extraction module is used for extracting features from the preprocessed vibration signals; the machine learning diagnosis module analyzes and classifies the extracted features by using stack integration based on a plurality of trained machine learning models, and judges the health state of the main shaft; and the output module is used for outputting the diagnosis result and sending out an alarm signal when abnormality is detected. Real-time monitoring and automatic diagnosis of the main shaft bending fault are achieved, compared with a traditional method depending on expert experience and manual detection, the fault detection efficiency and accuracy can be greatly improved, and misjudgment and missed judgment risks caused by human factors are reduced.

A human body posture estimation method based on a dynamic graph convolutional network belongs to the field of human body posture estimation, and comprises the following steps: step 1, simplifying a human body structure in a video, and constructing a human body skeleton key point structure chart; 2, defining a graph structure to represent a spatial relationship between human joints; thirdly, a graph structure is defined to represent the motion relevance between the joints of the human body; 4, constructing a dynamic graph convolutional network by using dynamic space-time graph convolution; 5, 3D human body posture behavior data enhancement is carried out; and 6, constructing human body behavior data in the virtual scene by using the 3D human body posture data. According to the method, the modeling capability of the complex relation between the joints is improved, the robustness of the model is improved, and complex behaviors are recognized more accurately.

The invention belongs to the technical field of path planning, and particularly relates to a robot path planning method based on an RRT improved algorithm, and the method comprises the steps: obtaining environment space information needing path planning, defining parameters, and obtaining the minimum distance between a coordinate point and an obstacle; a bidirectional random tree is constructed and initialized, and sampling points are obtained through a sampling function; finding a nearest neighbor point, selecting a new node, carrying out safety distance judgment, and if not, carrying out sampling again; generating a discretization path; setting a cost function during local node expansion; performing loop iteration to generate discrete point cost, taking a minimum cost value, searching an optimal node and inserting the optimal node into the current tree; an overall path Path after local optimization is obtained; and discretizing the whole Path, setting a cost function of nodes during global planning, selecting the node with the minimum cost for reconnection, and finally obtaining a smooth and effective optimal path. According to the method, the optimality and smoothness of the path are effectively improved.

The invention relates to the technical field of force feedback handles, in particular to a remote surgical robot control system based on a force feedback handle and a control method thereof. The method comprises the following steps: carrying out multi-dimensional force data acquisition on an end effector of the surgical robot, and carrying out contact force size, direction and time sequence feature extraction to obtain multi-dimensional force feature data; performing surgical operation safety baseline analysis according to the multi-dimensional force feature data to generate surgical operation safety baseline data; performing dynamic force feedback threshold calculation according to the surgical safety operation baseline data to obtain force feedback threshold range data; and performing adaptive compression processing on different force feedback signals according to the force feedback threshold range data to obtain dynamic force feedback control parameters. Through real-time control instruction optimization and a closed-loop feedback strategy, the system can quickly respond to an operation intention, early warning is carried out on potential risks, and it is ensured that the operation process is safer and more reliable.

The invention relates to the technical field of ship navigation early warning, and discloses a ship direction monitoring and early warning integrated platform which comprises a ship speed acquisition unit, a ship course angle data acquisition unit, a ship navigation data analysis unit and an early warning unit. According to the ship direction monitoring and early warning integrated platform, early warning is carried out on the ship navigation direction and the navigation state by integrating the wind speed, the water flow speed and the noise data in the navigation process in the current navigation environment, the risk and the course deviation angle in the navigation process can be obtained at the same time, and under the severe navigation condition, the ship direction can be monitored and early warned. The method can still accurately obtain the current ship navigation risk and course deviation, and avoids the situation that the position information and the navigation state of the ship are acquired in real time only by means of sensors such as radar and a global positioning system (GPS), and the early warning effect is affected due to delayed data transmission possibly caused by network delay or signal interruption under the severe navigation condition. And therefore, accurate early warning can be made in a better way in a variable navigation environment.

The invention relates to the technical field of intelligent evaluation and early warning methods, in particular to a nuclear radiation dose space distribution intelligent evaluation and early warning method and system, and the method comprises the following steps: obtaining multi-source monitoring data which comprises gamma radiation dose, alpha radiation dose and beta radiation dose measuring instrument data; performing fusion and enhancement processing on the multi-source monitoring data to obtain an enhanced radiation monitoring signal; based on the enhanced radiation monitoring signal, high-precision prediction of nuclear radiation dose spatial distribution is carried out through a deep probabilistic neural network model; according to the high-precision prediction result, in combination with a nuclear accident severity level standard, a radiation alert evaluation result and early warning information are generated, short-term radiation fluctuation can be captured, a long-term change trend can be identified, and the understanding ability of the system to a complex radiation field is greatly improved.

The invention discloses a virtual reality interaction method for constructing multi-modal fusion based on application scene features, and relates to the technical field of virtual reality. In order to solve the technical problem that in the prior art, when an existing multi-modal fusion technology is used for processing fusion of different modal data, the characteristic difference between different modals is large, the technical scheme provided by the invention comprises the following steps: acquiring and preprocessing multi-modal data; constructing a cross-modal knowledge enhancement network, extracting initial features, and enhancing the consistency and difference between visual and auditory features; important context information in fusion features is optimized and enhanced based on an optimization network of frequency spectrum and space attention; constructing an edge guide learning network, and combining the edge guide learning network to the tactile data; the visual, auditory and tactile features are fused and applied to a virtual reality scene; and optimizing the model through structural similarity loss, mean square error loss, significance weight loss and edge loss. The method is suitable for cooperative work of multi-modal features in a complex environment.

The invention provides a ground surface settlement monitoring method and system fusing Beidou and InSAR data. The method comprises the following steps: receiving positioning data from a Beidou satellite system and earth surface deformation data acquired by a synthetic aperture radar interference measurement system; based on the positioning data and the earth surface deformation data, correcting the earth surface deformation data according to the environmental factors through a space-time fusion model to obtain corrected earth surface deformation data; by means of the corrected surface deformation data, a multi-stage analysis technology is adopted, the development trend of surface subsidence is determined, a surface subsidence distribution diagram is generated, and the surface subsidence distribution diagram is used for displaying spatial distribution characteristics of surface subsidence; and according to the ground surface settlement distribution diagram, the future ground surface settlement condition is monitored by using the space-time fusion model, and a ground surface settlement monitoring report can provide a scientific basis for early warning and prevention of geological disasters. The ground surface settlement monitoring efficiency and monitoring effect are improved.

The invention discloses an ultra-short-term photovoltaic power prediction method and system based on sky-ground multi-modal data fusion. The method comprises the following steps: S1, acquiring multi-modal data; s2, processing and fusing the multi-modal data; s3, evaluating the quality of the fused multi-modal data, and judging whether the peak signal-to-signal ratio of the fused multi-modal data is greater than or equal to a preset threshold value or not: if so, entering the next step; s4, constructing an integrated prediction model, and performing iterative training on the integrated prediction model by using the multi-modal data; and S5, inputting the fused multi-modal data into the integrated prediction model to obtain a photovoltaic power prediction trajectory. According to the method, the complex change of the surrounding environment of the photovoltaic power station can be more comprehensively captured by fusing the sky-ground multi-mode data, so that the accuracy of photovoltaic power prediction is improved. By processing and fusing data from different sources, the advantages of various data can be fully utilized, and the comprehensiveness and depth of prediction are improved.

The invention provides a recommendation strategy generation method based on big language model enhancement and related equipment. The method comprises the steps of obtaining a recommendation task; inputting the recommendation task into an intelligent agent, and obtaining a recommendation strategy output by the intelligent agent; wherein the intelligent agent is obtained by training based on a sample recommendation task and a large language model, and the large language model is used for predicting user behaviors based on the sample recommendation task. According to the method, the big language model is combined with the reinforcement learning agent, so that the problem that an accurate recommendation strategy is difficult to quickly provide by a traditional method is effectively solved, and the efficiency and the adaptability of a recommendation system are improved while the accuracy and the individuation degree of the recommendation strategy are improved.

The invention discloses a remote physiological signal estimation method and system based on a diffusion model, and relates to the technical field of non-contact physiological signal detection. The training process of the diffusion model is as follows: forward diffusion is performed on an original rPPG signal to obtain a noise rPPG signal; performing feature extraction on the face video to obtain a multi-scale space-time diagram; the noise rPPG signal and the multi-scale space-time diagram are fused; carrying out backward diffusion on the fused data to obtain de-noised data; outputting a predicted rPPG signal according to the denoised data; performing model training by minimizing the difference between the predicted rPPG signal and the original rPPG signal; and performing remote physiological signal estimation by using the trained diffusion model. According to the invention, the accuracy of rPPG signal estimation is improved.

The invention discloses a big data read-write adaptive method based on a decision algorithm and a big data read-write system, and belongs to the technical field of intelligent decision of a data center, high-speed read-write operation of data is processed in real time in a service system, and a data read-write strategy and resource allocation are dynamically adjusted by analyzing a data access mode and a system load condition; data are preloaded through an intelligent prefetching strategy, and the storage and access paths of hotspot data are optimized, so that the waiting time of a user and the consumption of system resources are reduced. According to the method, data management can be simplified, data access efficiency can be improved, data consistency and security can be enhanced, the problem of multi-database management and query complexity faced by enterprises can be effectively solved, and more efficient and more consistent data access and management experience can be provided for the enterprises.

The invention relates to an automatic driving YOLO target detection method and system for coping with light influence, and the method comprises the steps: employing a vehicle-mounted camera to shoot the actual condition images of streets and roads on a plurality of streets, obtaining the vehicle actual condition images of different streets and different roads in different time periods, and forming an image data set; marking the image data set by using a LabelImg tool, and marking a vehicle target in the image, including a bounding box and category information of a vehicle; constructing an automatic driving YOLO target detection network model coping with light influence; and training an automatic driving YOLO target detection network model coping with the light influence by using the obtained image data set, wherein the trained automatic driving YOLO target detection network model coping with the light influence is used for coping with vehicle target detection under the light influence. Accurate vehicle distance adjustment and safe driving decisions can be provided for the automatic driving vehicle, and driving safety and efficiency under various light conditions are ensured.

The invention discloses an intelligent self-adaptive real-time task scheduling method and system based on multi-dimensional optimization. The method comprises the following steps: S1, inputting a task; s2, a DAG task is decomposed into independent sequential sub-tasks; s3, dynamically calculating the priorities of the tasks by adopting a multi-factor dynamic priority scheduling module, and updating the priorities of the tasks; s4, dynamically adjusting an acceleration factor by adopting a self-adaptive acceleration factor management module; s5, vertex correlation analysis is carried out, and a variance of processor load imbalance is calculated by adopting a load balanced distribution algorithm and is minimized; s6, in combination with static analysis and dynamic inspection, a hybrid schedulability judgment module is adopted to judge the tasks, and judgment results are fused; and S7, fusing decisions by adopting a decision fusion algorithm, obtaining a scheduling strategy through a scheduling strategy coordinator, executing the task, and monitoring the task in real time. Real-time monitoring and real-time optimization scheduling are realized, and the utilization rate of resources is improved.

The invention relates to the technical field of building shock insulation, and discloses a building shock insulation rubber support which comprises a bottom connecting plate and a top connecting plate, a damping rubber body is arranged between the bottom connecting plate and the top connecting plate, and a first through hole is formed in the middle of the damping rubber body; a plurality of fixing grooves are formed in the damping rubber body in the axial direction, and metal plates are arranged in the fixing grooves. By arranging the bottom connecting plate with the adjusting rod, one part of the adjusting rod is inserted into the damping rubber body, and one end of the adjusting rod is movably connected with the bottom connecting plate, after vibration is finished, if the damping rubber body cannot restore to the original shape, force is applied to one end of the adjusting rod through a hydraulic mechanism in a pushing or pulling mode, and the damping rubber body cannot restore to the original shape. Under pushing of the adjusting rod, resetting of the damping rubber body can be rapidly completed, and operation is convenient and rapid.

The invention provides an image restoration method and system based on dynamic decomposition and fusion, and the method comprises the steps: decomposing a to-be-restored image with hybrid features according to a degradation mode, and extracting degradation features of which the number is the same as the type number of the degradation mode; respectively processing each degradation feature to obtain a recovery feature corresponding to each degradation mode; and the recovery features are dynamically fused to obtain a clear recovery image with the same size as the to-be-recovered image, so that the function of performing high-quality recovery on the complex hybrid image is realized. According to the method, the recovery feature map is decomposed, processed and fused under multiple scales, the recovery feature map fusing the recovery features of the multiple scales is obtained, and the visual effect of hybrid image recovery is improved. According to the method, the symmetric U-shaped network is constructed based on the corresponding model formed by the method, and the processing sub-module corresponding to the degradation mode is constructed, so that complex and diversified degraded images in a real environment are well dealt with, and an efficient and reliable solution is provided for the field of image restoration.

The invention provides a distributed multi-agent regional traffic control method and system and electronic equipment, and the method comprises the steps that a sub-region agent determines target intersection agents according to current traffic information, and transmits a regional cooperative control instruction to each target intersection agent, the target intersection intelligent body receives association strategy information of the association intersection intelligent body, determines target strategy information according to the current traffic information, the regional cooperative control instruction, the preference information and the association strategy information, and sends a target control instruction to the lane intelligent body and / or the flow direction intelligent body according to the target strategy information, and the lane intelligent agent controls the controlled equipment according to the target control instruction and / or the flow direction intelligent agent controls the controlled equipment according to the target control instruction. According to the invention, the transmission cooperation capability between the intelligent agents is improved, and adaptive adjustment is realized, so that global optimization can be carried out, and the adaptability and the intelligent level of the whole traffic system are improved.

The invention provides an adaptive CFAR detection method based on scene classification, and the method comprises the steps: carrying out the scene classification of an input SAR image through employing a K-means clustering algorithm, carrying out the target detection of a pure sea area obtained through classification through employing VI-CFAR, and carrying out the CFAR detection of a coastal area through employing a significance model. According to the method, the problems that a traditional CFAR algorithm is high in false alarm rate and unstable in detection performance in port and land complex backgrounds are effectively solved, detection parameters are optimized according to the complexity of different scene backgrounds, and therefore it is ensured that the CFAR algorithm can still maintain the constant false alarm rate in the sea clutter background, and the robustness of target detection is remarkably improved. The ocean area and the land area in the image are effectively distinguished, and the land area is shielded. According to the technical scheme, the problem that a traditional CFAR detection algorithm is interfered by a complex land background when detecting ships on the sea surface is solved.

The invention provides a financial bill risk value calculation method and device, equipment and a storage medium, relates to the technical field of financial bill risk assessment, and can comprehensively and deeply mine potential risks in financial bills by integrating various anomaly detection models and classification models. The anomaly detection model can accurately identify the anomaly in the data, and provides a high-quality risk data sample for the classification model, thereby ensuring the accuracy and reliability of risk probability calculation. The risk probability is predicted by using the pre-trained risk classification model, so that the calculation efficiency is greatly improved. Compared with a traditional risk assessment method, the method does not need to manually carry out tedious data analysis and judgment, and the risk identification period is remarkably shortened. And the risk probability is converted into the corresponding risk value, so that the risk assessment result is more visual and easy to understand. Risk management and decision making of related financial departments are facilitated, and comprehensive control of financial risk conditions of enterprises is facilitated.

The invention relates to the field of robot technology and artificial intelligence, and particularly discloses a thumb independent optimization five-finger manipulator control method based on hierarchical strategy control. The method comprises the following steps: S1, designing a hierarchical strategy control algorithm framework, and obtaining current target object information; s2, dividing a high-level strategy network and a low-level strategy network, wherein the high-level strategy network determines whether to activate the action of a thumb; the low-layer strategy network outputs the action probability of each finger joint based on the decision of the high-layer strategy network; s3, evaluating a strategy optimization effect by using an evaluation module; S4, carrying out training and optimization; s5, repeating the training process in S4; s6, updating the strategy according to the collected experience after the action is executed every time; s7, after training is completed, the model of each finger and strategy parameters learned in the training process are stored; and S8, verifying the performance of the trained model in a simulation environment. According to the invention, the problem of uncoordinated actions caused by excessive coupling between fingers can be effectively solved.

The invention relates to the technical field of photovoltaic energy, and discloses a composite photovoltaic power generation prediction method based on visual identification, and the method comprises the steps: obtaining the equipment data, weather forecast data and historical power generation data of a photovoltaic station; constructing a photovoltaic power generation prediction model to obtain first prediction data of photovoltaic power generation; the method comprises the following steps: collecting environmental data of a photovoltaic panel before a photovoltaic station prediction day, extracting key features, and calculating to obtain influence correction factor data; and constructing a composite prediction model to obtain second prediction data of photovoltaic power generation. The prediction accuracy is enhanced by acquiring multi-source data, preliminary prediction is performed in combination with weather forecast and equipment data, the environmental data of the photovoltaic panel are acquired through a visual identification technology, key features are extracted, influence correction factors are calculated, and the influence of local environmental change on the generating capacity is captured. And the preliminary prediction result is combined with the influence correction factor to construct a composite prediction model, so that more accurate final power generation capacity prediction is obtained, and the prediction accuracy is improved.

The invention provides an automatic driving model based on a multi-modal large model, a training method and an automatic driving method, and relates to the technical field of computers, in particular to the technical field of automatic driving and artificial intelligence. According to the implementation scheme, a training corpus data set is obtained, wherein the training corpus data set at least comprises a visual text alignment corpus and a spatial understanding training corpus for an automatic driving scene; encoding visual data in the visual text alignment corpus by using a visual encoder to obtain encoded data; mapping the coded data by using a mapping layer; processing the mapped coded data, the mapped text data and the spatial understanding training corpus by using a generation layer to obtain a first prediction result and a second prediction result of the automatic driving model; parameters of the automatic driving model are adjusted based at least on the first prediction result and the second prediction result. The automatic driving model obtained through training in the embodiment of the invention has the understanding ability of multi-modal information and also has the reasoning ability in an automatic driving scene.