1366results about How to "Accurately determine" patented technology

The invention provides an inventory optimization method and system based on a deep learning model, and relates to the technical field of deep learning, and the method comprises the steps: obtaining the multi-dimensional data of a commodity, constructing a dynamic convolution kernel through employing a graph neural network, constructing a soft clustering distribution matrix in combination with a multi-layer perceptron, and obtaining a long-term dependence feature fusing a space dimension and a time dimension. And fusing the short-term and long-term features, inputting the fused short-term and long-term features into a bidirectional long-short-term memory network to generate a sales prediction sequence, and calculating a prediction confidence interval to obtain a final sales prediction result. And calculating a safe inventory level based on a sales prediction result, generating a replenishment decision by using a dynamic planning model based on deep reinforcement learning in combination with an inventory cost function, and finally sending the decision to a supply chain execution system. The sales volume is accurately predicted through the deep learning model, the inventory management is optimized, the storage cost, the stockout cost and the overstock cost are reduced, and the supply chain efficiency is effectively improved.

The invention provides a tunnel quality safety detection system and method based on laser radar data, and the method achieves the fusion and complementation of crack detection based on point cloud density change and crack detection based on curvature change, and achieves the quick recognition and precise detection of a crack region. The potential crack area is rapidly positioned through point cloud density change detection, and the boundary of the crack is further accurately positioned in combination with curvature change detection, so that the accuracy and integrity of crack detection are improved. For tiny deformation which is very tiny in change in point cloud density and curvature and is difficult to directly detect, a projection plane is further determined on the basis of the identified crack, and after point cloud data is projected to a two-dimensional plane, the characteristics of the tiny crack in the image are highlighted through image enhancement, so that the crack is identified. And then an edge detection algorithm is used to identify the micro crack so as to make up for the defects of a previous point cloud density and curvature detection method in the aspect of micro crack detection, and the accuracy and integrity of crack detection are further improved.

The invention discloses a real-time track obstacle detection method and system and a medium. The method comprises the following steps: acquiring a visual image of a track area; segmenting the visual image by using a lightweight target segmentation model to obtain a single-frame track line, an obstacle and the category of the obstacle; according to the single-frame track line, a final track area is obtained based on dynamic multi-frame track area fitting; judging whether the obstacle is in the final track area or not, and if yes, obtaining a detection frame of the obstacle in the visual image; and according to the obtained detection frame of the obstacle in the visual image, projecting the obstacle detection frame in the visual image into the radar point cloud data to obtain an obstacle point cloud range frame, and according to the obstacle point cloud range frame, calculating the distance from the obstacle to the train head. According to the invention, real-time detection and distance measurement can be carried out on the track obstacle, and the track area can be accurately determined in the image, so that whether the obstacle is in the track area or not can be judged, and a more accurate obstacle distance measurement result can be obtained.

The invention relates to the technical field of fault detection for a wireless communication network, and discloses a fault detection method for the wireless communication network. By collecting data of base station signal strength, network delay, data packet loss rate and user equipment signal quality, the problem of insufficient fault detection caused by a single index is solved. Through multi-dimensional data acquisition, the system can comprehensively evaluate network performance, the fault detection accuracy is improved, and different fault types can be effectively identified especially in a complex fault mode. By storing the data according to the time sequence, the problem of time sequence chaos is avoided, and accurate detection of time-varying faults is ensured. The comprehensive data vector generated by each time of sampling comprises a plurality of network performance indexes, so that the fault detection and positioning capability is improved. Abnormal values are eliminated through data preprocessing, the data quality is ensured, an accurate basis is provided for subsequent analysis, and the reliability of a detection result is ensured.

The embodiment of the invention discloses a speech recognition method and a related device, and at least relates to a speech recognition technology in artificial intelligence, speech data to be recognized are used as input data of a time delay neural network in an acoustic model, and an output layer of the time delay neural network comprises acoustic modeling units corresponding to a plurality of syllables respectively, so that the speech recognition efficiency is improved. And the syllable probability distribution corresponding to the voice frames included in the voice data can be obtained by taking the syllables as the recognition granularity through the time delay neural network. When syllable recognition is carried out through the output layer, auxiliary judgment can be carried out on the syllables to which the voice frames belong on the basis of pronunciation rules in combination with front and back syllable information of the voice frames, so that more accurate syllable probability distribution is output. Moreover, since the syllables are generally composed of one or more phonemes, the method has higher fault-tolerant capability, not only can more accurately determine the speech recognition result based on the probability distribution of the syllables, but also has low requirements for the quality of the speech data to be recognized, and effectively expands the application scenarios of the speech recognition technology.

The invention belongs to the technical field of data asset management, and discloses an enterprise data asset auditing method and system based on big data, and the method comprises the steps: collecting financial information data, business operation data, management decision data and external industry data of an enterprise; preprocessing the collected financial information data, business operation data, management decision data and external industry data to obtain a financial feature data set, a business operation feature data set, a management decision feature data set and an external industry feature data set; performing feature extraction and weighted fusion on the financial feature data set, the business operation feature data set, the management decision feature data set and the external industry feature data set to obtain a comprehensive feature data set; constructing an audit risk prediction model, inputting the comprehensive feature data set into the audit risk prediction model, and predicting to obtain an audit risk coefficient of the enterprise data assets; and a more comprehensive view angle is provided, and the data asset risk of the enterprise can be evaluated more accurately.

The invention relates to a tunnel ponding early warning method and device, computer equipment and a storage medium. The method comprises the steps that at least two first flow detection units are arranged at an inlet and an outlet of a tunnel, at least one second flow detection unit is arranged at a water outlet of the tunnel, local water accumulation threshold values of a plurality of water accumulation sensitive areas are determined based on historical water accumulation data, and the local water accumulation threshold values are arranged according to the threshold values to obtain a threshold value distribution sequence; dividing the threshold distribution sequence into a first sequence and a second sequence based on a preset proportion, and determining a first global threshold by a local ponding threshold at the boundary of the first sequence and the second sequence; calculating the inlet and outlet flow difference according to the first flow data and the second flow data, and further determining the water accumulation amount; and adjusting a second global threshold value according to the ponding risk index, and starting a corresponding risk early warning strategy when the ponding amount exceeds the first global threshold value or the second global threshold value. Low-cost and high-precision tunnel ponding monitoring is realized based on simplified sensing data, and the safety of tunnel passage is improved.

The invention discloses an intelligent identification method for high-position collapse geological disasters. The method comprises the steps that INSAR monitoring data, a radar topographic map and a remote sensing image map of a to-be-identified area are acquired; obtaining surface deformation information according to the INSAR monitoring data, and determining a hidden danger area according to the surface deformation information and a radar topographic map; registering the remote sensing image map of the hidden danger area based on the radar topographic map; and inputting the registered remote sensing image into a high-position collapse and slip identification model constructed based on CNN and RNN networks, and carrying out accurate identification on the high-position collapse and slip geological disaster point. According to the method, information of different data sources is fully utilized, the comprehensive capability and accuracy of geological disaster monitoring are improved, geological disaster monitoring is carried out on high-altitude collapse through multi-level and multi-angle analysis in combination with a deep learning network, the geological disaster occurrence place in a high-altitude area can be accurately recognized with high precision, and the geological disaster monitoring efficiency is improved. And scientific support is provided for geological disaster prevention and control work in high-altitude areas.

The invention provides a method for determining the volatilization behavior of antimony, a silicon single crystal rod, a silicon wafer and a solar cell, and the method comprises the steps: determining the volatilization behavior of antimony in a leading and releasing stage and / or an equal-diameter stage: in the leading and releasing stage, pulling out a small end from molten silicon; the total feeding amount and the initial antimony concentration are obtained; the mass, the phosphorus-antimony concentration and the phosphorus concentration of the small head are obtained; according to the total feeding amount, the phosphorus-antimony concentration, the initial antimony concentration and the phosphorus concentration, the volatilization amount of antimony in the small end pulling stage is calculated; in the equal-diameter stage, the actual resistivity of the silicon rod at multiple positions is obtained; converting the actual resistivity at the plurality of positions into actual phosphorus and antimony concentrations; acquiring the actual phosphorus concentration at each position; calculating the actual antimony concentration at each position according to the actual phosphorus-antimony concentration and the actual phosphorus concentration; and according to the actual antimony concentration, the effective segregation coefficient of antimony, the initial phosphorus concentration and the solidification fraction, the volatilization coefficient of antimony in the equal-diameter stage is fitted. By means of the method, the volatilization behavior of antimony in the single crystal pulling process can be determined.

The invention provides an AR positioning and direction correction method and device, equipment and a storage medium, and relates to the technical field of augmented reality, and the method comprises the steps: obtaining a first high-precision positioning point and a second high-precision positioning point, and respectively calculating azimuth angles in a geographic coordinate system and an AR coordinate system; the initial orientation when the device is started is then determined by using the angle difference between the azimuth angles. According to the initial orientation, coordinate orientation rotation can be carried out on three-dimensional scene elements in the AR scene, so that direction correction is completed. By using the high-precision positioning point information, the initial orientation of the equipment can be determined more accurately, so that the accuracy of AR positioning is improved. Moreover, no external auxiliary equipment or infrastructure is needed, and accurate AR positioning and direction correction can be realized only by means of the equipment and known high-precision positioning point information, so that the hardware cost is reduced.

The invention relates to the technical field of machining, in particular to a deburring method and a deburring device.The deburring method comprises the steps that a workpiece to be polished is fixed to a positioning tool; performing visual identification on the position of the to-be-polished workpiece to generate a first position signal; adjusting the to-be-polished workpiece to a preset position according to the first position signal; performing visual identification on the position of the to-be-polished workpiece to generate a second position signal; and the polishing tool is moved to a to-be-machined area inside or outside the workpiece according to the second position signal, and deburring operation is executed. According to the scheme, the defect that the deburring effect is poor due to inaccurate positioning in the prior art is overcome, and more accurate and efficient deburring operation is achieved.

The invention discloses a dam termite nest three-dimensional imaging method and system based on a ground penetrating radar, and the method comprises the steps: obtaining the three-dimensional ground penetrating radar data of a target region, and carrying out the data preprocessing, and obtaining the preprocessed three-dimensional ground penetrating radar data; performing feature extraction processing and encryption processing on the preprocessed three-dimensional ground penetrating radar data to obtain a multi-channel radar data body; based on the U-shaped network structure, constructing an ant nest imaging three-dimensional deep learning network model; and performing data imaging processing on the multi-channel radar data volume based on the ant nest imaging three-dimensional deep learning network model to obtain an ant nest imaging result based on the three-dimensional ground penetrating radar. According to the embodiment of the invention, the complex features of the ant nest and the dam structure on the three-dimensional ground penetrating radar image can be more accurately captured, and then the accuracy of ant nest imaging is improved. The method can be widely applied to the technical field of termite nest detection.

The invention discloses a textile texture defect detection system and detection method based on machine vision. The detection method comprises the steps that a matrix light source is located on one side of a textile detection area; acquiring an image of a detection area, detecting texture change of the textile in the detection area, and marking defect candidate areas; adjusting the angle change of the matrix light source and the brightness change of the defect candidate area, and generating an image; extracting multiple groups of image information, comparing the multiple groups of image information, and judging the defect position of the textile; the detected defects are marked in the image, and defect feature information is output; according to the method, the defect candidate area is preliminarily determined, and the matrix light source is matched to correspond to the defect area at different irradiation angles, so that the texture light and shade contrast of the surface of the textile in different directions is enhanced, the tiny offset of the weft skew defect is more clearly displayed in the image, the position of the defect is further determined, and the detection accuracy is improved. And the accuracy of defect detection can be improved.

The invention is suitable for the technical field of data analysis, and provides an industrial chain identification method and device, terminal equipment and a storage medium, and the method comprises the steps: firstly determining an enterprise operation keyword corresponding to each to-be-identified enterprise according to the operation scope fields of a plurality of to-be-identified enterprises; then, performing similarity calculation on the enterprise operation keyword of each to-be-identified enterprise and the industrial feature word and sentence of the corresponding industrial chain position to obtain the industrial chain position similarity of each to-be-identified enterprise, and then according to the industrial chain position of each to-be-identified enterprise and the industrial chain position similarity, identifying the to-be-identified enterprise according to the industrial chain position of each to-be-identified enterprise and the industrial chain position similarity. And determining at least two target enterprises from the plurality of to-be-identified enterprises, and finally determining upstream and downstream relationships among the target enterprises. Therefore, whether each to-be-identified enterprise is the enterprise of the corresponding industrial chain position is judged by determining the industrial chain position similarity, so that the target enterprises are accurately screened out, the upstream and downstream relationship between the target enterprises is determined, and a more accurate industrial chain is obtained.

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

The invention relates to the technical field of circuit component layout, in particular to a component layout system of a DC-DC power module, which obtains a candidate position range according to a first preset position range and a second preset position range, and obtains a reference distance according to an initial value set, a target value, a preset wiring width and a preset dielectric constant. According to the method, a series of possible candidate positions are generated by comprehensively considering different distance and angle combinations, so that the layout possibility of a target element on a target printed circuit board can be comprehensively explored, and an output voltage sequence and response delay time corresponding to each candidate position are obtained respectively; according to the method, performance of stability, accuracy, reliability, timeliness and the like of a circuit under different candidate positions is represented through the characteristic of the candidate positions, then the target priority corresponding to each candidate position is obtained, the candidate position corresponding to the maximum target priority is determined as the target position of the target element, the layout reasonability of the target element is improved, and the reliability of the circuit is improved. And the performance and the reliability of the whole circuit are improved.

The invention discloses a real-time laser coal checking system and method, and relates to the technical field of material management and inventory checking, and the system comprises the following components: a laser detection module, a data processing module, a communication module, a monitoring module and a server module. The laser detection module is adopted to perform high-frequency scanning on the coal pile to obtain the three-dimensional point cloud data of the coal pile, the crown block displacement data measured by the laser range finder and the material and density information of the material pile are combined, the volume and weight of the coal pile are calculated through an algorithm, the outer contour of the coal pile can be determined more accurately, and the accuracy of the coal pile is improved. According to the shape characteristics and the density distribution condition of the coal pile, the coal pile is divided into a plurality of small geometries for volume calculation, and compared with traditional manual measurement or simple geometric shape approximation, the method has the advantages that the measurement precision of the volume and the weight of the coal pile can be remarkably improved; and more accurate data support is provided for material management and inventory checking of enterprises.

The invention discloses a crop canopy phenotypic parameter extraction method and device, a medium and a product, and relates to the field of phenotypic parameter extraction, and the method comprises the steps: obtaining a three-dimensional point cloud set of a target crop; according to the three-dimensional point cloud set of the target crop, determining a point cloud skeleton of the target crop by using a Laplacian algorithm; then, optimization and instance segmentation are carried out on the target crop point cloud skeleton, and organ-level fine instance segmentation is completed; finally, crop phenotypic parameter extraction is achieved based on the three-dimensional point cloud and skeleton extraction, and phenotypic parameters comprise the plant height, the crown breadth, the leaf number, the leaf length, the leaf width and the leaf included angle. According to the method, the canopy phenotype parameters of the target crop can be accurately determined.

The invention provides a wound nursing intelligent decision-making method and system based on high-precision image recognition. The method comprises the following steps: in response to a received wound monitoring request, extracting a patient identifier, wound image information corresponding to a multi-angle high-precision image, wound background information and multi-modal sensor information from the wound monitoring request; a pre-trained three-dimensional convolutional neural network model is used for automatically recognizing the wound state, and a wound recognition result is obtained; based on the wound image information and the wound background information, assisting in positioning through an augmented reality technology; performing wound healing environment assessment based on the information of the multi-modal sensor; retrieving matched nursing strategy information from a preset nursing scheme database based on patient historical information and personalized treatment preference information corresponding to the patient identifier, the wound identification result, the wound positioning information and the wound healing environment evaluation information; and pushing the nursing strategy information. According to the scheme, the wound nursing quality is improved.

The invention discloses a thermal insulation layer defect detection method based on machine vision, relates to the technical field of defect detection, and solves the technical problem that single data matching cannot comprehensively judge defect reasons and causes errors to defect judgment. The method can automatically adjust the threshold value according to the gray feature distribution of different segmented areas in the whole image, is more suitable for the local difference and overall change conditions of the thermal insulation layer image, carries out the detailed analysis of the edge features through building a rectangular coordinate system for a target area with no gray feature matching result, and improves the accuracy of gray feature matching. According to the method, more clues about the defects can be mined from the edge information, and the distribution and formation mechanism of the defects in the thermal insulation layer can be more comprehensively understood by judging the integrity of the abnormal shape and combining and analyzing the associated region of the incomplete shape, so that the defect reasons can be more accurately determined.

The invention discloses a virtual digital human interactive question and answer method, system and device and a storage medium, and relates to the field of virtual reality. The method comprises the following steps: carrying out first processing on dialogue content of a user, and carrying out second processing on a facial image of the user to obtain a first emotional state; performing third processing on the text after the first processing to obtain a second emotional state of the user, and determining a target emotional state in combination with the first emotional state and the second emotional state; performing fourth processing on the text after the first processing based on a deep learning model to generate a first answer, and adjusting an expression mode of the first answer according to the target emotional state and the dialogue context to generate a second answer; and constructing a virtual digital person by using a virtual reality technology, and determining the facial expression, the body movement and the voice intonation of the virtual digital person according to the emotional tendency in the second answer to display the second answer. By implementing the technical scheme provided by the invention, the emotional state of the user can be identified more accurately, and then the answer more conforming to the emotion of the user is generated.

The invention relates to an intelligent maintenance robot for an electric tower anti-falling guide rail, and solves the problems that in a guide type anti-falling device for overhead transmission line inspection, when the guide rail has a deformation defect, the connection state between two adjacent sections of rails is abnormal, and a bolt group is abnormal, safety accidents are easily caused by manual maintenance; the robot comprises a moving platform, and the moving platform comprises a supporting frame, a driving synchronous belt wheel, a driven synchronous belt wheel, a synchronous belt, a driving motor, a driving roller, a driven roller, a first rear pressing mechanism, a second rear pressing mechanism, a first front pressing mechanism and a second front pressing mechanism. A mechanical arm is connected to the movable platform. The method can be widely applied to detection and maintenance of the rigid guide rail for preventing the electric tower from falling.

The invention relates to the technical field of data processing, in particular to an intelligent recommendation system fusing big data and AI, and the system comprises a scheme obtaining module which obtains a plurality of target marketing schemes; the scheme analysis module analyzes a plurality of target marketing schemes to determine a plurality of marketing features; the data acquisition module collects a plurality of historical behavior data of a user; the data analysis module analyzes a plurality of historical behavior data to determine user characteristics; the association determination module analyzes association between the user features and the plurality of marketing features based on the initial association AI model, and determines prediction priorities of the plurality of target marketing schemes based on an association analysis result; a recommendation module constructs a user recommendation page based on the predicted priority, and determines target priorities of a plurality of target marketing schemes based on the real-time behavior data of the user; and the feedback module compares a comparison result of the prediction priority and the target priority to adjust the initial association AI model to obtain a target association AI model. According to the invention, the accuracy of personalized marketing scheme recommendation of the user is improved.

The invention discloses a method and a system for detecting and repairing security vulnerabilities of computer software, and relates to the technical field of computer software security, and the key points of the technical scheme are as follows: performing feature extraction on the computer software through static feature extraction and dynamic feature extraction; the database module is used for extracting features of software, matching the extracted features with a known vulnerability feature library to detect whether security vulnerabilities exist in the software, judging a repair priority according to the severity of the detected vulnerabilities, determining a repair strategy according to the types of the vulnerabilities and performing repair, and storing the extracted software features, the detected vulnerability information and repair records by the database module. The vulnerability feature library is updated regularly; according to the method, the accuracy and the efficiency of vulnerability detection are improved in a mode of combining static feature extraction and dynamic feature extraction, the repair priority is judged according to the severity of the detected vulnerability, then the repair strategy is determined according to the vulnerability type, repair is performed, and the timeliness and the effect of repair are improved.

The invention discloses a chamfer defect detection method, device and equipment and a storage medium, and relates to the technical field of defect detection.The method comprises the steps that an obtained to-be-detected device image is preprocessed, and chamfer contour points and chamfer contour point pixel coordinates are determined in the preprocessed image; correcting the pixel coordinates of the chamfer contour points, and fitting a chamfer edge straight line by using the corrected pixel coordinates of the chamfer contour points; according to the chamfer edge straight line, screening the corrected chamfer contour point pixel coordinates, and determining a target chamfer end point; and calculating the actual chamfer length based on the target chamfer endpoint, and comparing the actual chamfer length with the preset chamfer length to judge whether the chamfer has defects or not. According to the method, the detection requirements of chamfers of different shapes and sizes can be met by preprocessing and correcting the images, fatigue and subjective judgment errors possibly existing in traditional manual detection are avoided through automatic image processing and data analysis processes, and the detection efficiency is improved.

The invention discloses an unmanned aerial vehicle task planning method and device for weather modification, and the method comprises the steps: detecting the feature data of a rainfall cloud system, determining the current moving trend and the current task waypoint of the rainfall cloud system, determining an estimated target waypoint, and planning a task route from the current position to the estimated target waypoint; executing the task route, and judging whether the estimated target waypoint is updated or not; if so, executing a route planning step according to the updated estimated target waypoint; if not, arriving at the current task waypoint based on the task route; determining a sowing operation area based on the feature data; and according to the sowing operation area, planning an operation route, and based on the operation route, sowing flame strips. The problems that in the prior art, an artificial weather influencing method is low in efficiency and high in implementation cost are solved. The effective utilization rate of the flame bars can be increased, the economic cost of weather modification operation is saved, and the weather modification operation can be accurately and efficiently carried out.

The invention relates to the technical field of tunnel foreign matter detection, in particular to a visual detection method and system for foreign matters in an intelligent tunnel and a medium, and the method comprises the steps: determining a texture difference coefficient of each contour in each frame of tunnel grey-scale map based on the complexity and average distribution condition of texture feature coefficients of all pixel points on each contour; determining a shadow change coefficient of each contour in each frame of tunnel grey-scale map based on the correlation of histograms of all super-pixel blocks in the contour of the same target between different frames of tunnel grey-scale maps and the dispersion degree of texture difference coefficients of the contour of the same target between different frames of tunnel grey-scale maps; and foreign matters in the tunnel are detected in combination with the neural network model. By analyzing the texture difference between the inner side and the outer side of the contour and the influence degree of the light on the texture of the same target area between different frames, the accuracy of tunnel internal foreign matter detection is improved.

The invention provides a method and a device for determining a linear operation and maintenance standard of a long-span bridge. The method comprises the following steps of: firstly, determining a quantitative relation between a track static long-wave uneven cis-chord measurement value and vehicle body vertical acceleration data; determining a vehicle body vibration acceleration limit value caused by the dynamic deformation of the high-speed railway bridge according to a vehicle body vertical acceleration limit value caused by the uneven static long wave of the track on the high-speed railway bridge, a vehicle body vibration acceleration value caused by the dynamic deformation of the high-speed railway bridge and a vehicle body vibration acceleration value caused by the random irregularity of the track; and finally, determining a linear chord measurement value of the high-speed railway bridge according to the quantitative relation and a vehicle body vibration acceleration limit value caused by dynamic deformation of the high-speed railway bridge. The method can effectively solve the problem that in the technical field of rail transit, the operation and maintenance standard of the line shape of a long-span bridge is not accurate.

The invention discloses a curved surface porous structure modeling simulation method and system for finite element analysis, and belongs to the technical field of mechanical engineering simulation, and the method mainly comprises the steps: carrying out the initial grid division of a target curved surface part, and obtaining a grid node set covering a curved surface; according to a preset hole center coordinate, three closest grid nodes are automatically searched in the grid node set, a local reference plane is established, and the hole axis direction is determined; generating an offset sketch plane in the normal direction of the reference plane, projecting the hole center to the sketch plane, drawing a circular sketch, and executing a stretching and cutting command to form a hole; and circularly executing the operation to realize automatic generation of multiple holes on the curved surface. And finally, the porous structure is subjected to grid division again, so that subsequent operation is facilitated. According to the method, the modeling process is combined with parameterization analysis and an automatic process, the efficiency and stability of porous modeling of the complex curved surface structure are remarkably improved, and a basis is provided for finite element pretreatment of the complex curved surface structure.

The invention relates to a game scene recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a rendering resource name and a rendering resource identifier required when a target game application renders a game picture corresponding to at least one game scene; matching the rendering resource name with a rendering resource name in a preset first corresponding relation; under the condition that the rendering resource name is successfully matched with the rendering resource name in the first corresponding relation, adding the rendering resource identifier into the first corresponding relation to form a second corresponding relation; and intercepting a corresponding target rendering resource identifier when the target game application renders each frame of game picture in the running process in real time, and determining a target game scene matched with the target rendering resource identifier based on the second corresponding relationship. In this way, it is not needed to consume a large number of computing resources to conduct image recognition on the game picture, therefore, the performance influence on game operation is reduced, and meanwhile the use scene of game scene recognition can be expanded.