6551 results about "Feature based" patented technology

The invention discloses a Transform-based cross-modal fusion multi-modal emotion recognition method and device, which are used for solving the problems of modal isomerism, difficulty in time alignment and insufficient dynamic emotion modeling in a multi-modal emotion recognition task, and the method takes the accuracy and robustness of emotion recognition as performance evaluation indexes. Firstly, feature information of three modes of vision, voice and text is obtained, feature extraction is performed on each mode through a deep learning model, then features of different modes are fused by using a cross-mode Transform module, and a complex dependency relationship between the modes is dynamically modeled through a multi-head self-attention mechanism, so that more accurate emotion recognition is realized, and the emotion recognition efficiency is improved. And finally, performing emotion prediction on the fused features based on time sequence modeling and an emotion classification module. According to the method, the problems of modal isomerism, difficulty in time alignment and insufficient dynamic emotion modeling in multi-modal emotion recognition can be effectively solved.

A method for structuring the latent space of an autoencoder is provided. The method includes analyzing natural language descriptions related to input data; creating language-guided libraries that categorize and abstract data features based on the analyzed descriptions; mapping input data into the categorized and abstracted features within the latent space of the autoencoder; and training the autoencoder to minimize reconstruction loss while adhering to the structure imposed by the language-guided libraries.

The invention discloses a user behavior prediction system and method based on multi-modal data fusion, and particularly relates to the field of user behavior prediction, and the system comprises a multi-modal data collection module, a preprocessing and feature extraction module, a cross-modal fusion module, a user behavior prediction module, and a model optimization and feedback module. According to the system, multi-dimensional original data such as visual sense, auditory sense, text, physiological signals and environment context of a user are acquired in real time through a multi-modal data acquisition module; then, deep networks such as ResNet, VGGish and BERT are adopted to extract high-dimensional feature vectors of all modals, and contribution weights of features of different modals are dynamically learned through an attention mechanism; and finally, based on a time sequence model of Transform and LSTM, analyzing fusion features, and outputting probability distribution of future behavior intentions. And parameter joint optimization and continuous learning are realized through a multi-objective loss function and end-to-end back propagation.

The invention relates to the technical field of artificial intelligence security, and discloses a multi-modal large model confrontation security detection method and system, and the method comprises the steps: obtaining initial multi-modal data from original data sources, such as images, texts and audios, simulating the behavior of an attacker through reinforcement learning to generate a confrontation sample, and generating a cross-domain confrontation sample through transfer learning, extracting a multi-modal feature vector; the modal weight is dynamically adjusted through an attention mechanism based on the feature vector, the vulnerable modal weight is reduced, the credible modal weight is enhanced, inconsistency between abnormal modals is recognized in combination with disturbance analysis, and a weighted feature vector is output; abnormal input is detected by comparing semantic relevance of different modes, if semantic conflicts are found, an alarm is triggered, input is refused, and a corrected feature vector is output; and dynamically closing the untrusted mode and enhancing the trusted mode based on the semantic verification result, and outputting a final security detection result. According to the invention, the security of the multi-modal large model in a complex attack environment can be improved.

The invention relates to the technical field of land surveying and mapping, in particular to a surveying and mapping data intelligent analysis and management method and system based on the Internet of Things. The method comprises the following steps: collecting multi-source surveying and mapping data of a target area through the Internet of Things, and carrying out area perception fusion to obtain geological survey original fusion data; carrying out space-semantic-attribute surveying and mapping feature space reconstruction on the geodesic survey original fusion data to obtain a land semantic unit set; performing significant land element chain right confirmation on each space object in the land semantic unit set to obtain a mapping chain identification block; extracting land element association features according to the identification blocks on the surveying and mapping chain to obtain a land map embedded vector; and acquiring real-time target area multi-source sensing data, and performing land surveying and mapping task intelligent scheduling on the land map embedded vector by using the real-time target area multi-source sensing data so as to obtain a land surveying and mapping instruction network. According to the invention, the response speed, the scheduling efficiency and the task execution quality of land surveying and mapping can be improved.

The invention relates to the field of distributed machine learning, provides a big data-oriented distributed model training optimization method, and solves the problems of load imbalance, low resource utilization rate, large communication overhead, insufficient fault-tolerant efficiency and the like caused by data fragmentation staticization in the prior art. Load balancing is realized through intelligent clustering and overlapping control; the multi-dimensional heterogeneous resource evaluation model monitors calculation / storage / network indexes in real time, and realizes adaptive scheduling in combination with a task prediction and optimization algorithm; the hierarchical gradient synchronization mechanism adopts a tree-shaped parameter server and a dynamic compression technology, so that the communication traffic is reduced by 50%, and the precision loss is less than 0.8%; the incremental checkpoint system uses erasure code coding and parallel recovery to shorten the fault recovery time from 15 minutes to within 2 minutes, the resource utilization rate reaches 85% or above, the convergence speed is improved by 30%-40% in ResNet, BERT and other model training, and the large-scale training efficiency and the system stability are remarkably optimized.

The invention relates to the technical field of remote sensing monitoring, in particular to a remote sensing target detection method and system for a low-visibility image. The method comprises the following steps: acquiring multi-modal remote sensing image data; carrying out defogging enhancement processing on the low-visibility input image; normalizing the defogged RGB image and the defogged IR image, and then splicing and fusing the RGB image and the IR image; carrying out layer-by-layer coding on the multi-modal fusion image by adopting a mixed trunk structure fusing Transform, Mamba and CNN (Convolutional Neural Network); performing frequency domain decomposition on the trunk output features based on two-dimensional wavelet transform; generating an HR feature map by adaptively selecting a key region; and carrying out cross-scale aggregation on the HR feature map to obtain a detection target frame. Through the multi-modal image defogging enhancement and feature distillation mechanism, the definition and contrast of the remote sensing image in severe weather such as haze and rainy days are effectively enhanced, the shielding interference of environmental degradation on small target detection is weakened, and the stability and adaptability of the model in complex weather scenes are enhanced.

The invention discloses an electric power marketing management information platform daily electric power fitting method and related equipment, and relates to the technical field of electric power data management, and the method comprises the steps: obtaining historical load data, external environment data and equipment operation state data of a target region; constructing an initial load fitting model based on the historical load data; extracting a date characteristic factor according to a preset time classification rule, and dynamically correcting the initial load fitting model based on the date characteristic factor to generate a corrected load model; generating a multi-source fusion feature based on the external environment data and the equipment operation state data; and inputting the multi-source fusion features into the corrected load model, and outputting a target load prediction result.

The invention discloses an intelligent definition method and system for industrial edge data acquisition, a medium and equipment. The method comprises the following steps: acquiring operation data of field equipment in real time; performing protocol analysis and cleaning on the data to generate standardized data points, dynamically detecting the communication state and adaptively adjusting the acquisition frequency; classifying and aggregating the standardized data points into a running state feature set and calculating feature indexes; edge side anomaly detection is carried out based on the feature set, and a protocol container library is synchronously called to match a device communication protocol to generate matching information; an acquisition strategy optimization instruction is generated in combination with the abnormal result and the matching information, and transmission characteristic indexes and instructions are packaged; and structuring storage feature indexes according to equipment types and time dimensions to form a historical operation database, and managing a storage period by adopting a sliding window mechanism. According to the invention, protocol adaptive analysis, dynamic acquisition adjustment and edge intelligent analysis are realized through software definition, the hardware dependence and field debugging risk are reduced, and the data acquisition efficiency and the intelligent level are improved.

The invention discloses a voice interaction method and device based on lip language enhancement, equipment and a storage medium, and the method comprises the steps: extracting lip language features based on an image sequence of a lip region, and carrying out the feature extraction of a voice signal, and obtaining an audio feature; performing cross-modal fusion coding on the lip language features and the audio features to generate mixed features containing audio-visual information; inputting the mixed features into a large language model, understanding the intention of the interaction object and generating a corresponding semantic reply; and finally, synthesizing into voice and / or converting into characters. According to the invention, by introducing the lip features, additional visual clues are provided for speech recognition, and the robustness and accuracy of speech recognition can be significantly improved; effective fusion coding is carried out on the lip language features and the sound features, and semantic information splitting caused by simple and independent recognition is avoided; and the capability of the large model is fully utilized, so that more natural and more intelligent interaction experience is realized.

The invention relates to the technical field of industrial Internet of Things, in particular to a machine equipment online state monitoring and fault diagnosis system, which comprises the following steps of: acquiring multi-source heterogeneous sensing data through an edge computing node deployed on an equipment body, performing adaptive noise filtering and feature dimension reduction processing on original data, and acquiring multi-source heterogeneous sensing data; outputting a standardized equipment state vector set; inputting the equipment state vector set into a dynamic knowledge graph engine, constructing a fault evolution network comprising space-time correlation characteristics based on an equipment operation entropy change quantification model, and generating a graph node connection relationship with a weight coefficient; and inputting the fault evolution network into a migration reinforcement learning module, and outputting a diagnosis decision set comprising a fault type, a severity degree and an evolution path through knowledge migration of a cross-device fault mode. According to the method, the problems of edge redundancy and single feature expression in traditional rule-based atlas construction are effectively avoided, and the structuring ability and physical traceability of fault recognition are improved.

The invention discloses an industrial surface defect detection method based on multi-scale feature fusion, and the method comprises the steps: collecting the multi-source data of a detected surface in real time through a multi-modal sensor array, and forming a structured data set through time-space synchronization and denoising; constructing an adaptive geometric correction model to realize spatial transformation and scale normalization of multi-scale features, and cooperatively realizing cross-modal alignment and preliminary fusion through texture and physical attribute branches of a double-flow decoding network; dynamically reweighting the fusion features based on a defect physical model, strengthening physical mechanism defect characterization and suppressing interference; combining optical flow compensation and three-dimensional convolution to extract spatio-temporal evolution characteristics, and forming dynamic defect characterization; and finally outputting defect type and severity evaluation through the classification model in combination with the process parameter library. Therefore, the adaptability of the method to a complex industrial environment is enhanced, and the detection stability can be maintained under different materials, illumination conditions and dynamic interference.

The invention discloses a natural gas leakage quantification method based on a double-branch neural network, and the method comprises the steps: S1, loading original monitoring data, extracting basic features, constructing time sequence features based on the basic features and derivative features, and carrying out the standardization processing of the time sequence features; s2, dividing the time sequence characteristics into small flow data and conventional flow data by taking leakage flow 0.1 m < 3 > / h as a threshold value, and dividing the small flow data and the conventional flow data into a training set, a verification set and a test set; s3, constructing a double-branch neural network model; s4, formulating a training strategy, designing a loss function, performing performance verification on the model, and taking the finally stored model as an optimal model after training is finished; and S5, inputting test set data into the model, obtaining a leakage flow prediction value, calculating an evaluation index, verifying the performance of the model on the test set, and confirming the effectiveness and generalization ability of the model. According to the method, accurate prediction from data monitoring to leakage flow is realized, and the method is high in quantification capability, good in stability and high in generalization capability especially for small-flow leakage.

The invention discloses a BIM model automatic generation method and system based on point cloud data, and belongs to the field of building information modelling, and the transmission method comprises the steps: obtaining original point cloud data, and employing a filtering algorithm based on point cloud density adaptive adjustment to carry out the preprocessing of the point cloud data; constructing a voxel octree structure for the preprocessed point cloud data, and performing semantic classification on the point cloud; geometric modeling is carried out based on the segmented point cloud subsets, and a fitting algorithm is adopted to carry out shape completion on a point cloud area; semantic annotation is carried out on the components subjected to geometric reconstruction, a corresponding relation between component types and spatial attributes is constructed, fusion features based on a point feature histogram and a local curvature are adopted, and classification is carried out; a standard BIM component family is converted, and a three-dimensional BIM model is constructed through the mapping relation. According to the method, the voxel octree data structure and the deep semantic segmentation neural network model are combined, division and semantic recognition are performed on the point cloud data, the intelligent degree of the model is improved, and manual intervention is reduced.

The invention provides an arc fault detection method and device based on lightweight, and a storage medium, and the method comprises the steps: obtaining an arc current signal of a power distribution network load in a preset time period, determining a signal-to-noise ratio parameter, determining a dynamic window length according to the signal-to-noise ratio parameter, carrying out the Hilbert transformation of the arc current signal according to the dynamic window length, and obtaining an arc fault detection result. The method comprises the steps of obtaining m amplitude envelope data, extracting features from the m amplitude envelope data to obtain p time domain statistical features, calculating arc current signals by adopting a preset Fourier transform method to obtain arc current frequency spectrum data, processing the arc current frequency spectrum data to obtain q frequency domain features, and fusing the p time domain statistical features and the q frequency domain features based on a preset feature fusion algorithm to obtain a target arc current feature, and inputting the target arc current feature into a preset lightweight arc fault detection model to obtain an arc fault detection result. Therefore, the accuracy of arc fault detection is improved.

Disclosed in the present invention is a neural network-based defect detection method for gluing quality on aircraft skin. The method includes: data acquisition: taking photos of aircraft skin by using a camera to acquire image data; preprocessing the acquired image data; annotating the data by using annotation software to acquire a data set for network training; establishing a defect detection network model based on feature erasure and boundary refinement, where the defect detection network model includes a feature extraction network, a semantic-guided feature erasure module, a multi-scale feature fusion network, and a defect prediction network based on boundary refinement, which are sequentially connected, the data set is used for training the network model, and trained model parameters are saved; and detecting a directly collected skin gluing image by using the trained network model and outputting detection results.

The invention relates to a terrain real scene modeling method, device and equipment and a storage medium thereof. According to the method, multi-source heterogeneous data related to the terrain in a target area is integrated, a multi-modal data cube is generated through noise filtering and data fusion under a unified coordinate system, then a data cavity area is identified based on density clustering and elevation gradient analysis, and geophysical features are extracted. Innovatively constructing a neural implicit inference model fused with physical constraints to perform joint modeling on the earth surface and underground structures, and finally converting implicit terrain representation into an explicit three-dimensional terrain model; seamless fusion modeling of the earth surface and the underground space under the complex shielding environment is achieved, the physical rationality of the model and the hidden area reconstruction precision are remarkably improved, meanwhile, it is ensured that the generated model strictly conforms to the geological physical law, and the geological engineering safety and the planning reliability are effectively guaranteed.

The invention discloses a scene topology understanding method and device, a storage medium and a program product, and relates to the field of computer systems based on a specific calculation model, and the method comprises the steps: inputting a multi-view environment image set into a backbone network, and generating bird's-eye view features corresponding to the environment image set; calculating a spatial transformation matrix of the aerial view features at the current moment and the aerial view features of the previous K frames, and performing space-time alignment on the obtained K + 1 frames of aerial view features to obtain multi-frame fusion features; inputting the multi-frame fusion features into a map prior model to obtain aerial view correction features; decoding the aerial view correction features based on a topological decoder, and generating a lane topological graph; comparing the lane topological graph with the annotation data, calculating an error loss function, and optimizing network parameters based on the error loss function; and generating an optimized topological graph, and determining a scene topology result based on the optimized topological graph. By implementing the method, the environment topology understanding capability in a complex scene can be improved, and the generation precision of the lane topological graph is optimized.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical treatment and health and the like, and discloses a violation content auditing method, device and equipment based on multi-modal data and a medium. Inputting the visual semantic features and the composite audio features into a multi-modal model, generating fusion features through model alignment and fusion, and analyzing the fusion features based on a knowledge base to judge whether illegal content fragments exist in the multi-modal data, and when the illegal content fragments exist, positioning the illegal content fragments in the multi-modal data and generating an auditing report. According to the method, the visual semantic features and the composite audio features are fused, cross-modal compliance analysis is realized in combination with the knowledge base, frame-level or time-axis-level positioning is performed on the illegal content segments, and the auditing report containing the evidence is generated, so that the problems of insufficient single-modal detection accuracy and poor positioning capability are solved, and the auditing accuracy is improved.

The invention relates to the technical field of image processing, in particular to a feature point automatic labeling method and system based on point cloud data. The method comprises the following steps: acquiring regional multi-source point cloud data, and performing multi-modal data fusion to obtain point cloud fusion data; performing shoreline structure ground point cloud segmentation based on the point cloud fusion data to obtain a ground point cloud segmentation data set; performing edge detection on the ground point cloud segmentation data set, and identifying geometric salient points according to an edge detection result so as to obtain a feature point candidate set; performing ground feature type classification based on the feature point candidate set to obtain a target classification data set; distributing a symbolic pattern for the target classification data set and binding a point cloud feature attribute to obtain a symbolic data set; and performing multi-level symbol dynamic adjustment and interactive labeling based on the symbolized data set to obtain a symbol dynamic view. The method is helpful for improving the accuracy and efficiency of symbolization expression of the shore feature points, and has strong interactivity.

This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support enhanced sensor fusion techniques. In a first aspect, a method of includes receiving point cloud data for two or more frames from a radar device and generating scene flow parameter data based on the point cloud data. The method also includes generating voxel position adjustment data based on the scene flow parameter data, and generating feature concatenation information associated with two or more sensors based on the voxel position adjustment data and feature information associated with the two or more sensors. The method further includes performing feature detection and tracking based on the feature concatenation information to generate tracking information for one or more objects, and outputting the tracking information. Other aspects and features are also claimed and described.

The invention relates to the technical field of resource matching, and discloses a cross-platform e-commerce resource dynamic matching search method, which comprises the following steps: carrying out real-time analysis on commodity description information from different e-commerce platforms, extracting a core attribute of a commodity and generating a unified semantic representation; when cross-platform data conflicts occur, a conflict resolution strategy is dynamically generated, and the conflict resolution strategy is executed by a local preprocessing module; acquiring data content after conflict resolution, selecting a target edge node based on the data content in combination with user geographical location information, and dynamically configuring a cache data set of the target edge node; and generating corresponding multi-dimensional matching features based on user intention information in a natural query language in combination with the commodity data in the configured cache, determining a candidate commodity set and a corresponding search result based on the multi-dimensional matching features, obtaining feedback information of the user on the search result, and updating the intention analysis model and the matching strategy based on the feedback information. According to the invention, efficient cross-platform resource matching can be realized.

The invention relates to the technical field of science and technology operation management and control, and discloses a science and technology operation intelligent management and control method and system based on big data. According to the method, firstly, heterogeneous data sources in the scientific and technological operation process are collected, and a standardized operation data set is generated through multi-modal fusion processing; performing dynamic feature classification on the key operation indexes, extracting time sequence features and spatial correlation features of the key operation indexes, and constructing a multi-level operation state graph based on feature importance weights; then matching a service rule base with the atlas, identifying abnormal nodes and resource conflict paths, and generating an optimization instruction set containing node repair priorities and conflict resolution strategies; an executable management and control operation sequence is generated; and finally, collecting a feedback data stream, and updating the service rule base and the feature importance weight through an incremental learning mechanism to form a closed-loop optimization link. According to the method, heterogeneous data can be effectively integrated, the operation problem can be accurately identified, the optimization strategy can be quickly generated, and intelligent management and control and continuous optimization of scientific and technological operation can be realized.

The invention relates to an aerial photography target detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an aerial image acquired by an image sensor; inputting the aerial image into a pre-trained target detection model to obtain a target detection result; the target detection model comprises a backbone network, a neck network and a head network; wherein the backbone network is used for performing feature extraction on an aerial image to obtain image extraction features; the neck network is used for performing multi-scale fusion on the image extraction features to obtain a plurality of fusion features of different scales; the neck network comprises a bidirectional information transfer network, the bidirectional information transfer network comprises a separation and attention enhancement module, and the separation and attention enhancement module is used for generating fusion features corresponding to tiny targets; and the head network comprises a detection head corresponding to the tiny target and is used for obtaining a target detection result corresponding to the fusion feature based on the fusion feature. By adopting the method, the detection accuracy under the complex aerial image can be improved.

The invention discloses a calculation task allocation method and device, equipment, a storage medium and a product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-executed calculation task, and extracting the features of the to-be-executed task to obtain a feature label; decomposing the to-be-executed calculation task based on the feature labels to obtain sub-tasks; constructing a directed acyclic graph based on the dependency matrix of each sub-task, and performing topological sorting on each sub-task to obtain a priority and an execution sequence; according to the method, a to-be-executed calculation task is decomposed into a plurality of sub-tasks through feature labeling, a directed acyclic graph is constructed according to the dependency relationship among the sub-tasks, and the sub-tasks are distributed according to the reference execution time, the priority and the execution sequence. The priority and the execution sequence of each sub-task are determined by utilizing topological sorting, and the sub-tasks are allocated to each GPU for execution in combination with the reference execution time of each sub-task on different GPUs, so that the calculation efficiency of the calculation task is effectively improved.

The invention discloses a time-space interaction vehicle trajectory prediction method based on speed perception, and the method comprises the steps: obtaining driving trajectory data of a target vehicle and surrounding vehicles in a perception range of the target vehicle, inputting the driving trajectory data into a pre-trained trajectory prediction model, and obtaining the trajectory data of the target vehicle in a prediction time period; the trajectory prediction model comprises an encoder module, a speed sensing interaction modeling module and a decoder module; in the encoder module, a spatial-temporal feature encoder is used for obtaining spatial-temporal feature codes based on the driving tracks of the target vehicle and other vehicles; the scene perception encoder is used for extracting a global spatial dependency relationship between vehicles to obtain a scene perception spatial code; the speed perception interaction modeling module is used for extracting space-time interaction features and scene interaction features of the target vehicle and surrounding vehicles by using a multi-head attention mechanism based on the space-time features and scene perception space codes, and further obtaining global interaction features; and the decoder module is used for obtaining a driving track of the target vehicle in the prediction time period based on the space-time interaction characteristics and the global interaction characteristics. According to the method, the vehicle-scene spatial dependency can be accurately captured, and the trajectory prediction accuracy is improved.

The invention provides an electricity stealing behavior detection method based on feature fusion and a CNN-LSTM hybrid model, and belongs to the technical field of electric power information technology and deep learning. According to the method, after power load data and user behavior characteristics are subjected to data processing and enhancement, a deep learning model is combined with a self-attention mechanism to process user electricity consumption data, user electricity stealing behavior anomaly detection is carried out, and the electricity stealing risk identification accuracy and calculation efficiency can be remarkably improved. According to the invention, power grid enterprises can be helped to efficiently deal with electricity stealing conditions, and comprehensive and accurate identification of electricity stealing behaviors is guaranteed. By learning user historical load data, integrating time sequence characteristics of user loads and optimizing a data abnormity diagnosis and judgment mechanism, the electricity stealing user detection accuracy is improved, and reliable support is provided for power grid enterprise decision making.

The invention discloses a virtual historical character dialogue method and system with role knowledge and context awareness, and relates to the technical field of man-machine interaction, and the method comprises the steps: constructing a multi-level role depth model; when a question of a current user is received, identifying information of a virtual scene where the current user is located, analyzing micro-expressions of the face of the user and voice rhythm characteristics of speech of the user, analyzing an emotional state and an interaction intention of the user based on a multi-modal fusion algorithm, and generating a user state vector; executing a dynamic Prompt construction program, extracting related information from the multi-level role depth model and the user state vector, and generating a structured Prompt; and inputting the structured Prompt into a large language model, generating a reply text conforming to role features based on questions of the current user, and driving a virtual character model. The method solves the problem that in the prior art, virtual historical figures cannot provide real immersion and credible interactive experience with emotional connection.

The invention provides a model-based interaction method and system, wearable equipment and a storage medium, and belongs to the technical field of intelligent interaction.The method comprises the steps that in response to a received interaction instruction, voice data, a gesture image, eye movement data and an environment image are obtained based on the interaction instruction; extracting user intention features based on the voice data, the gesture image and the eye movement data, and determining scene type features based on the environment image; determining an interaction theme based on the interaction instruction, obtaining user historical interaction information associated with the interaction theme from a context memory database, and generating a context feature vector based on the user historical interaction information; and inputting the user intention feature, the scene type feature and the context feature vector into an intention recognition model based on quantum enhancement to obtain a user intention, and generating interaction response data based on the user intention. According to the invention, the accuracy of user intention recognition can be improved, and the intelligence of interaction is improved.

The invention relates to the technical field of artificial intelligence, and discloses a video generation method and device, equipment and a storage medium. The method comprises the following steps: splitting a target script through a large language model to obtain a split script, and extracting feature information of each role from the target script; generating a corresponding role image graph based on the feature information through a generation tool; respectively inputting the role image graph and each corresponding split script into a third language model to obtain a split graph corresponding to each split script; matching a corresponding target audio for each split script; combining each split script with the corresponding split image and the target audio to generate a corresponding split video; and combining all the split videos to obtain a target video. By adopting the method, matched videos with correct logic and plot coherence can be automatically and efficiently generated according to story characters, the individual requirements of users are met, and a large amount of labor cost, money cost and time cost can be saved.