179results about How to "Improve expressiveness" patented technology

The invention relates to the technical field of image processing, and discloses an industrial article appearance detection method and system based on machine vision. The method comprises the steps that a workpiece image is collected, and a standardized image is obtained through Gaussian filtering, histogram equalization and Otsu algorithm preprocessing; feature vectors are extracted through edge detection, Hough transform and a gray-level co-occurrence matrix; training a defect identification model by adopting a CNN of an attention mechanism; inputting an image for real-time detection; fusing the detection data and the environmental parameters by using a D-S theory; and establishing a database based on a distributed architecture to generate a quality report. According to the method, the detection accuracy is improved through multi-source information fusion, and efficient management and analysis of mass detection data are realized by adopting a distributed architecture.

The invention discloses a human body behavior recognition method and system based on a space-time fusion network, and relates to the technical field of behavior recognition, and the method comprises the steps: obtaining a human body skeleton sequence, carrying out the joint position coding of the sequence, taking the coded sequence as an input feature, inputting the input feature into the space-time fusion network based on graph convolution and Transform, and outputting a human body behavior recognition result; wherein the space-time fusion network comprises a plurality of groups of graph convolution Transform space fusion modules and multi-scale time fusion modules which are connected in sequence, after input features are input, local structure features and global space features are extracted through the parallel adaptive graph convolution module and Transform module respectively, feature fusion is carried out through the correlation fusion module, and the local structure features and the global space features are fused through the correlation fusion module. And the fused features are input into a multi-scale time fusion module, and are subjected to feature extraction through a multi-scale convolution branch and a Transform branch and then spliced, so that a more accurate human behavior recognition result is output.

A high-expressive-force audio generation method based on a natural language description text comprises the steps that S1, a pre-training multi-language text encoder is used for encoding an input natural language description instruction, and semantic information is extracted; s2, with text coding representation as a condition, semantic unit sequences of the audio are sequentially predicted through an autoregression model (AR), and the semantic unit sequences represent content event information appearing in the audio; s3, taking the text coding representation and the audio semantic unit sequence output in the S2 as a prefix condition, predicting a coarse-grained acoustic unit sequence of the audio through AR, and determining the overall duration and basic acoustic information of the audio; s4, predicting a fine-grained acoustic unit sequence of the audio by using a non-autoregressive model (NAR), and modeling audio detail representation and high-frequency information; and S5, inputting the multi-layer acoustic unit sequence into a vocoder to generate a high-quality audio waveform. The method directly supports the generation of the audio by a sentence of natural language description instruction, and improves the naturalness, expressive force and controllability of the generated audio.

The invention discloses a remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding, which relates to the technical field of remote sensing image processing, and comprises the following steps: step 1, collecting and preprocessing a remote sensing image, and constructing a training sample set; 2, constructing an image segmentation network, wherein the image segmentation network comprises a hierarchical encoder, a receptive field module unit and a network decoder which are connected in sequence; 3, training and optimizing the image segmentation network by adopting the training sample set to obtain a remote sensing image ground object segmentation model; and 4, collecting a remote sensing image to be segmented, and inputting the remote sensing image to the remote sensing image ground object segmentation model to obtain a ground object segmentation result. According to the method, the advantages of the advanced visual basic model and the U-shaped network architecture are combined, so that rapid and accurate segmentation of the ground target is realized.

The invention provides a multi-modal protein function prediction method and system, and the method comprises the following steps: carrying out the processing of a one-dimensional convolution layer and a pooling layer of protein sequence data, extracting the local dependence features in a protein sequence, and capturing the mode and key sequence features in the protein; using protein sequence data as input, and using a large-scale pre-trained protein language model to extract residue-level embedded information in a protein sequence as node features to be applied to the contact graph; the method comprises the following steps: taking protein sequence data as input, predicting the probability of contact between protein residues based on a Cb-Cb distance, and constructing a contact graph; and performing joint processing on features of different modes by using a multi-head attention mechanism and a residual structure, integrating data from different modes through feature fusion, and fusing the extracted key sequence features, the residue level embedded information and the contact graph. The prediction method is accurate in prediction and good in performance.

The invention provides a converter valve fault identification method based on voiceprint small sample learning, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining a to-be-identified target audio comprising converter valve environment noise, and carrying out the noise reduction processing based on FRCRN, and obtaining a noise-reduced audio signal; carrying out feature extraction based on the Mel frequency cepstrum coefficient and the Gammatone filter bank cepstrum coefficient, and carrying out dimension reduction on features based on a principal component analysis method to obtain feature vectors; inputting the feature vector into a voiceprint recognition model which is completely trained based on a voiceprint small sample for recognition, and obtaining a recognition result; according to the method, the to-be-recognized audio is denoised based on the FRCRN, most noise in the converter valve environment can be filtered out, and the technical effect of accurately recognizing the to-be-recognized audio is achieved; by adjusting the structure of the voiceprint recognition network, useful information of the features can be highlighted, redundancy of repeated information is reduced, and therefore the recognition accuracy of the voiceprint recognition model in the converter valve noisy environment is improved.

The invention discloses a mobile game scene interaction intelligent optimization method based on a generative adversarial network, and aims to improve the game experience of players. Comprising the following steps: S1, collecting behavior data and interaction information of a player in a mobile game, and generating a preliminary behavior feature model; s2, constructing a generative adversarial network model; s3, generating diversified game scene interaction examples according to the trained generator; s4, evaluating and optimizing the generated scene interaction example by using a discriminator; s5, real-time feedback of the player is received, and the behavior feature model of the player is updated; s6, dynamically adjusting a generation strategy based on the updated behavior feature model, and optimizing a scene interaction effect; s7, environment data are integrated, scene interaction is optimized in real time, and the immersion of players is enhanced; and S8, providing user-defined scene interaction options for the players, and allowing the players to adjust according to personal preferences. The interactive experience and game fun of players can be effectively improved.

The invention provides a fluid simulation data prediction and noise reduction method, system and device, and relates to the technical field of fluid simulation, and the method mainly comprises the steps: 1, constructing a simulation model; the simulation model comprises an auto-encoder, a denoising model and a decoder which are arranged in sequence; the auto-encoder is used for encoding condition input data and mapping the condition input data to a potential space to obtain characterization data; the denoising model is used for introducing noise into the representation data and converting the representation data into target data through denoising processing; the decoder is used for decoding the target data and mapping the target data to a functional space to obtain simulation result data; and step 2, inputting initial condition data of fluid dynamics into the simulation model, and outputting corresponding prediction result data. According to the scheme, the space noise reduction and output generation operation is completed in the potential space, the operation efficiency can be improved, the operation cost can be reduced, the output can be smoother, and therefore the quality and stability of the output are improved.

The invention discloses a Mura defect detection method and device of a TFT-LCD display screen and electronic equipment, and relates to the field of display screens. The method comprises the following steps: acquiring an original image of a TFT-LCD display screen to be detected; preprocessing the original image to obtain a target image, the preprocessing including image noise reduction and image enhancement; based on the target image, constructing a multi-scale feature map of the Mura defect, the multi-scale feature map comprising a local mean map and a local variance map under multiple scales: performing adaptive weight fusion on the local mean map and the local variance map to obtain a confidence map of the Mura defect; according to the confidence map, utilizing morphological operation to extract a suspected defect area; performing shape analysis and contrast analysis on the suspected defect area to obtain shape features and contrast features of the suspected defect area; and screening out a target Mura defect region from the suspected defect region based on the shape feature and the contrast feature. By implementing the technical scheme provided by the invention, the accuracy of Mura defect detection is improved.

The invention relates to the technical field of numerical simulation, in particular to a grid model generation method for the fluid displacement process of well cementation engineering. The method comprises the following steps: acquiring geological data of a well cementation project area, and constructing an initial geological model; well cementation engineering design data are obtained, well cementation engineering topological structure modeling is carried out, and a well cementation engineering topological structure model is obtained; according to the initial geologic model and the well cementation engineering topological structure model, fluid dynamic simulation is carried out, and a fluid characteristic matrix is obtained; performing fluid displacement process simulation according to the fluid characteristic matrix to obtain fluid displacement process data; performing fluid displacement process optimization on the well cementation engineering design data based on the fluid displacement process data to obtain optimized fluid displacement process data, and performing resource allocation redistribution on the well cementation engineering design data according to the optimized fluid displacement process data to obtain optimized well cementation engineering design data. According to the invention, the accuracy of fluid displacement simulation can be improved.

The invention relates to the technical field of audio processing and loudspeaker box control technologies, in particular to a loudspeaker box control method, system and device based on a built-in sound source and a storage medium, and the method comprises the steps: obtaining a selection instruction of a user, and calling a corresponding sound source file based on the selection instruction; receiving the called sound source file by using a built-in preset audio processing algorithm, and adjusting audio parameters of the sound source file; performing deep optimization combination on the processed audio parameters corresponding to the plurality of audio source files subjected to audio parameter adjustment by using an audio mixing algorithm so as to obtain a playing audio signal; and transmitting the playing audio signal to an integrated amplification circuit for power amplification, and enhancing the signal strength to drive a loudspeaker to work. The application has the effect of improving the audio quality and the user experience.

The invention relates to the technical field of deep learning, and discloses a farmland full-process management method and system based on deep learning, and the method comprises the steps: collecting image data, environment data and crop physiological indexes of a target farmland; generating noise reduction data of the environmental data based on a moving average algorithm; generating a farmland image based on the conditional generative adversarial network and the image data; extracting time features of the noise reduction data by using a crop evaluation model, and generating a dependency relationship of the noise reduction data based on the time features and a long-short term memory network; extracting multi-level spatial features of the farmland image according to the crop evaluation model, and further generating fusion features of the target farmland; and performing layer-by-layer processing on the fusion features by using a full connection layer and an output layer of the crop evaluation model to obtain a crop state value of the target farmland, generating a management decision of the target farmland according to the crop state value, and managing the target farmland. According to the invention, the efficiency of farmland whole-process management can be improved based on deep learning.

The invention discloses a marine organism detection method, device and equipment and a storage medium, and relates to the technical field of target detection, and the marine organism detection method comprises the steps: obtaining a marine organism data set, and dividing the marine organism data set into a training set and a test set; introducing a Swin Transform network and an efficient multi-scale attention mechanism to improve the initial marine organism detection model, and obtaining a reference marine organism detection model; training and testing the reference marine organism detection model by using the training set and the test set to obtain a target marine organism detection model; and detecting the marine organisms in the marine organism image by using the target marine organism detection model. The target marine organism detection model obtained by the invention can more accurately detect the marine organisms and automatically identify and position the marine organisms, so that the detection efficiency is improved, and reliable data support is provided for scientific research and environmental protection.

The invention discloses a diseased fish detection method and device, and belongs to the technical field of computer vision detection. In order to solve the problems that in the prior art, diseased fish disease detection efficiency is low, accuracy is not high, and real-time detection cannot be achieved, a diseased fish detection model is constructed, and the diseased fish detection model comprises a backbone network, a neck network and a detection head network; the method comprises the following steps: inputting a diseased fish image into a backbone network based on a spatial deep convolutional neural network for feature extraction to obtain a visual feature map, and then inputting the visual feature map into a contrast-enhanced attention transfer structure of a neck network for feature fusion processing to obtain a fused feature map; and the fusion feature map is input into a detection head network, and a sick fish target detection result is obtained through detection of a multi-head prediction small target detection algorithm, so that fish school disease detection is performed in real time, the detection efficiency and detection precision of fish diseases are effectively improved, and the method has relatively high practicability and application universality.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a multi-module collaborative voice generation method, which comprises the following steps: acquiring a reference text and reference voice, converting the reference text into a phoneme sequence and generating potential features, converting the reference voice into a Mel spectrogram and extracting style features, and extracting fundamental frequency information. A phoneme sequence and a Mel spectrogram are input into a text alignment module to generate alignment information, voice duration is predicted based on the alignment information and potential features, fundamental frequency of voice is predicted through fundamental frequency information, the predicted duration, fundamental frequency and style features are input into a decoder to generate a reconstructed Mel spectrogram, and finally the reconstructed Mel spectrogram is converted into voice audio data through a vocoder. According to the method, the generated voice can better reflect the natural rhythm and tone change of the text content by combining accurate control on the voice duration, the fundamental frequency and the style characteristics, and the rhythm and expressive force of the voice are enhanced, so that the naturalness and the fidelity of voice synthesis are improved.

The invention relates to a three-dimensional aquatic vegetation canopy reflection characteristic modeling method based on a real scene. The method comprises the following steps that leaf reflection and transmission spectrums are obtained through calculation of a plant leaf radiation transmission model; in combination with an actual aquatic vegetation scene, vegetation canopy reflection characteristics are described through canopy structure parameters and leaf BRDF; calibrating model parameters by adopting four-flow approximation and linear approximation, and applying the model parameters to approximate solution of vegetation canopy reflectivity; finally, a LuxCoreRender physical rendering engine is used for coupling input parameters such as incident radiation, vegetation canopy reflection factors, water optical attribute parameters and observation geometry, and the vegetation canopy reflectivity is calculated in combination with an aquatic vegetation scene. According to the method, a high-precision three-dimensional aquatic vegetation canopy reflection model is established, remote sensing radiation modeling precision and application value can be improved, an important tool platform is provided for wetland remote sensing monitoring and ecological protection and coastal wetland blue carbon sink function evaluation, and the method has popularization and application prospects.

The invention is suitable for the technical field of computers, and provides an optimization method, system and equipment for a particle system, and the method comprises the steps: loading the particle system, and randomly initializing the particle attributes of particles in the particle system; based on motion and interaction rules of particles, quantum calculation is adopted to predict behaviors of the particles in real time, and dynamic special effects of corresponding scenes are generated; according to the scene and the state of the player, the special effect attributes of the particles are dynamically adjusted, and the special effect attributes comprise the transparency, the color and the texture of the particles; the method comprises the following steps: tracking the life state of each particle in real time, marking each particle, generating a particle multiplexing pool, and generating a particle multiplexing strategy based on the particle multiplexing pool, and the particle multiplexing strategy is used for dynamic distribution of reusable particles. And the overall adaptability and rendering performance of the particle system are improved, so that a more real and vivid visual effect can be obtained.

The invention relates to a tree painting projection data collection and analysis system and method, and the system comprises a data collection module, a data preprocessing module, a feature extraction module, a quantitative analysis module, a classification and prediction module, and a result evaluation module. The modules cooperate with each other to realize standardized processing, feature extraction, quantitative analysis, intelligent classification and prediction and result evaluation of data. According to the method, the holographic theory and the Ama pothole theory are combined, the drawing features are finely analyzed through the cross-modal comparative learning and graph neural architecture search combined algorithm, a scientific and objective psychological data acquisition and analysis method is provided, the diagnosis sensitivity and specificity are improved, a powerful tool is provided for clinical psychological assessment, and the method is suitable for clinical psychological assessment. The method has important clinical and research values, and has wide application prospects in the fields of psychological problem screening, social psychological services, judicial, public security, marriage matching, talent selection and the like.

The invention discloses a financial user emotion and psychological portrait analysis method based on a large language model. The method comprises the steps of collecting user text data; preprocessing the collected user text data; performing sentiment analysis and psychological feature modeling on the user text data by using a large language model to obtain a sentiment feature vector and a psychological feature vector of the user; combining the emotion feature vector and the psychological feature vector of the user with a risk scoring model to generate a comprehensive risk score; and the user portrait and the risk score are visually displayed through a visual means. According to the method, the non-structured data and the structured data are combined, sentence-by-sentence sentiment classification and psychological feature modeling are performed on the user text data by adopting the large language model, unified feature processing and user portrait generation are realized, the integrity and multi-dimensional coverage capability of the user portrait are remarkably improved, and a more reliable basis is provided for risk assessment.

The invention discloses a digital twinning-oriented multi-engine adaptive rendering system and a digital twinning-oriented multi-engine adaptive rendering method. The adaptive rendering system comprises a component layer, an adaptation layer and an engine layer, the adaptive rendering method comprises the following steps: setting a GPU monitoring index and setting an engine switching condition according to the monitoring index; preprocessing the universal 3D object data, converting a data format into a data format of a corresponding object in a UE engine or a WebGL engine, and distributing the corresponding data to different engines; the method comprises the following steps: streaming different types of data from a Web side to a UE server side according to different schemes by utilizing a pixel streaming function provided by UE and a designed data streaming scheme, then carrying out real-time cloud rendering by a UE engine, streaming a rendering result to the Web side, and displaying the rendering result in real time on a browser; and monitoring the GPU in real time, and selecting a rendering engine according to monitoring data. The problems that an existing rendering engine is single, the rendering effect is not excellent, and GPU performance is limited are solved.

The invention discloses a collaborative voice gesture generation method and system based on deep learning, and the method comprises the steps: obtaining an initial gesture sequence, and carrying out the forward diffusion of the initial gesture sequence, and obtaining a disturbance sequence; obtaining a voice feature, an initial attitude feature and a time embedding vector, and carrying out cross-modal fusion on the voice feature, the initial attitude feature and the time embedding vector to obtain a multi-modal feature; and iteratively denoising the disturbance sequence under the guidance of the multimode features by using an extended long-short-term memory network to obtain a new gesture sequence. According to the method, the extended long-short-term memory network and the extended model are combined and used, the correlation between different multi-modal features and gestures can be effectively captured, natural and expressive gestures can be deduced from condition information, and the generated collaborative gestures have higher quality and diversity.

The invention relates to a cotton leaf disease identification method and system based on multilayer context feature screening, and belongs to the field of computer vision. According to the ConvNeXt-based cotton leaf disease identification method, a cotton leaf disease data set is constructed, and a system capable of identifying cotton physalospora piricola, brown blotch, angular leaf spot, verticillium wilt, fusarium wilt, anthracnose and powdery mildew and returning early warning information and prevention and treatment measures is established. According to the method provided by the invention, the ConvNeXt network is used as a backbone network, a feature enhancement module is added, the contrast among different regional features of the cotton leaves is improved, and on the basis, a feature screening attention mechanism of feature screening guided by multilayer context information is introduced, so that more effective feature screening is realized, and experiments show that the feature screening attention mechanism is more accurate. Compared with the recognition accuracy of the original ConvNeXt network, the recognition accuracy of the network model provided by the invention is improved by 4.1%.

The invention relates to the technical field of image recognition and processing, and discloses an emotion-driven 2D supernatural digital human video generation system of a multi-modal model, and the system comprises a voice input module which is used for receiving a voice signal of a user and then converting the voice signal into a digital signal; the voice preprocessing module is used for carrying out noise elimination and normalization processing on the voice signals; the voice emotion analysis module extracts emotion features based on the digital signals of the voice preprocessing module; the multi-modal generation module is used for mapping the emotional characteristics into digital human gestures and digital human population type actions; and the video generation module is used for synchronizing the gesture and the mouth shape action with the voice signal and generating a 2D digital human video. According to the method and the device, the speech emotion features are accurately mapped into the gestures and mouth shape actions of the digital human through the multi-modal generation model, the actions highly matched with the emotion types, the emotion intensity and the mood features are generated, so that the expression effect with rich emotions is visually presented, and the user experience is more realistic.

The invention relates to an adaptive emotion-driven timbre clone character-to-speech method and device. Segmenting the target text according to sentences, extracting semantic features, and splitting each sentence into a target phoneme sequence; the method comprises the following steps: splitting a reference text into reference phoneme sequences, splicing the reference phoneme sequences with each target phoneme sequence to obtain a combined phoneme sequence, processing a reference audio to obtain a reference voice feature and a frequency spectrum, processing based on a semantic feature corresponding to a sentence, the combined phoneme sequence and the reference voice feature to obtain a corresponding voice feature, and extracting a corresponding emotional feature from each sentence semantic feature, and processing based on the speech feature, the emotional feature and the target phoneme sequence corresponding to each sentence and the frequency spectrum to obtain a speech signal corresponding to the target text. And extracting emotional features from the semantic features of the target text, enabling the emotional colors of the voice signals to fit the text, and automatically adjusting the emotional colors of the voice signals based on the mapping relationship between the preset output features and the emotional features.

The invention discloses a hardware Trojan horse detection and positioning method based on a graph convolutional neural network, and the method comprises the steps: converting a circuit structure into a graph structure based on a graph learning method, and extracting the basic structure features of nodes in the process; constructing two new features Cov and Lfp based on a deep search strategy and a topological logic analysis method to perfect feature information of circuit nodes; aggregating neighbor features of the nodes based on the GCN and updating self node feature information to improve local sensing and generalization ability of the nodes; using a global feature fusion method based on an attention mechanism to extract and update global features of the graph, and fusing the global features with the node feature vectors after the neighbor features are aggregated; balancing training data based on a stochastic gradient descent thought in combination with a small-batch oversampling and undersampling method; and using a multi-layer perceptron model to train the balanced data based on a leave-one cross validation method, predicting an unknown circuit, and identifying potential HTs nodes in the circuit. According to the invention, HTs detection and positioning are realized.

The invention relates to the technical field of medical image analysis, in particular to a training method and system for a cataract recognition model and a storage medium. The method comprises the following steps: acquiring cataract eye image samples and non-cataract eye image samples in different stages; lesion region segmentation and image synchronous simulation enhancement are carried out on the cataract eye image samples and the non-cataract eye image samples in different stages to obtain cataract lesion enhanced image samples and non-cataract enhanced image samples; extracting local detail features of the lesion and extracting structural features of a mask pair, and constructing a multi-task convolutional neural network learning framework to train a cataract recognition model and optimize focus weighted loss; and obtaining a cataract related key feature set and carrying out online incremental learning updating to generate a cataract recognition online incremental updating model. According to the invention, the accuracy and robustness of cataract recognition model training can be improved.

The invention provides a social engineering attack detection method based on context awareness, and aims to solve the problem that dynamically changing social engineering attacks cannot be effectively handled in the prior art. According to the method, the emotional state, the decision-making mode and the daily behavior mode of a user are continuously monitored by constructing a context awareness system, and user behaviors are analyzed and monitored in real time in combination with a personalized behavior baseline model. The system measures the deviation between the user behavior and the baseline model by using a composite function and a multi-dimensional feature fusion technology, and when an abnormal behavior is detected, the system automatically triggers security policy adjustment, such as starting multi-factor authentication or limiting high-risk operation. Experimental results show that social engineering attacks can be effectively recognized in complex and changeable attack scenes, and the detection accuracy and response speed are remarkably improved. The method can be widely applied to the field of network security, and is especially suitable for an environment requiring highly customized security protection.

The invention relates to a drawing method and device based on touch panel pressure detection, a medium and equipment, and the method comprises the steps: determining a touch distance between a touch starting point of a touch drawing operation on a touch panel and a pressure sensor of the touch panel, and determining a resolution ratio of the touch panel to a display screen; determining a target display scale of the drawing coordinate system according to the resolution ratio, and adjusting the display scale of the drawing coordinate system according to the target display scale; determining drawing information of the drawing pen according to the pressure at the touch starting point, and controlling the drawing pen to execute pressing drawing according to the drawing information; in the pressing drawing process, in response to a newly-added touch drawing operation on the touch panel, determining drawing adjustment information according to pressing point information of the newly-added touch drawing operation and whether a track pressing point in the pressing movement track displaces or not; drawing adjustment is conducted according to the drawing adjustment information, and the drawing pen is continuously controlled to execute pressing drawing with the pressing movement track as the drawing track based on the completed drawing adjustment.

The invention relates to the technical field of medical image enhancement, and discloses a time-driven Transform diffusion model-based photoacoustic image enhancement method, which comprises the following steps of: constructing a diffusion model based on a stochastic differential equation; based on the forward process of a diffusion model, noise is added into the photoacoustic image reconstructed under the non-ideal condition, and the photoacoustic image reconstructed under the non-ideal condition is converted into a known prior distribution image; the prior information is continuously updated through the reverse process of the diffusion model, and the noise is predicted by using a time-related network, so that the training of the diffusion model is realized; sampling the noise state of the photoacoustic image reconstructed under the non-ideal condition through the trained diffusion model, and iteratively solving a reverse stochastic differential equation by using a numerical scheme so as to enhance the photoacoustic image reconstructed under the non-ideal condition to obtain an enhanced photoacoustic image; distortion and artifacts in the photoacoustic image can be suppressed, and detail information of the photoacoustic image can be recovered to the greatest extent.

The invention relates to the field of electric digital data processing, in particular to a multi-mode integrated rainfall prediction method based on artificial intelligence. The method comprises the steps of collecting meteorological data, training a neural network based on chaotic disturbance, training an LSTM based on quantum Monte Carlo, collecting new meteorological data, and inputting new precipitation influence factor features into the trained neural network based on chaotic disturbance for feature fusion. And inputting the actual feature vector set into the trained quantum Monte Carlo-based LSTM for prediction to obtain the precipitation of the target date. The existing multi-mode integrated rainfall prediction method has the problem of low prediction accuracy. The multi-mode integrated rainfall prediction method based on artificial intelligence provided by the invention is relatively high in prediction accuracy.