1614 results about "Multi-task learning" patented technology

The invention provides a home abnormal state signal detection method and system based on multi-modal sensing, and relates to the technical field of detection, and the method comprises the steps: collecting human body motion, acoustics and environment parameters through a millimeter wave radar, an acoustic sensor and an environment sensor, inputting the parameters into a deep fusion network, a spatio-temporal attention mechanism and a multi-scale convolutional neural network are used to extract a spatio-temporal feature sequence, and joint probability features are formed in combination with an acoustic feature spectrum analysis result. And inputting the joint probability features into a time sequence knowledge graph, and obtaining scene adaptive features after processing by a graph attention network and a double-flow auto-encoder network. And finally, the multi-task learning network is combined with the risk propagation neural network and the recursive neural network to carry out anomaly prediction and risk level evaluation, and is combined with historical early warning information to output an early warning strategy. According to the invention, multi-modal data can be effectively fused, the accuracy and reliability of home abnormal state detection are improved, and a more accurate risk assessment and early warning strategy is provided.

Provided in the present application is an intelligent question answering method based on a collaboration between a large language model and a knowledge graph, relating to the technical fields of artificial intelligence and natural language processing, the method comprising: decomposing a complex question into a plurality of simple questions, and analyzing the degree of association between the simple questions and a basic function so as to form a multi-hop reasoning path; automatically extracting structured information from the simple questions on the basis of a multi-task learning framework of a large model, so as to construct a knowledge graph; and constructing a cumulative reasoning learning framework on the basis of a logic reasoning large model, and performing iterative verification on a process result formed by the knowledge graph on the basis of the multi-hop reasoning path, so as to correct the reasoning path until a correct answer is inferred.

The invention discloses a brain disease classification method and system. Precise diagnosis is realized through multi-modal data fusion and dynamic modeling. The method comprises the following steps: collecting multi-modal brain image information and cognitive behavior information of a user; performing dynamic function connection analysis on the resting state functional magnetic resonance time sequence signal to obtain a time-varying brain network feature matrix, and performing white matter fiber bundle topology reconstruction on a structure connection matrix; constructing a four-dimensional correlation tensor by using the time-varying network features, the structural connection weights and the anatomical features through a neurodynamic model; performing multi-task learning on the four-dimensional correlation tensor based on a time-varying graph neural network model, and outputting a quantitative diagnosis result; and finally generating a clinical classification report integrating the individualized brain network remodeling target, the disease progress risk layering and the treatment response prediction. By dynamically fusing the structure and functional features, comprehensive characterization of the pathological mechanism of the brain disease is realized, and decision support with both accuracy and interpretation is provided for clinical diagnosis.

The invention provides a multi-heat-source multi-material additive manufacturing optimization method and system based on machine learning, and relates to the field of additive manufacturing, and the method comprises the following steps: collecting process parameters, material physical properties and target response data in real time, and constructing a multi-source data set; on the basis, a multi-task learning model is trained, common features are extracted, target responses are synchronously predicted, a proxy target function is constructed through predicted values, if errors exceed a threshold value, experimental verification is conducted, and new data is fed back to update the model. And applying the weight coefficient to a multi-objective evolutionary algorithm, iteratively screening a Pareto candidate solution set, verifying a high-uncertainty solution, and updating the model to error convergence. And selecting and deploying an optimal parameter combination by using an entropy weight-TOPSIS method, and embedding an online learning mechanism to form closed-loop optimization. According to the method, multi-task learning and a self-adaptive evolutionary algorithm are combined, and efficient optimization of multi-heat-source multi-material additive manufacturing process parameters can be achieved.

The invention belongs to the technical field of intelligent perception and mode recognition, and particularly relates to a human body behavior recognition method based on millimeter wave radar and multi-task learning. The method comprises the steps that millimeter wave radar point cloud data and RGB video streams are synchronously collected, and a five-dimensional point cloud scene is generated through three-dimensional analysis and dynamic target extraction; a hierarchical Point Transform network is constructed to extract radar space-time features, and human body key point features are generated by using visual auxiliary attitude estimation; radar and key point features are dynamically fused through a cross-modal attention mechanism, a multi-task joint optimization strategy is combined, behavior classification serves as a main task, attitude estimation serves as an auxiliary task, and a behavior recognition result is output. According to the method, through multi-task cooperation and cross-modal feature interaction, on the premise of ensuring privacy security, the accuracy and robustness of human behavior recognition in a complex scene are remarkably improved, and efficient and reliable technical support is provided for the fields of intelligent monitoring, human-computer interaction and the like.

The invention discloses a water supply network sound leakage monitoring method based on multi-modal data fusion and multi-task learning, and the method comprises the steps: inputting an original sound signal, and carrying out the labeling of a label; converting the original sound signal to obtain a corresponding logarithmic Mel spectrogram; performing feature extraction on the original sound signal to construct a time-frequency feature set; forming a data set by the original sound signal, the logarithmic Mel spectrogram, the label and the time-frequency feature set; constructing a multistage task prediction network based on a residual convolutional neural network framework; performing multi-task training on the multi-level task prediction network by using the data set to obtain a water supply network sound leakage monitoring model; and inputting the original sound signals of the collection points into the water supply network sound leakage monitoring model to obtain a prediction result. The invention further provides a water supply network sound leakage monitoring device. According to the method provided by the invention, the leakage detection aspect is promoted to more comprehensive sound leakage monitoring application through a data-driven acoustic detection technology.

The invention relates to the technical field of distributed resource management and optimization, in particular to a distributed resource life cycle evaluation and dynamic updating method, which comprises the following steps: data acquisition: collecting multi-modal data of distributed resources, including resource state data, use behavior data, environment data and historical maintenance data; feature extraction: carrying out feature engineering processing on the multi-modal data, and extracting key indexes such as a resource health state, a degradation rate and environmental sensitivity; building a life cycle evaluation model, building the model by using the time sequence data of the resources based on a multi-task learning framework, and predicting the health state and the residual life of the resources; and optimizing a dynamic updating strategy, and monitoring and dynamically adjusting in real time. The method provided by the invention overcomes the problems of insufficient life cycle dynamics and rigid updating strategy in a traditional method, has the characteristics of high efficiency, intelligence and accuracy, and is suitable for intelligent management and optimization of new energy equipment, industrial assets and other distributed resources.

The invention belongs to the technical field of intelligent medical treatment, and particularly relates to a traditional Chinese medicine tongue diagnosis and prescription recommendation system based on multi-modal feature fusion. The system comprises a data preprocessing module used for preprocessing tongue picture image data and text data; the feature extraction module is used for extracting image features and text features from the preprocessed tongue picture image data and text data; the multi-modal feature fusion module is used for effectively fusing the extracted image features and text features by adopting a self-attention mechanism as a core fusion strategy to generate joint features; the multi-task learning module is used for completing parallel learning of a plurality of tasks on the basis of the representation of the joint features; and the model training and optimization module is used for designing a training method, a loss function and an optimization algorithm, so that the targets of disease name judgment, symptom judgment and prescription conditioning recommendation are completed after the multi-task neural network model processes the joint features.

A method based on a multi-task learning model comprises the following steps: acquiring and processing histopathological image data of gastritis through a data preparation and preprocessing step; feature extraction is performed by using a self-supervised learning pre-trained model, and image blocks are coded into high-dimensional feature vectors; and constructing a multi-task learning model, learning feature representation through a full connection layer module and an attention layer module, and outputting a classification result of each task. And carrying out model training and optimization by using an optimizer, adding multitask loss through a loss function, and dynamically adjusting the model performance. The trained model can automatically detect and grade gastritis, atrophy, acute activity, intestinal metaplasia and other pathological indexes, outputs a standardized evaluation result, and assists in pathological diagnosis. According to the method, a multi-task deep learning framework based on self-supervised learning pre-training is constructed, a traditional single-task modeling mode is broken through, deep learning framework design is driven through pathological index association, and accuracy and clinical practicability of non-neoplastic disease assessment of the stomach are remarkably improved.

The invention belongs to the technical field of medical image processing, and discloses a CT image segmentation and classification system based on segmentation feature guidance, and the specific technical scheme is as follows: the system adopts a shared encoder to extract general features, realizes collaborative optimization of segmentation and classification through a double decoding path, adopts a partial decoder in a segmentation path, and adopts a partial decoder in the segmentation path; in combination with a local feature attention module, through multi-scale feature fusion and a boundary perception mechanism, the region consistency of a global segmentation map is gradually optimized, edge detail information is supplemented, and a classification path generates a space attention weight through a segmentation feature guide module by utilizing segmentation prediction; the classification network is guided to focus on a focus area and suppress background interference, a self-adaptive loss weighting strategy based on multi-task learning is adopted, the double-task gradient flow is dynamically balanced, and the gradient competition problem in the multi-task learning is effectively relieved.

The invention belongs to the technical field of knowledge maps, and discloses a traditional Chinese medicine knowledge map fusion system based on semantic alignment. Comprising a multi-modal semantic embedding and entity alignment layer, a structure embedding and attribute fusion service presentation layer, an enhanced TransR model and knowledge graph construction layer, an intelligent rule engine and conflict resolution layer, an end-to-end automatic assembly line layer, a multi-task learning framework and incremental dynamic updating. Through innovative combination of a multi-level semantic alignment technology and an intelligent traditional Chinese medicine rule engine, end-to-end automatic fusion of traditional Chinese medicine knowledge maps is realized, and heterogeneous knowledge maps from a plurality of data sources are automatically converted into a standardized unified knowledge map through an assembly line. Compared with a traditional character string matching method, the accuracy rate of the method is about half, and the alignment accuracy rate is improved to 80-90%. More importantly, under the same data condition, the fusion time is greatly shortened, and the incremental updating efficiency is remarkably improved.

The invention discloses an intestinal cancer immune response graph neural network prediction method, a medium and equipment, and the method comprises the steps: collecting pathological image information, immunodetection information and basic clinical information, extracting a tissue space distribution characteristic spectrum through a deep convolutional network, and constructing a graph neural network model in combination with an immunomarker expression characteristic matrix; spatial interaction characteristics of a tumor microenvironment are modeled by adopting a graph attention mechanism, finally a treatment response probability, an optimal treatment opportunity and an adverse reaction risk are predicted through a multi-task learning framework, and a clinical decision report containing a prediction response curve, a risk early warning threshold and a treatment time window suggestion is output. According to the method, through multi-modal data fusion and spatial interaction modeling, accurate prediction of intestinal cancer immunotherapy response is realized, and a more comprehensive reference basis is provided for clinical decision making.

The invention relates to the technical field of power grid monitoring, in particular to a power operation risk identification method, system and device based on multi-modal data fusion and a storage medium. In order to solve the problems of multi-modal data splitting, topological constraint missing and the like in traditional power disturbance analysis, an improved BERT model is constructed, and electrical signal time-frequency features and text semantic information are mapped to a unified vector space through a multi-modal embedding mechanism; a time sequence attention mechanism is adopted to establish a time dependency relationship between signals and texts, and a graph attention network is combined to realize risk propagation modeling under power grid topology constraints; and collaborative optimization of disturbance classification, risk prediction and trend analysis is carried out through a multi-task learning framework. The technical problems that heterogeneous data fusion is difficult and risk identification precision is insufficient are effectively solved, accurate identification and intelligent early warning of electric power operation risks are achieved, and the safe operation level of a power grid is improved.

The invention provides an airfoil flow field prediction method based on multi-task learning, and the method comprises the steps: firstly building an airfoil flow field prediction model based on multi-task learning, which comprises an encoder, a backbone network and a multi-head decoder; then training the established model by using an airfoil flow field data set and adopting an optimization strategy based on multi-task learning; and finally, performing geometric parameterization and grid generation processing on an airfoil which actually needs flow field prediction to obtain standardized airfoil flow field data, and inputting the airfoil flow field data into the trained airfoil flow field prediction model for prediction to obtain full flow field physical quantity distribution and lift-drag coefficient information. According to the method, a multi-task loss optimization strategy is used in the prediction model training process, so that the problem of conflict between airfoil profile surface loss and volume loss optimization can be effectively solved, and then the construction of an airfoil profile proxy model and the accurate prediction of flow field information and aerodynamic parameters are realized.

The invention relates to an intelligent computing resource allocation method based on reinforcement learning. According to the technical scheme, the method comprises the steps that monitoring data from different sources including hardware monitoring, software logs and network bandwidths are fused, and a multi-dimensional time sequence state space is formed; carrying out dimensionality reduction and de-noising processing on the multi-modal data by using a depth auto-encoder; multi-task learning MTL is introduced into time sequence modeling, and resource requirements and state evolution of multiple tasks are predicted at the same time; generating a plurality of predictive resource scheduling strategies by using a GAN (Generative Adversarial Network), and dynamically selecting a strategy scheme when a load changes; each strategy is realized by an independent sub-network, and part of core knowledge is shared; through a strategy evolution mechanism, according to a historical feedback optimization strategy combination including task completion time and resource consumption, in a heterogeneous resource environment including a plurality of cloud computing platforms and edge computing nodes, based on difference of resource types, fine-grained scheduling of strategies is carried out; and scheduling the decision by using a distributed Q-learning mechanism in the reinforcement learning model.

The invention provides a personalized fitness system and method based on multi-modal data and an adaptive large model. According to the method, multi-modal data are integrated, and heterogeneous data collaborative analysis is realized by using a space-time alignment algorithm and a confidence coefficient weighting mechanism. A multi-task learning framework is adopted, physiological prediction, exercise risk early warning and psychological incentive strategy generation tasks are synchronously processed, a user stage target is adapted through a dynamic attention mechanism, and federal learning and transfer learning technologies are combined. A nonlinear periodic planning engine based on reinforcement learning dynamically adjusts training load and action difficulty according to real-time biomechanical simulation results and recovery state evaluation, and meanwhile, a lightweight model compression technology and end-side reverse dynamics calculation are adopted. Based on the scheme, the exercise performance prediction precision and the early warning timeliness are improved, and the exercise loss risk caused by overtraining is reduced; the cold start data bottleneck is broken through; low-delay virtual coach interaction and privacy protection are realized; and dynamically adjusting the training intensity and the incentive strategy.

This specification describes systems and methods, implemented as computer programs on one or more computers in one or more locations, for controlling an agent to perform multiple different tasks in an environment. The described techniques partition the architecture of a controller into a dispatcher that understands the environment and an executor that understands how to control the agent, with a control channel between them that structures the partitioning. This allows implementations of the controller to generalize better.

The invention relates to the field of data processing, and particularly provides a big data mining method and system based on digital enterprise management, and the method comprises the steps: obtaining multi-modal session data generated in the process of carrying out digital service interaction between a target enterprise and a user, extracting a user demand feature set from the multi-modal session data, and based on a preset multi-task learning framework, carrying out joint training on the user demand feature set, generating a demand analysis model, calling the demand analysis model to analyze the user demand feature set, generating an optimization strategy set associated with the target enterprise service process, and sending the optimization strategy set to the server. And updating the digital service execution logic of the target enterprise according to the optimization strategy set, and performing incremental training on the demand analysis model based on user feedback data. According to the invention, the response efficiency and the function adaptability of the digital service process can be improved.

The invention relates to the technical field of computer vision, and particularly discloses an adaptive pyramid and multi-stage path aggregation-based lightweight multi-task small target detection algorithm, which comprises an adaptive feature pyramid network, a multi-stage path aggregation module, a lightweight Transform module, an optimized channel attention mechanism, a multi-task learning head and an algorithm training method. According to the lightweight multi-task small target detection algorithm based on adaptive pyramid and multi-stage path aggregation, dynamic weight adjustment of different levels of features is realized by combining an adaptive FPN, and the expression ability of multi-scale features is enhanced. The MPAM module introduces a lightweight Transform module on the original basis, global feature modeling is performed by using an axial attention mechanism, the perception ability of the model to a small target is improved, and a channel attention mechanism is optimized to reduce calculation overhead.

The invention discloses a power equipment fault prediction system based on big data analysis. The method comprises the following steps: acquiring initial equipment multi-dimensional data; constructing a dynamic topology network of the power equipment, including a dependency relationship between the equipment and a fault propagation path, performing embedded learning on the dynamic topology network by using a GNN graph neural network, and extracting equipment collaboration features in the initial equipment multi-dimensional data; a multi-task learning framework is constructed in combination with the equipment cooperation features to predict the equipment fault probability and the remaining service life, and an equipment health index is obtained; and acquiring environmental parameters, dynamically adjusting a fault judgment threshold based on the equipment health index and the environmental parameters, generating a prediction result, integrating the prediction result with an SCADA system, and triggering graded early warning. And the influence of environmental factors on the operation state of the equipment is fully considered. Under different environmental conditions, the equipment fault risk can be judged timely and accurately.

The invention discloses a machine generated text detection method, a terminal, a medium and a program product in the field of natural language processing, and the method comprises the steps: inputting a to-be-detected target text into a trained text detection model, and obtaining a detection result outputted by the text detection model; the text detection model comprises a first semantic feature extraction network, a second semantic feature extraction network and a fusion classification network; the first semantic feature extraction network is used for extracting semantic features of keywords in a target text to generate a first representation vector; the second semantic feature extraction network is used for extracting overall semantic features of the target text and generating a second representation vector; the fusion classification network processes the first representation vector and the second representation vector to generate a detection result about whether the target text is a machine-generated text; the training of the text detection model adopts a multi-task learning strategy. According to the method, multi-task training is introduced, so that the accuracy and robustness of machine generated text detection are effectively improved.

The invention relates to the field of big data analysis, in particular to an intelligent recommendation system based on user behaviors. The method comprises the following steps: acquiring user explicit behavior data and user implicit behavior data in a system, acquiring interaction depth index data of a user in the system, adding noise to sensitive behaviors in the data by using a differential privacy technology, establishing a variable time attenuation function, segmenting a behavior sequence according to sessions by using a hierarchical Transform encoder, and obtaining a variable time attenuation function; establishing a GNN user intelligent recommendation model based on a heterogeneous graph neural network, connecting the multi-task learning framework with the heterogeneous graph neural network to obtain a target GNN user intelligent recommendation model, optimizing a recommendation result of the model by using a multi-target optimization algorithm, inputting feature multi-granularity behavior data into the user intelligent recommendation model for recognition, and performing recommendation on the target GNN user intelligent recommendation model. And obtaining a user recommendation result. The problem of recommendation homogenization caused by a single target can be avoided, and intelligent recommendation efficiency and recommendation accuracy are improved.

The invention provides a city calculation basic model and equipment based on a Mama time sequence, and relates to the technical field of data processing. In the model provided by the embodiment of the invention, a Mama framework is combined with multi-task time sequence analysis. Aiming at the non-stationarity of urban time series data, a frequency prompt network is designed for decoupling in combination with a Koopman operator theory and dynamic mode decomposition, a steady mode and non-stationary fluctuation are analyzed from the angles of time and frequency, and a frequency mode memory pool (FPMP) is introduced for realizing cross-scene feature reuse. The advantage of a Mama model in capturing long-term time dependence is utilized, and an attention mechanism similar to Mama is designed to simulate channel dependence in a multivariable time sequence. A learnable supplementary sequence and a multi-task prompt mark are introduced to support dynamic multi-task adaptation, and the contradiction between urban data isomerism and task diversity is relieved. Shared knowledge and specific task knowledge are balanced through shared experts and specific task experts of the multi-task attention module, the negative migration problem in multi-task learning is relieved, and the generalization ability of the model is enhanced.

The invention provides an equipment operation and maintenance intelligent decision support system based on large model reasoning, and aims to improve the accuracy of equipment fault prediction and the intelligent level of operation and maintenance decision. The system obtains equipment operation data in real time through a data acquisition module, performs reasoning analysis on equipment health conditions by using a large-scale pre-trained deep learning model, and predicts the residual service life of equipment and various fault types. The system combines multi-task learning and a multi-objective optimization algorithm, intelligently optimizes operation and maintenance decisions, generates personalized maintenance suggestions, helps operation and maintenance personnel to effectively reduce the downtime of equipment, reduces the maintenance cost, and prolongs the service life of the equipment. The system can be widely applied to the fields of manufacturing industry, energy, traffic and the like, and the accuracy and efficiency of equipment management are remarkably improved.

The invention relates to the technical field of intelligent power distribution, in particular to an optical storage and charging integrated system based on a distributed soft bus, which comprises hardware equipment: a photovoltaic module, a wind driven generator, an energy storage module, a charging pile, acquisition equipment, a photovoltaic controller, a DCDC module and a mains supply / thermoelectric generator; communication and control: a distributed soft bus, a time sensitive network (TSN) and an intelligent control unit (EMS); according to the scheme, photovoltaic, wind power, energy storage, charging piles and other hardware equipment are connected through a distributed soft bus, real-time transmission of control instructions is achieved through a TSN, data are analyzed through intelligent algorithms such as a charging and discharging model and a multi-task learning model, an optimization strategy is generated, multi-energy cooperative control (including photovoltaic direct supply and energy recovery in the case of faults) is executed through an EMS, and the energy efficiency is improved. A user can set priorities through a terminal to participate in scheduling, and finally model parameters are corrected based on feedback data to form a light storage and charging integrated system of data acquisition, prediction optimization, intelligent control, user interaction and closed-loop evolution.

The invention provides a software supply chain risk analysis method. A data acquisition and preprocessing module acquires component information from a plurality of software warehouses and performs format unified processing; the components are modeled as nodes through a hypergraph construction module, the dependency relationship is modeled as hyperedges, and a hypergraph structure is dynamically constructed and updated so as to express many-to-many dependency relationship more accurately; performing representation learning on the hypergraph structure through a hypergraph neural network, generating embedded vectors of the components, and fusing context features of the components; based on an embedded vector, risk scoring, anomaly detection and classification are carried out by adopting multi-task learning and a graph attention mechanism, so that the generalization ability of the model and the risk identification precision are improved; online incremental updating of a hypergraph structure and model parameters is achieved through a dynamic updating and feedback mechanism, and the real-time performance and stability of the model are ensured. According to the method, the data transmission security, the transmission efficiency and the compatibility between devices are improved, and the method has higher risk analysis capability and system adaptability.

The present invention discloses a neural network accelerated simulation method for the radar scattering field of a wide-band target group, belonging to the technical field of electromagnetic simulation. The method of the present invention constructs a KAN neural network model at the central frequency of the wide band, and constructs KAN neural network models at other target frequencies through transfer learning or direct training; uses the trained KAN neural network model to generate a multi-frequency point numerical Green's function data set, and then constructs a wide-band training sample to train the multi-task learning model to realize the global prediction of the numerical Green's function of the entire target wide band; uses the numerical Green's function output by the multi-task learning model to realize the fast simulation of the scattering field of the wide-band target group. The method of the present invention can realize the fast and accurate simulation of the radar scattering field of the wide-band target group.

The invention provides a psychological analysis method and system based on multi-modal features, and relates to the technical field of psychological assessment. The method comprises the following steps: synchronously obtaining voice data, video data, text data and physiological signal data of a user; respectively denoising the data to obtain each piece of denoised modal data; performing feature extraction on each modal data to obtain each modal feature; mapping each modal feature vector to a unified semantic space through an attention weighting mechanism to generate a fusion feature matrix; a trained psychological analysis model is adopted to perform multi-task learning on the fusion feature matrix, and emotion classification, pressure indexes and psychological health risk scores are synchronously output; and updating model parameters of the psychoanalysis model through an online incremental learning mechanism based on the real-time feedback data of the user and the newly added sample. Through accurate data denoising, efficient feature extraction and flexible model optimization, comprehensive and accurate analysis of the psychological state of the user is realized.

The invention relates to the technical field of photovoltaic power prediction, in particular to a photovoltaic power station cluster power prediction method and system based on multi-task learning, and the method comprises the following steps: obtaining the three-dimensional position and shielding characteristics of a power station, constructing a sun incidence vector, recognizing the array shielding relation and space illumination distribution, and extracting the wind speed disturbance characteristics. And deducing a propagation path and a response time sequence, and executing multi-task prediction dynamic adjustment output. According to the method, a three-dimensional space shielding relation is established by combining topographic features and a solar radiation path, space shielding characteristics are measured and calculated through an earth surface inclination angle, an orientation angle and a shielding angle, the influence of the topography on illumination distribution is effectively captured, the interference of landform differences on photovoltaic output is reflected, and meteorological and space cooperation features are fused; the prediction precision is improved, non-linear errors caused by terrain and space distribution are considered, the adaptive capacity of power prediction to dynamic disturbance is enhanced, and steady-state operation guarantee of a photovoltaic power station cluster under the complex terrain condition is achieved.

The invention relates to the crossing field of precision agriculture and artificial intelligence technology, in particular to a soil component detection system based on machine learning and infrared spectroscopy, which is characterized in that a soil spectrum is acquired on site through a portable Fourier infrared spectrometer, and after pretreatment, feature vectors are constructed by fusing climate, soil and crop data; the deep learning decision-making module extracts spectral features by using one-dimensional convolution, fuses multi-dimensional information through an attention mechanism, synchronously outputs a fertilization scheme, crop suitability scores and soil improvement measures by a multi-task learning sub-network, and finally, verifies by combining an agronomic knowledge base so as to obtain a fertilization result. According to the method, a comprehensive decision report containing a quantitative fertilization formula, a crop suitability sequence and a soil improvement scheme is generated, precise agricultural guidance is realized, spectral features are automatically extracted by adopting a one-dimensional convolutional neural network, and a multi-modal data fusion and multi-task learning framework is combined, so that the system achieves relatively high precision in the aspect of soil nutrient prediction.