751 results about "Feature combination" patented technology

The invention discloses a multi-field part size and appearance defect intelligent detection system, and relates to the field of image analysis. The system comprises an image acquisition module, an image preprocessing module, a feature extraction module, a defect identification and size measurement module, a data processing and analysis module, an automatic control module and a man-machine interaction module. According to the method, CNN and LBP, Hough transform and SIFT algorithms are fused, high-level semantics and bottom-level texture / geometric features are considered, 2304-dimensional fusion feature vectors are formed through feature splicing, the feature extraction integrity of parts in multiple fields is improved, texture detail features can be accurately extracted, geometric shape features can be accurately obtained, and the method is suitable for large-scale popularization and application. Meanwhile, the adaptive feature selection mechanism dynamically optimizes the feature combination according to the detection result, the problem of calculation redundancy is reduced, and the detection precision is ensured while the detection efficiency is improved.

The invention relates to a remote education data processing system which comprises the following steps: under a remote teaching task, pre-defining a task intention and a data expectation point; a semantic timestamp and a task binding label are printed on each data fragment; mapping the collected confusion data including silence, eye movement drift and prediction into a unified learning semantic vector; a micro-expression + interactive behavior + time sequence decision path ternary modeling mode is introduced, and a potential cognitive intention corresponding to the feature combination is recognized; teaching context information is fused; constructing a cognitive state mapping model; reasoning a current cognitive state label from multi-modal sensing data; searching intervention track VS effect feedback data in a historical database; generating a predicted intervention behavior sequence by using a sequence modeling algorithm; a dynamic combination suggestion chain including light prompt, content reconstruction, personalized practice and tutoring invitation is adopted; and superposing the cognitive state sequences of all students into a group cognitive trajectory map.

The invention discloses a method for identifying impurities and bubbles in a wine bottle based on multi-feature comprehensive judgment, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: employing a high-resolution industrial camera to be combined with an LED light source, and continuously shooting multiple frames of images of the wine bottle under the consistent shooting angle and illumination condition; carrying out the preprocessing of the collected image through employing a self-adaptive histogram equalization and Gaussian blur method; extracting the edges of impurities and bubbles in the wine bottle on the image by adopting a Canny edge detection algorithm to obtain an edge image; segmenting the edge image into a plurality of target areas by using a contour detection technology, and extracting possible bubble and impurity areas from the edge image; extracting target area features including circularity, gray average, gray uniformity, texture features and color space; and according to the extracted features, bubbles and impurities are distinguished by applying a comprehensive judgment rule. According to the method, the bubbles and the impurities are comprehensively judged by adopting multi-feature combination, so that the accuracy and the robustness of detection are greatly improved.

An intelligent regulation and control method for a DevOps platform monitoring period comprises the following steps: firstly, acquiring a multi-dimensional index data stream of a system, and forming an instant multi-dimensional vector through stream-oriented calculation, window processing, feature combination and the like so as to judge the state of the system; and quantifying event information by using an event level model to determine an emergency degree. A confidence vector is obtained through operation of a preset rule base, a corresponding scheduling strategy is triggered, and resources are allocated according to the fuzzy logic and the event emergency degree. Meanwhile, the event priority is determined in combination with expert experience and fuzzy logic, and a flexible management plan is executed and a result is evaluated accordingly. And finally, according to the rule base evaluation, dynamically adjusting the rule weight ratio, and optimizing the judgment on the multi-dimensional indexes of the system. According to the invention, dynamic regulation and control of a monitoring period, accurate evaluation of systems and events, intelligent scheduling and handling are realized, and the stability, high efficiency and self-adaptability of a DevOps platform are improved.

The invention discloses a multi-source heterogeneous data fusion and processing method based on a localized LLM model, and relates to the technical field of factory energy management.The method comprises the steps that multi-source heterogeneous data is collected from a factory energy management system, and the collected original data is preprocessed and standardized; performing feature selection, feature extraction and feature combination on the processed data; carrying out embedding dimensionality reduction by adopting principal component analysis and a localized LLM model; performing intelligent semantic analysis and fusion on the dimension reduction feature data by utilizing a localized LLM model, performing weighted fusion on embedded vectors by adopting a multi-head attention mechanism, and extracting semantic association among the data; and performing intelligent anomaly detection on the fused high-quality data by using localized LLM model embedding analysis and cosine similarity calculation. According to the method, the processing efficiency and quality of the multi-source heterogeneous data are comprehensively improved, high-quality data support is provided for comprehensive energy management of factories, and efficient and intelligent energy scheduling and management optimization are achieved.

The invention discloses an explosion-proof junction box fault diagnosis method and system based on a sensor, which are used in the field of fault diagnosis, and the method comprises the following steps: obtaining historical multi-source sensor data reflecting the state of an explosion-proof junction box; extracting a time sequence sample of the preprocessed historical multi-source sensor data by using a sliding time window method; multi-domain features reflecting fault types are extracted from the time sequence samples, and a fault diagnosis model is constructed based on the feature combination with the optimal diagnosis performance; performing feature extraction on the multi-source sensor data acquired in real time, and inputting the extracted features into a fault diagnosis model for fault diagnosis; and the operation state and the diagnosis result of the explosion-proof junction box are displayed in real time. According to the method, the subtle change of the fault signal is captured from multiple angles, the Pearson correlation coefficient is used for screening the features significantly related to the fault type, and the dimension reduction processing is carried out through principal component analysis, so that the operation efficiency and accuracy of the model are improved.

The invention discloses a transformer partial discharge detection method and system based on multi-modal feature combination, and relates to the technical field of transformer detection, and the key points of the technical scheme are that the method comprises the steps: collecting an electromagnetic wave signal, a pulse current signal and a sound wave signal of a target transformer; respectively extracting an electromagnetic wave time-frequency matrix, a pulse current waveform parameter and a sound wave space coordinate; performing multi-modal feature fusion on the electromagnetic wave time-frequency matrix, the pulse current waveform parameters and the sound wave space coordinates based on a dynamic weighting strategy to generate a joint feature tensor; and inputting the joint feature tensor into a pre-constructed neural network model, identifying a discharge type and optimizing a positioning coordinate. According to the method, multi-modal features are subjected to tensor fusion, cross-modal correlation learning is realized through the neural network model, information islands can be eliminated, and the misjudgment rate is effectively reduced; and electromagnetic wave-current-sound wave signal adaptive fusion is realized through a dynamic weight coefficient, and the signal-to-noise ratio is obviously improved through characteristic complementation in an oil paper insulation discharge scene.

The invention discloses a shield tunneling intelligent auxiliary method based on stratum types. The method comprises the steps that parameters of a current shield tunneling machine in the tunneling process are collected; through Pearson's correlation coefficient calculation, correlation coefficients of all the parameters and the total thrust and the cutterhead torque are obtained respectively, and a feature combination is obtained; utilizing a K-means algorithm to calculate and obtain a stratum classification result which is clustered by taking a basic combination consisting of the total thrust and the cutterhead torque and a feature combination as a feature set; a cooperative training algorithm is adopted, and dug stratum classification based on the basic combination and the feature combination is obtained under semi-supervised learning; a machine learning algorithm is utilized to carry out learning training on types of excavated stratums, unknown stratum conditions in the tunneling direction are identified, and a reference range of total thrust and cutterhead torque is given. The method can be circularly executed in the shield tunneling process, the excavated stratum classification result is continuously updated, the method has the characteristics of practical feasibility, real-time performance and the like, and important auxiliary decision-making information can be provided for shield tunneling.

The invention relates to the technical field of glass detection, and discloses a method, a device and equipment for detecting glass after light sweeping. The method comprises the following steps: collecting multi-source original sensing data of glass to be detected, carrying out signal denoising, synchronous transformation and multi-scale glass feature extraction on the multi-source original sensing data, and carrying out feature combination, feature dimension reduction compression, region segmentation and region contour reconstruction on the multi-scale glass features to obtain an initial defect region set; performing spatial-temporal feature combination of multi-source features on the initial defect region set to obtain an enhanced defect feature set; and constructing a region similarity matrix corresponding to the enhanced defect feature set, performing defect category judgment and multi-dimensional glass quality scoring on the region similarity matrix to obtain glass quality evaluation data, performing process association on the glass quality evaluation data, and generating a final detection report of the to-be-detected glass. According to the method, the result accuracy of quality detection on the glass subjected to light sweeping is improved.

The invention provides a multi-source spatio-temporal data fusion processing method and device. The method comprises the following steps: preprocessing multi-source spatio-temporal data; performing standardization processing on the preprocessed multi-source spatio-temporal data to obtain standardized data; performing alignment processing on the standardized data by using a space-time registration technology to obtain registration data; constructing a multi-layer network structure, and performing data arrangement on the registration data by using the multi-layer network structure to obtain structured data; and establishing a unified geographic element classification system according to the structured data. Sampling the standardized feature vectors by adopting an MCMC urban sampling algorithm to obtain feature distribution parameters; calculating a covariance matrix based on the feature distribution parameters and performing feature value decomposition; and defining geographic element categories according to the distinction degree of the feature combination. The method also comprises a corresponding device implementation. According to the method, the problems of low efficiency and poor precision of multi-source spatio-temporal data fusion in the prior art are solved, the precision of data fusion is improved, and the method has relatively high practicability and adaptability.

The invention provides an abnormal behavior recognition method and system based on multi-dimensional data analysis, and the method comprises the steps: carrying out the cleaning and standardization processing of structured data and unstructured data, obtaining a data set in a unified format, employing a natural language processing technology, processing the document text in the data set, extracting the entity, relation and behavior information, and carrying out the recognition of abnormal behaviors. Generating a structured feature vector; constructing behavior statistics, time sequence and association features by using the feature vectors and the structured data, selecting a feature combination by adopting a sampling algorithm, establishing an entity relation graph according to association data in a constructed multi-dimensional feature set, calculating association strength among entities, and optimizing the entity relation graph according to the association strength to establish a network structure model; a feature weight system is set according to the model and a multi-dimensional feature set, a multi-dimensional abnormal score is calculated by using a pruning tensor structure measurement method, an abnormal score is comprehensively calculated by using a low-rank tensor recovery technology, and an early warning list is output, so that the recognition accuracy and efficiency can be improved.

Embodiments of the present disclosure are directed to onboarding a model from a training platform to an inference platform and selecting parameters of the model to optimize performance of the model. For example, the onboarding of the model to the inference platform can be based on a series of interactions between a model onboarding systems at the training platform and at the inference platform. An optimization process can include a searching-based process to derive optimal settings for the model. The optimization process can simulate feature combinations of the model and identify an optimal combination of settings of the model for increased model performance.

The invention provides a media data fusion method and system, core voice switching equipment and a storage medium, and the method comprises the following steps: carrying out the feature extraction processing of multi-source heterogeneous audio data and video data, and obtaining an audio data stream, a video key frame and the semantic features of the data; performing synchronization processing on the audio data stream and the video key frame based on the semantic features of the data to obtain synchronized audio and video data; the method comprises the following steps: synchronizing audio and video data, extracting key features of the synchronized audio and video data, obtaining content correlation features in the audio and video data, performing feature selection and feature combination processing on the key features of the synchronized audio and video data, and performing content correlation maximization optimization on the content correlation features according to weights of the content correlation features. Obtaining an optimized audio and video feature set; and constructing a data mixed stream optimization model, and carrying out fusion mixed stream processing on the optimized audio and video feature set to obtain fused audio and video mixed stream data.

The invention belongs to the technical field of landslide susceptibility analysis, and relates to a landslide susceptibility ensemble learning evaluation method considering spatial heterogeneity partitioning and factor feature screening, which comprises the following steps: generating a landslide sample based on historical landslide catalog data, and selecting a non-landslide sample through environmental factor frequency ratio analysis; the method comprises the following steps of: extracting static and dynamic environment factor data sets, realizing factor space interpretation force transformation by utilizing a t-SNE-ISO clustering algorithm and a feature screening strategy, eliminating high-correlation factors through a Pearson correlation coefficient method, quantifying interpretation force of each factor on landslide space differentiation by combining a geographic detector, screening optimal feature combinations under global and partition frameworks respectively, and performing landslide space differentiation on the landslide space. According to the method, a Stacking integrated learning framework is combined with CNN, DNN, MLP-based learners and LR element learners, a landslide susceptibility probability prediction model is formed, the generalization ability and prediction accuracy of the model are improved, and the method is especially suitable for landslide high-incidence areas with severe topographic relief and complex geological conditions.

The invention provides a display panel defect detection method and system based on multi-modal data fusion, and the method comprises the steps: obtaining multi-type representation data generated in a detection process of a display panel, and carrying out the feature mapping of the multi-type representation data; respectively mapping the panel appearance characterization data, the panel signal characterization data and the panel interlayer characterization data to a preset feature space to generate a cross-type mapping feature set, and performing feature association enhancement on the cross-type mapping feature set to obtain a cross-type mapping feature set; establishing an association relationship among the appearance mapping features, the signal mapping features and the interlayer mapping features, generating an association enhanced feature set, performing defect feature reasoning on the association enhanced feature set, extracting a feature combination conforming to a defect feature mode, and generating a defect feature reasoning result; and outputting a defect detection result of the display panel. According to the invention, the accuracy and reliability of the defect detection result of the display panel can be improved.

The invention provides an Alzheimer's disease diagnosis method based on multi-modal brain network feature fusion, which is based on a multi-modal brain image, a neural network and an attention mechanism, and has the main innovation points that: 1) effective feature combination of three types of multi-modal data of MRI, DTI and fMRI can reflect all feature information of a patient sample; and 2) aiming at different image data, a targeted feature extractor is used, the three-dimensional convolution is more suitable for feature learning of a three-dimensional MRI whole brain image, the Mama model is more suitable for learning of fMRI time sequence features, and the graph convolution network is more suitable for learning of DTI fiber number structure brain network features. And 3) the innovative mixed attention mechanism is fused with three types of multi-modal features, position coding and a Transform structure are used at the same time, the mixing effect and the classification accuracy of the multi-modal features are improved, and compared with a convolution and full connection layer structure, richer information can be learned.

The invention discloses a camouflage target detection method and system based on cross-scale global and local feature combination, and the method comprises the steps: extracting feature maps of M scales from an input image # imgabs0 # through an encoder, inputting a multi-branch convolution block to obtain enhanced features, inputting the enhanced features into a pre-trained decoder, and carrying out the multi-scale fusion to obtain final fusion features, a decoding result obtained through up-sampling is classified to obtain a camouflage target detection result; wherein the decoder is provided with a # imgabs1 # layer, any # imgabs2 # layer comprises # imgabs3 # decoder nodes, all the decoder nodes are subjected to up-sampling layer by layer and step by step, fusion is carried out through double convolution operation, and then the output features of the decoder nodes are obtained through multi-stage combined scanning feature fusion blocks. The invention aims to solve the detection difficulty when the camouflage target is highly similar to the background, the edge is not obvious or a large amount of shielding exists under the complex background, and overcome the problem that the camouflage target detection precision is low due to the fuzzy edge and the small target size.

The invention relates to the technical field of image target detection, and discloses a hyperspectral image segmentation method based on spectrum-spatial feature combination, comprising the following steps: 1) acquiring a hyperspectral image data set; 2) performing hyperspectral image segmentation based on multi-scale space-spectral feature combination of deep learning; and 3) evaluating a network segmentation effect. The hyperspectral image is segmented by using a deep learning method, the spectral features and the spatial features of the hyperspectral image are effectively extracted and fused by providing a spectral-spatial feature combined segmentation method, and meanwhile, the prediction accuracy of the model is improved.

The invention provides a rice disease identification method and system based on a CNN-CBAM-BiGRU combined model. According to the method, richer feature combinations are obtained by improving the CNN, the influence of dimension reduction on data is weakened by improving a CBAM attention mechanism, and information loss is avoided through BiGRU. The method can effectively overcome the defects that a traditional convolutional neural network lacks global attention to the context and a recurrent neural network lacks local attention. In an experiment, through comparison with classical models such as VGG16, LeNet, AlexNet, GoogleNet V1 and RestNet 50, a result shows that the recognition accuracy of the CNN-CBAM-BiGRU combined model provided by the invention on the four diseases is as high as 98.03%, and a reliable recognition method is provided for rice disease recognition research.

The invention discloses a lower limb movement gait recognition method and system based on feature fusion, and belongs to the technical field of gait recognition. Comprising the following steps: acquiring a surface electromyogram signal and a motion inertia signal of a to-be-predicted object; carrying out feature extraction on the surface electromyogram signal and the motion inertia signal by utilizing wavelet transform, obtaining gait features and screening an optimal feature combination; and processing the optimal feature combination through the trained gait recognition model to obtain a gait recognition result. Complex multi-modal data can be effectively processed and analyzed, so that high-precision gait recognition and evaluation are realized; the problem that the accuracy of gait evaluation needs to be improved due to the fact that single signal processing is difficult to comprehensively reflect a complex gait dynamic process in the prior art is solved.

The invention relates to a construction safety risk early warning method and system based on cross-modal visual language retrieval, belongs to the technical field of combined image retrieval and multi-modal retrieval, and designs a multi-granularity image-text semantic feature decoupling module, a multi-granularity feature combination module and a multi-granularity combination-target alignment module. Through a multi-granularity semantic decoupling technology, local features and global features of an image and a text are decoupled respectively, alignment between multi-modal query and a target image is considered at the same time, multi-granularity combination is carried out on the decoupling features of the image and the text in the multi-modal query, and multi-granularity combination features of the multi-modal query are obtained. According to the method, combined features are pushed to approach target image features from a multi-granularity level, cross-modal alignment of a multi-granularity detail level is realized, semantic information between multi-modal query and a target image is aligned more accurately, and overall cross-modal understanding and application effects are improved.

The invention discloses a channel siltation probability early warning method and system for water flow feature recognition, and relates to the technical field of channel maintenance, and the method comprises the steps: obtaining channel characteristic parameters, inputting the channel characteristic parameters into an interaction knowledge graph, and determining a key water flow feature index set; performing random feature combination based on the index set, screening K coordination feature groups in combination with historical operation data, training K reference deposition prediction models, and performing integration to generate a deposition probability prediction model; collecting real-time water flow data through a sensor, processing the data and inputting the data into the model to predict the channel siltation probability; if the prediction result meets the early warning condition, siltation early warning is triggered. Therefore, the technical effects of improving the early warning perspectiveness, reducing the misjudgment rate and enhancing the complex environment adaptability are achieved.

The invention discloses a supervised learning-based data recognition method and system, particularly relates to the technical field of data recognition, and is used for solving the defects of an existing supervised learning method in low-frequency feature capture and feature association modeling. Training data are collected from a plurality of data sources and samples which do not meet a quality threshold are filtered; performing information gain measurement on the features through a dimension reduction algorithm, and screening a feature set with high information gain; generating a sparse feature combination set by using an association rule algorithm, and extracting key low-frequency features and an interaction relationship thereof; inputting the low-frequency feature set into the gradient elevator for supervised training, and strengthening the influence of the low-frequency features through an adaptive weighting strategy; in the training process, the gradient updating trend and Shapley value distribution of the low-frequency features are monitored, a weighting strategy is adjusted for abnormal features to correct model weight distribution, the generalization ability and prediction precision of the model are improved, and the method is suitable for feature recognition and analysis of complex data scenes.

The invention provides a coral reef remote sensing image multi-modal feature generation and restoration method and system, and relates to the technical field of remote sensing image restoration, and the method comprises the steps: obtaining coral reef image data based on a multi-source sensor, and carrying out the preprocessing; performing image morphological feature and spectral feature extraction on the preprocessed coral reef image data by using a convolutional neural network, and establishing a feature database; carrying out weighted fusion on the multi-source features based on a feature combination network, generating comprehensive feature expressions, and storing the comprehensive feature expressions into a feature database; the coral reef image to be restored is matched with the feature database, and guidance parameters are generated; and inputting the guidance parameters into the generative adversarial network, and performing pixel-level reconstruction on the missing region of the coral reef image to be restored. According to the method, a complete closed-loop system is constructed, multi-source information scheduling, pixel-level guide reconstruction and semantic feedback verification are covered, image information can be supplemented, ecological information can be reasonably reconstructed, and a high-quality data basis is provided for subsequent classification, monitoring and protection work.

The invention provides an artificial intelligence advertisement pushing method based on multi-dimensional historical data analysis, and the method comprises the steps: constructing second-level, minute-level, hour-level and other behavior feature views of different time granularities for extracted original features, and forming multi-time scale feature representation; analyzing feature views under different time scales through a graph mining algorithm, mining an association rule between feature nodes, and constructing a cross-scale feature association graph; in the feature correlation map, according to the spectral clustering result of the feature nodes and the gravitation direction of the feature edges, the temporal correlation degree of different feature combinations is judged; if the time correlation degree of the feature combination exceeds an empirical threshold value, endowing the time weight of the feature combination with a high weight coefficient of power law distribution; and dynamically adjusting the network depth and the connection density of the association atlas according to the vertical dimension and the semantic hierarchy of the features, and optimizing the feature weight distribution in the atlas.

The invention relates to the technical field of image processing, and discloses a morphology-based image texture feature extraction method, which comprises the following steps: an image preprocessing step: carrying out graying processing on an original image, and carrying out smoothing processing on a grayscale image by using a Gaussian filter; a morphological operation step: selecting structural elements suitable for image texture characteristics, performing expansion and erosion operation on the smoothed image, performing opening operation on the expanded image, and performing closing operation on the eroded image; and an adaptive feature selection step: carrying out local binary pattern feature extraction on the image after morphological processing, adaptively determining a threshold according to statistical distribution of LBP features, and segmenting the image into a foreground and a background. The image texture feature extraction method based on morphology aims at solving the problems that feature extraction is inaccurate, noise interference is likely to happen, and feature combination is complex in an existing image texture feature extraction method.

The invention provides a target tracking method and system based on global and local two-way extraction and asynchronous enhancement, and the method comprises the steps: carrying out the initialization of a template image and a search image, and carrying out the sequence division through block embedding; extracting global features and local features of the template image and the search image at the same time, and performing feature fusion on the global features and the local features of the template image and the search image; the output of the global and local joint module is input into an asynchronous enhancement module for asynchronous interaction and feature enhancement; and inputting the finally enhanced output feature to a prediction head to obtain a tracking result. According to the method, global and local features are extracted at the same time through the feature combination module, and the features after interaction are enhanced by using asynchronous enhancement operation in the feature fusion stage, so that the robustness and the feature expression ability of the model are improved.

The invention provides a multi-modal spoken language pronunciation evaluation method based on a large language model, and belongs to the technical field of spoken language evaluation, and the method comprises the steps: obtaining the audio data of a spoken language tester; performing feature coding processing on the audio data through an acoustic encoder to obtain audio representation information, and mapping the obtained audio representation information into a public space through a modal adaptation layer; setting an audio evaluation instruction, separating the audio evaluation instruction into a plurality of phrases through a word segmentation device, converting the phrases into high-dimensional text features through a word embedding module, and mapping the high-dimensional text features into a public space; splicing the audio representation information in the public space with the high-dimensional text features, carrying out multi-modal feature combination, and constructing an evaluation sequence; and the big language model carries out evaluation prediction on the evaluation sequence to obtain a corresponding pronunciation accuracy evaluation result and a fluency evaluation result. The method does not need to depend on an automatic voice recognition system, and the evaluation efficiency of the audio data is greatly improved while the evaluation process is simplified.

The invention provides an intelligent electric energy meter service life prediction method and device and a readable storage medium, and belongs to the technical field of device service life prediction.The method comprises the steps that multi-dimensional input is constructed by fusing key environment data and an operation time sequence, and the microcosmic, periodic and long-term characteristics of the input are extracted through multi-scale convolution support; the feature combination is dynamically optimized through an adaptive fusion module; constructing a time sequence prediction model, embedding a convolution attention mechanism in an encoder, and compressing redundant information of key features by combining sparse self-attention distillation through key features of feature combination of channel-space double attention dynamic enhancement optimization; the decoder adopts a mask probability sparse attention and iterative prediction strategy to generate an error prediction sequence based on the global features of the encoder to avoid future information interference; and calculating the residual life according to the intersection point of the error prediction sequence and the failure threshold. According to the method, the long sequence prediction precision, the key feature utilization rate and the calculation efficiency are improved, and reliable support is provided for preventive maintenance of the intelligent electric meter.

The invention discloses an intelligent monitoring method and system for preventing an old person from falling down based on multiple sensors, and relates to the technical field of falling monitoring, and the method comprises the following steps: merging behavior data, physiological data and environmental data into a data set; obtaining a feature combination from the related features based on an association rule, and quantifying the influence of the feature combination on the falling probability of the elderly; based on a machine learning algorithm, learning a relationship between the related features and whether the old person falls down, and predicting an old person falling probability corresponding to each sample of the new data set; optimizing the falling probability of the elderly based on the quantification result; if the optimized falling probability of the old people exceeds a certain threshold value, executing a corresponding early warning scheme; the system comprises a data acquisition module, a feature combination acquisition module, a probability prediction module, a probability optimization module and an early warning execution module. According to the invention, the fall probability corresponding to each sample can be obtained, the quantitative influence of the detected feature combination is superposed to the prediction result, and the accuracy of fall risk assessment is further improved.