288 results about "Data human" patented technology

The invention provides an underground water pollutant concentration prediction method and system based on machine learning, and relates to the technical field of underground water pollutant concentration prediction.The method comprises the steps that historical data, hydrogeological parameters, meteorological data, human activity data and geochemical parameters of underground water pollutant concentration of a target area are preprocessed; dividing a training set, a verification set and a test set; constructing a preset resolution feature set based on a geochemical mechanism; selecting an adaptive machine learning model according to data characteristics and coupling a physical mechanism; performing hyper-parameter tuning by adopting Bayesian optimization, and supplementing small sample data in combination with transfer learning to complete model training; predicting the underground water pollutant concentration of the target area by using the trained model, and outputting a pollutant concentration prediction result with an uncertainty interval; the invention provides a technical scheme for predicting the concentration of underground water pollutants, which is efficient, accurate and high in adaptability.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to assessing certainty of artificial intelligence models used for detection or segmentation of pathologies. Accordingly, a system can comprise a memory that can store computer executable components. The system can further comprise a processor that can execute at least one of the computer executable components. The computer executable components can comprise a synthetic data generation component that generates biologically-inspired synthetic data that approximates a task-specific data manifold of a medical image from a radiomic features perspective; an artificial intelligence component that uses an artificial intelligence model to learn relevant representations of the synthetic data for an at least one image task; and a training component that utilizes the relevant representations and the artificial intelligence model to generate a task-specific model for the at least one image analysis task.

The invention relates to the technical field of rural space governance and intelligent decision making, in particular to a rural space planning method and related equipment, and the method comprises the steps: obtaining multi-source data of a target rural, the multi-source data comprising land data, population data and rural economic data of the target rural; performing fusion processing of space-time alignment on the multi-source data to obtain fusion data; constructing a spatio-temporal knowledge graph based on the fused data, and extracting entity attributes and spatial relationships; and inputting the entity attributes and the spatial relationship into a pre-trained planning optimization model, iteratively optimizing a rural space matching strategy according to rigid constraints, and outputting an optimal planning result, the technical problems that in the prior art, rural planning faces data splitting, element analysis isolation, planning scheme staticization and actual development requirements are disjointed, the decision making process depends on subjective experience, and economic-ecological benefit tradeoff is difficult to quantify are effectively solved.

The invention belongs to the technical field of urban climate adaptability planning, and provides an urban toughness evaluation method, device and equipment based on heat island data and a medium, and the method comprises the following steps: collecting dynamic heat island data, humanity perception data and toughness potential data, and preprocessing multi-source data; constructing a three-dimensional index system of the pressure degree-coping capacity-toughness potential of the heat island; s3, determining an index weight by adopting a reinforcement learning adaptive weight model, and calculating to obtain a final toughness value; s4, predicting short-term and long-term toughness value changes based on an LSTM-attention mechanism model, forming a toughness level-potential level linkage matrix in combination with the final toughness value and the potential level, and determining an intervention priority; according to the method, short-term thermal risk early warning and long-term toughness trend prediction are realized through the LSTM-attention mechanism model, and a high-risk area is identified in advance; through the constructed toughness-potential linkage matrix, the intervention priority is defined, and the resource utilization efficiency is effectively improved.

The invention relates to the technical field of infectious disease monitoring and early warning, and discloses an intelligent influenza early warning system based on community multi-modal data fusion. The community-level multi-modal data fusion architecture is constructed, medical health data, environmental data, crowd activity data and network behavior data are integrated, spatial-temporal features are dynamically extracted and fused in combination with a deep learning model, and the problem of community monitoring blind areas caused by a single data source of an existing early warning system is solved; a long short-term memory network and convolutional neural network cascade architecture is utilized to capture a localized propagation rule, and the defect that a region-level prediction model cannot adapt to community heterogeneity is overcome; the risk score is generated in real time, the grading response instruction is triggered, a'monitoring-early warning-intervention 'closed loop is established, the early warning timeliness is remarkably improved, a basic-level response chain scission gap is filled, early prevention and control of flu outbreak are finally achieved, and public health resource consumption is reduced.

The invention discloses a hydropower station data operation and maintenance method, which comprises the following steps of: arranging a sensor network on hydraulic facilities and electromechanical gold junction equipment, acquiring data, preprocessing the data, registering in space and time scales, converting data signals into acoustic, optical and electric signals, and transmitting the acoustic, optical and electric signals to a server; the method comprises the following steps: performing signal fusion of a three-dimensional sonar signal and an RGB image based on an attention concentration mechanism, performing deep analysis on data, extracting a sensor data mode of hydraulic facilities and electromechanical junction equipment under normal working condition operation, establishing a fault diagnosis model, performing real-time diagnosis on the hydraulic facilities and the electromechanical junction equipment, and constructing a response decision knowledge base. Establishing a hydropower optimization scheduling model, and displaying the information of the hydropower station; the system integrates the Internet of Things, big data, artificial intelligence, cloud computing, BIM three-dimensional modeling and digital twinning technologies, realizes real-time monitoring, intelligent diagnosis and optimal scheduling of equipment and facilities of the hydropower station, and improves the overall digital intelligent operation management level of the hydropower station.

The invention relates to the technical field of epidemic disease prediction, and discloses an intelligent epidemic disease prediction system based on deep learning. A multivariate data acquisition module of the system acquires environmental meteorological data, population flow data, medical resource distribution data and historical epidemic situation propagation data related to epidemic diseases in real time; a deep learning prediction module analyzes regional propagation dynamic characteristics through a space-time diagram neural network according to the multi-source data; a risk area identification module constructs an area risk level thermodynamic diagram according to the area propagation dynamic characteristics, and identifies a high-risk area of which the risk level exceeds a preset threshold value; and the resource matching analysis module calculates the resource coverage range of each medical institution in combination with the medical resource distribution data and the spatial position of the high-risk region. The system can integrate multi-source data, accurately analyze the epidemic propagation trend, intelligently identify high-risk areas, realize reasonable matching of medical resources, and provide effective technical support for epidemic prevention and control.

The invention discloses a mechanical arm path planning system, and relates to the technical field of man-machine interaction and safety control, the mechanical arm path planning system comprises a sensing module, a man-machine cooperation module, an optimization module and a regulation and control module, the man-machine cooperation module identifies the behavior intention and the working state of an operator to generate second data, and the optimization module fuses the first data, the second data and the state data of the mechanical arm body, selects a path planning strategy in a grading manner according to the environmental complexity, generates and optimizes a target path, and outputs an optimization result comprising a standard path and an alternative path. And the regulation and control module dynamically regulates and controls the optimization result, generates a regulation and control result through instruction conversion, deviation compensation and multi-stage response and feeds back the regulation and control result, the dynamic environment can be accurately dealt with, man-machine safety cooperation is achieved, the efficiency, safety and adaptability of mechanical arm path planning are improved, and the method is suitable for complex man-machine cooperation scenes.

The invention discloses a robot dog target following method based on computer vision. The robot dog target following method comprises the following steps: S10, preparing human body data, human body weight identification data and a single target tracking data set; s20, designing a lightweight human body detection network architecture and a detection human body frame, and performing model training based on the human body data; s30, constructing a lightweight single-target tracking model, selecting a detection frame of a to-be-tracked target as initialization input, receiving an initial frame transmitted by a robot dog camera as a template image, and performing specified template tracking and following; s40, constructing a lightweight full-scale model, starting a relocation mechanism after a lost target is tracked by a single target, and controlling the robot dog to turn around in situ, globally search a specified target and relocate a disappearing target; and S50, based on the tracking result of the single target, converting the target position on the image to an actual three-dimensional coordinate, and controlling the motion displacement of the robot dog to complete the following operation.

The invention relates to the technical field of city updating simulation, and discloses a city updating multi-scene simulation evaluation system based on digital twinning. The system comprises a multi-source data acquisition module, a space grid division module, a scene simulation engine and a dynamic evaluation module. The multi-source data acquisition module acquires real-time monitoring data and historical city update project data of a city physical space, and the real-time monitoring data covers environmental parameters, infrastructure operation data and people flow dynamic data, so that a digital twinborn body is constructed. The space grid division module divides the digital twin into space grid units according to the urban functional area type and the updating target and gives attribute tags to the space grid units. And the scene simulation engine generates a simulation parameter combination based on the attribute tag, and drives the digital twin to carry out multi-scene dynamic simulation. And the dynamic evaluation module outputs a state evaluation value of each space grid unit according to a simulation result, the state evaluation value comprises an infrastructure load state and a people flow distribution state, and orderly promotion of city updating work is assisted.

The invention discloses an intelligent operation decision-making method, system and device for a flash furnace and a medium, and the method comprises the steps: obtaining the smelting process data of the flash furnace, the manual observation information of the smelting process and the inspection and test data of a smelted product, and building a global database to carry out the unified management of the data; a fire observation opening area of the flash furnace, the interior of a flue gas pipeline and the furnace wall of a slag tap are monitored, and furnace condition sensing information is obtained; regulating and controlling loop setting of a reaction zone of the flash furnace according to the smelting process data, the manual observation information, the inspection and test data, the furnace condition sensing information and the first target index; and according to the smelting process data, the manual observation information and the second target index, electrode rising and falling of an electrode area of the flash furnace and the gear of the transformer are regulated and controlled. According to the embodiment of the invention, the working condition of the smelting process of the flash furnace can be monitored and analyzed, and the operation decision is intelligently executed according to the monitoring result. The method can be widely applied to the field of flash furnace smelting.

An improved parcel growth prediction system that uses parcel data, population data, and artificial intelligence to predict the growth of a geographic area at a micro level (e.g., a real estate parcel level) is described herein. For example, the improved parcel growth prediction system may generate a graph model and apply the graph model as an input to an artificial intelligence model to predict the likelihood that a particular parcel may be developed some time in the future. Ultimately, implementing the improved parcel growth prediction system described herein may lead to more precise placements of infrastructure projects and / or to infrastructure projects that more precisely support the needs of the population of a geographic area as time passes.

The invention belongs to the technical field of flood emergency risk avoidance, and particularly relates to a flood avoidance transfer path planning and intelligent matching method based on multi-algorithm cooperation, and the method comprises the following steps: S1, multi-source data integration: integrating flood inundation data, population distribution data, administrative division data and dangerous area data; s2, dynamic avoidance area generation: respectively processing a dangerous avoidance area and a flood submerging avoidance area to finally obtain two accurate avoidance areas; s3, constructing a multi-algorithm collaborative flood avoidance transfer path planning model; s4, constructing an intelligent layered placement matching model: designing a layered matching algorithm model, and realizing intelligent matching of the transfer unit and the placement area; and S5, generating and optimizing a flood avoidance transfer scheme. According to the method, accurate planning of a flood avoidance transfer path is realized through multi-algorithm collaborative fusion, and meanwhile, a hierarchical matching strategy and a dynamic adjustment mechanism are constructed, so that the problems of scientificity and high efficiency of placement matching can be solved, and the quality and efficiency of flood avoidance transfer work are comprehensively improved.

The invention relates to the technical field of ability evaluation, and discloses a personnel ability evaluation method based on human intelligence and virtual reality, an edge computing device and a medium. Firstly, a target virtual scene is constructed based on post requirements and task parameters set by a target task; human body multi-modal data of the target object and simulator data of the simulator are collected when the target object executes the target task in the target virtual scene based on the simulator; then, feature extraction and weighted calculation are carried out on the human body multi-modal data and the simulator data, and objective adaptation degree scoring data are determined; and determining personnel state data and workload of the target object based on the human body multi-modal data. And matching the simulator data with preset operation data, and determining abnormal data in the simulator data. And finally, based on the objective fitness score data, the personnel state data, the workload and the abnormal data, evaluating the task execution capability of the target object to obtain a task execution capability evaluation result of the target object.

The invention relates to an Internet of Things data man-machine interaction visualization system based on artificial intelligence, which belongs to the field of man-machine interaction technology, industrial Internet of Things and artificial intelligence technology and comprises a multi-modal data acquisition unit, a cognitive load state real-time inference module, a man-machine interaction interface self-adaptive generation module and a closed-loop regulation control module. The multi-modal data acquisition unit is used for acquiring multi-modal data related to the state of an operator in real time; the cognitive load state real-time inference module is used for inferring and generating a probability vector representing the current cognitive load state of the operator based on the acquired multi-modal data; according to the scheme, a complete feedback control loop is constructed by arranging the multi-modal data acquisition unit, the cognitive load state real-time inference module, the human-computer interaction interface self-adaptive generation module and the closed-loop regulation control module.

The invention discloses an intelligent electric crank for a handcart of a high-voltage switch cabinet of a transformer substation, and relates to the technical field of electrical equipment operation tools, a driving device of the intelligent electric crank integrates a direct-current brushless motor and a planetary reducer, and continuous torque adjustment of 10-50Nm is realized; the multi-specification adaptive transmission joint is forged by alloy, and supports multi-specification interfaces and quick release structures; the control module is based on a high-performance microcontroller and is provided with a multi-path interface and an AI processing unit; the sensor array monitors multi-dimensional data in real time; the man-machine interaction module provides a visual operation interface; the power management module supports a fast charging technology; a high-precision sensor and an edge AI are integrated, real-time health monitoring and dynamic adjustment of handcart operation of the high-voltage switch cabinet are achieved, faults are early warned in advance, parameters are optimized, meanwhile, modular design is adopted, a multi-specification adaptive transmission connector rapidly adapts to multiple specifications, man-machine interaction is visual, power management supports rapid charging, communication is compatible with a station control system, and high-voltage switch cabinet handcart operation real-time health monitoring and dynamic adjustment are achieved. And the operation flexibility and the system expansibility are both considered.

A system and method for closed-loop tracking of advertising events through offer redemption with artificial intelligence feedback. A session identifier links device, pass, content, and contextual data throughout a content playback session. Advertisements dynamically inserted into the content stream inherit the session identifier. An offer platform generates offers linked to the session identifier and pass identifier, enabling tracking through distinct lifecycle states from push to redemption. A database captures timestamped and geo-referenced data for each event. An artificial intelligence engine uses redemption and avail events as verified ground-truth outcomes for training machine learning models, enabling supervised learning that establishes causal relationships between ad exposure and purchasing activity. An inventory gateway receives merchant product inventory data. An optimization engine employs demand forecasting and reinforcement learning to generate inventory-driven triggers and offer recommendations. A merchant interface presents analytics for inventory optimization.

The invention relates to the technical field of pest control, in particular to a method for evaluating habitat suitability and diffusion trend of codling moths and application. The method comprises the following steps: S1, collecting occurrence distribution data of codling moths; s2, acquiring a plurality of pieces of bioclimate variable data, human activity influence indexes and apple yield data of codling moth occurrence distribution, constructing a multi-dimensional environmental factor data set according to the plurality of pieces of bioclimate variable data, the human activity influence indexes and the apple yield data, and performing cross validation on the data set; and S3, based on a Biomod2 set model, establishing a plurality of single ecological models according to the occurrence distribution data and the multi-dimensional environmental factor data set, selecting high-accuracy models according to TSS and AUC values of the single models, integrating the models to generate a set model, and obtaining a habitat suitability result of codling moths and a contribution rate of main environmental factors. Scientific reference is provided for early warning, monitoring and prevention of codling moths.

The invention relates to an airport site selection evaluation optimization method, which comprises the following steps of: inputting a candidate take-off and landing point set and a destination point set, acquiring geographic space data, airspace limitation data, population distribution data and meteorological environment data related to candidate take-off and landing points and flight paths, and carrying out standardization processing on the geographic space data, the airspace limitation data, the population distribution data and the meteorological environment data; for each candidate take-off and landing point, calculating a landform suitability score, a population density influence degree score, a flight efficiency score and a safety compliance score; allocating configurable weight coefficients for the four predetermined dimensions, and performing weighted summation to obtain a comprehensive score of each candidate take-off and landing point; and carrying out sorting according to the comprehensive scores of all the candidate rising and landing points, and outputting a site selection recommendation ranking. The technical defects that an existing low-altitude aircraft take-off and landing point site selection method is high in subjectivity, single in evaluation dimension, difficult to adapt to dynamic task requirements and neglect real three-dimensional airspace environment constraints can be solved, and an automatic, quantifiable and multi-constraint-condition comprehensive site selection decision is made.

The invention discloses a warehousing network model and algorithm based on two-stage model collaborative optimization, and belongs to the technical field of warehousing network models. The invention discloses a warehousing network model and algorithm based on two-stage model collaborative optimization. The warehousing network model comprises an analysis and prediction module, an inventory collaborative management module and an optimization model. According to the invention, the problem of lack of overall planning of the full-link cost of the storage network in the prior art is solved. Through collaborative optimization of the first stage model and the second stage model, balance of long-term cost and short-term cost is realized, full-link cost optimization is achieved, the storage space utilization rate is improved, maximum utilization of manpower, equipment and space resources is realized, and through integration of regional economic data, population density, a traffic network, competitor layout and other multi-dimensional data, the real-time performance of the system is improved. Costs, efficiency and risks of different site selection schemes are calculated, a clear quantitative basis is provided for long-term decisions such as storage node layout and facility scale determination, and large deviation of demand probability fitting is avoided.

The invention discloses an artificial intelligence-driven urban potential updating area identification and division method, which comprises the following steps of: firstly, constructing an index system according to three dimensions of building space, industry form composition and crowd vitality by using the collected building number, land function data, POI (Point of Interest) industry form data, LBS (Location Based Service) crowd data, high-definition remote sensing image data and road network data; the method comprises the following steps: carrying out hierarchical classification identification on an update object through a natural discontinuity point method and a K-Means clustering algorithm, carrying out intelligent division and optimization on a city update unit through a DBSCAN clustering algorithm and a reinforcement learning model of a graph network structure database, and finally carrying out division and boundary optimization on a city update area. According to the invention, automatic identification and division of potential updating objects, updating units and updating areas of the city can be realized, and digital and intelligent application conversion of city planning work is promoted.

The invention relates to the technical field of wireless charging assembly line automatic control, in particular to an intelligent cooperative control system for a wireless charging assembly line, and adopts the technical scheme that a central scheduling module and a beat cooperative algorithm unit can construct a dynamic state model based on global real-time data; a digital twin sub-module is introduced to perform simulation deduction verification on an instruction in a virtual environment, a beat redistribution strategy can automatically adjust a material flow when a fault occurs, and a visual positioning and compensation module can identify a material position and attitude offset in real time and generate compensation data. The man-machine interaction interface can visualize the whole line state, prediction information and alarm information in real time, the historical database and optimization learning unit can store data and iteratively optimize algorithm parameters, uncertain interference is analyzed through Monte Carlo simulation, and a Pareto optimal solution set is solved through an NSGA-II algorithm. The production takt of the three stages of feeding, dispensing assembling and baking discharging is dynamically matched, and dynamic takt synchronization and productivity optimization of the whole production line are achieved.

The invention discloses a logistics behavior safety risk assessment system based on multi-source heterogeneous data combination, and the system comprises a multi-source data integration and preprocessing module which is used for accessing logistics business data of heterogeneous data sources, including logistics package data, package attribute data, personnel attribute data and communication attribute data, carrying out preprocessing operation on the data; the logistics behavior knowledge graph construction module is used for constructing a logistics behavior knowledge graph; the graph embedding representation learning module is used for learning entity and relation embedding representation of the logistics behavior knowledge graph through a TransE model; the risk assessment and prediction module is used for predicting a behavior risk probability through R-GCN and MLP models; and the risk decision and early warning module is used for triggering an early warning strategy according to the prediction result. According to the invention, through integration of multi-source information, the logistics behavior knowledge graph is constructed, and the graph neural network technology is applied, so that accurate prediction and real-time early warning of logistics behavior safety risks are realized.

The invention belongs to the field of artificial intelligence and machine learning, aims to solve the problems of high manual generation cost, poor authenticity, low negative sample quality and insufficient scene coverage of multi-modal tool calling data, and comprises four core modules: a tool knowledge base module stores API metadata through PostgreSQL, and generates various user intentions and coherent calling sequences in combination with pre-training LLM; the multi-agent interaction module generates conversation and calling data containing multi-modal input through cooperation of a user, an assistant and an environment agent; the adversarial environment simulation module generates high-quality negative samples in batches by means of three adversarial strategies and automatically marks the high-quality negative samples; and the human feedback iteration module determines convergence by a performance improvement rate according to a model failure case optimization strategy. The system supports local / cloud deployment, adapts to LLM and Agent model training, and is suitable for training and robustness evaluation of dialogue type AI assistants and vertical field intelligent Agents.

The invention relates to the technical field of flood control and disaster reduction, and particularly discloses a flood storage and detention area dynamic personnel transfer early warning method and system, and the method comprises the steps: collecting and fusing hydrological monitoring data, personnel dynamic distribution information and geographic information in real time, and constructing a unified dynamic data base; based on the dynamic data base, generating a gridded real-time risk level by fusing a flood routing model and real-time personnel density data; according to the real-time risk grade, dynamically triggering and issuing a grading early warning instruction; based on the real-time submerging prediction result and the dynamic road condition information, generating and dynamically updating an optimal transfer path for the threatened individual; pushing customized early warning information corresponding to the early warning instruction and the optimal transfer path to an individual terminal; according to the invention, based on hectometer-level gridding real-time risk assessment and a three-level early warning mechanism, a submerging prediction model and a special group positioning technology are fused, and high-risk point location coverage is realized.

The invention provides a human preference alignment method and device for an artificial intelligence large model, and the method comprises the steps: obtaining a human preference training set of different answers of different models to the same question, and constructing sample data based on the human preference training set; the human preference training set comprises a plurality of answers of different models for the same question, and the answers are marked with sorting results performed according to human preferences; pre-training a reward model based on the sample data; sampling the to-be-trained model based on a preset question set, scoring a sampling result through a reward model, and constructing training set data; the to-be-trained model is trained based on the training set data, so that the to-be-trained model is aligned with human preferences, the human preferences of the large model are aligned by directly learning the sorting of the samples by the reward model, the consumption of training resources is reduced, the stability of large model training is improved, and in addition, by comparing the differences of different answers, the training efficiency is improved. And the training efficiency and effect of large model human preference alignment are improved.

The application discloses a method for intelligent identification of changes in river and lake water areas by a UAV and early warning of abnormal problems in rivers and lakes, comprising the following steps: constructing a digital twin bottom plate data of rivers and lakes; manually editing a basic flight route of the rivers and lakes, intelligently generating a shooting flight route based on the basic flight route and the digital twin bottom plate data of the rivers and lakes, splicing the basic flight route and the shooting flight route, and obtaining a dynamic flight route of the UAV; performing dynamic flight route flight according to the dynamic flight route, collecting data information during flight, and returning the data information to a UAV base station through a network and transmitting the data information to an edge computing device; generating river and lake orthographic images and river and lake spatial terrain data by combining the data information collected by the UAV with water area management lines; and identifying and comparing the orthographic images before and after the two times by using a water area surface identification model and an image difference method, so as to obtain a water area surface change area and abnormal problems in the rivers and lakes. The method solves the problems of low identification accuracy, low image spatial resolution and unintelligent flight route scheduling in the existing UAV patrol of the rivers and lakes.

The invention provides a blue space degradation diagnosis method and system, computer equipment and a medium, and belongs to the field of ecological environment monitoring, and the method comprises the steps: obtaining a remote sensing image, climate data and human activity data of a to-be-diagnosed blue space, and extracting water body images of the to-be-diagnosed blue space at a plurality of time points through the remote sensing image; calculating a multi-class landscape form index of each grid in the water body image; clustering the water body image based on the multi-class landscape form index of each grid to obtain a blue space combination mode corresponding to each grid; inputting the climate data, the human activity data and the landscape form index into a random forest model to obtain a contribution degree; and based on the contribution degree, screening from the climate data, the human activity data and the landscape form index to obtain a water body change driving factor, and determining a degradation diagnosis result of the blue space to be diagnosed. The blue space combination mode constructed by the method can reflect the structural difference of the blue space, and the accuracy of degradation diagnosis of the blue space is guaranteed.

The present invention relates to a method and an apparatus for detecting anomalies in an operation behavior of a device under test (DUT), in particular during electromagnetic susceptibility (EMS) measurements. The apparatus comprises a monitoring unit adapted to generate a first set of observation data of the operation behavior of a DUT while the DUT is not subjected to disturbances and adapted to generate a second set of observation data of the operation behavior of a DUT while the DUT is subjected to disturbances and comprising an AI module trained with the first set of observation data generated by the monitoring unit and adapted to process the second set of observation data to detect anomalies in the operation behavior of the DUT while being subjected to the disturbances and comprising a reporting unit adapted to reporting anomalies in the operation behavior of the DUT detected by the trained AI module.

The present application relates to the field of electric digital data processing, and in particular to a method for sensing and decision-making of a door lock interaction system based on embodied intelligence, which comprises collecting sensing data, labeling an intention label and an environmental noise label corresponding to each sensing data to obtain labeled sensing data; constructing a sensing and decision-making model and training the sensing and decision-making model to obtain a trained sensing and decision-making model; collecting new sensing data, inputting the voiceprint data, the relative distance data between the person and the door lock, and the door lock state data in the new sensing data into the trained sensing and decision-making model after aligning them to a unified reference according to a time stamp to obtain an intention probability distribution, selecting the intention with the highest probability as a decision result and triggering a corresponding door lock control instruction. The existing sensing and decision-making method of the door lock interaction system based on embodied intelligence has the problem of poor user experience. The method provided by the present application can provide good user experience.