688 results about "Learning unit" patented technology

The invention relates to the technical field of power utilization monitoring, and discloses a photovoltaic user power utilization abnormity monitoring method and system based on artificial intelligence. The photovoltaic user electricity consumption abnormity monitoring system based on artificial intelligence comprises a data acquisition module which is used for acquiring photovoltaic power generation data, electricity consumption data and environment data of a user; the data preprocessing and feature engineering module is used for cleaning, aligning and normalizing the original data acquired by the data acquisition module and constructing a feature data set for model training and reasoning; and the artificial intelligence analysis engine module comprises an unsupervised learning unit, a supervised learning unit and a deep learning unit. According to the invention, the false alarm rate and the missing report rate can be effectively reduced, the accurate diagnosis of the abnormal type can be realized, and the intelligent and accurate operation and maintenance requirements of power grid enterprises on the power utilization monitoring of photovoltaic users are met.

An object of a system according to an embodiment is to automatically learn a behavior pattern of a target person, detect an abnormality, and issue an alert.SOLUTION: A system according to an embodiment includes a GPS device, a AI learning unit, an abnormality detection unit, and an alert generation unit. The GPS device keeps track of the current location of the subject. The AI learning unit automatically learns a daily behavior pattern based on the position information of the target person acquired by the GPS device. The abnormality detection unit detects an abnormality by comparing the behavior pattern learned by the AI learning unit with the current position information. The alert issuing unit issues an alert based on the abnormality detected by the abnormality detection unit.SELECTED DRAWING: Figure 1

The invention discloses a teaching resource intelligent management system and method based on big data, and relates to the technical field of teaching resource intelligent management. Constructing a teaching resource arrangement model based on the mastery index of the micro knowledge points; solving the teaching resource arrangement model by adopting a two-stage heuristic decomposition algorithm to generate an optimized learning arrangement sequence; sequentially pushing the assembled micro learning units to a user terminal in a streaming manner according to the sequence of the optimized learning arrangement sequence, and obtaining process interaction data of a user; extracting process interaction data to analyze answer accuracy and response time stability; updating the total mastery index according to the two-dimensional normal probability model; and triggering re-optimization of the subsequent optimization learning arrangement sequence based on the updated total mastery index. Instant refreshing of the state is realized; the analysis efficiency is improved.

A machine learning device includes an image set acquiring unit to acquire an image set including images, and an image set selecting unit to select an image set similar to the acquired image set from a plurality of image sets different from the acquired image set. In addition, the machine learning device includes a performance comparison unit, and a preprocessing acquisition unit to select a learning model from a plurality of machine-learned learning models based on a performance comparison result by the performance comparison unit and to acquire preprocessing performed on an image set used for machine learning of the learning model selected. Furthermore, the machine learning device includes a model learning unit to perform the acquired preprocessing on the acquired image set and to cause a learning model that has not yet trained to perform machine learning using the preprocessed image set.

The invention relates to the technical field of disease auxiliary diagnosis, in particular to a digital mammary gland artificial intelligence auxiliary diagnosis system based on multi-modal fusion, and the system comprises a multi-modal data collection module which is used for obtaining digital mammary gland image data and rehabilitation scheme data of a patient; the image quality correction module is used for carrying out acquisition quality evaluation and correction on the digital mammary gland image data; the feature modeling and evaluation module is used for performing feature extraction on the corrected digital mammary gland image data and rehabilitation scheme data, and comprises an image-drug action mechanism cooperation unit and an image-rehabilitation bimodal co-learning unit; and the rehabilitation effect prediction module is used for constructing a rehabilitation effect prediction model and outputting a rehabilitation prediction result under the influence of the scheme specificity of the current rehabilitation scheme of the patient. According to the method, the digital mammary gland image and the patient rehabilitation scheme are deeply fused, so that the accuracy and reliability of mammary gland tumor rehabilitation prediction are effectively improved.

The invention relates to the technical field of power system equipment monitoring, in particular to a substation equipment state monitoring embedded edge analysis system, which comprises a monitoring front-end module for acquiring and transmitting substation equipment operation state data; the edge processing module comprises a multi-scale wavelet transform unit, a topology continuity analysis unit and a manifold learning unit, wherein the multi-scale wavelet transform unit decomposes data and separates signals and noise through a self-adaptive threshold mechanism; the topological persistence analysis unit maps the de-noised signal to a high-dimensional feature space, calculates a persistent coherence group, and extracts a topological feature vector; and the manifold learning unit constructs a nonlinear manifold structure, calculates a geodesic distance, and executes discharge type identification and anomaly evaluation, and the FPGA and ARM heterogeneous calculation architecture is adopted, and through the synergistic effect of multi-scale wavelet transform, topology persistence analysis and manifold learning, high-precision extraction of weak discharge signals and accurate identification of fault modes are realized.

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.

A system and method for distribution anomaly prediction for new mineral exploration using mineralogical understanding and artificial intelligence analysis of geochemical data are provided, the system comprising: a database development unit configured to collect regional distribution data including pre-collected geochemical data and geologic spatial data of a region and to integrate map data and data set to construct integrated data into a database; a model learning unit configured to generate and learn an exploration mineral distribution anomaly model based on machine learning, wherein the exploration mineral distribution anomaly model enables prediction of distribution anomaly based on geologic and ore deposit geological understanding of exploration mineral using the integrated data; and a distribution anomaly prediction unit configured to predict the distribution anomaly of the exploration minerals in an exploration region using the learned exploration mineral distribution anomaly model.

The invention relates to the technical field of artificial intelligence, discloses a human outsourcing intelligent customer service body based on a large model and reinforcement learning and a service method, and aims to solve the problems that an existing customer service system is rigid in service process, broken in customer experience and incapable of learning evolution from artificial expert experience. The intelligent customer service body comprises an intention analysis unit, a dynamic strategy generation unit, a closed-loop learning unit and the like. Wherein the dynamic strategy generation unit is used for generating and executing a service strategy by utilizing a large language model; and the closed-loop learning unit realizes continuous learning and capability self-optimization of the intelligent customer service body through explicit reasoning chain monitoring, correction instruction analysis, multi-dimensional reward calculation and double-track system model iteration. Through adoption of the technical scheme, the service flow flexibility, continuity and customer experience can be improved, and the technical problems of insufficient system rigidity and learning evolution are effectively solved.

An appearance inspection apparatus includes: an annotation unit that associates annotation information indicating whether a defect of a structure is normal with an input image to be used for an appearance inspection of the structure, the information being determined by a user based on the input image; a learning unit that generates a trained model by deep learning using the information and the input image associated with the information with respect to an initially-set trained model; and a defect inference unit that outputs a result obtained by inferring the defect based on the input image using the trained model generated by the learning unit, in which the annotation unit associates the information with the input image for which the result is different from a result of the determination made by the user for the input image to cause the learning unit to relearn the trained model.

To provide a technology capable of generating a learned model according to acquired measurement data and of proceeding to perform inference.SOLUTION: According to one embodiment, an information processing system is provided. The information processing system includes a learning part and an inference part. The learning part inputs to the learning model a first reconstructed image and a second reconstructed image and generates a learned model such that an output with the first reconstructed image as an input becomes the second reconstructed image. Each of the first reconstructed image and the second reconstructed image is an image reconfigured on the basis of any one of a plurality of projection images included in measurement data. The inference part acquires an output image outputted by inputting to the learned model a third reconstructed image. The third reconstructed image is reconfigured on the basis of any one of the plurality of projection images included in the measurement data.SELECTED DRAWING: Figure 1

The application relates to an acupuncture training method and device and a storage medium, and comprises the following steps: S1: an environment construction step: a virtual reality training environment is constructed, the virtual reality training environment comprises a learning unit for acupoint knowledge display and an examination unit for interactive operation; wherein the examination unit pre-stores a three-dimensional human acupoint coordinate model established based on standard anatomy data, the three-dimensional human acupoint coordinate model defines standard space coordinates of each acupoint and a permitted coordinate deviation range of the acupoint; S2: a knowledge display and operation collection step: the learning unit is controlled, and graphic and three-dimensional anatomical information of at least one target acupoint combination is displayed to a user; subsequently, the examination unit is controlled to load a three-dimensional human model corresponding to the target acupoint combination, and interactive operation data of the user for positioning the target acupoint combination through an interactive device is received; and the application can better realize acupuncture training.

An information processing device includes: a machine learning unit to learn a relationship between an evaluation value and a parameter on a basis of a search point of the parameter and an evaluation value of the search point, and predict the evaluation value for a search candidate point of the parameter; and a search progress acquiring unit to acquire progress information indicating progress of a search on a basis of the search point, the evaluation value of the search point, the search candidate point, and the evaluation value of the search candidate point predicted by the machine learning unit.

The system according to the embodiment aims to propose the most suitable means of transportation and route in consideration of the user's travel history and preferences. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, a proposal unit, and a learning unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes transportation methods and routes based on the analysis results obtained by the analysis unit. The learning unit learns the user's travel history and preferences.

The application relates to a time series data feature enhancement representation method and device based on multi-scale contrast learning in the field of computer information technology. The method comprises the following steps: extracting three types of node relationship data and basic attribute information of each order node of original time series order data respectively, constructing an order node feature matrix, constructing a relationship graph for the three types of node relationship data by using a neighborhood subgraph order node feature aggregation unit, processing the order node basic features corresponding to each relationship graph, extracting global semantic features and local semantic features according to the order node basic features by using a global level order contrast learning unit and a local level order contrast learning unit respectively, and fusing the two features to obtain multi-scale fusion logistics order enhanced features after the order basic attribute is enhanced. By using the method, the sparsity and class imbalance of logistics order features can be relieved, multi-scale information fragmentation can be solved, and the order semantic expression and downstream task adaptability can be improved.

This control device comprises: an acquisition unit that acquires control information of a machine tool that forms a three-dimensional structure having at least one type of periodicity on the surface of a workpiece, and an analysis result generated by analyzing the workpiece obtained as a result of operating the machine tool on the basis of the control information; a machine learning unit that trains a machine learning model on the basis of a data set including the control information and the analysis result; a prediction unit that predicts the control information by inputting a desired analysis result to the machine learning model; and a control unit that operates the machine tool on the basis of the prediction result of the control information.

A system capable of optimizing early alarm operation by introducing an alarm filtering technology so as not to cause false alarm to an abnormal signal due to signal noise is disclosed. The system comprises: a data acquisition unit for selectively acquiring historical data according to the operation of a electric power facility by selecting a preset multivariate input tag; a recommendation unit for generating learning data, which is a multivariate signal for machine learning, based on a preset similarity from the historical data; a compression unit for generating re-sampling data by compressing the learning data; a learning unit for performing real-time monitoring by using the re-sampling data as input data of a pre-designed early warning learning model; and a calculation unit for generating a final warning when a predetermined condition predefined through the real-time monitoring is satisfied.

A system (100) for detecting and analyzing foam insulation in a building shell cavity comprises a shock generator (102), an acoustic sensor (104), and a control unit (106) connected to the shock generator (102) and the acoustic sensor (104). The control unit (106) is configured to enable the shock generator (102) to generate and apply a predefined force at a predefined location on the surface of the building shell (200) where the foam insulation (204) in the cavity (202) of the building shell (200) is to be detected and analyzed.The control unit (106) further measures acoustic attributes of acoustic signals generated when the predefined force is applied at the predefined location using the acoustic sensor (104) and analyzes the measured acoustic attributes using a learning unit to detect the presence or absence of the foam insulation (204) in the cavity (202).

The system according to this embodiment aims to learn the trends of a company's past taglines and generate new taglines. [Solution] The system according to the embodiment comprises an acquisition unit, a learning unit, and a generation unit. The acquisition unit acquires past taglines of companies. The learning unit learns the trends of past taglines acquired by the acquisition unit. The generation unit generates new taglines based on the trends learned by the learning unit.

This provides a technology that enables policy learning such that constraint violations are less than or equal to the acceptable probability. [Solution] An information processing device for performing constrained reinforcement learning, comprising: an input unit for inputting the state and actions of an agent; a reward calculation unit for calculating a reward based on the state and actions of the agent; a determination unit for determining whether or not constraint conditions are satisfied based on the state and actions of the agent; and a learning unit for learning a policy to maximize the reward under the condition that the probability of violating the constraint conditions is less than or equal to a predetermined allowable probability.

To control a device group for executing the same task with a simpler configuration.SOLUTION: The control apparatus 1 performs adversarial training of the generative model including the generator 121 that generates pseudo action data similar to true action data as the true action data for actions sequentially executed by each device in the device group to transition from one state to the next state at each time, and the discriminator 122 that discriminates between the pseudo action data generated by the generator 121 and the true action data, in the trained recurrent neural network constructed by the training of the first learning unit 11.SELECTED DRAWING: Figure 1

A component mounting system (10) is provided with: a mounting head (24) for mounting a component on a substrate on which solder is applied; a heat line head (43) that irradiates a heat line to the solder after the component is mounted; a camera (45) that captures an image of the solder in parallel with irradiation of the heat line; a learning unit (53) that generates a learning model using the solder image as an input and the solder quality as an output; a determination unit (52) that inputs an image of the solder captured by the camera (45) to the learning model and determines whether or not the solder is qualified; and a control unit (51) that stops the irradiation of the heat line when it is determined that the welding quality is qualified.

This device for generating crystal structure information on the basis of an artificial intelligence model comprises: a data preprocessing unit that constructs an interleaved dataset by arranging text and images to cross each other; a learning unit that includes a visual encoder for generating image feature data from the images, a language model for generating text-encoded data from the text, and a projector for converting the image feature data and the text-encoded data into data in a shareable form, learns a relationship between the images and the text on the basis of the converted data, initializes the projector, and then performs, on the basis of the interleaved dataset, fine tuning for simultaneously training the language model and the projector to perform condition learning for generating information, which satisfies a specific condition, and filling learning in a method for filling a masked portion; and an information generation unit for generating at least one piece of crystal structure information on the basis of a prompt input.

The system according to this embodiment aims to enable users to practice effective proposal methods and negotiation strategies in advance, based on the characteristics of their clients' representatives. [Solution] The system according to the embodiment comprises a reception unit, a learning unit, a generation unit, a simulation unit, and a feedback unit. The reception unit inputs information of the contact person of the business partner. The learning unit learns based on the information input by the reception unit. The generation unit generates advice and suggestions based on the data learned by the learning unit. The simulation unit performs a dialogue simulation based on the advice and suggestions generated by the generation unit. The feedback unit inputs feedback on the dialogue performed by the simulation unit.

This invention relates to the field of intelligent education technology and discloses a tiered training method for editing skills based on deep learning. The method includes: constructing a training course library containing course units; using the course unit as the smallest learning unit, and based on the pre-dependencies of the course units, collecting real-time interactive operation data of learners to construct multi-dimensional feature vectors for learners; inputting the multi-dimensional feature vectors into a trained deep neural network model to output the learner's current assessed comprehensive course ability index; using a clustering method to divide all learners into three levels: basic, intermediate, and advanced; associating each level with a subset of course units, obtaining the matching degree between each learner's current assessed comprehensive course ability index and the difficulty coefficient, and generating a personalized course learning path recommendation for each learner. This invention achieves tiered training for learners' editing skills.

The invention discloses an elevator prediction scheduling method and system based on user habit self-learning, and the method comprises the steps: carrying out the statistical analysis based on historical elevator taking event data, and judging whether a floor combination meeting a preset condition exists or not; combining all the independent floors with the floors meeting the preset conditions to serve as a self-learning unit; for each self-learning unit, updating the elevator calling probability of the respective learning unit by using an exponential weighted average algorithm; when the elevator does not have the real-time task, all elevator calling probabilities corresponding to the current time window are inquired, and the self-learning units meeting the triggering condition are extracted as a target candidate set; calculating an optimal pre-stop layer by utilizing a mathematical model based on the target candidate set, and calculating a comprehensive probability corresponding to the optimal pre-stop layer; and calculating an income evaluation function based on the comprehensive probability, and generating an instruction to drive the elevator to run to an optimal pre-stop layer to enter a prediction waiting state when an obtained value meets a condition.

The invention discloses an image segmentation point prompt optimization method and system based on a double-space heterogeneous graph, and belongs to the field of computer vision and image segmentation. The problems that an existing image segmentation method is poor in automatic prompt point quality, unstable in segmentation performance and low in cross-scene adaptability are solved. The method comprises the following steps: firstly, carrying out blocking and double-space distance modeling on an input image, and constructing a heterogeneous graph environment fusing depth feature vectors and space position information; designing a dynamic operation action set and a state representation and reward mechanism based on deep reinforcement learning, and training intelligent agent iterative optimization prompt node distribution; and finally, the optimized prompt nodes are input into a pre-trained segmentation model to complete high-precision segmentation, an adaptive module does not need to be additionally trained in the whole process, and plug-and-play cross-scene adaptation is realized. The system comprises a state characterization unit, and the state characterization unit is sequentially connected with an action management unit, a reward calculation unit and a strategy learning unit. The method is applied to image segmentation.

An object of the system according to the embodiment is to automate a design process in product development and achieve efficiency and optimization.SOLUTION: A system includes a reception unit, a learning unit, a generation unit, a trial unit, and a visualization unit. The reception unit inputs a performance target of a customer. The learning unit learns the past design data based on the performance target input by the reception unit. The generation unit generates a design based on the data learned by the learning unit. The trial unit performs trial and error of the design generated by the generation unit. The visualization unit visualizes the result obtained by the trial unit.SELECTED DRAWING: Figure 1

The present invention enables more accurate estimation of a three-dimensional structure including an internal structure of a target without requiring a large number of captured images. A three-dimensional structure estimation device (10) includes: an acquisition unit (111) that acquires a plurality of fluoroscopic images obtained by imaging a target from mutually different directions; a learning unit (112) that, using the plurality of fluoroscopic images, learns a learning model to which input data indicating three-dimensional coordinates of an arbitrary point inside the target is input and which outputs first output data indicating a signed distance of the arbitrary point with respect to a surface of an internal structure possessed by the target and second output data indicating a first attenuation coefficient at the arbitrary point; a calculation unit (113) that inputs, to the learning model, input data indicating respective points inside the target and, by correcting the first attenuation coefficient indicated by the second output data on the basis of the signed distance indicated by the first output data, calculates second attenuation coefficients at the respective points inside the target; and an estimation unit (114) that estimates a three-dimensional structure of the target on the basis of the second attenuation coefficients at the respective points inside the target.

The objective is to improve the accuracy of the generated abnormal signal data. [Solution] The signal management device 1 includes a generator that generates pseudo-data statistically similar to true data, with each of the sequences of intensity for each frequency component corresponding to the second data being treated as true data, and a discriminator that identifies whether the pseudo-data generated by the generator belongs to the class corresponding to true data or the class corresponding to pseudo-data. The device also includes a third learning unit configured to learn multiple generative models, each having an objective function set by the probability distributions of the first data and the second data determined from the ratios estimated by the first learning unit, and the second parameter estimated by the second learning unit.