70 results about "Applications of artificial intelligence" patented technology

A wind energy forecasting system processes data from one or more numerical weather prediction models with power output data from a wind energy facility using artificial intelligence. This artificial intelligence is applied in one or more neural networks that produce specific power output forecasts for each numerical weather prediction model. A statistical ensembling approach is then applied to the resulting numerical weather prediction model forecasts and integrated with a persistence power output forecast to arrive at a consensus, overall forecasted power output for the wind energy facility.

The invention discloses an intelligent resource allocation method in the Internet of Vehicles, which applies an artificial intelligence algorithm to solve the problem of resource allocation in a vehicle network so as to maximize the revenue of a network operator. Specifically, the method comprises: establishing a base station-roadside node combined vehicle edge calculation and cache resource scheduling framework to distribute requested resources for vehicles; establishing a network operator revenue function in combination with the operator revenue and the user experience quality to evaluate the resource distribution problem, and establishing a joint optimization problem to maximize the network operator revenue; solving the joint optimization problem through deep reinforcement learning, obtaining an intelligent task scheduling and resource distribution scheme, arranging the obtained scheme in an intelligent control system, and performing intelligent scheduling and arrangement on vehiclerequests and server resources. According to the intelligent resource distribution method in the Internet of Vehicles, the revenue of a network operator can be maximized while the user experience is considered, and a new idea and angle are provided for practical application of artificial intelligence.

An ultrasound image-based multi-model liver diffuse disease intelligent diagnosis method and system, the present invention relates to an intelligent diagnosis method for liver diffuse diseases by using depth learning algorithm to extract image features and image texture features and applying XGBoost algorithm to ultrasound images, It is the application of artificial intelligence method in ultrasonic image-based diagnosis, and can provide doctors with auxiliary suggestions for disease diagnosis. The invention comprises the following steps: 1, preprocessing the ultrasonic image of the liver; 2.preliminary classification of liver diffuse diseases based on convolution neural network; thirdly, the convolution neural network features and image texture features are combined to form multi-model features, and the XGBoost algorithm is used to achieve the final classification of liver diffuse diseases. The invention combines the depth learning algorithm and the traditional feature extraction algorithm, gives consideration to the shape feature and the texture feature of the image, and applies the XGBoost algorithm to improve the accuracy of the classification algorithm, and is suitable for the liver diffuse disease auxiliary diagnosis based on the ultrasonic image.

The invention belongs to the technical field of communication and education, and relates to a teaching diagnostic analysis system through comprehensive application of the artificial intelligence technology and a teaching diagnostic analysis method thereof. The teaching diagnostic analysis system comprises a prefabricated classroom indicator module, a data acquisition module, a face recognition andprocessing module for extracting images, a voiceprint recognition and processing module for extracting audio signals, a voice recognition and processing module for converting voice into texts and recognizing high frequency content and a natural language processing module for performing secondary analysis on the text content. A correlation analysis module is used for establishing a correlation analysis view with the time value acting as the index and generating the classroom teaching quantitative indicator analysis result. A diagnostic analysis module constructs the correlation analysis view of the learning condition, the knowledge content, the teaching process and the teaching characteristics with the time value acting as the dimension so as to form the teaching analysis result. The big data acquisition standard is established by using the artificial intelligence technology so that the classroom teaching analysis data can be accurately acquired; and the teaching process, knowledge content analysis and learning condition analysis can be correlated so that the teaching effect generated by different teaching modes can be analyzed.

The invention discloses an application layer dynamic intrusion detection system and detection method based on artificial intelligence, wherein the detection system comprises an application layer gateway, a detection module, a judgment and operation module, a sample database and an updating module, the detection module comprises a detection model mixed with a convolutional neural network and a bidirectional long and short term memory neural network. The detection module after initialization is used for making an attack judgment on an application layer data packet, filtering the data packet above the threshold value and putting the data packet into a malicious sample database, and meanwhile, the data packet under the threshold value is not processed. The updating module is used for traininga new model by using the malicious samples and normal samples with a certain proportion in the sample database and updating the detection model in the detection module in real time. According to the invention, a universal detection method is used for the attack method of the application layer, the method has the advantages of high detection rate and low misjudgment rate. Meanwhile, the intrusion detection system has the advantage of dynamic updating model, and has good filtering effect on unknown zero-day attack.

The invention relates to an intelligent cerebral apoplexy risk monitoring system, aims at monitoring cerebral apoplexy risk by utilizing personal information (comprising age, gender, blood pressure, stature, weight, constitutional index and the like) of health examination, physical examination and hospital admission, and blood routine examination and blood biochemistry data, belongs to the application of artificial intelligence and big data in the field of health care, and belongs to the cross technical field of artificial intelligence, big data and health care. The invention mainly aims at providing a simple, practicable and high-correctness cerebral apoplexy risk monitoring system. The intelligent cerebral apoplexy risk monitoring system is established through carrying out over ten thousands of predictions, simulations and analysis assessments on the data of more than five hundred and ninety thousands of normal persons and more than twenty thousands of cerebral apoplexy patients by means of prediction simulation and big data value extraction technologies of artificial intelligence, and is capable of helping users and doctors to carry out cerebral apoplexy risk monitoring so as to provide hope for the users to monitor the cerebral apoplexy risks and finally keep away from cerebral apoplexy.

Method for assisting a real estate holding company to maintain an optimal valuation of a number of properties having a number of buildings includes the steps of selecting a property for inspection, launching an application, from an electronic computing device, for identifying one or more serviceable roofs among a number roofs of the buildings within the property, obtaining a series of time-lapse images of the roofs of the buildings within the property, analyzing the series of time-lapse images of the roofs using artificial intelligence-based instructions of the application to identify a variety of roof characteristics, identifying the buildings with one or more serviceable roofs requiring maintenance by analyzing a number of pixelated images of the roofs of the buildings and contacting an insurance service provider providing insurance coverage to the buildings with the serviceable roofs requiring maintenance to perform necessary maintenance activities.

The invention relates to an automatic classification method for breast tumor ultrasound images, and belongs to the technical field of applications of artificial intelligence. According to the invention, quantitative features of the breast tumor ultrasound images are tightly combined, histogram features, color features, profile features, edge features and echo features in the breast tumor ultrasound images are quantified, a decision-making tree, a Naive Bayesian method and a random forest method are selected to serve as machine learning methods, and a decision-making tree, Naive Bayesian and random forest weighted fusion multi-dimensional classification method is proposed to perform recognition on the breast images. The automatic classification method can effectively improve the automatic classification accuracy of the breast tumor ultrasound images.

The invention discloses an ecological and environmental warning system and method based on laser radar and deep learning path optimization. The system comprises an ecological and environmental warningboat and a bank-based server, wherein the ecological and environmental warning boat comprises a core control module, a sailing drive module, a water quality detection module, an intelligent obstacleavoidance evidence module, a communication module and a power module; the bank-based server comprises a data analysis module and a route planning module; the bank-based server is used for checking theposition of the ecological and environmental warning boat, receiving and analyzing data passed back by the ecological and environmental warning boat, planning the path of the ecological and environmental warning boat and predicting a central position of the pollution source according to multi-point data; the ecological and environmental warning boat completes water quality monitoring and samplingunder the optimal path and treats slight pollution on premise of performing data analysis and path planning by the bank-based server. The problems that the traditional water quality monitoring is greatly limited by the environment, the sampling period is long, much money is spent and the like can be accurately solved, and application of artificial intelligence in an aspect of improving the ecological environment is really realized.

The invention relates to a UAV (unmanned aerial vehicle) power inspection image key power component automatic diagnosing and marking system which comprises a power component target detection module, apower component fault detection module, a human-computer interaction module providing a human-computer interaction function, a marking module and a UAV power inspection image library. According to the system, the intelligent automatic diagnosing and marking of a UAV power inspection image is achieved, the workload of the inspection personnel is reduced, the inspection efficiency and the accuracyrate are improved, and a data support is provided for the application of artificial intelligence in the field of power inspection key power component identification and fault detection. At the same time, the standardization of power inspection image storage and marking is promoted.

A system and method of communication based on the Reverse Multiple-Choice Method of teaching and testing is disclosed where at least one communicant is a machine. The method is applicable for training a machine for knowledge engineering and artificial intelligence oriented applications, as well as for a trained machine to assist a human being engaged in the activity of teaching or testing.

The invention relates to the field of legal advice, particularly relates to a multi-round conversation method and a system based on the application of artificial intelligence in legal consultation. The multi-round conversation method based on the application of artificial intelligence in legal consultation comprises steps: 1, consultants conduct voice input on inquiring questions through a conversation terminal; 2, that server receives the voice information and then match the answer information corresponding to the voice information; 3, if the match voice information in the server match the corresponding answer information of the voice information, the answer information is sent to the session terminal; 4, if there is no suitable answer information matching with the voice information in the server, the relevant legal provisions of the voice information in the server are looked for, and then the legal provision as the answer information corresponding to the voice information is sent tothe session terminal. The programme is suitable for legal counselling by consultants who do not have a legal basis.

The invention provides a method for automatically recognizing a shear line. The method comprises the following steps: performing standardized processing on a wind field; partitioning lattice points and performing multiplication cross computation on the wind vectors on the lattice points after partitioning, and obtaining cyclonic characteristic points in the wind field through a multiplication cross positive value; taking an establishment judgment threshold of the maximum multiplication cross positive value, and screening out shear nodes from the cyclonic characteristic points; eliminating intersected shear lines according to a shear node analysis method, and then constructing the shear line by connecting the shear nodes in groups. The possible shear of the judgement and screening can be performed by utilizing the two-dimensional vector multiplication cross result, and the shear nodes are finally connected to form the shear line, thereby reaching an aim of automatically recognizing andpositioning the shear line. The shear line analysis in the current meteorological service still uses the human-machine interaction way, the disadvantage problem that the forecast personnel performs manual operation according to the own experience is solved, thereby laying a solid foundation for realizing the automatic analysis forecast and artificial intelligence in the weather service.

The invention belongs to the field of artificial intelligence and plant protection, relates to interdisciplinary cross application of artificial intelligence and plant protection subjects, and particularly relates to a grape leaf scab identification method based on a fine-grained generative adversarial network. Comprising the steps of data collection and labeling, significant scab region detection and segmentation, fine-grained generative adversarial network image enhancement, training of a deep learning classification model, and grape leaf scab identification by using the trained model. The method mainly solves the problem that the leaf scab recognition rate is low under the conditions that grape leaf diseases are in the form of scab, in the early stage of morbidity, novel diseases, rare scab or insufficient training samples, is mainly used for scab recognition in the early stage of morbidity of the grape leaf scab, and can take corresponding intervention measures as soon as possible. A foundation is laid for precise pesticide application in the next step, economic losses are reduced to the maximum extent, the dosage can be reduced, and the environment is protected. The method can also be expanded to the situation that other plant leaf diseases are scabs.

The invention relates to an extensible interactive speech service system on the basis of a broad band network, which comprises a communication supporting module, a visible flow generator, a flow explaining module and a medium service module, wherein since the system adopts a mode of treating interactive speech services as a platform rather than an application to process, various speech services are developed according to concrete service demands on a foreground, then, the speech services are stored as a VoiceXML document and are provided for a background universal explaining system to explain the file, the speech flow is controlled, concrete speech output and input operations are finished through a resource module to finish the speech interactive functions. Thereby, since a large amount of applied links of artificial intelligence is used, a large amount of manual seats can be reduced, thereby liberating maximum labor resources, the application range of the system is directly expanded, the development period of the system is further accelerated, and the development cost and the maintenance cost are effectively lowered.

The embodiment of the invention discloses a method and system for realizing a network game, wherein the method comprises the following steps that: a front-end controller receives a code uploaded through a browser by a user and involved to a game and a user control command, acquires control parameters according to the code and the user control command, and sends the control parameters to a background controller, wherein the code is edited according to the rules of the network game by the user; the background controller calls the code of the corresponding user according to the control parameters to generate an action message and sends the action message to an action actuator; and the action actuator actuates actions according to the action message and generates result information and new environment information of the game. In the embodiment of the invention, the user who only needs to have the browser can participate in the network game, and users who know the rules of the network game and have programming base and high learning ability can all participate in the network game; the users can write an own algorithm on line to carry out the network game with algorithms of others; in addition, the application of artificial intelligence can be popularized.

A digital quaternary fractal computer unit, system and method for applications of artificial intelligence. The digital quaternary fractal computer comprises optical, nano-scale and quantum embodiments. The system of computation is unique to the device and employs relativistic, quaternary and fractal mechanisms to perform computation. The full theory of relative quaternary fractal computation and encoding is documented in the various references herein.Several methods are also disclosed which evolved out of, and help enhance, the various embodiments. It is emphasized that this abstract is provided to enable a searcher to quickly ascertain the subject matter of the technical disclosure and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

The invention discloses a machine translation model and a pseudo-professional parallel corpus determination method, system and device, belongs to the technical field of information, and further relates to application of artificial intelligence in the field. The method comprises the following steps of: obtaining a first universal parallel corpus and professional parallel word pairs in the professional field, searching a candidate parallel statement pair corresponding to each professional parallel word pair from the first universal parallel corpus, and replacing the corresponding universal parallel word pair in the corresponding candidate parallel statement pair with the professional parallel word pair to obtain a pseudo-professional parallel corpus. According to the scheme, more pseudo-professional parallel corpora are generated according to the professional parallel word pairs. Moreover, professional information of professional parallel word pairs in the professional field is introduced into the scheme, so that the translation quality of the obtained neural machine translation model in the professional field is greatly improved after the basic neural machine translation model is further finely tuned by using the pseudo-professional parallel corpus generated by the scheme.

The invention belongs to the technical field of application of artificial intelligence to grain storage, and particularly relates to a granary grain storage quantity parallel detection method, which comprises the following steps of: firstly, generating virtual data samples according to real data samples by adopting a mixed data generation method, and then inputting the virtual data samples into parallel detection models, wherein a primary layer adopts decomposition condition fuzzy reasoning to perform feature extraction, realizing virtual and real data feature interaction through a feature sharing layer, realizing multi-layer feature extraction according to target function design, and then outputting the grain quantity through a regression layer; in order to further improve the generalization ability, adopting an interval type-2 fuzzy integrated virtual-real interaction parallel detection model, and finally outputting an interval type-2 fuzzy reasoning system driven by real data. The granary grain storage quantity parallel detection method is high in detection result precision and high in model generalization capability, and has important technical application and popularization values.

The improved exercise of artificial intelligence by providing a systematic way fora computing system to interface with output from AI models. To do this, the computing system obtains results of an input data set being applied to an AI model. The results are then refined based characteristic(s) of the AI model and perhaps the input data set. Based upon characteristic(s) of the AI model and perhaps the input data set, interface element(s) are identified that can be used to interface with the refined results. The interface element(s) are then communicated to an interface element that interfaces with the refined results. The interface element(s) may include, for instance, operator(s) or term(s) that may be used to query against the refined results and / or an identification of visualization(s) that may be used to present to a user results of queries against the refined results.

The invention relates to a real-time acquisition and analysis method based on parallel fractional physiological signals and belongs to application of artificial intelligence and the information technology in the medical field. The method is characterized in that physiological sensor data is read through an abstraction layer; the physiological signal data is transmitted to a server through a remoteinterface; the physiological signal is analyzed through a fractional index, firstly, the uploaded physiological signal and historical data are synthesized into a physiological signal data sequence, the sequence and different fractional orders are used as input parameters and transmitted to N Map terminals, stability and variance of the corresponding order differential sequence are calculated by each Map end, the result is transmitted to a Reduce end, and the fractional physiological signal index is calculated by the Reduce end and returned to a client; if the index is not within the normal range, the alarm information is emitted by the client to a user. The method is advantaged in that the method is simple, safe and efficient and can be widely applied to the intelligent health service, intelligent nursing and man-machine interaction fields.

The invention provides an intelligent data association relationship determining method based on information operation and maintenance, and belongs to the field of application of artificial intelligence technologies to equipment operation and maintenance. According to the method, key alarm points can be found accurately, and derivative alarms caused by the key alarm points are filtered; the alarm relationship is combed in a mode of combining an artificial intelligence algorithm and manual setting of rules is adopted to tease the alarm relationship, and the alarm recognition accuracy and efficiency are improved; the possibility of operation and maintenance managers facing the alarm disaster is reduced; software and hardware changes can also be dynamically learnt to automatically perform corresponding adjustment, and the possibility of bad alarms due to changes in the operation and maintenance environment is avoided.

The invention discloses a human body posture recognition method based on a convolutional neural network of covariance matrix transformation, and relates to the application field of artificial intelligence, and the method comprises the steps: employing a smart phone to collect a sensor time sequence related to a human body posture, carrying out the normalization of original data, segmenting a data set and fixing an action attribute label by using operations such as a sliding window, then establishing a convolutional neural network system by using covariance matrix transformation, eliminating data correlation by using inverse transformation of a covariance matrix, adding covariance operation before each layer of convolution to avoid data correlation, training network parameters by using a training data set, testing the data set to verify the network precision, and finally solidifying the network model to generate a pb file, and migrating the pb file to the android client through the Android studio, so that the mobile equipment can identify the current state of the user by using an accelerometer and a gyroscope of the mobile equipment.

The invention provides a method and a device for extracting data features in the field of artificial intelligence. In the technical scheme of the invention, a target feature in quantized data is extracted based on a quantized feature extraction parameter by adopting the additive convolution operation, i.e., the sum of absolute values of the difference values of the quantized feature extraction parameter and the quantized data is calculated, so that the target feature is obtained according to the sum; in this way, storage resources can be saved, meanwhile, computing resources can be saved, andtherefore application of artificial intelligence to resource-limited equipment can be reduced. Besides, the invention further provides a method for quantizing feature extraction parameters and the data by using the same quantization parameters, so that the feature data can be inversely quantized on the basis of the quantization parameters when the extracted feature data is inversely quantized, thecalculation complexity can be reduced while the accuracy of the feature data is improved, and calculation resources are saved. Furthermore, the invention also provides a hardware device for realizingthe addition convolution operation.

It describes an intelligent environment management process and system based on Internet of Things (IoT) technology, Cloud Computing, and the application of Artificial Intelligence (AI) and Machine Learning (ML) techniques aimed at providing an environment adapted to its real use in a customized way, which will bring countless benefits to users with a more intelligent use of the environment's features based on actions and suggestions from data collection and pre-processing; Processing and Application of Artificial Intelligence (AI) Strategies in the Cloud and User Interface. The invention thus provides intelligent, adaptive management for greater comfort, in addition to automatically measuring, analyzing, and acting on the environments' comfort and efficiency based on the preferences of their users and managers.

The invention relates to a system and method of implementation of artificial intelligence and tomography imaging to determine the biomechanical degradation or degeneration in human cornea. The invention relates to a combination tool using artificial intelligence and tomography imaging to map the region of degeneration in the cornea. The method of artificial intelligence and corneal tomography imaging includes analysis of changes in the structure of the cornea, constructing the 3D volumes using corneal tomography, meshing the 3D volumes with the elements for biomechanical simulations by using finite element modules, application of artificial intelligence to determine the region of biomechanical degeneration in cornea. The combination tool of the invention is effective in predicting the progression of the disease by analyzing the chronic steepening of the cornea by quantitating the parameters such as increase in curvature, aberrations of the cornea.

The invention discloses a standardized sampling method for extracting pathological speech MFCC features for artificial intelligence analysis, and the method comprises the following steps: collecting speech data, carrying out speech data collection on 82 standard Chinese syllables according to the sequence of a standard Chinese speech evaluation system vocabulary, editing the acquired speech data,so that editing work of 82 syllables is finished, then classifying and filing, carrying out signal extraction on the 82 edited syllables, extracting MFCC features of each syllable through specified pre-emphasis, framing, windowing, fast Fourier transform, a triangular band-pass filter and extended framing processing, and forming an MFCC voice library by using the processed data. According to the method, specific MFCC features of each syllable are extracted through a standardized process method, a digitized, standardized and structured speech feature database is constructed, the method can serve pathological speech feature big data and various applications of artificial intelligence analysis, and objectivity and efficiency of pathological speech research and application are improved.

The invention discloses a human body ultrasonic detection real-time guide strategy based on deep learning. The human body ultrasonic detection real-time guide strategy comprises a demonstrator for human body ultrasonic detection, a skill evaluation strategy based on deep learning and a real-time adjustment strategy based on a sampling principle. The demonstrator is used for collecting a pressure signal and an attitude signal in the detection process; the skill evaluation strategy divides a human body ultrasonic image according to the effective degree of contained information, a training set is made and used for training a classification neural network, and therefore the neural network capable of judging whether the ultrasonic image meets the diagnosis requirement or not is obtained; according to the real-time adjustment strategy, on the basis of the skill evaluation strategy, multi-modal information collected by a demonstrator is added into a deep learning process, a multi-modal information fusion neural network is trained, a sampling set is made, and a sampling principle is combined to realize a function of guiding real-time adjustment of an ultrasonic probe. The strategy can help to complete medical ultrasonic detection, and greatly promotes the application of artificial intelligence in the field of ultrasonic detection.

The invention relates to the technical field of artificial intelligence and APP anomaly detection, in particular to an application software anomaly detection method and system applied to artificial intelligence. The target auxiliary abnormal behavior event description is obtained by adjusting the positioning tag configuration type event description obtained by the artificial intelligence terminal at the cloud side by combining the application software abnormal behavior event description at the edge side; the application software abnormal behavior event positioning is performed on the to-be-positioned first application software abnormal behavior event description acquired by the edge side artificial intelligence terminal, so that the situation that the description attention of the acquired abnormal behavior event description is different due to the difference between different artificial intelligence terminals can be prevented to a certain extent; therefore, the positioning accuracy of the abnormal behavior event of the application software and the comprehensiveness of abnormal detection of the application software can be remarkably improved, and the credibility of the positioning condition of the first abnormal behavior event is ensured.