80 results about "Autodidacticism" patented technology

Method for web based language learning that empowers self-directed learners by introducing measurement within an integrated system of context-based non-didactic learning. Measurement enables self-directed learners to set goals and observe their own achievements; to make sure that learning material matches their specific vocabulary; and to establish a priority for study that suits their needs. Measurability is achieved within a system where words and lexical phrases are chosen by the learner from familiar content in an integrated system of listening, reading, pronunciation, writing and structured conversation. A database system is incorporated which enables the learner to create individual word or phrase card files that are then tagged with additional identifiers for use in creating custom lists to assist in the learning process. Additional feedback is provided by an automated writing correction program that checks for syntax errors in the learner's written work.

The invention relates to a complex object automatic recognition method based on multi-category primitive self-learning, which comprises the steps of: a) establishing a representational set of multi-category object images; b) preprocessing images in a training set and respectively extracting point, linear and planar primitives; c) conducting concentrated matching calculation, screening and merging to the obtained numerous primitives in a confirmation image set, and respectively constructing point, linear and planar primitive dictionaries; and d) selecting a certain quantity of primitives from the dictionaries, using the primitives as a weak classifier after the primitives are mated and combined, and respectively training the strong classifiers of the three categories of primitives through self-learning; and e) combining the strong classifiers of the three categories of primitives in a probabilistic polling space to realize the accurate positioning, contour extraction and categorical recognition of multi-category complex objects. The method provided by the invention has the advantages that the intelligent level is high and the demands for the recognition and image interpretation of multi-category complex objects can be met.

The invention discloses a method for anomaly detection and positioning of a mobile communication network based on network experience quality. The method is characterized in that real-time anomaly monitoring and anomaly positioning are performed on a network through an anomaly detection subsystem and an anomaly root cause positioning subsystem which are based on network experience quality; at an anomaly diagnosis part, three key performance indexes are selected from the angle of network synthesis user experience to serve as network diagnosis characteristics, and a method of coarse-grained threshold division and fine-grained clustering is adopted to perform abnormal classification; at an anomaly root cause positioning part, a mode of cumulative distribution function matching is adopted to obtain anomaly symptom characteristics, clustering analysis is performed in each type, and root cause positioning of different anomalies can be performed; and finally a cellular network anomaly detection and anomaly root cause positioning subsystem is formed. According to the method, not only can obvious anomalies be detected, but also potential anomalies can be detected, and anomaly root cause positioning can be performed according to different anomaly types; independent study can be performed, and the anomaly detection root cause positioning accuracy is improved continuously.

The invention discloses an artificial intelligence machine learning experiment skill scoring system, and particularly relates to the technical field of artificial intelligence. The artificial intelligence machine learning experiment skill scoring system comprises a hardware architecture and a software architecture, the hardware architecture is composed of a laboratory end device and a server machine room device, and the software architecture is set as a distributed micro-service hierarchical architecture. According to the invention, the cameras with multiple visual angles are adopted to acquire experimental operation video data of students; artificial intelligence technologies such as deep learning, Pattern recognition, Image processing, natural language processing, special intelligent experiment equipment and informationized electronic test paper are matched to achieve automated scoring, meanwhile, the system stores the experiment operation video and the scoring result; A teacher canlog in the system through the Internet to manually recheck an intelligent scoring result error, an automatic scoring result can be autonomously learned through a deep learning algorithm, the accuracyof automatic scoring is improved, and students can carry out score query and dispute processing through the Internet.

The invention discloses a ship intelligent collision avoidance method based on reinforcement learning. The ship intelligent collision avoidance method based on reinforcement learning comprises the steps of firstly, obtaining static data and dynamic data of two ships; secondly, checking the validity of the data and judging whether a collision avoidance program needs to be started or not; calculating a relevant collision avoidance parameter and judging whether a dangerous situation can be caused or not; if the collision danger cannot be generated, enabling the ships to advance by keeping speedsand directions according to a collision avoidance rule; if the collision danger can be generated, using a reinforcement learning method to learn a collision avoidance strategy, using input data as thecalculated parameter to perform training, outputting a strategy generated after training and obtaining a rudder angle for which the ship needs to steer; thirdly, executing the strategy, dynamically updating the dynamic data of the two ships in the step 1 and returning a bonus value; and fourthly, determining a reversion time of course according to the collision avoidance rule after the executionof the strategy is finished, and then enabling the ship to reverse the course. According to the ship intelligent collision avoidance method based on reinforcement learning, autonomic learning and improvement of ship collision avoidance are realized, and an unfavorable situation caused by sailors and so on absolutely relying on experiences is avoided.

The invention provides an enterprise training method and a management system. The system comprises a background training server and a mobile terminal. The method comprises the steps of establishing an examination question document database in the background training server; carrying out simulation exercise, autonomic learning and examination by use of the mobile terminal; carrying out statistic analysis on examination results; and spontaneously setting a training task by an enterprise. The background training server comprises a gallery document management module, a personnel maintenance module and a training statistic module; the gallery document management module sets a training rule and examination questions in combination with training demands according to contents of the examination question document database, generates the training task and issues the training task through the mobile terminal. The training is transferred to a training tool set by the enterprise and is suitable for all domestic enterprises which have internal training management requirements; the enterprises are guided to arrange personalized training knowledge base, a product provision question bank and a knowledge management mechanism; and the enterprises can add and select proper knowledge according to practical requirements and finally accumulate an own personalized electronic knowledge base.

The invention discloses a robot path planning method based on an ANFIS fuzzy neural network, and mainly solves the problems of complex trap path reciprocating and path redundancy in conventional reactive navigation. The method comprises the following steps: to begin with, establishing a kinematic model for a mobile robot; providing a mobile robot navigation controller based on the fuzzy neural network by means of autonomous learning function of the neural network and fuzzy reasoning ability of the fuzzy theory; constructing a Takagi-Sugeno fuzzy inference system based on an adaptive fuzzy neural network structure and serving the Takagi-Sugeno fuzzy inference system as a reference model for local reaction control of the robot; the fuzzy neural network controller outputting offset angle and operation speed in real time, and adjusting the migration direction of the mobile robot online to enable the mobile robot to be able to adjust speed automatically and approach the goal collisionless; and through an improved virtual target method, selecting an optimal path capable of allowing the robot to escape a trapping state.

The invention relates to an on-line sequence limit learning machine method possessing an autonomous learning capability and belongs to the intelligent robot technology field. Nine portions are included and comprise an external state set, an external motion set, a rewarding signal, a value function, a state transition equation, a limit learning machine network hidden layer output set, an intermediate parameter transfer equation, a limit learning machine output set and a limit learning machine output weight transfer equation. In the on-line sequence limit learning machine method possessing the autonomous learning capability, an on-line sequence limit learning machine is taken as a framework and Q learning is combined and reinforced. The on-line sequence limit learning machine method possessing the autonomous learning capability is provided and a model is used in mobile robot path program research so that a robot realize autonomous learning navigation according to an external environment state and rewarding. An autonomous learning capability of the robot in an unknown environment is increased.

The invention provides an autonomous motion identification technology based private coach smart band, and particularly provides an integrated private coach smart band fusing three functions of standard library self-definition, motion identification and standard action self-correction. The smart band has three modes which are an action definition mode, a motion identification mode and a training mode respectively. In the action definition mode, a user can self-define standard actions and construct a standard library, equivalently, the user has a private coach; in the motion identification mode, the user can utilize the smart band to obtain a motion result for analysis to perform self-learning and realize self-improvement; and in the training mode, a training action is selected from a terminal device and motion is performed. The smart band is capable of predicting more standard actions by utilizing new motion data and data in the standard library according to a prediction algorithm so as to self-correct the standard actions and update the standard library, and the prediction is more accurate along with continuous increment of training actions.

The invention relates to an indicator diagram identification method based on a regularized attention convolutional neural network, which comprises the following steps of: 1, establishing a data preprocessing module, and carrying out dimension and grey-scale map processing on a working condition sample set of an oil pumping unit; 2, establishing a regularized attention convolution module, and reinforcing, inhibiting and inactivating the autonomously learned convolution features; 3, embedding the regularized attention convolution module into the convolutional neural network to form a regularizedattention convolutional neural network; 4, establishing an indicator diagram recognition module, and inputting the gray level image of the indicator diagram into the regularized attention convolutional neural network for recognition; 5, establishing an attention loss function, and training a regularized attention convolutional neural network model; 6, inputting the oil pumping unit working condition data collected in real time into the indicator diagram recognition model, and repeating the steps 2-4; 7, taking the indicator diagram identification method based on the RA-CNN as a core, and constructing an intelligent diagnosis system of the working condition of the oil pumping unit. The identification precision of the indicator diagram can be effectively improved.

The invention discloses an autonomous learning concentration degree real-time generating method based on an online learning behavior. The method comprises the following steps of S1, forming an autonomous learning concentration degree displaying parameter Es by a video playing parameter, a viewing time length parameter and a concurrent behavior parameter, and forming a learning concentration degreeexpression formula; S2, respectively constructing a data two-dimensional matrix; and S3, through a concentration degree total parameter Es which is composed of three parameters of P1, Rt and Pa, comprehensively reflecting a learning concentration condition which is reflected in each behavior in the online learning process. The method suggests generation of the concentration degree parameter Es according to a teaching video playing behavior, a video viewing time length and concurrent learning behavior data, and acquisition of online learning concentration degree data is automated and simplified, and real-time concentration degree data acquisition and process analysis become possible, thereby totally changing a current analysis thought and method for the online learning concentration degree, so that online learning process guidance and analysis based on data supporting become possible.

The invention discloses a WEB application security protection method based on automatic learning. The method comprises the steps that 1, logs of non-attack requests are screened; 2, a regular expression set with specific rules is generated through machine learning according to fields in the logs, and white list rules are formed; 3, the regular expression set is adopted to perform matching on received requests, and the requests not in the white list rules are intercepted or marked; and 4, the marked requests are recognized, if the requests are normal, the requests are added into the white listrules, and the requests are intercepted in case of attacks. Through the method, the white list rules can be generated through automatic learning, the missing report rate and the mistaken report rate are low in use, and an unknown vulnerability can be prevented.

The invention discloses an online teaching system and an online teaching method. The online teaching system comprises an online teaching center, a learning terminal and an educational terminal, wherein the learning terminal and the educational terminal are connected with the online teaching center through a network; the learning terminal is used for enabling a student to study through the online teaching center; the educational terminal is used for enabling a teacher to carry out course pre-release and synchronous teaching through the online teaching center; and the online teaching center is used for providing teaching courses and evaluation materials, enabling the student using the learning terminal to study independently, and establishing connection between the learning terminal and the educational terminal so that the teacher can carry out synchronous teaching through the educational terminal and complete interaction with the student. The online teaching system and the online teaching method provided by the invention allow the student to realize independent study, enable the student and the teacher to interact with each other through establishing the connection between the learning terminal and the educational terminal, so as to further achieve the purpose of synchronous teaching and improve the learning efficiency.

The invention discloses an automatic software test system and method constructed based on an artificial intelligence algorithm, and the system can autonomously learn test specification requirements and previous test data and results, and summarize and refine a test specification requirement model. The system can autonomously learn programming language design content and generate a programming language model. The system can be combined with different software platforms and hardware platforms to carry out self-adaption on a programming language model to generate a target system model, and the target system model is used for guiding automatic software testing to be carried out on different software and hardware platforms. By adopting the test system, a system and a method for autonomously learning test requirements and programming specifications, autonomously adapting to different software and hardware platforms to automatically generate test cases, automatically carrying out software tests and automatically providing software test reports can be provided.

An embodiment of the invention provides a self-adaptive learning method and a self-adaptive learning device. The self-adaptive learning method comprises the steps of: acquiring subjects, knowledge points and a playing moment included in a teaching video; displaying test questions for online practice at the playing moment; receiving results of the questions answered by a user; and determining whether to play the teaching video continuously according to a correct rate of the results or recommend other learning resources after the playing moment. The self-adaptive learning method and the self-adaptive learning device associate the video content with test questions, so that the user can answer the test questions while watching the video; and the subjects and the knowledge points involved in the test questions and the video content are closely related, thus a mastery degree of the knowledge points of the user is assessed, the understanding of the knowledge points of the user is deepened, and the self-learning effect of the user is improved.

The invention relates to a college mobile teaching method, which comprises the following steps that before class, a teacher uploads teaching files on a network teaching platform, and students watch contents uploaded by the teacher on line for preparing lessons before class; in class, the students sign in on the platform before classes begin, the teacher checks the attendance conditions and performs evaluation, and the teacher asks questions, selects answerers, issue preemptive answers and performs live broadcast recording through a mobile terminal in class; and after class, the students watchvideos uploaded by the teacher again, the teacher uploads exercises and answers, and the students perform self examination and correction, perform discussion in group chat when encountering a problemafter the self examination, and feed the discussion results back to the teacher. The method is favorable for enhancing the class interaction and improving the class activity, and is favorable for culturing the independent study ability; the goal of changing a college teaching mode mainly through teaching into a teaching mode mainly through learning is achieved; and the limited class time is used for mastering important and difficult point knowledge and culturing the problem solving ability, so that the study efficiency is improved. By using the method, the mobile intelligent terminal needs tobe used, so that the problem of mobile phone playing by students in class is also solved.

The invention discloses a teaching system of a flipped classroom pattern. The teaching system comprises a before-class part, a class part and an after-class part; students and a teacher use smart phones, a computer and an intelligent large screen to realize teaching of the flipped classroom pattern, and a flipped classroom APP is installed in each of the smart phones, the computer and the intelligent large screen; and the flipped classroom APP is provided with a micro course resource, a typical case resource, a professional public policy diagnosis tool, a diverse grouping pattern, a real-time statistical tool, a five-star review function, a review paintbrush, a countdown tool, a real-time interaction zone, a multi-dimensional performance scoring mode and a real-time linkage function. The social security theory teaching system created for flipped classrooms breaks through the single and boring theoretical teaching pattern of the traditional public management course, sufficiently animates the classroom atmosphere via various teaching modes, deepens the understanding on relevant theoretical knowledge, and cultivates students' abilities of self-regulated learning, problem discovery and collaborative solution of problems.

The invention discloses a risk stratification method for myocardial ischemia based on deterministic learning and deep learning. The method includes the steps that conventional 12-lead electrocardiogram signals are collected, based on the deterministic learning theory, neural network modeling and identification are conducted on intrinsic electrocardiodynamic characteristics of the shallow electrocardiogram signals, and the intrinsic dynamic characteristics of ECG signals are obtained; the convolutional neural network under the framework of deep learning is used for achieving the risk stratification of myocardial ischemia. The method combines the deterministic learning dynamic modeling method and the deep learning classification method for the first time, the method is applied to early riskstratification of myocardial ischemia based on the conventional 12-lead electrocardiogram signals, no additional detection equipment is needed, and the method is easy and convenient to use and easy tooperate. Through the deterministic learning method, the dynamic characteristics more sensitive to the ischemic state are extracted, the deep neural network can learn data features independently without further data characterization, and the complexity of the system is reduced.

The invention discloses a pedestrian re-identification method based on hole convolution and an attention learning mechanism, which is used for solving the technical problem that the existing pedestrian re-identification method is poor in practicability. The technical scheme includes: firstly, desigining bottleneck modules based on hole convolution, and connecting a plurality of bottleneck modulesin series to form a trunk network; Pre-training the trunk network to obtain a pre-training model; extracting Attention feature maps at different levels of the backbone network, limiting the consistency of the attention feature maps, and learning attention features at different levels autonomously; Training the network by adopting a cross entropy loss function, a triple loss function and an attention feature map constraint loss function; And directly extracting a final feature by utilizing the trunk network, searching a pedestrian image with the minimum distance from the feature of the to-be-searched pedestrian in a pedestrian retrieval library, endowing the identity to the to-be-searched pedestrian, and finishing a re-identification process. According to the method, the convolutional neural network and the attention learning mechanism are combined, pedestrian re-identification can be accurately carried out, and the practicability is good.

The invention discloses an SQL loophole detecting method based on artificial neuron network. The method consists of an SQL statement analysis module and an artificial neuron network detection module. The main function of the SQL statement analysis module is to convert the SQL statement submitted by the Web application into a feature vector group r composed of 0 and 1, and then submit the resulting feature vector to the artificial neuron network detection module for analysis and detection, and fully apply the self-learning function of the neuron network to realize the detection of SQL statement through the artificial neuron network algorithm obtained by training and regex match. Compared with the traditional method, the SQL loophole detecting method is more convenient, accurate and fast, and does not need to modify the code itself. In addition, the system is developed by Javan language only, which is easy to maintain and can be used for secondary development. The system can well realize function expansion and cross-platform migration and has great application value for SQL injection loophole detection and research.

The invention discloses a pronunciation scoring method. The method comprises the following steps: 1) uploading or recording an audio file having standard pronunciation from a teacher; 2) recognizing the audio file having the standard pronunciation into a corresponding text by virtue of a system, and saving the text as a standard text; 3) opening the audio file having the standard pronunciation inthe steps 1) and 2) by a learner, listening to the standard pronunciation, recording pronunciation by the learner himself, and uploading the pronunciation to the system; 4) recognizing a sample pronunciation file of the learner into corresponding sample characters by the system, and saving the sample characters; and 5) comparing differences between the file and the sample text by virtue of the system, so that quantified data is obtained, and finally returning the quantified data to the learner. According to an oral language testing mode provided by the invention, the learner can make pronunciation by himself, and then the learner can compare the pronunciation with sample pronunciation provided by the teacher, so as to finally judge the accuracy degree and standard degree of the pronunciation of the learner and to give corresponding scores; therefore, the learner can master own pronunciation situation, and autonomous learning can be achieved.

The present invention discloses a DR-based pulmonary tuberculosis intelligent identification method and system. The method is characterized in that: a deep neural network is formed and trained by using a large number of manually labeled samples, and the deep neural network identifies pulmonary tuberculosis image feature in a DR image through self-learning of the pulmonary tuberculosis image features. The resulting pulmonary tuberculosis intelligent identification method can realize automatic identification of the pulmonary tuberculosis image features in the DR image, can realize automatic screening of the DR-based pulmonary tuberculosis, and can effectively reduce the screening cost; and furthermore, the scheme has high recognition efficiency and high recognition accuracy, can effectivelyavoid misdetection and unidentification, and can effectively solve the problem existing in the prior art.

The invention discloses an entity class online management system based on the Internet. By establishing online classes corresponding to entity classes and extending lecture space and time of the entity classes, the individualized teaching is realized, and the teaching efficiency is improved; by establishing an Internet system service end, support demands are provided for teaching and managing interacting, resource sharing, lecture scenarizing, teaching precision, family and school interacting and after-school tutoring, online teaching interaction experience is optimized, the learning interestand autonomous learning ability of students are improved, teachers can better know learning situations of the students, and high-quality teaching is realized.

The invention discloses a clinical medicine three-basic education system based on a cloud platform, which comprises a main server, a plurality of cloud servers connected with the main server and a plurality of student terminals and teacher terminals connected with the cloud servers, wherein each student terminal is internally provided with a registration module, an autonomous learning module, a training enhancement module, an assessment module, a difficult problem summary module, an audio/video call module and a learning data calling module. The clinical medicine three-basic education system combines the learning, training and assessment of clinical medicine knowledge together, and improves the learning efficiency of the medical staff. Meanwhile, the system has a function of explaining difficult problems, realizes the sharing of teaching resources and facilitates the use. The students can learn the clinical medicine knowledge through the system, thereby making up the deficiencies of the prior art on the aspect of clinical medicine three-basic education.

The invention belongs to the technical field of artificial intelligence. The invention discloses an autonomous learning method and system of an agent for man-machine cooperative work. The method comprises the steps of obtaining a cooperation data set, training a cooperation agent and a simulation agent according to the cooperation data set; and assessing whether the cooperation agent and the simulation agent meet assessment requirements or not according to the obtained assessment data generated by cooperation of the trained cooperation agent and the simulation agent in the environment, judgingwhether the trained simulation agent needs new imitation learning or not if the assessment requirements are met, and ending autonomous learning of the trained cooperation agent if the assessment requirements are not met. The system comprises a cooperation agent, a simulation agent and a server. Through the scheme, the dynamic change of the environment can be adapted, the same performance effect can be obtained in the similar environment, the demonstration behaviors of different teaches can be simulated, so that the trained intelligent agent can adapt to the dynamic change of the teaches, andthe teaches with different operation levels can also achieve the same cooperation effect.