Research On Acquisition And Calculation Method Of Influencing Factors Of Learning Concentration In Mobile Learning Environment

With the popularity of intelligent mobile terminals,the interactive learning experience of mobile terminal learning is more convenient.The organic combination of intelligent mobile terminals and education and teaching has gradually become the mainstream learning method in the new era.The mobile terminal learning environment breaks the boundaries of the traditional classroom.Learners can use the mobile terminal reasonably without the limitation of time and place,which solves the problem of integration before and after class.Since novel coronavirus pneumonia in 2020 has been seriously affected,a large number of learners can not conduct normal offline courses,so online learning through mobile terminals is becoming more and more important.Learning through mobile terminals is widely used in learners' daily life,which brings a lot of convenience for learners and teachers.However,through the mobile terminal,learners and teachers can not understand whether students listen carefully and study concentration in class as well as offline classroom,and mobile terminal online learning can not monitor and guide students' learning behavior.In order to solve this problem,through the acquisition of terminal learning behavior,this paper explores the influencing factors of learners' learning concentration in the mobile learning environment and monitors the online learning status.Therefore,this paper uses monitoring technology and event processing technology to integrate deep learning algorithm to obtain three types of mobile terminal learning behavior data,which are terminal data acquisition,touch screen operation acquisition and human behavior recognition.Firstly,based on the Android framework,we develop a tool to acquire learners' behavior data to acquire the terminal data of learners' autonomous learning process,and take the virtual simulation experiment as an example to capture the occurrence of learners' touch-screen events and achieve the acquisition of touch-screen operation data.Secondly,the acceleration sensor data collected in the terminal data acquisition tool is taken as the original data set,and the preprocessed acceleration sensor data is imported into the improved neural network model(cnn-lstm)which integrates the long-term memory network and convolution neural network to recognize human behavior.Through research and application experiments,this paper first proposes the method of human behavior recognition The improved cnn-lstm model is compared with hidden Markov model,machine learning algorithm and LSTM model.Finally,the weight of learners' behavior data is fitted by linear regression equation to predict the influence coefficient of learners' behavior data on learning concentration in mobile learning environment.In this paper,based on the application scenario of mobile terminal learning,we obtain the learning behavior data,implement a terminal data acquisition tool to obtain the device perception information of learners' learning state,capture the touch screen operation of learners' experiment based on virtual simulation experiment,and obtain the learning activity state of learners by improving cnn-lstm,The acquisition of the above mobile terminal learners' learning behavior data is the premise of analyzing the influence factors of learners' online learning concentration.By fitting the data weight of online learning behavior of learners,the online learning behavior of learners is monitored,the influencing factors of learning concentration are explored,and the influence coefficient of mobile terminal learning behavior on learning concentration is calculated.