Constructing and Testing AI International Legal Education Coupling-Enabling Model

Constructing and Testing AI International Legal Education Coupling-Enabling Model

4.1. AI Data Analysis

With the change of the international law education mode supported by the intelligent teaching ecosystem based on AI technology, there is a move from the traditional classroom online to strengthen the classroom interaction, and then to intelligent teaching [17]. Through the collection of students’ whole process behavioral data, with the help of big data statistical analysis methods [18], an analysis report of students’ learning situation is formed, and AI data analysis technology is used to reasonably label students with intelligent classification methods. Labeling refers to grouping users according to their basic attributes, classroom performance, learning level, test level, etc., to accurately identify the degree of mastery of a particular student’s knowledge points and to realize an accurate portrait of student learning. Then, the intelligent teaching ecosystem combines the knowledge reasoning function of the knowledge map to provide students with intelligent legal knowledge points, such as pushing, assigning personalized homework, etc., and provide intelligent teaching assistants to assist students in their learning.
Figure 3 shows the AI data learning behavior analysis mode, the model of which is based on the learning behavior data of international law students when using the AI teaching system, through different analysis processes, and finally the analysis results, and the results are fed back to the learning stakeholders. That is, the analysis model consists of learning data collection, data analysis [19], results presentation of the three basic links, through the storage of data, data collection, and processing, visual presentation of the results to achieve the process of learning behavior analysis, according to the results of the analysis of the results of the learner, and then provide intervention and feedback and a series of related learning guidance; learning behavior analysis is a cyclical process of continuous improvement.
The computational model established through Pearson is shown as follows:

r = ( X X ¯ ) ( Y Y ¯ ) n × σ x × σ y

In the formula, σ x and σ y represent the standard deviation of the two variables, n is the capacity of the sample, and the meaning of n is the sum of the product of the two standardized scores divided by the sample capacity. The value of r is between −1 and +1: the positive value of r indicates that the correlation between the two is positive, and the negative value of r indicates that the correlation between the two is positive.

After analyzing the data of learners’ learning behaviors, this is used to explore the relationship that exists between various learning behaviors of the learners. In this paper, Spearman correlation coefficient analysis is employed to examine the correlation between various learning behaviors exhibited by learners. This method assesses the linear relationship between variables, and notably, its calculation model does not necessitate adherence to a normal distribution for the data. The formula for calculation is as follows:

r = 1 6 i = 1 n d i 2 n 3 n

The application of these two correlation coefficients helps to reveal the relationship between various learning behaviors of learners in the innovative exploration of the coupled empowerment model of AI and international legal education, providing a powerful tool for further analysis.

4.2. AI Knowledge Graph

Knowledge mapping mainly focuses on how to use AI-related technology to acquire structured domain knowledge to meet the systematic knowledge base organization and management needs of intelligent parenting assistants, and at the same time, on the basis of the knowledge provided by the knowledge mapping for the analysis and determination of parenting problems, it combines the theories of psychology, pedagogy, and sociology to construct a comprehensive solution model for parenting problems. Figure 4 shows the architecture of the AI intelligent knowledge mapping system, which is mainly divided into the data collection layer [20], the knowledge mapping layer, and the dialog system layer; the data collection layer is responsible for the acquisition and management of international law education problems and theoretical data [21]. The knowledge mapping layer is responsible for constructing the knowledge map based on the data collected in the data layer. The Dialogue System Layer is mainly based on the structured domain knowledge provided by the Knowledge Graph and uses AI technology to realize the function of intelligent education assistant. The knowledge graph mainly provides domain knowledge for the AI education system and supports the dialog system. The construction of the knowledge graph mainly includes graph schema definition, knowledge acquisition and knowledge fusion. Based on the information of the three factors of problem behavior, internal individual characteristics, and external environment, the AI technology summarizes the reasons for the emergence of the problem and gives the solution countermeasures, relevant theoretical knowledge, and related cases.

4.3. AI Intelligent Diagnosis

AI intelligent teaching is a new teaching idea and teaching method, in which the simulation is the teacher and the service object is the student, that aims to synthesize the theory of educational psychology and cognitive science based on the characteristics of the learner and the state, tracking the changes in the characteristics of the learner and the state and automatically generating teaching information and adjusting the teaching process and teaching strategy [22]. Figure 5 shows the structure of AI intelligent diagnostic system in which the domain model stores the specialized knowledge of the course taught to the students, which can generate questions and provide correct answers to the questions and the process of solving the problems. The diagnostic model analyzes the student’s response using diagnostic rules to determine what the student already knows or what misconceptions the student has generated and passes them on to the current state of the student model. The role of the teacher model is to incorporate knowledge of instructional strategies and lesson structure to select questions for the student to answer, to monitor and evaluate their behavior, and to select appropriate remedial materials for the student when needed. The cross-interpretation model in the teacher model, as well as the student model, is the main means of realizing that individuals teach in an interactive way [23].
Using the BP neural algorithm in an artificial neural network, combined with the cognitive theory, a cognitive student model that can reflect the learning level and cognitive ability of students is established [24].
The basic structure of BP neural network is a feedforward neural network with more than three layers, mainly using the BP algorithm to solve the problem of hidden layer errors that cannot be calculated due to not being directly connected to the outside world. The BP algorithm belongs to supervised learning algorithms and is an effective method for calculating the derivative of large-scale systems composed of multiple basic subsystems [25]. The structure of the BP neural network is shown in Figure 6. The network trains ( X k , Y k ) through samples to complete learning. If the k -th pair of samples is provided to the network, the output error will be δ j k = y j k j k . j is the j -th component of the actual output of input sample X k ,   j k = f r W r j b r k θ j , r is the number of hidden layer neurons, θ j is the threshold of the f -th neuron in the output layer, b r k is the sigmoid function, r is the net output of hidden and neurons, and b r k = f i W i r a i k T r [26]. The mean squared error of the output layer for sample k is E k = 1 2 j n y j k j k 2 , and E k is the number of output layer units, which decreases gradually with E k correction of connection weights [27].
The input of the network includes 15 quantities as input nodes by selecting six levels of cognitive activities, i.e., the judgment values of six aspects of literacy, comprehension, application, analysis, synthesis and evaluation, and test scores, as well as age, education level [28], physiological conditions, learning environment, mood, learning efficiency, etc., and the output nodes by selecting the degree of mastery of students in terms of concepts, skills, and applications. It actually accomplishes a nonlinear mapping from a 15-dimensional space to a 3-dimensional space, i.e.:

X Y f b p X = X 1 , X 2 , X 3 , , X 15 Y = Y 1 , Y 2 , Y 3

In the above equation, X 1 , X 2 , , X 6 represent the assessment values of six levels of cognitive activities, respectively, X 7 represents the test scores, and X 8 , X 9 , , X 15 represent age, education, physiological conditions, learning environment, mood, and learning efficiency, respectively. Y 1 , Y 2 , Y 3 denote students’ mastery of concepts, skills, and applications, respectively [29].
The BP neural network consists of an input layer, an output layer, and a hidden layer. The input to the input layer is denoted as xi and its output is expressed as follows:

O i ( 1 ) = x ( i ) , i = 1 , 2 , , n

with w i j ( 2 ) and f [ ] representing the weight coefficients of the implicit layer of the BP neural network and denoting the mapping function, the computation formulas for its input and output are respectively expressed as follows:

n e t i ( 2 ) ( k ) = j = 1 m w i j ( 2 ) O j ( 1 ) ( k )

O i ( 2 ) ( k ) = f net i ( 2 ) ( k )

with w l i ( 3 ) and g [ ] representing the weight coefficients of the output layer of the BP neural network and denoting the mapping function, the computation formulas for its input and output are respectively expressed as follows:

n e t l ( 3 ) ( k ) = i = 1 p w l i ( 3 ) O i ( 2 ) ( k )

O l ( 3 ) ( k ) = g n e t l ( 3 ) ( k )

for the p st sample, whose actual and network outputs are O p ( k + 1 ) and O p ( k + 1 ) , respectively, then the error is given by the following:

E p = 1 2 O p ( k + 1 ) O p ( k + 1 ) 2

Through the above steps, the BP neural network can be trained according to the input data and expected output of the students, and the weights can be continuously adjusted, so that a cognitive student model can be created that reflects the learning level and cognitive ability of the student [30]. This model can output the student’s mastery of concepts, skills, and applications through the learner’s cognitive activity assessment values and other relevant information, which supports the subsequent creation of a coupled empowerment model of AI and international legal education [31].

Disasters Expo USA, is proud to be supported by Inergency for their next upcoming edition on March 6th & 7th 2024!

The leading event mitigating the world’s most costly disasters is returning to the Miami Beach

Convention Center and we want you to join us at the industry’s central platform for emergency management professionals.
Disasters Expo USA is proud to provide a central platform for the industry to connect and
engage with the industry’s leading professionals to better prepare, protect, prevent, respond
and recover from the disasters of today.
Hosting a dedicated platform for the convergence of disaster risk reduction, the keynote line up for Disasters Expo USA 2024 will provide an insight into successful case studies and
programs to accurately prepare for disasters. Featuring sessions from the likes of The Federal Emergency Management Agency,
NASA, The National Aeronautics and Space Administration, NOAA, The National Oceanic and Atmospheric Administration, TSA and several more this event is certainly providing you with the knowledge
required to prepare, respond and recover to disasters.
With over 50 hours worth of unmissable content, exciting new features such as their Disaster
Resilience Roundtable, Emergency Response Live, an Immersive Hurricane Simulation and
much more over just two days, you are guaranteed to gain an all-encompassing insight into
the industry to tackle the challenges of disasters.
By uniting global disaster risk management experts, well experienced emergency
responders and the leading innovators from the world, the event is the hub of the solutions
that provide attendees with tools that they can use to protect the communities and mitigate
the damage from disasters.
Tickets for the event are $119, but we have been given the promo code: HUGI100 that will
enable you to attend the event for FREE!

So don’t miss out and register today:

And in case you missed it, here is our ultimate road trip playlist is the perfect mix of podcasts, and hidden gems that will keep you energized for the entire journey


This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More