Data processing method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a data processing method and device, and relates to the technical field of education. According to the specific implementation scheme, an education strategy is generated based on a two-person game model and teaching task data; the education strategy is input into an education subject model pre-constructed for an education subject, an action sequence output by the education subject model is obtained, and the education subject model is used for representing the corresponding relation between the education strategy and the action sequence; the action sequence and the teaching task data are input into a learning subject model pre-constructed for a learning subject, a learning strategy output by the learning subject model is obtained, and the learning subject model is used for representing the corresponding relation between the action sequence and the learning strategy and between the teaching task data and the learning strategy; inputting the learning strategy into a pre-constructed main body state conversion model to obtain a current main body state output by the main body state conversion model; and based on the current subject state, evaluating the performance of the learning subject model on the teaching task data to obtain performance data.

Description

Technical Field

[0001] The present invention belongs to the field of education, and in particular to a data processing method and device, an electronic device, and a computer-readable storage medium. Background Art

[0002] The education system can be viewed as an intelligent system in which an agent - the teacher - transmits information to another agent - the learner. As a computational model of the education system, machine teaching is dedicated to solving the problem of how to discover the best training data to guide learners to reach the target model with minimal effort.

[0003] Traditional machine teaching is limited to a class of restrictive learners and hyperparameters with fixed inductive biases. Such learners cannot update their inductive biases during the learning process. For example, the teacher-student model involves the process of teachers imparting knowledge to students. The teacher generates learning strategies and guides learners to learn, thereby achieving better learning efficiency. However, due to the fixed inductive bias of the teacher-student model, learners lack adaptability when facing new tasks. Learners cannot adjust their learning strategies according to changes in tasks, resulting in insufficient generalization ability and difficulty in learning and transferring knowledge from different types of tasks.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the disclosure and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0005] The present disclosure provides a data processing method and device, an electronic device, and a computer-readable storage medium.

[0006] According to the first aspect, a data processing method is provided, which includes: generating an educational strategy based on a two-person game model and teaching task data, the two-person game model being a model pre-constructed for an educational subject and a learning subject; inputting the educational strategy into the educational subject model pre-constructed for the educational subject, obtaining an action sequence output by the educational subject model, and the educational subject model being used to characterize the correspondence between the educational strategy and the action sequence; inputting the action sequence and the teaching task data into a learning subject model pre-constructed for the learning subject, obtaining a learning strategy output by the learning subject model, and the learning subject model being used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy; inputting the learning strategy into a pre-constructed subject state transformation model, obtaining a current subject state output by the subject state transformation model, and the subject state transformation model being used to characterize the correspondence between the subject state and the learning strategy; and evaluating the performance of the learning subject model on the teaching task data based on the current subject state to obtain performance data.

[0007] According to the second aspect, a data processing device is provided, which includes: a generation unit, configured to generate an educational strategy based on a two-person game model and teaching task data, the two-person game model is a model pre-constructed for an educational subject and a learning subject; an action acquisition unit, configured to input the educational strategy into the educational subject model pre-constructed for the educational subject, and obtain an action sequence output by the educational subject model, the educational subject model is used to characterize the correspondence between the educational strategy and the action sequence; a strategy acquisition unit, configured to input the action sequence and the teaching task data into the learning subject model pre-constructed for the learning subject, and obtain the learning strategy output by the learning subject model, the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy; a transformation unit, configured to input the learning strategy into a pre-constructed subject state transformation model, and obtain the current subject state output by the subject state transformation model, the subject state transformation model is used to characterize the correspondence between the subject state and the learning strategy; an evaluation unit, configured to evaluate the performance of the learning subject model on the teaching task data based on the current subject state, and obtain performance data.

[0008] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation manner of the first aspect.

[0009] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect.

[0010] The data processing method and device provided by the embodiments of the present disclosure first generate an educational strategy based on a two-person game model and teaching task data, and the two-person game model is a model pre-constructed for an educational subject and a learning subject; secondly, the educational strategy is input into the educational subject model pre-constructed for the educational subject to obtain an action sequence output by the educational subject model, and the educational subject model is used to characterize the correspondence between the educational strategy and the action sequence; thirdly, the action sequence and teaching task data are input into a learning subject model pre-constructed for the learning subject to obtain a learning strategy output by the learning subject model, and the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy; then, the learning strategy is input into a pre-constructed subject state transformation model to obtain a current subject state output by the subject state transformation model, and the subject state transformation model is used to characterize the correspondence between the subject state and the learning strategy; finally, based on the current subject state, the performance of the learning subject model on the teaching task data is evaluated to obtain performance data. Therefore, through the two-person game model, the subject state of the learning subject can change dynamically with the changes in the action sequence of the educational subject, strengthen the adjustment and evolution of the subject state of the learning subject, help the learning subject to better adapt to the learning tasks, and improve the learning personalization and adaptability of the learning subject.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is a flow chart of an embodiment of a data processing method according to the present disclosure;

[0014] Figure 2 is a schematic structural diagram of an embodiment of a data processing device according to the present disclosure;

[0015] Figure 3 It is a block diagram of an electronic device used to implement the data processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0017] The technical solution of the present disclosure is described below by means of specific embodiments. It should be understood that one or more steps mentioned in the present disclosure do not exclude the existence of other methods and steps before and after the combination step, or other methods and steps may be inserted between these explicitly mentioned steps. It should also be understood that these examples are only used to illustrate the present disclosure and are not used to limit the scope of the present disclosure. Unless otherwise specified, the numbering of each method step is only for the purpose of identifying each method step, and does not limit the order of arrangement of each method or limit the scope of implementation of the present disclosure. Changes or adjustments in their relative relationships can also be regarded as the scope of implementation of the present disclosure without substantial changes in the technical content.

[0018] The sources of the raw materials and instruments used in the examples are not particularly limited and can be purchased from the market or prepared according to conventional methods known to those skilled in the art.

[0019] In response to the defects in traditional technologies, the present invention proposes a data processing method. Through a two-person game model, the educational subject can guide the learning subject to continuously adjust its subject state in practice, form an inductive bias for future tasks, and improve the learning personalization and adaptability of the learning subject. Figure 1 A process 100 according to an embodiment of a data processing method of the present disclosure is shown. The data processing method comprises the following steps:

[0020] Step 101, generating an educational strategy based on a two-player game model and teaching task data.

[0021] In this embodiment, the two-person game model is a mathematical model pre-constructed for the educational subject and the learning subject, which is used to describe the interaction between the educational subject and the learning subject. Since the educational subject and the learning subject have multi-dimensional states, in order to effectively quantify the educational subject and the learning subject, an educational subject model and a learning subject model can be constructed for the educational subject and the learning subject respectively.

[0022] In this embodiment, the learning subject model and the education subject model are constructed separately, and then the two-person game model is constructed, allowing focus on understanding the independent behavior and characteristics of each subject. Once a clear understanding of the learning subject and the education subject is obtained, they can be placed in the two-person game model to consider the strategic interaction between the learning subject model and the education subject model.

[0023] In this embodiment, the education subject model is a model of behavioral strategies constructed for the education subject, which can reflect at least one aspect of the education subject; the learning subject model is a model of behavioral strategies constructed for the learning subject, which can reflect at least one aspect of the learning subject; the education subject model and the learning subject model can be two key components in the two-person game model, the education subject model represents the behavioral strategy of the education subject, and the learning subject model represents the behavioral strategy of the learning subject. The education subject model and the learning subject model cooperate with each other in the two-person game model to jointly promote the learning process, and the actual game process between the education subject and the learning subject is also a process in which the education subject model and the learning subject model adjust parameters. The education subject model guides the learning subject to learn through action sequences and education strategies, and the learning subject model continuously adjusts the learning strategy according to the guidance of the education subject and its own learning status, and finally achieves the learning goal.

[0024] Optionally, the education subject model and the subject state of the learning subject can also be components of the two-person game model. The two-person game model can also characterize the corresponding relationship between the education strategy of the education subject and the subject state of the learning subject. The two-person game model can emphasize the adjustment and evolution of the learner's subject state. In the two-person game model, the strategy space of the learning subject and the education subject are defined respectively. The two-person game model can enable the education subject model to dynamically adjust its teaching strategy according to the current subject state of the learner, thereby optimizing the learning process of the learning subject.

[0025] In this embodiment, the subject state is a multi-dimensional state space, where the dimensions represent the characteristics, knowledge level, and confidence of the learning subject. The initial value of the subject state of the learning subject can be determined through preliminary evaluation or basic knowledge test.

[0026] In this embodiment, the educational task data is teaching data related to the learning subject and the educational subject respectively. The subject state of the learning subject will change with the changes of the teaching task data and the learning process of the learning subject. For example, the educational task data includes: learning knowledge data, and the subject state of the learning subject will become richer and more complete due to the learning knowledge data. The educational task data also includes important factors that shape the subject state of the learning subject. For example, the educational task data includes: the knowledge level and learning preference of the learning subject. The educational subject can formulate better educational strategies by understanding the knowledge level and learning preference of the learning subject. The educational task data can provide a basis for parameter setting for the two-person game model. For example, the knowledge level and learning preference of the learning subject can be determined through the educational task data, so that the teaching strategy can be better specified; the internal state of the learning subject will change with the changes of the educational task data and the learning process; the payoff functions of the educational subject model and the learning subject model are both related to the educational task data.

[0027] In this embodiment, the educational strategy is a strategy for guiding the learning subject to learn. The educational strategy can guide the educational subject to perform a multi-step action sequence. The actions in the action sequence have their own execution order, and each action is to achieve the educational strategy. The actions of the educational subject can be in various forms, such as giving specific feedback, asking questions, guiding discussions, or providing examples. The educational strategy is a rule established through a two-person game model to describe the impact of each action of the educational subject on the subject state of the learning subject. For example, when the educational subject gives positive feedback, the confidence of the learning subject may increase; and after the educational subject points out the error, the learning subject may need to adjust its knowledge state.

[0028] In this embodiment, the above step 101 includes: determining the subject state of the learning subject based on the teaching task data; inputting the subject state into the two-person game model to obtain the educational strategy output by the two-person game model, wherein the two-person game model is a model that reflects the correspondence between the subject state of the learning subject and the educational strategy of the educational subject, wherein the learning subject model of the learning subject is used to generate the subject state of the learning subject, and the educational subject model of the educational subject is used to generate the educational strategy.

[0029] Optionally, the educational task data also includes: educational indicators and learning indicators, wherein the educational indicators are indicators of the benefit function of the educational subject model in the two-person game model, including the learning outcomes and learning efficiency of the learning subject. The learning indicators are indicators of the benefit function of the learning subject model in the two-person game model, including: learning satisfaction and knowledge mastery.

[0030] Optionally, the above step 101 further includes: detecting whether the education strategy meets the index requirements of the education index in the education task data, wherein the index requirement refers to whether the education index meets a preset threshold. If so, executing step 102; otherwise, adjusting the parameters of the education subject model or the learning subject model in the two-person game model so that the education strategy meets the index requirements of the education index.

[0031] In this embodiment, the education subject is a subject that provides knowledge and learning direction to the learning subject based on the teaching task data, wherein the education subject behavior strategy can be reflected by the education subject model constructed for the education subject, and the education subject model can generate an action sequence, and the action sequence can be applied to the learning subject. For example, the education subject is a virtual person such as a digital teacher or a digital master, or the education subject is an actual person; the learning subject is a subject that receives the information of the education subject and makes a learning state, wherein the learning subject behavior strategy can be reflected by the learning subject model constructed for the learning subject, for example, the learning subject is a student, an apprentice, etc.

[0032] Step 102, input the education strategy into the education subject model pre-constructed for the education subject, and obtain the action sequence output by the education subject model.

[0033] In this embodiment, the education subject model is used to characterize the correspondence between the education strategy and the action sequence. The education strategy and the action sequence are both information related to the education subject in the two-person game model. The education strategy is the strategy of the education subject to educate the learning subject, and the action sequence is the action sequence of the education subject to educate the learning subject.

[0034] In this embodiment, the education subject model is a machine learning model. When constructing the education subject model, the usual steps include: first, it is necessary to define a functional relationship that maps the input (such as data corresponding to the education strategy) to the output (such as data corresponding to the action sequence of the education subject). Then define a cost function (also called a loss function), which measures the difference between the model prediction value and the actual value. The cost function is used to evaluate the quality of the education subject model. The parameters in the functional relationship are adjusted through an optimization process (such as a gradient descent algorithm) to minimize the cost function. This process aims to find a set of parameters that makes the functional relationship perform best on a given data set. After multiple iterative optimizations, the final functional relationship should be the optimal or most suitable education subject model for the current teaching task data.

[0035] Step 103, inputting the action sequence and teaching task data into a learning subject model pre-constructed for the learning subject, and obtaining a learning strategy output by the learning subject model.

[0036] In this embodiment, the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy. Among them, the learning strategy is the information involved in the learning subject in the two-person game model, and the teaching task data is the information involved in the learning subject and the education subject in the two-person game model. The learning strategy is the strategy for the learning subject to learn the knowledge corresponding to the teaching task data under the guidance of the action sequence of the education subject, and the action sequence is the action sequence of the education subject to specifically educate the learning subject.

[0037] In this embodiment, the learning subject model is a machine learning model. When constructing the learning subject model, the usual steps include: first, it is necessary to define a functional relationship that maps input (such as learning behavior data) to output (such as learning outcomes or teaching effects). Next, define a cost function that measures the difference between the predicted value and the actual value of the learning subject model. The cost function is used to evaluate the quality of the learning subject model. The parameters in the functional relationship are adjusted through an optimization process (such as a gradient descent algorithm) to minimize the cost function. This process aims to find a set of parameters that makes the functional relationship perform best on a given data set. After multiple iterations of optimization, the functional relationship finally obtained should be the optimal or most suitable learning subject model for the current teaching task data.

[0038] Step 104: input the learning strategy into the pre-built subject state transformation model to obtain the current subject state output by the subject state transformation model.

[0039] In this embodiment, the subject state conversion model is used to characterize the corresponding relationship between the subject state and the learning strategy. The subject state conversion model is intended to describe the state changes of the learning subject under different learning strategies, rather than the changes in the learning strategy itself.

[0040] In this embodiment, the subject state is a multidimensional state space of the learning subject, and the dimensions represent the knowledge level, characteristics, confidence, etc. of the learning subject under the current teaching task data. The subject state transformation model is a subject state that reflects the learning subject under the current learning strategy.

[0041] In this embodiment, the subject state transformation model enables the educational subject to monitor the changes in the subject state of the learning subject in real time during each educational interaction. By collecting the subject state of the learning subject, it breaks through the limitation of traditional machine teaching that only targets static learning subjects, and gives the learning subject higher adaptability and autonomous learning ability.

[0042] Step 105 , based on the current subject state, evaluate the performance of the learning subject model on the teaching task data to obtain performance data.

[0043] In this embodiment, the performance data is a reflection of the degree of completion of the specific task of the learning subject model on the data task data. The learning subject model outputs the learning strategy through the subject state transformation model to obtain the current subject state of the learning subject. The current subject state of the learning subject can reflect the dimensional value of the learning subject or the learning subject model from multiple dimensions. The dimensional value of each dimension represented by the subject state is compared with the standard value of the corresponding dimension of the teaching task data to obtain the performance data of the learning subject model on the teaching task data.

[0044] Specifically, the above step 105 includes: determining the dimension value of each dimension of the current subject state; extracting the standard value related to each dimension in the teaching task data; for each dimension, comparing the dimension value of the dimension with the standard value of the dimension to obtain comparison data of each dimension; performing weighted summation on the comparison data of all dimensions in the current subject state to obtain performance data.

[0045] Optionally, the above 105 includes: according to the current subject state and learning task data, using multiple evaluation indicators to evaluate the performance of the learning subject model on the current task to obtain performance data, wherein the evaluation indicator can be a loss function, F1 score, etc., and the performance data can be the accuracy, generalization ability, etc. of the learning subject model.

[0046] Optionally, in order to better adapt to the changes in the subject state of the learning subject, the present disclosure can also introduce a collaborative learning algorithm. Specifically, the data processing method includes: obtaining the experience data of the reference subject, and in response to the data value of the performance data being less than the data value of the experience data, adjusting the parameters of the learning subject model. This collaborative learning algorithm allows multiple learning subjects to learn from each other's experience, while providing the learning subject with dynamic resources and strategy guidance based on its state. For example, when a learning subject needs repeated guidance on a certain concept, the system can identify its learning obstacles and meet its needs through different teaching strategies (such as examples, analogies, or enhanced feedback).

[0047] The data processing method provided in this embodiment combines digital technology with intelligent technology, and realizes high integration, optimization and personalized push of resources through computer processing, big data analysis, artificial intelligence and other means, so as to achieve the purpose of improving efficiency, enhancing interactivity and personalized experience. In the field of education, digitalization usually involves converting traditional educational resources into digital form, and using intelligent algorithms to adapt to the needs of learning subjects and provide adaptive and personalized learning experience.

[0048] The present disclosure proposes a new teaching framework. If the initial bias of the learning subject is not suitable for the current task and cannot be changed, the educational subject may have to hide part of the training data in order to teach them a good model. More precisely, by hiding part of the data, the learning subject can be taught a better model than providing the entire data set. For teaching machine learning algorithms, this teaching strategy is similar to data poisoning, and for teaching humans, it is an undesirable behavior that attempts to manipulate the learning subject. However, considering that the bias of the learning subject can be changed and influenced by the educational subject, this gives rise to a completely new teaching strategy: helping the learning subject adjust their subject state, essentially teaching them better inductive biases. This approach not only teaches the learning subject to perform better in the learning stage, but also helps them perform better in future tasks without the educational subject, thereby empowering the learning subject.

[0049] The present disclosure proposes the concept of "teaching for learning", and the concept of "teaching for learning" (TtL) emphasizes that the education subject not only imparts knowledge, but also cultivates the learning ability of the learning subject, so that it can select the best model without the intervention of the education subject, and apply it to similar tasks in the future. The present disclosure formalizes the concept of "teaching for learning" into a two-person game between a learning subject and an education subject, unifies the inductive bias in machine learning algorithms (such as model family, initialization, etc.) with the inductive bias in human learning subjects (such as prior task knowledge and meta-knowledge, etc.), and models both situations as potential subject states of the learning subject. The main difference from traditional machine teaching is that the subject state of the learning subject in the new framework of the present disclosure will change dynamically with the behavior of the education subject. Therefore, in the new framework, the task of the education subject not only includes guiding the learning subject to approach the best model, but also includes ensuring that the learning subject can autonomously learn a good model in similar tasks in the future without the supervision of the education subject. In order to achieve this goal, the education subject needs to guide the learning subject to reach a subject state that contains inductive biases suitable for current and future tasks.

[0050] The data processing method provided by the embodiment of the present disclosure first generates an educational strategy based on a two-person game model and teaching task data, and the two-person game model is a model pre-constructed for an educational subject and a learning subject; secondly, the educational strategy is input into the educational subject model pre-constructed for the educational subject to obtain an action sequence output by the educational subject model, and the educational subject model is used to characterize the correspondence between the educational strategy and the action sequence; thirdly, the action sequence and the teaching task data are input into the learning subject model pre-constructed for the learning subject to obtain a learning strategy output by the learning subject model, and the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy; then, the learning strategy is input into a pre-constructed subject state transformation model to obtain a current subject state output by the subject state transformation model, and the subject state transformation model is used to characterize the correspondence between the subject state and the learning strategy; finally, based on the current subject state, the performance of the learning subject model on the teaching task data is evaluated to obtain performance data. Therefore, through the two-person game model, the subject state of the learning subject can change dynamically with the changes in the action sequence of the educational subject, strengthen the adjustment and evolution of the subject state of the learning subject, help the learning subject to better adapt to the learning tasks, and improve the learning personalization and adaptability of the learning subject.

[0051] In some embodiments of the present disclosure, the above method also includes: obtaining a new educational strategy based on performance data; inputting the new educational strategy into the educational subject model to obtain a new action sequence output by the educational subject model; inputting the new action sequence and teaching task data into the learning subject model to obtain a new learning strategy output by the learning subject model.

[0052] In this embodiment, the performance data is the performance result of the learning subject obtained by analyzing the learning subject model. The performance data includes: learning bottleneck data, learning strategy effectiveness data and learning mode, wherein the learning bottleneck can show the difficulty or shortcomings of the learning subject. For example, if the learning subject scores low on a specific concept, it means that they may have obstacles in understanding the concept. Learning strategy effectiveness data is data that helps evaluate the effectiveness of existing educational strategies. For example, if the performance of the learning subject does not improve significantly after receiving a certain teaching method, it means that the strategy may need to be adjusted or improved. Learning mode is the learning mode and regularity data of the learning subject. For example, some learning subjects may be more suitable for learning through vision, while others may be more suitable for learning through hearing.

[0053] In this embodiment, the above-mentioned new educational strategy based on performance data includes: updating the parameters in the educational subject model based on the performance data so that it more accurately reflects the learning situation of the learning subject. For example, the parameters in the model regarding the learning speed or learning style of the learning subject can be adjusted according to the performance of the learning subject on different tasks. The educational subject model can generate new educational strategies based on the updated parameters. For example, if the model finds that the learning subject has difficulties with a certain concept, it can suggest that the educational subject adopt different teaching methods or provide more practice opportunities.

[0054] In this embodiment, the education subject can monitor the state changes of the learning subject in real time during each teaching interaction. By collecting information such as the learning subject's reaction, learning behavior, guesses and errors, the education subject can adjust the teaching strategy in time according to the current state and performance of the learning subject. This can be achieved with the help of a feedback loop to ensure that the subject state of the learning subject can flexibly respond to the guidance of the education subject and accurately adjust the subject state of the learning subject.

[0055] The present disclosure introduces an evaluation mechanism to quantify the state of the learning subject. This mechanism tracks the learning progress and understanding level of the learning subject through regular evaluation and feedback, using indicators (such as confidence index, mastery level, etc.). Machine learning algorithms can be used to analyze these data and predict changes in the adaptability and future performance of the learning subject. According to the subject state of the learning subject, the educational subject can dynamically adjust the difficulty of the learning content and tasks in order to provide a personalized learning path. Through the reinforcement learning algorithm, the educational subject can learn the best guidance strategy, thereby gradually guiding them to contact more challenging content without affecting the self-confidence and learning motivation of the learning subject.

[0056] The data processing method provided in this embodiment obtains a new educational strategy based on performance data; inputs the new educational strategy into the educational subject model to obtain a new action sequence output by the educational subject model; inputs the new action sequence and teaching task data into the learning subject model to obtain a new learning strategy output by the learning subject model. The teaching strategy can be dynamically adjusted according to the performance of the learning subject to adapt to the learning status of the learning subject that changes over time. This real-time feedback design enhances the interaction between the learning subject and the educational subject, resulting in more effective learning.

[0057] In some optional implementations of the present disclosure, the performance data include: learning style and learning level, mastered knowledge points and feedback information, and the new education strategy obtained based on the performance data includes at least one of the following: determining the learning plan strategy and the teaching content strategy based on the learning style and learning level, and using the learning plan strategy and the teaching content strategy as the new education strategy; removing the information related to the mastered knowledge points in the education strategy to obtain the new education strategy; generating learning suggestion information based on the feedback information, and using the learning suggestion information as the new education strategy.

[0058] In this optional implementation, the learning path includes a learning plan strategy and a teaching content strategy. The learning path can be optimized through performance data, such as designing different learning plan strategies and teaching content strategies for learning subjects with different learning styles or different learning levels.

[0059] In this optional implementation, adjusting the teaching content includes removing or adding information, and dynamically adjusting the teaching content and teaching difficulty according to the performance data of the learning subject. For example, if the learning subject has mastered a certain concept, the relevant content can be skipped and the next learning stage can be entered.

[0060] In this optional implementation, the learning suggestion information includes personalized learning suggestions or strategies for solving learning problems, feedback and guidance: the education strategy may include content that provides feedback and guidance to the learning subject. For example, the education subject may provide personalized learning suggestions or strategies for solving learning problems based on the performance data of the learning subject.

[0061] This optional implementation provides a method for obtaining a new educational strategy. Based on learning style and learning level, a learning plan strategy and a teaching content strategy are determined, and the learning plan strategy and the teaching content strategy are used as new educational strategies; information related to mastered knowledge points in the educational strategy is removed to obtain a new educational strategy; based on feedback information, learning suggestion information is generated, and the learning suggestion information is used as a new educational strategy, which provides a reliable implementation for obtaining a variety of new educational strategies and improves the reliability of obtaining new educational strategies.

[0062] In some optional implementations of the present disclosure, the above-mentioned learning subject model is constructed through the following steps: constructing a dynamic conversion model that characterizes the changes in the subject state of the learning subject under teaching task data over time; constructing a task selection model, the task selection model is used to characterize the correspondence between the action sequence, learning task data and the learning strategy under the current subject state, and the current subject state is provided by the dynamic conversion model; using the dynamic conversion model and the task selection model as the learning subject model, and optimizing the parameters of the learning subject model through the cost function of the learning subject model.

[0063] In this embodiment, the dynamic conversion model is responsible for describing the law of the change of the subject state of the learning subject over time. It reflects the state evolution process of the learning subject under the influence of different learning tasks and teaching strategies. The task selection model is based on the dynamic conversion model, which links the action sequence, learning task data and learning subject strategy, and guides the education subject model to select the most appropriate teaching strategy and task to promote the positive change of the subject state of the learning subject and ultimately achieve the teaching goal. That is, the dynamic conversion model provides the task selection model with a theoretical basis for the change of the learning subject state, and the task selection model is the application of the dynamic conversion model in actual teaching.

[0064] In this optional implementation, the cost function is a function used to measure the gap between the model prediction and the actual data. The total cost is obtained by calculating the square difference between the predicted value and the target value and summing them, and then dividing by two and multiplying by the number of samples. The cost function of the learning subject model includes: the cost function of the task selection model and the cost function of the dynamic conversion model. By calculating the actual values ​​of the cost functions of the two, the purpose of optimizing the parameters of the learning subject model can be achieved.

[0065] The learning subject model construction method provided by the present invention constructs a dynamic conversion model that characterizes the changes of the subject state of the learning subject under teaching task data over time; constructs a task selection model, and the task selection model is used to characterize the correspondence between the action sequence, the learning task data and the learning strategy under the current subject state, and the current subject state is provided by the dynamic conversion model; the dynamic conversion model and the task selection model are used as the learning subject model, and the parameters of the learning subject model are optimized through the cost function of the learning subject model, which provides a reliable implementation basis for the construction of the learning subject model in machine learning and improves the accuracy of the learning subject model.

[0066] In some optional implementations of the present disclosure, the above-mentioned construction of a dynamic conversion model that characterizes the changes of the subject state of the learning subject over time under teaching task data includes: determining a first recognition inductive bias in the machine learning algorithm and a second recognition inductive bias of the learning subject; determining the subject state of the learning subject based on the first recognition inductive bias and the second recognition inductive bias; constructing a dynamic conversion model that characterizes the changes of the subject state over time, and optimizing the parameters of the dynamic conversion model through the cost function of the dynamic conversion model.

[0067] In this optional implementation, the above-mentioned determination of the first identification inductive bias in the machine learning algorithm and the second identification inductive bias of the learning subject includes: identifying inductive biases from the machine learning algorithm, such as model architecture, hyperparameters, initialization, etc., to obtain the first identification inductive bias; identifying inductive biases from human learning subjects, such as prior knowledge, meta-knowledge, learning style, etc., to obtain the second identification inductive bias.

[0068] In this optional implementation, the above-mentioned determination of the subject state of the learning subject based on the first recognition inductive bias and the second recognition inductive bias includes: abstracting the first recognition inductive bias and the second recognition inductive bias into parameters of the subject state of the learning subject, such as the weight of the modeling preference function, the parameters of the learning algorithm, etc.

[0069] In this optional implementation, a dynamic transformation model is established to characterize the changes of the subject state over time based on the education subject's actions and learning strategies. For example, the tutor's actions may affect the learning subject's modeling preferences, while variable recommendation actions may affect the learning subject's model selection.

[0070] In this optional implementation, a Markov switching model can be used to describe the changes in the subject state of the learning subject. The actions of the educational subject will cause the subject state of the learning subject to switch from "not understanding collinearity" to "understanding collinearity", and the variable recommendation action will affect the weight of the learning subject's modeling preference function.

[0071] The method for constructing a dynamic transformation model provided by this optional implementation integrates the concepts of inductive bias in machine learning and human learning, including model families, initialization, prior knowledge, and meta-knowledge, to provide a more comprehensive description of the subject state of the learning subject. This unity will optimize the teaching process and make it more targeted.

[0072] In some optional implementations of the present disclosure, the subject state transformation model is constructed by the following steps: identifying at least two key factors that affect the educational subject and the learning subject; determining quantitative dimension indicators based on the key factors; constructing a state transition function based on the key factors and the quantitative dimension indicators, and the state transition function is used to describe the probability of the learning subject transferring from one state to another; setting parameters of the state transition function based on the influence data of the educational subject on the learning subject to obtain the learning subject transformation function; establishing a correspondence between the learning subject transformation function and a pre-constructed learning strategy to obtain the subject state transformation model, and optimizing the parameters of the subject state transformation model through the cost function of the subject state transformation model.

[0073] In this optional implementation, the key factors are factors that affect the learning subject's cognition and behavior, such as prior knowledge, learning style, etc. The quantitative dimension indicator is an indicator obtained by selecting the dimension of the subject state from the key factors and converting the dimension into an indicator. The state transition function is a state transition rule.

[0074] In this optional implementation, the specific steps of constructing the subject state transformation model are shown in Step 1 to Step 4 below:

[0075] Step1: Define the subject status dimension.

[0076] Identify influencing factors: Analyze factors that may affect the learning subject's cognition and behavior during the learning process, such as:

[0077] a Prior knowledge: the relevant knowledge and experience that the learning subject has before learning specific knowledge or skills.

[0078] bLearning style: The learning method preferred by the learner, such as visual, auditory or kinesthetic learning.

[0079] c Motivation: The intrinsic and extrinsic motivation of the learning subject to learn specific knowledge or skills.

[0080] d Metacognition: the learning subject's ability to recognize and monitor his or her own learning process.

[0081] eEmotional state: The emotional response of the learning subject during the learning process, such as anxiety, interest or frustration.

[0082] fCognitive load: the cognitive burden borne by the learning subject during the learning process.

[0083] Select dimensions: According to the characteristics of the learning task and the characteristics of the learning subject, select the most critical influencing factors as the dimensions of the subject state. For example, for mathematics learning, you can choose "mathematical knowledge level" and "learning style" as dimensions.

[0084] Quantitative dimensions: Convert each dimension into a quantifiable indicator, such as using a scale or test to assess the subject's prior knowledge level, or using observation to record the subject's learning style.

[0085] Step 2: Establish state transition rules.

[0086] Analyze the relationship between influencing factors: Study how different dimensions influence each other, for example, the level of prior knowledge will affect the learning motivation and cognitive load of the learning subject.

[0087] Establish a state transition function: According to the relationship between the influencing factors, a state transition function is established to describe the probability of the learning subject moving from one state to another. For example, if the learning subject has a thorough understanding of a concept, then they are more likely to enter the "understanding" state.

[0088] Consider the influence of the education subject's behavior: The education subject's behavior will affect the subject state of the learning subject. For example, the encouragement of the education subject can improve the motivation of the learning subject, and the guidance of the education subject can help the learning subject overcome cognitive obstacles. In the state transition function, it is necessary to consider the influence of the education subject's behavior on the state transition probability.

[0089] Step 3: Design learning strategies.

[0090] Determine the teaching objectives: clarify the goals that you hope to achieve in teaching, such as improving the knowledge level of the learning subjects, cultivating the learning interests of the learning subjects, etc.

[0091] Select teaching activities: According to the current status of the learning subject and the teaching objectives, choose appropriate teaching activities, such as explanation, demonstration, practice, discussion, etc.

[0092] Adjust learning strategies: Dynamically adjust learning strategies based on changes in the learning subject's state. For example, if the learning subject's cognitive load is too high, the education subject can reduce the learning difficulty or provide more support.

[0093] Step 4: Implementation and Evaluation

[0094] Implement teaching strategies: Implement teaching strategies according to the design plan, and record the status changes of the learning subjects and the teaching effects.

[0095] Evaluate teaching effectiveness: Use an evaluation indicator system to evaluate teaching effectiveness, such as the learning subject's grades, learning attitude, learning motivation, etc.

[0096] Optimize teaching strategies: Based on the evaluation results, optimize teaching strategies, such as adjusting teaching activities, improving teaching materials, etc.

[0097] The method for constructing a subject state transition model provided by this optional implementation method first obtains the learning subject transition function, then establishes the correspondence between the learning subject transition function and the learning strategy, and finally optimizes the parameters of the subject state transition model through the cost function, thereby providing a reliable implementation basis for the construction of the subject state transition model and improving the reliability of the subject state transition model.

[0098] An example of a specific technical solution for the subject state transformation model is as follows:

[0099] Learning task: Cultivate the learning subject's mathematical problem-solving ability.

[0100] Subject status dimension: Mathematical knowledge level, using mathematical tests to assess the mathematical knowledge level of the learning subject; problem-solving strategies, observing the strategies used by the learning subject when solving problems, such as trial and error, analytical method, etc.

[0101] State transition rule: If the learning subject has a higher level of mathematical knowledge, they are more likely to choose the analytical method to solve the problem; if the learning subject has a lower level of mathematical knowledge, they are more likely to choose the trial and error method to solve the problem; the guidance of the educational subject can help the learning subject transition from the trial and error method to the analytical method.

[0102] Learning strategies: For learners with a higher level of mathematical knowledge, the education subject can provide more complex mathematical problems and encourage them to use analytical methods to solve them. For learners with a lower level of mathematical knowledge, the education subject can first provide some simple mathematical problems and guide them to use trial and error methods to solve them, and then gradually transition to analytical methods.

[0103] Evaluation indicators: the accuracy rate of learning subjects in solving mathematical problems, the frequency of learning subjects using different problem-solving strategies, and the learning subjects' interest in mathematical learning.

[0104] In some optional implementations of the present disclosure, the above-mentioned two-player game model is constructed through the following steps: determining the game elements including the educational subject and the learning subject; based on the game elements, defining the strategy space and payment function of the educational subject and the learning subject; the strategy space of the educational subject includes: subject state and sub-model, the sub-model is used to characterize the learning subject's understanding and prediction of the data, and convert the corresponding subject state; the strategy space of the educational subject includes teaching strategies; based on the strategy space, constructing a two-player game model, the two-player game model is used to characterize the correspondence between the subject state of the learning subject, the action sequence of the educational subject and the sub-model of the learning subject under the teaching task data, and optimize the parameters of the two-player game model through the cost function of the two-player game model.

[0105] In this optional implementation, the steps for constructing a two-player game model are as shown in Step_1 to Step_5:

[0106] Step 1: Determine the game elements - learning subjects and education subjects:

[0107] aLearning subject: represents the learning subject, which can be a student, machine learning algorithm, etc.

[0108] bEducational subject: represents the educational subject, which can be an educational subject, AI assistant, etc.

[0109] Learning Task: Define the learning objectives and dataset.

[0110] Model space: the set of models that the learning subject can choose from.

[0111] Subject state space: the set of subject states of the learning subject, such as prior knowledge, learning strategies, etc.

[0112] Action space: The set of actions that can be performed by the educational subject, such as providing data, explaining concepts, etc.

[0113] State transition kernel: describes how the state of the learning subject changes according to the actions of the education subject and its own strategy.

[0114] Observation set: a set of information observable by the educational subject, such as the model selected by the learning subject, learning progress, etc.

[0115] Conditional observation probability: describes the relationship between the information observed by the education subject and the state of the learning subject.

[0116] Cost function: a function that evaluates the effectiveness of teaching, such as model error, manipulation level, etc.

[0117] Step_2: Define the subject state of the learning subject, which is used to describe the learning subject's preference for different models, which will affect its choice of learning subject model and learning strategy, thereby affecting the two-person game process between the education subject and the learning subject.

[0118] Modeling preference: Define the learning subject’s preference function for the model, such as the weight of factors such as model complexity and interpretability.

[0119] Learning algorithm: defines the algorithm used by the learning agent to build the learning agent model, such as linear regression, neural network, etc.

[0120] Agent state evolution: defines how the agent state of the learning agent changes over time, such as through Bayesian updating, reinforcement learning, etc.

[0121] Step_3: Construct a framework for the educational subject model, which describes how the educational subject observes the subject state of the learning subject, what educational strategies can be adopted, and how to make action sequence decisions based on the observation results and its own educational strategies.

[0122] State space: The set of states observed by the education subject, including the model selected by the learning subject and the estimate of the subject state of the learning subject.

[0123] Action space: the set of actions that can be performed by the educational subject, such as providing data, explaining concepts, etc.

[0124] State transition kernel: describes how the subject state of the learning subject changes according to the actions of the education subject and its own education strategy.

[0125] Observation set: a set of information observable by the educational subject, such as the learning subject model, learning progress, etc.

[0126] Conditional observation probability: describes the relationship between the information observed by the education subject and the subject state of the learning subject.

[0127] Cost function: a function that evaluates the effectiveness of teaching, such as model error, manipulation level, etc.

[0128] Step_4: Select a solution method to enable the educational subject to learn the optimal teaching strategy, thereby affecting the two-person game process between the educational subject and the learning subject.

[0129] Fully observable Markov decision process (MDP): When the educational subject can fully observe the subject state of the learning subject, methods such as dynamic programming can be used to solve the optimal teaching strategy.

[0130] Partially Observable Markov Decision Process (POMDP): When the education subject cannot fully observe the subject state of the learning subject, approximate methods such as value iteration, Monte Carlo planning, etc. can be used.

[0131] Reinforcement learning: The educational subject can learn the optimal teaching strategy through trial and error based on the feedback and reward signals from the learning subject.

[0132] Step_5: Implementation and optimization can be achieved through code implementation and experimental verification, so as to further optimize the education subject model and learning strategy, making the game process between the education subject and the learning subject more in line with the actual situation.

[0133] Code implementation: Use programming language to implement game models and solution algorithms.

[0134] Parameter setting: Set model parameters according to specific tasks and learning subject characteristics.

[0135] Experimental verification: Evaluate the teaching effect through experiments and optimize the model.

[0136] Specific example for two-player game model building: variable selection task. Learning task: select variables in a linear regression model. Model space: a binary vector space of d dimensions indicating whether each variable is included or not. Subject state space: Modeling preferences: weights on factors such as variable correlation and collinearity. Learning algorithm: linear regression algorithm. Subject state evolution: update modeling preferences based on information provided by the education subject and the learning subject's own observations through Bayesian updating. Action space: select a variable to explain or recommend. State transition kernel: the learning subject chooses whether to accept the education subject's advice based on modeling preferences. Observation set: the model selected by the learning subject. Conditional observation probability: the subject state can be estimated through the model selected by the learning subject. Cost function: model error, manipulation level, education subject action cost, etc.

[0137] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a data processing device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0138] like Figure 2As shown, the data processing device 200 provided in this embodiment includes: a generation unit 201, an action obtaining unit 202, a strategy obtaining unit 203, a conversion unit 204, and an evaluation unit 205. Among them, the above-mentioned generation unit 201 can be configured to generate an educational strategy based on a two-person game model and teaching task data, and the two-person game model is a model pre-constructed for an educational subject and a learning subject. The above-mentioned action obtaining unit 202 can be configured to input the educational strategy into the educational subject model pre-constructed for the educational subject, and obtain the action sequence output by the educational subject model, and the educational subject model is used to characterize the correspondence between the educational strategy and the action sequence. The above-mentioned strategy obtaining unit 203 can be configured to input the action sequence and the teaching task data into the learning subject model pre-constructed for the learning subject, and obtain the learning strategy output by the learning subject model, and the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy. The above-mentioned conversion unit 204 can be configured to input the learning strategy into a pre-built subject state conversion model to obtain the current subject state output by the subject state conversion model, and the subject state conversion model is used to characterize the corresponding relationship between the subject state and the learning strategy. The above-mentioned evaluation unit 205 can be configured to evaluate the performance of the learning subject model on the teaching task data based on the current subject state to obtain performance data.

[0139] In this embodiment, the specific processing and technical effects of the generating unit 201, the action obtaining unit 202, the strategy obtaining unit 203, the transforming unit 204, and the evaluating unit 205 in the data processing device 200 can be respectively referred to in Figure 1 The relevant descriptions of step 101, step 102, step 103, step 104, and step 105 in the corresponding embodiments are not repeated here.

[0140] In some embodiments of the present disclosure, the above-mentioned data processing device 200 also includes: an adjustment unit (not shown in the figure), and the adjustment unit is configured to: obtain a new educational strategy based on the performance data; input the new educational strategy into the educational subject model to obtain a new action sequence output by the educational subject model; input the new action sequence and the teaching task data into the learning subject model to obtain a new learning strategy output by the learning subject model.

[0141] In some embodiments of the present disclosure, the performance data include: learning style and learning level, mastered knowledge points and feedback information, and the adjustment unit is further configured to at least one of the following: determine the learning plan strategy and the teaching content strategy based on the learning style and the learning level, and use the learning plan strategy and the teaching content strategy as a new education strategy; remove the information related to the mastered knowledge points in the education strategy to obtain a new education strategy; generate learning suggestion information based on the feedback information, and use the learning suggestion information as a new education strategy.

[0142] In some embodiments of the present disclosure, the learning subject model is constructed by a learning construction unit (not shown in the figure), and the above-mentioned learning construction unit is configured to: construct a dynamic conversion model that characterizes the changes of the subject state of the learning subject under the teaching task data over time; construct a task selection model, and the task selection model is used to characterize the correspondence between the action sequence, the learning task data and the learning strategy under the current subject state, and the current subject state is provided by the dynamic conversion model; use the dynamic conversion model and the task selection model as the learning subject model, and optimize the parameters of the learning subject model through the cost function of the learning subject model.

[0143] In some embodiments of the present disclosure, the above-mentioned learning construction unit is further configured to: determine a first recognition inductive bias in the machine learning algorithm and a second recognition inductive bias of the learning subject; determine the subject state of the learning subject based on the first recognition inductive bias and the second recognition inductive bias; construct a dynamic transformation model that characterizes the changes of the subject state over time, and optimize the parameters of the dynamic transformation model through the cost function of the dynamic transformation model.

[0144] In some embodiments of the present disclosure, the subject state transformation model is constructed by using an internal construction unit (not shown in the figure), and the above-mentioned internal construction unit is configured to: identify at least two key factors affecting the educational subject and the learning subject; determine quantitative dimension indicators based on the key factors; construct a state transition function based on the key factors and the quantitative dimension indicators, and the state transition function is used to describe the probability of the learning subject transferring from one state to another; based on the influence data of the educational subject on the learning subject, set parameters of the state transition function to obtain a learning subject transformation function; establish a corresponding relationship between the learning subject transformation function and a pre-constructed learning strategy to obtain a subject state transformation model, and optimize the parameters of the subject state transformation model through the cost function of the subject state transformation model.

[0145] In some embodiments of the present disclosure, a two-player game model is constructed by a game construction unit (not shown in the figure), and the above-mentioned game construction unit is configured to: determine game elements including an educational subject and a learning subject; based on the game elements, define the strategy space of the educational subject and the learning subject; the strategy space of the educational subject includes: subject state and sub-model, and the sub-model is used to characterize the learning subject's understanding and prediction of data, and convert the corresponding subject state; the strategy space of the educational subject includes teaching strategies; based on the strategy space, a two-player game model is constructed, and the two-player game model is used to characterize the correspondence between the subject state of the learning subject, the action sequence of the educational subject and the sub-model of the learning subject under teaching task data, and optimize the parameters of the two-player game model through the cost function of the two-player game model.

[0146] The data processing device provided by the embodiment of the present disclosure, first, the generation unit 201 generates an education strategy based on a two-person game model and teaching task data, the two-person game model is a model pre-constructed for the education subject and the learning subject; the action acquisition unit 202 inputs the education strategy into the education subject model pre-constructed for the education subject, and obtains the action sequence output by the education subject model, and the education subject model is used to characterize the correspondence between the education strategy and the action sequence; the strategy acquisition unit 203 inputs the action sequence and the teaching task data into the learning subject model pre-constructed for the learning subject, and obtains the learning strategy output by the learning subject model, and the learning subject model is used to characterize the correspondence between the action sequence and the teaching task data and the learning strategy; the conversion unit 204 is configured to input the learning strategy into a pre-constructed subject state conversion model, and obtain the current subject state output by the subject state conversion model, and the subject state conversion model is used to characterize the correspondence between the learning strategy subject state and the learning strategy; the evaluation unit 205 evaluates the performance of the learning subject model on the teaching task data based on the current subject state, and obtains performance data. Therefore, through the two-person game model, the subject state of the learning subject can change dynamically with the changes in the action sequence of the educational subject, strengthen the adjustment and evolution of the subject state of the learning subject, help the learning subject to better adapt to the learning tasks, and improve the learning personalization and adaptability of the learning subject.

[0147] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0148] Figure 3A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their modes are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0149] like Figure 3 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0150] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0151] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0152] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, causes the modes / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0154] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0157] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0158] The foregoing description of specific exemplary embodiments of the present disclosure is for the purpose of illustration and demonstration. These descriptions are not intended to limit the present disclosure to the precise form disclosed, and it is clear that many changes and variations can be made based on the above teachings. The purpose of selecting and describing the exemplary embodiments is to explain the specific principles of the present disclosure and its practical application, so that those skilled in the art can realize and utilize various different exemplary embodiments of the present disclosure and various different selections and changes. The scope of the present disclosure is intended to be defined by the claims and their equivalents.

Claims

1. A data processing method, the method comprising: Generate an educational strategy based on a two-person game model and teaching task data, wherein the two-person game model is a model pre-built for an education subject and a learning subject; Inputting the educational strategy into an educational subject model pre-constructed for the educational subject to obtain an action sequence output by the educational subject model, wherein the educational subject model is used to characterize the corresponding relationship between the educational strategy and the action sequence; Inputting the action sequence and the teaching task data into a learning subject model pre-constructed for the learning subject, and obtaining a learning strategy output by the learning subject model, wherein the learning subject model is used to characterize the corresponding relationship between the action sequence and the teaching task data and the learning strategy; Inputting the learning strategy into a pre-built subject state transformation model to obtain a current subject state output by the subject state transformation model, wherein the subject state transformation model is used to characterize the corresponding relationship between the subject state and the learning strategy; Based on the current subject state, the performance of the learning subject model on the teaching task data is evaluated to obtain performance data.

2. The method according to claim 1, further comprising: deriving new educational strategies based on the performance data; Inputting the new educational strategy into the educational subject model to obtain a new action sequence output by the educational subject model; The new action sequence and the teaching task data are input into the learning subject model to obtain a new learning strategy output by the learning subject model.

3. The method according to claim 2, wherein: The performance data includes: learning style and learning level, mastered knowledge points and feedback information. The new education strategy based on the performance data includes at least one of the following: Determine a learning plan strategy and a teaching content strategy based on the learning style and the learning level, and use the learning plan strategy and the teaching content strategy as a new education strategy; Removing information related to the mastered knowledge points from the educational strategy to obtain a new educational strategy; Based on the feedback information, learning suggestion information is generated, and the learning suggestion information is used as a new educational strategy.

4. The method according to claim 1, wherein: The learning subject model is constructed by the following steps: Construct a dynamic transformation model to characterize the change of the learning subject's state over time under the teaching task data; Constructing a task selection model, wherein the task selection model is used to characterize the correspondence between the action sequence, the learning task data and the learning strategy under the current subject state, wherein the current subject state is provided by the dynamic conversion model; The dynamic conversion model and the task selection model are used as learning subject models, and the parameters of the learning subject model are optimized through the cost function of the learning subject model.

5. The method according to claim 4, wherein: The construction of a dynamic conversion model for representing the change of the subject state of the learning subject over time under the teaching task data includes: Identify first-identification inductive biases in machine learning algorithms and second-identification inductive biases in learning agents; determining a subject state of the learning subject based on the first identification inductive bias and the second identification inductive bias; A dynamic conversion model is constructed to characterize the change of the subject state over time, and the parameters of the dynamic conversion model are optimized through the cost function of the dynamic conversion model.

6. The method according to claim 1, wherein: The subject state transformation model is constructed by the following steps: Identify at least two key factors that influence the subject of education and the subject of learning; Based on the key factors, determine the quantitative dimension indicators; Based on the key factors and the quantitative dimension indicators, a state transition function is constructed, where the state transition function is used to describe the probability of a learning subject transferring from one state to another state; Based on the influence data of the education subject on the learning subject, setting parameters of the state transition function to obtain a learning subject transition function; A corresponding relationship between the learning subject conversion function and a pre-constructed learning strategy is established to obtain a subject state conversion model, and the parameters of the subject state conversion model are optimized through the cost function of the subject state conversion model.

7. The method according to claim 1, wherein: The two-player game model is constructed through the following steps: Determine the game elements including the education subject and the learning subject; Based on the game elements, define the strategy space of the education subject and the learning subject; The strategy space of the education subject includes: subject state and sub-model, the sub-model is used to characterize the understanding and prediction of the learning subject on the data and convert the corresponding subject state; the strategy space of the education subject includes teaching strategy; Based on the strategy space, a two-player game model is constructed. The two-player game model is used to characterize the correspondence between the subject state of the learning subject, the action sequence of the teaching subject and the sub-model of the learning subject under the teaching task data, and the parameters of the two-player game model are optimized through the cost function of the two-player game model.

8. A data processing device, comprising: A generating unit is configured to generate an educational strategy based on a two-person game model and teaching task data, wherein the two-person game model is a model pre-constructed for an educational subject and a learning subject; an action obtaining unit, configured to input the educational strategy into an educational subject model pre-constructed for the educational subject, and obtain an action sequence output by the educational subject model, wherein the educational subject model is used to characterize the corresponding relationship between the educational strategy and the action sequence; A strategy obtaining unit is configured to input the action sequence and the teaching task data into a learning subject model pre-constructed for the learning subject, and obtain a learning strategy output by the learning subject model, wherein the learning subject model is used to characterize the corresponding relationship between the action sequence and the teaching task data and the learning strategy; a conversion unit configured to input the learning strategy into a pre-built subject state conversion model to obtain a current subject state output by the subject state conversion model, wherein the subject state conversion model is used to characterize the corresponding relationship between the subject state and the learning strategy; The evaluation unit is configured to evaluate the performance of the learning subject model on the teaching task data based on the current subject state to obtain performance data.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 7.

Images