阅读说明：本技术 学习对象的认知分析方法、装置及其电子设备 (Learning object cognitive analysis method and device and electronic equipment thereof ) 是由 孙帅 卜晨阳 刘菲 胡学钢 于 2021-07-09 设计创作，主要内容包括：本发明公开了一种学习对象的认知分析方法、装置及其电子设备。其中,该认知分析方法包括：获取历史过程中所有学习对象作答习题的得分集合和每个习题所考察的知识点集合,其中,每个习题对应有多个知识点,然后基于得分集合和知识点集合,分析学习对象对每个知识点的认知概率参数集合以及每个知识点对关联题目的影响因子集合,之后采用认知概率参数集合以及每个知识点对关联题目的影响因子集合,构建认知模型,最后采用认知模型,分析目标学习对象作答新习题的答对概率。本发明解决了相关技术中无法处理一道习题中同时考察多个知识点,影响对学习对象的认知评估的准确性的技术问题。(The invention discloses a learning object cognitive analysis method and device and electronic equipment thereof. The cognitive analysis method comprises the following steps: the method comprises the steps of obtaining a score set of all learning object answering problems and a knowledge point set investigated by each problem in a historical process, wherein each problem corresponds to a plurality of knowledge points, analyzing a cognitive probability parameter set of the learning object to each knowledge point and an influence factor set of each knowledge point to an associated problem based on the score set and the knowledge point set, then adopting the cognitive probability parameter set and the influence factor set of each knowledge point to the associated problem to construct a cognitive model, and finally adopting the cognitive model to analyze the answer probability of a target learning object answering a new problem. The invention solves the technical problem that the accuracy of cognitive assessment on a learning object is influenced because a plurality of knowledge points cannot be simultaneously investigated in one exercise in the related technology.)

1. A cognitive analysis method of a learning object, comprising:

acquiring a score set of all learning object answering exercises and a knowledge point set investigated by each exercise in a historical process, wherein each exercise corresponds to a plurality of knowledge points;

analyzing a cognitive probability parameter set of each knowledge point and an influence factor set of each knowledge point on an associated topic by a learning object based on the score set and the knowledge point set;

constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic;

and analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

2. The cognitive analysis method according to claim 1, wherein the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the set of scores and the set of knowledge points comprises:

analyzing the initial mastering probability, the learning probability and the forgetting probability of the learning object on each knowledge point based on the score set and the knowledge point set;

and determining a cognitive probability parameter set of the learning object for each knowledge point based on the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point.

3. The cognitive analysis method according to claim 2, wherein the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the set of scores and the set of knowledge points further comprises:

confirming a first influence factor of each knowledge point on the associated topic error rate and a second influence factor of each knowledge point on the associated topic guessing rate;

constructing the set of impact factors with the first impact factor and the second impact factor.

4. The cognitive analysis method according to claim 3, wherein the step of constructing a cognitive model using the set of cognitive probability parameters and the set of influence factors of each knowledge point on the associated topic comprises:

calculating a first probability value of the answer of the learning object in the current cognitive state by adopting a first formula based on the score set and the knowledge point set;

calculating the error rate of the learning object as an answer exercise by adopting a second formula based on a first influence factor of each knowledge point on the error rate of the associated questions;

calculating the guessing rate of the answer exercises of the learning object by adopting a third formula based on a second influence factor of each knowledge point on the guessing rate of the associated questions;

calculating a second probability value of the answer to the exercises of the learning object by adopting a fourth formula based on a first probability value of the learning object for answering the target exercises, the error rate of the learning object for answering the target exercises and the guessing rate in the current cognitive state;

analyzing the grasping state of the learning object to each knowledge point at the current moment based on the first probability value and the second probability value;

and constructing a cognitive model corresponding to the learning object based on the grasping state of the learning object on each knowledge point at the current moment.

5. The cognitive analysis method of claim 4, wherein after the cognitive model is constructed, the cognitive analysis method further comprises:

if the question answered by the learning object at the previous moment does not relate to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment;

and calculating the grasping state of the learning object to the target knowledge point at the current moment by adopting a fifth formula based on the grasping state of the learning object to each knowledge point at the previous moment and the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment so as to update the cognitive model.

6. The cognitive analysis method of claim 5, wherein after the cognitive model is constructed, the cognitive analysis method further comprises:

if the question answered by the learning object at the previous moment relates to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment;

determining a first learning probability of answering a question corresponding to the target knowledge point and a second learning probability of not answering the question corresponding to the target knowledge point of the learning object at the previous moment;

calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a sixth formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the first learning probability of answering the question corresponding to the target knowledge point at the previous moment so as to update the cognitive model; alternatively, the first and second electrodes may be,

and calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a seventh formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and a second learning probability of the question corresponding to the target knowledge point which is not answered at the previous moment so as to update the cognitive model.

7. The cognitive analysis method according to claim 1, wherein after analyzing the answer probability of the target learning object to answer the new problem using the cognitive model, the cognitive analysis method further comprises:

training the cognitive model, and updating the mastering state of the learning object on each knowledge point;

and adjusting the cognitive probability parameters and the influence factors of the cognitive model based on the updated mastery states of the learning objects on the knowledge points.

8. An apparatus for cognitive analysis of a learning object, comprising:

the acquisition unit is used for acquiring a score set of all learning object answering exercises and a knowledge point set investigated by each exercise in the historical process, wherein each exercise corresponds to a plurality of knowledge points;

the first analysis unit is used for analyzing the cognitive probability parameter set of the learning object on each knowledge point and the influence factor set of each knowledge point on the associated topic based on the score set and the knowledge point set;

the construction unit is used for constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic;

and the second analysis unit is used for analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

9. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the cognitive analysis method of the learning object of any one of claims 1 to 7 via execution of the executable instructions.

10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium controls an apparatus to execute the cognitive analysis method of the learning object according to any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of cognitive analysis, in particular to a cognitive analysis method and device for a learning object and electronic equipment thereof.

Background

In recent years, online education systems are being developed vigorously, which provide students with abundant exercise exercises and promote the sharing of learning resources of the students. Cognitive tracking (KT) defines a task of tracking changes in cognitive states of students according to answer results of the students to problems in the historical process, and then predicting answer results of future problems.

In the related technology, a Bayesian cognitive tracking model (BKT) is mainly applied to a single Knowledge point scene, because the parameters of the BKT model generate exponential explosion along with the increase of the number of Knowledge points, the complexity of the model algorithm also increases exponentially, the application range of the BKT model is limited (namely the BKT model cannot be applied to a plurality of Knowledge point scenes), and meanwhile, the evaluation accuracy of student cognition in the learning process is influenced (because a subject often investigates a plurality of Knowledge points in an actual scene).

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a learning object cognitive analysis method and device and electronic equipment thereof, and aims to at least solve the technical problem that the accuracy of cognitive evaluation on a learning object is influenced because a plurality of knowledge points cannot be simultaneously investigated in one exercise in the related art.

According to an aspect of an embodiment of the present invention, there is provided a cognitive analysis method of a learning object, including: acquiring a score set of all learning object answering exercises and a knowledge point set investigated by each exercise in a historical process, wherein each exercise corresponds to a plurality of knowledge points; analyzing a cognitive probability parameter set of each knowledge point and an influence factor set of each knowledge point on an associated topic by a learning object based on the score set and the knowledge point set; constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic; and analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

Optionally, the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the set of scores and the set of knowledge points comprises: analyzing the initial mastering probability, the learning probability and the forgetting probability of the learning object on each knowledge point based on the score set and the knowledge point set; and determining a cognitive probability parameter set of the learning object for each knowledge point based on the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point.

Optionally, the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the set of scores and the set of knowledge points further includes: confirming a first influence factor of each knowledge point on the associated topic error rate and a second influence factor of each knowledge point on the associated topic guessing rate; constructing the set of impact factors with the first impact factor and the second impact factor.

Optionally, the step of constructing a cognitive model by using the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic includes: calculating a first probability value of the answer of the learning object in the current cognitive state by adopting a first formula based on the score set and the knowledge point set; calculating the error rate of the learning object as an answer exercise by adopting a second formula based on a first influence factor of each knowledge point on the error rate of the associated questions; calculating the guessing rate of the answer exercises of the learning object by adopting a third formula based on a second influence factor of each knowledge point on the guessing rate of the associated questions; calculating a second probability value of the answer to the exercises of the learning object by adopting a fourth formula based on a first probability value of the learning object for answering the target exercises, the error rate of the learning object for answering the target exercises and the guessing rate in the current cognitive state; analyzing the grasping state of the learning object to each knowledge point at the current moment based on the first probability value and the second probability value; and constructing a cognitive model corresponding to the learning object based on the grasping state of the learning object on each knowledge point at the current moment.

Optionally, after the cognitive model is constructed, the cognitive analysis method further includes: if the question answered by the learning object at the previous moment does not relate to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment; and calculating the grasping state of the learning object to the target knowledge point at the current moment by adopting a fifth formula based on the grasping state of the learning object to each knowledge point at the previous moment and the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment so as to update the cognitive model.

Optionally, after the cognitive model is constructed, the cognitive analysis method further includes: if the question answered by the learning object at the previous moment relates to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment; determining a first learning probability of answering a question corresponding to the target knowledge point and a second learning probability of not answering the question corresponding to the target knowledge point of the learning object at the previous moment; calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a sixth formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the first learning probability of answering the question corresponding to the target knowledge point at the previous moment so as to update the cognitive model; or, on the basis of the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the second learning probability of the question corresponding to the target knowledge point which is not answered at the previous moment, the grasping state of the learning object on the target knowledge point at the current moment is calculated by adopting a seventh formula so as to update the cognitive model.

Optionally, after analyzing the answer probability of the target learning object for answering the new question by using the cognitive model, the cognitive analysis method further includes: training the cognitive model, and updating the mastering state of the learning object on each knowledge point; and adjusting the cognitive probability parameters and the influence factors of the cognitive model based on the updated mastery states of the learning objects on the knowledge points.

According to another aspect of the embodiments of the present invention, there is also provided a cognitive analysis device of a learning object, including: the acquisition unit is used for acquiring a score set of all learning object answering exercises and a knowledge point set investigated by each exercise in the historical process, wherein each exercise corresponds to a plurality of knowledge points; the first analysis unit is used for analyzing the cognitive probability parameter set of the learning object on each knowledge point and the influence factor set of each knowledge point on the associated topic based on the score set and the knowledge point set; the construction unit is used for constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic; and the second analysis unit is used for analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

Optionally, the first analysis unit comprises: the first analysis module is used for analyzing the initial mastering probability, the learning probability and the forgetting probability of each knowledge point of the learning object based on the score set and the knowledge point set; and the first determining module is used for determining a cognitive probability parameter set of the learning object for each knowledge point based on the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point.

Optionally, the first analysis unit further comprises: the second determining module is used for determining a first influence factor of each knowledge point on the associated topic error rate and a second influence factor of each knowledge point on the associated topic guessing rate; a first construction module to construct the set of impact factors with the first and second impact factors.

Optionally, the construction unit comprises: the first calculation module is used for calculating a first probability value of the answer problem of the learning object in the current cognitive state by adopting a first formula based on the score set and the knowledge point set; the second calculation module is used for calculating the error rate of the learning object for answering the exercises by adopting a second formula based on the first influence factor of each knowledge point on the error rate of the associated questions; the third calculation module is used for calculating the guessing rate of the answer questions of the learning object by adopting a third formula based on a second influence factor of each knowledge point on the guessing rate of the associated questions; the fourth calculation module is used for calculating a second probability value of the answer to the target exercises of the learning object by adopting a fourth formula based on the first probability value of the answer to the target exercises of the learning object in the current cognitive state, the error rate of the answer to the target exercises of the learning object and the guessing rate; the second analysis module is used for analyzing the mastering state of the learning object on each knowledge point at the current moment based on the first probability value and the second probability value; and the second construction module is used for constructing a cognitive model corresponding to the learning object based on the mastering state of the learning object to each knowledge point at the current moment.

Optionally, the cognitive analysis device further comprises: the third determining module is used for determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment if the question answered by the learning object at the previous moment does not relate to the target knowledge point after the cognitive model is built; and the first updating module is used for calculating the mastering state of the learning object on the target knowledge point at the current moment by adopting a fifth formula based on the mastering state of the learning object on each knowledge point at the previous moment and the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment so as to update the cognitive model.

Optionally, the cognitive analysis device further comprises: the fourth determining module is used for determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment if the question answered by the learning object at the previous moment relates to the target knowledge point after the cognitive model is built; a fifth determining module, configured to determine a first learning probability that the learning object answers the question corresponding to the target knowledge point at a previous time and a second learning probability that the learning object does not answer the question corresponding to the target knowledge point; the second updating module is used for calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a sixth formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the first learning probability of answering the question corresponding to the target knowledge point at the previous moment so as to update the cognitive model; or, the third updating module is configured to calculate, based on the grasping state of the learning object at the previous time on each knowledge point, the forgetting probability of the learning object from the previous time to the current time on the target knowledge point, and the second learning probability of the question corresponding to the target knowledge point that is not answered at the previous time, the grasping state of the learning object at the current time on the target knowledge point by using a seventh formula, so as to update the cognitive model.

Optionally, the cognitive analysis device further comprises: the fourth updating module is used for training the cognitive model after analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model, and updating the mastering state of the learning object on each knowledge point; and the first adjusting module is used for adjusting the cognitive probability parameters and the influence factors of the cognitive model based on the updated mastery states of the learning objects on the knowledge points.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any one of the above-described cognitive analysis methods of a learning object via execution of the executable instructions.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the above cognitive analysis methods for a learning object.

In the embodiment of the invention, a score set of all learning object answer questions and a knowledge point set investigated by each question in a history process are obtained, wherein each question corresponds to a plurality of knowledge points, then a cognitive probability parameter set of the learning object for each knowledge point and an influence factor set of each knowledge point for an associated question are analyzed based on the score set and the knowledge point set, then a cognitive model is constructed by adopting the cognitive probability parameter set and the influence factor set of each knowledge point for the associated question, and finally the answer probability of a target learning object for answering a new question is analyzed by adopting the cognitive model. In the embodiment, a cognitive analysis technology capable of facing multiple knowledge points is adopted, the problem that a traditional BKT cannot process one question and simultaneously investigate multiple knowledge points is solved, the accuracy of the answer pair probability of a new answer question of a learning object is analyzed by adopting a cognitive model, and the technical problem that the accuracy of cognitive evaluation on the learning object is influenced by simultaneously investigating multiple knowledge points in one question cannot be processed in the related technology is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

FIG. 1 is a flow diagram of an alternative learning object cognitive analysis method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a learning object cognitive analysis device according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

To facilitate understanding of the invention by those skilled in the art, some terms or nouns referred to in the embodiments of the invention are explained below:

cognitive tracking (KT) is a technique for accurately tracking the dynamically changing cognitive state of a student based on his past exercise performance.

AUC (area Under curve), defined as the area enclosed by the ROC curve and the coordinate axis, is a performance index for measuring the quality of the model.

The embodiment of the invention can be applied to cognitive analysis systems/cognitive analysis software of various learning objects, for example, various online education software and education platforms. The present embodiment acquires a data set on an education platform, and based on a cognitive tracking model (or simply, a cognitive model) oriented to a plurality of knowledge points, can analyze the results of a study object (e.g., a student at a school, a study object using online education software, etc.) answering a question in the future to better serve the study object. The cognitive analysis method provided by the embodiment of the invention not only widens the application scene of the existing BKT model, so that the cognitive analysis method not only can process the condition of examining a plurality of knowledge points in topics, but also can independently track the change of each knowledge point, is still effective when new topics examined by combining different knowledge points appear at later time steps, and simultaneously tracks the problem of having a plurality of knowledge points, but can effectively avoid the problem that the algorithm complexity in the original BKT is exponentially increased along with the increase of the number of the knowledge points, and the heuristic optimization method is used for optimizing parameters, and the group intelligence is utilized, so that the local optimization can be avoided.

In accordance with an embodiment of the present invention, there is provided an embodiment of a method for cognitive analysis of a learning object, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

Example one

Fig. 1 is a flowchart of an alternative cognitive analysis method for a learning object according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:

step S102, acquiring a score set of all learning object answering problems in the history process and a knowledge point set examined by each problem, wherein each problem corresponds to a plurality of knowledge points.

And step S104, analyzing the cognitive probability parameter set of the learning object to each knowledge point and the influence factor set of each knowledge point to the associated topic based on the score set and the knowledge point set.

And S106, constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic.

And step S108, analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

Through the steps, a score set of all learning object answer questions and a knowledge point set investigated by each question in a historical process can be obtained, wherein each question corresponds to a plurality of knowledge points, then a cognitive probability parameter set of the learning object for each knowledge point and an influence factor set of each knowledge point for an associated question are analyzed based on the score set and the knowledge point set, then a cognitive model is constructed by adopting the cognitive probability parameter set and the influence factor set of each knowledge point for the associated question, and finally the answer probability of a target learning object for answering a new question is analyzed by adopting the cognitive model. In the embodiment, a cognitive analysis technology capable of facing multiple knowledge points is adopted, the problem that a traditional BKT cannot process one question and simultaneously investigate multiple knowledge points is solved, the accuracy of the answer pair probability of a new answer question of a learning object is analyzed by adopting a cognitive model, and the technical problem that the accuracy of cognitive evaluation on the learning object is influenced by simultaneously investigating multiple knowledge points in one question cannot be processed in the related technology is solved.

The following describes embodiments of the present invention in detail with reference to the respective steps.

Step S102, acquiring a score set of all learning object answering problems in the history process and a knowledge point set examined by each problem, wherein each problem corresponds to a plurality of knowledge points.

In embodiments of the present invention, learning objects include, but are not limited to: in school students, teachers needing to learn, parents needing to learn and other people (robot, computer and server) of any age needing to learn, a data set needed by the embodiment of the invention can be obtained from any online education platform, a score set of learning object answering exercises is represented as Y ═ Y }, Y ∈ {0, 1}, and a knowledge point set considered by each exercise is represented as KC.

And step S104, analyzing the cognitive probability parameter set of the learning object to each knowledge point and the influence factor set of each knowledge point to the associated topic based on the score set and the knowledge point set.

In the embodiment of the invention, the number of knowledge points is set as I, the number of learning objects is set as S, the evolution algebra is set as Gens, and the individual variation rate and the individual cross rate are set as the initial mastering Probability (PL) of each knowledge point of the learning objects₁，PL₂，...，PL_i，...，PL_I) (I ∈ {1, 2...., I }), wherein PL ∈ is given_iThe learning probability of each knowledge point of the learning object is (PT)₁，PT₂，...，PT_i，...，PT_I) (I ∈ {1, 2...., I }), wherein PT_iThe learning probability of the learning object to the ith knowledge point is shown, and the forgetting probability of the learning object to each knowledge point is (PF)₁，PF₂，...，PF_i，...，PF_I) (I ∈ {1, 2...., I }), wherein PF_iRepresentation studyGenerating forgetting probability of the ith knowledge point.

In the embodiment of the invention, each topic may examine a plurality of knowledge points, and the error rate and guess rate of the topic are determined by the examined knowledge points, so that the influence factor of each knowledge point on the associated topic error rate is set as (S)₁，S₂，...，S_i，...，S_I) (I ∈ {1, 2...., I }), wherein S ∈ S } S ∈ S [, 2 ·_iThe influence factor of the ith knowledge point on the question guessing rate associated with the ith knowledge point is set as (G)₁，G₂，...，G_i，...，G_I) (I ∈ {1, 2...., I }), wherein G ∈ {1, 2...., I }), wherein G_iAnd expressing the influence factor of the ith knowledge point on the question guessing rate associated with the ith knowledge point, wherein the guessing rate expresses the probability that the learning object can answer the question without learning the question.

Optionally, the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the score set and the knowledge point set includes: analyzing the initial mastering probability, the learning probability and the forgetting probability of the learning object to each knowledge point based on the score set and the knowledge point set; and determining a cognitive probability parameter set of the learning object for each knowledge point based on the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point.

In the embodiment of the invention, by analyzing the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point, the mastering state of the learning object for each knowledge point at the current moment can be obtained Wherein P is used for grasping the state at time t^(t)Indicating, understanding the state is also referred to as cognitionA set of probability parameters. For example, the grasping state can be roughly divided into { non-grasping, partial grasping, most grasping, and complete grasping }, where non-grasping can indicate that the learning object has a probability of answering the question of 0 to 0.2, partial grasping can indicate that the learning object has a probability of answering the question of 0.3 to 0.5, most grasping can indicate that the learning object has a probability of answering the question of 0.6 to 0.8, and complete grasping can indicate that the learning object has a probability of answering the question of 0.9 to 1, which is not limited herein.

Optionally, the step of analyzing the set of cognitive probability parameters of the learning object for each knowledge point and the set of influence factors of each knowledge point on the associated topic based on the score set and the knowledge point set further includes: confirming a first influence factor of each knowledge point on the associated topic error rate and a second influence factor of each knowledge point on the associated topic guessing rate; and constructing an influence factor set by the first influence factor and the second influence factor.

In the embodiment of the present invention, the first influence factor is the influence factor of each knowledge point on the failure rate of the associated topic, and is represented as (S)₁，S₂，...，S_i，...，S_I) (I e {1, 2.. eta., I }), the second influence factor is the influence factor of each knowledge point on the topic guessing rate associated with the knowledge point, and is expressed as (G)₁，G₂，...，G_i，...，G_I) (I ∈ {1, 2...., I }), the first impact factor and the second impact factor are constructed as a set of impact factors.

And S106, constructing a cognitive model by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic.

In this embodiment, a cognitive model is constructed by using a cognitive probability parameter set and an influence factor set of each knowledge point on an associated topic, that is, the current cognitive state of a learning object, including an initial mastering probability, a learning probability, a forgetting probability of each knowledge point by the current learning object, and influence factors of each knowledge point on an associated topic error rate and a guessing rate.

Optionally, the step of constructing the cognitive model by using the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic includes: calculating a first probability value of the answer to the question of the learning object in the current cognitive state by adopting a first formula based on the score set and the knowledge point set; calculating the error rate of the learning object as an answer exercise by adopting a second formula based on a first influence factor of each knowledge point on the error rate of the associated questions; calculating the guessing rate of the answer exercises of the learning object by adopting a third formula based on a second influence factor of each knowledge point on the guessing rate of the associated questions; calculating a second probability value of the answer to the exercises of the learning object by adopting a fourth formula based on a first probability value of the learning object for answering the target exercises, the error rate of the learning object for answering the target exercises and the guessing rate in the current cognitive state; analyzing the mastering state of the learning object to each knowledge point at the current moment based on the first probability value and the second probability value; and constructing a cognitive model corresponding to the learning object based on the grasping state of the learning object on each knowledge point at the current moment.

In this embodiment, let the target topic be E at time t^(t)Goal exercise E^(t)The set of the investigated knowledge points isThe learning object grasps each knowledge point at the current time t in a state ofI.e. the current cognitive state is P^(t)。

The first formula in the embodiment of the invention is as follows:wherein n is KC_t＝{kc₁，kc₂...，kc_k}，P^(t)And representing the current cognitive state, and calculating the probability eta of the learning object to answer the question under the current cognitive state without considering guessing and error factors of the learning object, namely a first probability value. The second formula is:wherein n is KC_t＝{kc₁，kc₂...，kc_k}，S_nAnd (4) representing the influence factor of each knowledge point on the associated question error rate, and calculating to obtain the error rate P (S) of the current learning object on the question. The third formula is:wherein n is KC_t＝{kc₁，kc₂...，kc_k}，G_nAnd (3) representing the influence factor of each knowledge point on the question guessing rate associated with the knowledge point, and calculating to obtain the question guessing rate P (G) of the current learning object. The fourth formula is: p_corrEta (1-P (s)) + (1-eta) P (g), where eta represents a first probability value, P(s) represents a failure rate of a current learning object to questions, P (g) represents a guessing rate of the current learning object to questions, the cognitive state of a student, guessing factors of the learning object to questions and the failure factors are comprehensively considered, and a fourth formula is used to finally obtain the probability P of the learning object to answer the current questions_corrI.e. the second probability value. And analyzing the mastering state of the learning object on each knowledge point at the current moment through the obtained probability value so as to construct a cognitive model.

Optionally, after the constructing the cognitive model, the cognitive analysis method further includes: if the question answered by the learning object at the previous moment does not relate to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment; and calculating the grasping state of the learning object to the target knowledge point at the current moment by adopting a fifth formula based on the grasping state of the learning object to each knowledge point at the previous moment and the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment so as to update the cognitive model.

In the present embodiment, the cognitive state of the learning object, that is, the grasping condition of each knowledge point by the learning object, changes with time. In this embodiment, the fifth formula is:wherein the content of the first and second substances,PF_nrepresenting the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment,this indicates the grasping state of the learning object at time t. For the knowledge points which are not considered in the topic at the previous time t, the learning object is not trained at the previous time t, so that only the forgetting effect of the learning object on the knowledge points is considered, and the grasping state of the learning object on the target knowledge points at the current time is calculated by adopting a fifth formula so as to update the cognitive model.

Alternatively, after the cognitive model is constructed, the cognitive analysis method further includes: if the questions answered by the learning object at the previous moment relate to the target knowledge point, determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment; determining a first learning probability of a learning object answering a question corresponding to the target knowledge point at the previous moment and a second learning probability of an unanswered question corresponding to the target knowledge point; calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a sixth formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the first learning probability of answering the question corresponding to the target knowledge point at the previous moment so as to update the cognitive model; or, on the basis of the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the second learning probability of the question corresponding to the target knowledge point which is not answered at the previous moment, the grasping state of the learning object on the target knowledge point at the current moment is calculated by adopting a seventh formula so as to update the cognitive model.

In this embodiment, the sixth formula is: wherein n is KC_t＝{kc₁，kc₂...，kc_k}，PF_nRepresenting the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment,indicates the grasped state of the learning object at the previous time t, S_nRepresenting the influence of each knowledge point on its associated topic error rate, G_nRepresenting the influence factor of each knowledge point on the guessing rate of the associated topic. The seventh formula is: wherein n is KC_t＝{kc₁，kc₂...，kc_k}，PF_nRepresenting the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment,indicates the grasped state of the learning object at the previous time t, S_nRepresenting the influence of each knowledge point on its associated topic error rate, G_nRepresenting the influence factor of each knowledge point on the guessing rate of the associated topic.

In this embodiment, for the knowledge point examined by the question at the time t, since the learning object is trained at the time t, the learning effect and the forgetting effect of the student on the knowledge point need to be considered, but at the previous time t, the learning effect obtained when the learning object answers the question and the question is wrongly answered is different. If the learning object answers the question, the grasping state of the learning object to the target knowledge point at the current time is calculated by adopting a sixth formula on the basis of the grasping state of the learning object to each knowledge point at the previous time, the forgetting probability of the learning object to the target knowledge point from the previous time to the current time and the first learning probability of answering the question corresponding to the target knowledge point at the previous time (namely the probability of answering the question by the learning object), so as to update the cognitive model. If the learning object wrote the question, the learning state of the learning object to the target knowledge point at the current time is calculated by adopting a seventh formula on the basis of the grasping state of the learning object to each knowledge point at the previous time, the forgetting probability of the learning object to the target knowledge point from the previous time to the current time and a second learning probability of the question corresponding to the target knowledge point at the previous time (namely the probability that the learning object wrongly answers the question), so as to update the cognitive model.

And step S108, analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model.

Optionally, after analyzing the answer probability of the target learning object for answering the new question by using the cognitive model, the cognitive analysis method further includes: training the cognitive model, and updating the mastery state of the learning object on each knowledge point; and adjusting the cognitive probability parameters and the influence factors of the cognitive model based on the updated mastery state of the learning object on each knowledge point. In this embodiment, the step of training the cognitive model includes:

step 1: initializing a population;

step 2: setting a loop iterator gen equal to 1, and executing steps 3-8 in a loop when gen is less than or equal to Gens;

and step 3: evaluating individual fitness, evolving population, and executing the step 4-8;

and 4, step 4: selecting a learning object S as 1, (S belongs to {1, 2.., S }), and circularly executing the step 5-8 when S is less than or equal to S;

and 5: when the time step T of answering the question of the learning object is equal to 1, and when T is less than or equal to T, executing the steps 6-8 in a circulating manner;

step 6: calculating the probability of answering the question of the learning object at the moment t according to the cognitive tracking model, storing the predicted value into a variable Pred, and updating the cognitive state of the learning object;

and 7: calculating the variable Pred and an evaluation index in the data set, and taking the evaluation index as an individual fitness value;

and 8: performing cross variation operation on the individuals by using an evolution algorithm according to the fitness value of the individuals in the population to generate a next generation population;

and step 9: and obtaining the DNA value of the optimal individual in the population of the last generation.

In this embodiment, the cognitive model may be iteratively trained by comparing the predicted answer result with the actual answer result of the learning object in the data set, so as to finally obtain the cognitive probability parameter and the influence factor, that is, the learning probability, the forgetting probability of the learning object on each knowledge point, and the influence factor of each knowledge point on the associated question error rate and the guess rate.

Example two

In the embodiment, a Bayes cognitive tracking method facing mixed knowledge points is used to solve the problems that the existing KT model cannot process the mixed knowledge points and the complexity of the algorithm increases exponentially with the increase of the number of the knowledge points only by simply expanding the original BKT model. The Bayes cognitive tracking method for the mixed knowledge points in the embodiment specifically comprises the following steps:

step 1, initialization:

and (5) solving the optimal parameters by using an evolutionary algorithm in heuristic optimization, and taking the parameters to be optimized as individual DNAs in the population.

1.1, setting the number of knowledge points as I; setting the number of students as S; setting evolution algebra of an evolution algorithm as Gens; setting individual variation rate and crossing rate of population of an evolution algorithm;

1.2, setting the initial mastery Probability (PL) of each knowledge point for students₁，PL₂，...，PL_i，...，PL_I) (I ∈ {1, 2...., I }), wherein PL ∈ is given_iRepresenting the initial mastery condition of the student on the ith knowledge point; probability of learning (PT) of student to each knowledge point₁，PT₂，...，PT_i，...，PT_I) (I ∈ {1, 2...., I }), wherein PT_iRepresenting the learning probability of the student on the ith knowledge point; student forgetting Probability (PF) for each knowledge point₁，PF₂，...，PF_i，...，PF_I) (I ∈ {1, 2...., I }), wherein PF_iRepresenting the forgetting probability of the student on the ith knowledge point. Each topic may examine a plurality of knowledge points, the error rate and guess rate of the topic are determined by the examined knowledge points, and the influence factor of each knowledge point on the associated topic error rate is set as (S)₁，S₂，...，S_i，...，S_I) (I ∈ {1, 2...., I }), wherein S ∈ S } S ∈ S [, 2 ·_iRepresenting the influence factor of the ith knowledge point on the failure rate of the associated questions; the influence factor of each knowledge point on the guessing rate of the associated topic is set as (G)₁，G₂，...，G_i，...，G_I) (I ∈ {1, 2...., I }), wherein G ∈ {1, 2...., I }), wherein G_iRepresenting the influence factor of the ith knowledge point on the guessing rate of the associated topic;

1.3, inputting diversity Y ═ Y }, Y ∈ {0, 1} of all student answering problems and a knowledge point set KC considered by all student answering problems.

Step 2, modeling:

at a certain time t, the question answered by the student is E^(t)The set of knowledge points for the topic investigation is The student at the current moment grasps each knowledge point in the state of

2.1, calculating the probability eta of the student answering the question in the current cognitive state without considering guessing and error factors of the student according to the formula (1);

wherein n is KC_t＝{kc₁，kc₂...，kc_k} (1)；

2.2, respectively calculating the error rate and the guessing rate of the current student to the questions according to the formulas (2) and (3);

wherein n is KC_t＝{kc₁，kc₂...，kc_k} (2)；

Wherein n is KC_t＝{kc₁，kc₂...，kc_k} (3)；

2.3, comprehensively considering the cognitive state of the student, guessing factors and error factors of the student along with the question, and obtaining the probability P of answering the current question by the student by using a formula (4)_corr；

P_corr＝η*(1-P(S))+(1-η)*P(G) (4)；

2.4, updating the time t +1, changing the cognitive state of the student, namely the grasping condition P of the student on each knowledge point^(t+1)。

2.4.1 topic E for time t_tThe knowledge points which are not considered are calculated according to the formula (5) only by considering the forgetting effect of the students on the knowledge points because the students are not trained at the moment t;

wherein the content of the first and second substances,

2.4.2 topic E for time t_tThe studied knowledge point needs to consider the learning effect and forgetting effect of the student on the knowledge point because the student is trained at the time t, but the learning effect obtained when the student answers the question and the question is wrongly answered at the time t is different and is calculated according to the formulas (6) and (7).

Wherein n is KC_t＝{kc₁，kc₂...，kc_k} (6)；

Wherein n is KC_t＝{kc₁，kc₂...，kc_k} (7)；

Step 3, model training

3.1, initializing a population;

3.2, setting a loop iterator gen equal to 1, and executing the steps 3.3-3.8 in a loop when gen is less than or equal to Gens;

3.3, evaluating individual fitness, evolving population and executing the step 3.4-3.8;

3.4, selecting a student S as 1, (S belongs to {1, 2,. and S }), and circularly executing the steps 3.5 to 3.8 when S is less than or equal to S;

3.5, the student answers the question with time step T equal to 1, and when T is less than or equal to T, the steps 3.6-3.8 are executed in a circulating manner;

3.6, calculating the probability of answering the question by the student at the moment t according to the step 2, carrying out binarization, obtaining whether the student can store the predicted value of the current question into a variable Pred, and updating the cognitive state of the student, namely the mastery degree of the student on each knowledge point;

3.7, calculating evaluation indexes such as AUC and accuracy of the predicted value Pred and the real answer result of the student in the data set, and taking the evaluation indexes as the fitness value of the individual;

3.8, carrying out cross variation operation on the individuals by using an evolution algorithm according to the fitness value of the individuals in the population to generate a next generation population;

and 3.9, obtaining the DNA value of the optimal individual in the population of the last generation, namely parameters PL, PT, PF, S and G of the model, wherein PL represents the mastering probability, PT represents the learning probability, PF represents the past probability, S represents the influence factor of each knowledge point on the associated topic error rate, and G represents the influence factor of each knowledge point on the associated topic guessing rate.

The Bayes cognitive tracking method with multiple knowledge points provided by the embodiment of the invention has the following beneficial effects:

(1) the application scene of the conventional BKT model is widened, so that the condition of examining a plurality of knowledge points in a question can be processed;

(2) the change of each knowledge point is tracked independently, and the method is still effective when new topics investigated by combining different knowledge points appear at later time steps;

(3) the problem of tracking multiple knowledge points is solved, and the problem that the complexity of the algorithm in the original BKT exponentially increases along with the increase of the number of the knowledge points is solved.

(4) And (3) adjusting and optimizing parameters by using a heuristic optimization method, and avoiding local optimization by using group intelligence.

The invention is illustrated below by means of a further alternative embodiment.

EXAMPLE III

The cognitive analysis device for learning objects provided in this embodiment includes a plurality of implementation units, and each implementation unit corresponds to each implementation step in the first embodiment.

Fig. 2 is a schematic diagram of a cognitive analysis device of a learning object according to an embodiment of the present invention, and as shown in fig. 2, the cognitive analysis device may include: an acquisition unit 20, a first analysis unit 22, a construction unit 24, a second analysis unit 26, wherein,

the acquisition unit 20 is used for acquiring a score set of all learning object answering problems in the history process and a knowledge point set considered by each problem, wherein each problem corresponds to a plurality of knowledge points;

the first analysis unit 22 is used for analyzing the cognitive probability parameter set of the learning object for each knowledge point and the influence factor set of each knowledge point on the associated topic based on the score set and the knowledge point set;

the construction unit 24 is configured to construct a cognitive model by using the cognitive probability parameter set and the influence factor set of each knowledge point on the associated topic;

and the second analysis unit 26 is used for analyzing the answer probability of the target learning object for answering the new question by adopting the cognitive model.

The cognitive analysis device for the learning object can acquire a score set of all learning object response problems and a knowledge point set considered by each problem in a historical process through the acquisition unit 20, wherein each problem corresponds to a plurality of knowledge points, then based on the score set and the knowledge point set, a cognitive probability parameter set of the learning object for each knowledge point and an influence factor set of each knowledge point on an associated problem are analyzed through the first analysis unit 22, then a cognitive model is constructed through the construction unit 24 by adopting the cognitive probability parameter set and the influence factor set of each knowledge point on the associated problem, and finally, a response pair probability of a target learning object to respond to a new problem is analyzed through the second analysis unit 2 by adopting the cognitive model. In the embodiment, a cognitive analysis technology capable of facing multiple knowledge points is adopted, the problem that a traditional BKT cannot process one question and simultaneously investigate multiple knowledge points is solved, the accuracy of the answer pair probability of a new answer question of a learning object is analyzed by adopting a cognitive model, and the technical problem that the accuracy of cognitive evaluation on the learning object is influenced by simultaneously investigating multiple knowledge points in one question cannot be processed in the related technology is solved.

Optionally, the first analysis unit comprises: the first analysis module is used for analyzing the initial mastering probability, the learning probability and the forgetting probability of each knowledge point of the learning object based on the score set and the knowledge point set; the first determining module is used for determining a cognitive probability parameter set of the learning object for each knowledge point based on the initial mastering probability, the learning probability and the forgetting probability of the learning object for each knowledge point.

Optionally, the first analysis unit further comprises: the second determining module is used for determining a first influence factor of each knowledge point on the associated topic error rate and a second influence factor of each knowledge point on the associated topic guessing rate; a first construction module to construct a set of impact factors from the first impact factor and the second impact factor.

Optionally, the construction unit comprises: the first calculation module is used for calculating a first probability value of the answer problem of the learning object in the current cognitive state by adopting a first formula based on the score set and the knowledge point set; the second calculation module is used for calculating the error rate of the learning object for answering the exercises by adopting a second formula based on the first influence factor of each knowledge point on the error rate of the associated questions; the third calculation module is used for calculating the guessing rate of the answer questions of the learning object by adopting a third formula based on a second influence factor of each knowledge point on the guessing rate of the associated questions; the fourth calculation module is used for calculating a second probability value of the answer to the exercises of the learning object by adopting a fourth formula based on the first probability value of the answer to the target exercises of the learning object in the current cognitive state, the error rate of the answer to the target exercises of the learning object and the guessing rate; the second analysis module is used for analyzing the mastering state of the learning object on each knowledge point at the current moment based on the first probability value and the second probability value; and the second construction module is used for constructing a cognitive model corresponding to the learning object based on the mastering state of the learning object on each knowledge point at the current moment.

Optionally, the cognitive analysis device further comprises: the third determining module is used for determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment if the question answered by the learning object at the previous moment does not relate to the target knowledge point after the cognitive model is built; and the first updating module is used for calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a fifth formula based on the grasping state of the learning object on each knowledge point at the previous moment and the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment so as to update the cognitive model.

Optionally, the cognitive analysis device further comprises: the fourth determining module is used for determining the forgetting probability of the learning object to the target knowledge point from the previous moment to the current moment if the question answered by the learning object at the previous moment relates to the target knowledge point after the cognitive model is built; the fifth determining module is used for determining a first learning probability of a learning object answering the question corresponding to the target knowledge point at the previous moment and a second learning probability of an unanswered question corresponding to the target knowledge point; the second updating module is used for calculating the grasping state of the learning object on the target knowledge point at the current moment by adopting a sixth formula based on the grasping state of the learning object on each knowledge point at the previous moment, the forgetting probability of the learning object on the target knowledge point from the previous moment to the current moment and the first learning probability of answering the question corresponding to the target knowledge point at the previous moment so as to update the cognitive model; or, the third updating module is configured to calculate, based on the grasping state of the learning object at the previous time on each knowledge point, the forgetting probability of the learning object from the previous time to the current time on the target knowledge point, and the second learning probability of the question corresponding to the target knowledge point that is not answered at the previous time, the grasping state of the learning object at the current time on the target knowledge point by using a seventh formula, so as to update the cognitive model.

Optionally, the cognitive analysis device further comprises: the fourth updating module is used for training the cognitive model after analyzing the answer probability of the target learning object for answering the new exercise by adopting the cognitive model, and updating the mastering state of the learning object on each knowledge point; and the first adjusting module is used for adjusting the cognitive probability parameters and the influence factors of the cognitive model based on the updated mastery states of the learning objects on the knowledge points.

The cognitive analysis device for learning objects may further include a processor and a memory, wherein the acquiring unit 20, the first analyzing unit 22, the constructing unit 24, the second analyzing unit 26, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel can be set to be one or more than one, and the answer probability of the target learning object for answering the new problem is analyzed by adjusting the kernel parameters.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform the cognitive analysis method of the learning object of any one of the above via execution of the executable instructions.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the above cognitive analysis methods for a learning object.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.