CN117454018B - Education platform implementation method and system based on tablet personal computer - Google Patents
Education platform implementation method and system based on tablet personal computer Download PDFInfo
- Publication number
- CN117454018B CN117454018B CN202311773999.9A CN202311773999A CN117454018B CN 117454018 B CN117454018 B CN 117454018B CN 202311773999 A CN202311773999 A CN 202311773999A CN 117454018 B CN117454018 B CN 117454018B
- Authority
- CN
- China
- Prior art keywords
- learning
- keyword
- resource
- target
- score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 235000019580 granularity Nutrition 0.000 claims description 88
- 239000013598 vector Substances 0.000 claims description 26
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000007635 classification algorithm Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012886 linear function Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010223 real-time analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a tablet personal computer-based education platform implementation method and a tablet personal computer-based education platform implementation system, wherein the method comprises the following steps: acquiring capability information and index information of a tablet personal computer; collecting keyword information of a user learning history of a learning application on a tablet computer; the education platform determines the division granularity of the keywords based on the capability information, the index information and the keyword information; classifying and associating all learning resources on the education platform according to the division granularity; obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform; and recommending learning resources based on the similarity. According to the invention, the learning resources are classified according to the keywords, so that the content of the learning resources can be more accurately understood and organized; determining the granularity of division according to the performance and the storage capacity of the tablet personal computer, and flexibly adjusting according to specific conditions; real-time analysis and recommendation updating of learning resources are realized, and learning effect and user satisfaction are improved.
Description
Technical Field
The invention belongs to the field of computer system engineering, and particularly relates to an education platform implementation method and system based on a tablet personal computer.
Background
In recent years, with the integration of internet + education, various online education platforms are rapidly developing. These platforms accumulate a multitude of users by virtue of their high quality and massive resources. Online education has become an important education mode and technical approach for learning knowledge acquisition, skill expansion, academic education and the like. How to provide individualized content to learners in a huge amount of course resources is a matter of study.
In the online education platform, a small number of learners are required to complete school tasks specified by schools, and more learners are required to learn based on interest driving. Therefore, the interest of the learner in the online education platform is mined, the needs of the learner can be better understood, and the platform can be helped to provide personalized teaching services for the learner.
With the increasing use of online education, online education platforms have become an important platform and space for multiple learners to create, share, and acquire knowledge together. Many different learners are involved in the online educational platform, each having different interests and being dynamically changing. To annotate and manage learner interests, online educational platforms typically provide a method for learners to customize interests by annotating topics. It is difficult for a learner to describe his own interests in detail and it is not necessary to update interest tags as interests change. In addition, there are many learners who do not positively mark their interests. Therefore, how to automatically find learning interests of learners in an open learning environment is a problem worthy of study.
In addition, in recent years, remote teaching is also performed in a large amount, so that tablet computers are also widely popularized. Besides the functions of remote teaching, entertainment and the like, the tablet personal computer can be in an idle state most of the time, which also causes a great deal of resource waste.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a tablet personal computer-based education platform implementation method, which comprises the following steps:
step S101, starting a tablet personal computer, and acquiring capability information and index information of the tablet personal computer;
step S103, collecting keyword information of a user learning history of a learning application on the tablet computer;
step S105, uploading the capability information, the index information and the keyword information to the education platform, wherein the education platform determines the division granularity of the keywords based on the capability information, the index information and the keyword information;
step S107, classifying and associating all learning resources on the education platform according to the division granularity;
step S109, obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and step S1011, recommending learning resources based on the similarity.
The capability information of the tablet personal computer comprises the performance and the storage capability of the tablet personal computer, and the index information comprises the threshold value of the performance and the threshold value of the storage capability.
The step S105 specifically includes:
assuming that N keywords need to be classified, the number of keywords is num_keywords, for each keyword i, the CPU performance threshold is cpu_threshold [ i ], the storage capability threshold is memory_threshold [ i ], the weight of the keywords is weight [ i ], cpu_performance represents performance, available_memory represents available storage capability,
wherein, the CPU performance score is expressed as cpu_score [ i ] =f (cpu_performance, cpu_threshold [ i ]);
the memory capacity score is expressed as memory_score [ i ] =g (available_memory, memory_threshold [ i ]);
the keyword number score is expressed as: num_keywords_score=h (num_keywords);
the keyword weight score is expressed as: weight_score [ i ] =k (weight [ i ]);
the composite score for a keyword is expressed as: overlap_score [ i ] =w1×cpu_score [ i ] +w2×memory_score [ i ] +w3×num_keys_score+w4×weight_score [ i ]; wherein w1, w2, w3, w4 are weights of the respective scores;
the keywords are divided into different granularities according to the comprehensive scores of the keywords.
And the CPU performance score, the storage capacity score, the keyword quantity score and the keyword weight score are obtained quantitatively by using a linear function.
The step S107 specifically includes: and classifying the keywords of the learning resources according to the division granularity by using a naive Bayesian text classification algorithm, and associating each learning resource with the keyword classification to which the learning resources belong.
The classifying the keywords of the learning resources according to the division granularity by using a naive bayesian text classification algorithm comprises the following steps:
assume that C represents a set of granularity, which contains the granularity of the division; d represents a collection of learning resources, each learning resource being represented as D i The method comprises the steps of carrying out a first treatment on the surface of the W represents a set of keywords, each keyword being represented as W j The method comprises the steps of carrying out a first treatment on the surface of the X represents a feature vector, meaning learning resource d i Medium keyword w j Occurrence of (2);
calculating the prior probability P (C) of each granularity C, namely the probability of occurrence of the granularity C in the whole learning resource set D;
for each keyword w j Calculating the keyword w under the condition of given granularity C j Probability of occurrence;
For a given learning resource d i Predicting the granularity C to which the naive Bayes algorithm belongs by using the naive Bayes algorithm, and calculating a learning resource d by using the following formula according to the assumption that each keyword appears independently of the naive Bayes i Posterior probability of granularity C:
Wherein P (d) i ) Is a normalization factor for ensuring that the sum of the posterior probabilities is 1.
Wherein, the associating each learning resource with the keyword category to which it belongs includes:
based on the calculated posterior probabilityWill learn resource d i Associated with the granularity with highest posterior probability, i.e., d i Classified as C.
Wherein, the step S109 includes:
step S1091, using one-time thermal coding to represent the target user or target learning resource as a feature vector;
step S1093, assuming M keyword classifications, marking a target feature vector as X_target, wherein X_target [ i ] represents the existence condition of the ith keyword classification in the target resource, 1 represents existence, and 0 represents nonexistence;
in step S1095, the Similarity between the target feature vector x_target and other learning resources is calculated by using a cosine Similarity formula, and if there is another learning resource feature vector denoted as x_i, where x_i [ j ] represents the existence of the j-th keyword category in the resource, the Similarity between the target resource and the learning resource is denoted as Similarity (x_target, x_i).
Wherein, the step S1011 includes:
selecting learning resources with similarity higher than a preset threshold as a candidate resource set;
the candidate resource sets are ordered and filtered based on specified conditions.
Generating a final recommendation result according to the sorted and filtered candidate resource sets;
and displaying the recommendation result to the user.
The invention also provides an education platform realization system based on the tablet personal computer, which comprises the tablet personal computer and the education platform,
the tablet computer includes:
the acquisition module is used for acquiring the capability information and index information of the tablet personal computer;
the collection module is used for collecting keyword information of a user learning history of the learning application on the tablet computer;
the transmission module is used for uploading the capability information, the index information and the keyword information to the education platform;
the educational platform includes:
a granularity dividing module for determining a division granularity of the keywords based on the capability information, the index information, and the keyword information;
the classification association module is used for classifying and associating all learning resources according to the division granularity;
the similarity calculation module is used for obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and the recommendation module is used for carrying out learning resource recommendation based on the similarity.
Compared with the prior art, the invention has the following advantages:
accurate content recommendation: by classifying the learning resources according to the keywords, the content of the learning resources can be more accurately understood and organized. The content-based recommendation algorithm can provide personalized and accurate learning resource recommendation according to interests and demands of learners and by combining information of keyword classification. Therefore, a learner can more quickly find learning resources meeting own requirements, and learning efficiency is improved.
Flexible division granularity: the granularity of division is determined according to the performance and the storage capacity of the tablet personal computer, so that flexible adjustment can be performed according to specific situations. If the tablet computer has higher computing and storage capabilities, a finer granularity keyword classification can be selected, providing more specific and personalized learning resource recommendation. Conversely, if the computing and storage capabilities of the tablet computer are limited, a coarser granularity keyword classification may be selected, yet a more accurate and useful learning resource recommendation may be provided.
Real-time recommendation update: based on the performance and the storage capacity of the dynamic real-time reporting of the tablet personal computer, the real-time analysis and recommendation updating of learning resources can be realized. When the performance and the storage capacity of the tablet personal computer change, the granularity of division and the parameters of a recommendation algorithm can be readjusted according to the latest capacity information, so that recommended learning resources are always matched with the demands of learners and the capacities of the tablet personal computer.
Improving learning effect and user satisfaction: through accurate content recommendation and real-time recommendation update, a learner can better acquire learning resources meeting the requirements and capabilities of the learner. This helps to improve the learning effect and satisfaction of the learner, making the learning process more efficient and pleasant.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flowchart illustrating a method for implementing an educational platform based on a tablet computer according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two.
It should be understood that although the terms first, second, third, etc. may be used to describe … … in embodiments of the present invention, these … … should not be limited to these terms. These terms are only used to distinguish … …. For example, the first … … may also be referred to as the second … …, and similarly the second … … may also be referred to as the first … …, without departing from the scope of embodiments of the present invention.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or device comprising such element.
Alternative embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Embodiment 1,
As shown in fig. 1, the invention discloses an education platform implementation evaluating method based on a tablet computer, which comprises the following steps:
step S101, starting a tablet personal computer, and acquiring capability information and index information of the tablet personal computer;
step S103, collecting keyword information of a user learning history of a learning application on the tablet computer;
step S105, uploading the capability information, the index information and the keyword information to the education platform, wherein the education platform determines the division granularity of the keywords based on the capability information, the index information and the keyword information;
step S107, classifying and associating all learning resources on the education platform according to the division granularity;
step S109, obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and step S1011, recommending learning resources based on the similarity.
Embodiment II,
The invention provides an education platform implementation method based on a tablet personal computer, which comprises the following steps:
step S101, starting a tablet personal computer, and acquiring capability information and index information of the tablet personal computer;
step S103, collecting keyword information of a user learning history of a learning application on the tablet computer;
step S105, uploading the capability information, the index information and the keyword information to the education platform, wherein the education platform determines the division granularity of the keywords based on the capability information, the index information and the keyword information;
step S107, classifying and associating all learning resources on the education platform according to the division granularity;
step S109, obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and step S1011, recommending learning resources based on the similarity.
The capability information of the tablet personal computer comprises the performance and the storage capability of the tablet personal computer, and the index information comprises the threshold value of the performance and the threshold value of the storage capability. The CPU performance information includes CPU performance, and the storage capability information includes available memory.
The step S105 specifically includes:
assuming that N keywords need to be classified, the number of keywords is num_keywords, for each keyword i, the CPU performance threshold is cpu_threshold [ i ], the storage capability threshold is memory_threshold [ i ], the weight of the keywords is weight [ i ], cpu_performance represents performance, available_memory represents available storage capability,
wherein, the CPU performance score is expressed as cpu_score [ i ] =f (cpu_performance, cpu_threshold [ i ]);
the memory capacity score is expressed as memory_score [ i ] =g (available_memory, memory_threshold [ i ]);
the keyword number score is expressed as: num_keywords_score=h (num_keywords);
the keyword weight score is expressed as: weight_score [ i ] =k (weight [ i ]);
the composite score for a keyword is expressed as: overlap_score [ i ] =w1×cpu_score [ i ] +w2×memory_score [ i ] +w3×num_keys_score+w4×weight_score [ i ]; wherein w1, w2, w3, w4 are weights of the respective scores;
the keywords are divided into different granularities according to the comprehensive scores of the keywords.
And the CPU performance score, the storage capacity score, the keyword quantity score and the keyword weight score are obtained quantitatively by using a linear function.
Taking the CPU performance score as an example, in some embodiment, the CPU performance score may be calculated using a linear function, where the range of values of the score is typically within some predefined interval. The form of the linear function may be:
cpu_score[i] = m * cpu_performance + b
where m is the slope and b is the intercept, which can be adjusted according to the actual situation to obtain a suitable score range and distribution.
In one embodiment, the CPU performance score may also use a Sigmoid function, which may map the input to a score range between 0 and 1. The form of the Sigmoid function may be:
cpu_score[i] = 1 / (1 + exp(-k * (cpu_performance - x0))),
where k is the slope parameter of the Sigmoid function, x0 is the center point of the function, and can be adjusted according to the actual situation to obtain a suitable score distribution.
Other scores can be calculated by adopting similar formulas, and if necessary, part of parameters can be set in advance by a platform end.
The step S107 specifically includes: and classifying the keywords of the learning resources according to the division granularity by using a naive Bayesian text classification algorithm, and associating each learning resource with the keyword classification to which the learning resources belong.
The classifying the keywords of the learning resources according to the division granularity by using a naive bayesian text classification algorithm comprises the following steps:
assume that C represents a set of granularity, which contains the granularity of the division; d represents a collection of learning resources, each learning resource being represented as D i The method comprises the steps of carrying out a first treatment on the surface of the W represents a set of keywords, each keyword being represented as W j The method comprises the steps of carrying out a first treatment on the surface of the X represents a feature vector, meaning learning resource d i Medium keyword w j Occurrence of (2);
calculating the prior probability P (C) of each granularity C, namely the probability of occurrence of the granularity C in the whole learning resource set D;
for each keyword w j Calculating the keyword w under the condition of given granularity C j Probability of occurrence;
For a given learning resource d i Predicting the granularity C to which it belongs using a naive Bayesian algorithm, a pseudo-according to naive BayesianAssuming that the occurrences of each keyword are independent of each other, the learning resource d is calculated using the following formula i Posterior probability of granularity C:
Wherein P (d) i ) Is a normalization factor for ensuring that the sum of the posterior probabilities is 1.
In one embodiment, the calculation of the prior probability P (C) for each granularity C, i.e. the probability that granularity C occurs throughout the learning resource set D, may be performed as follows:
the occurrence times of each granularity C in the learning resource set D are counted. Traversing the whole learning resource set D, determining the granularity C of each resource, and recording the granularity C;
the frequency of occurrence of each granularity C is calculated. Dividing the occurrence frequency of each granularity C in the learning resource set D by the total number of the learning resource sets D to obtain the occurrence frequency of each granularity C;
the frequency of occurrence of each granularity C is normalized to probability. Dividing the occurrence frequency of each granularity C by the sum of the occurrence frequencies of all granularities to obtain the prior probability P (C) of each granularity C, wherein the prior probability P (C) is expressed as follows:
P(C) = N(C) / N(D)
wherein P (C) represents the prior probability of granularity C, N (C) represents the number of occurrences of granularity C in learning resource set D, and N (D) represents the total number of learning resource sets D.
In one embodiment, the keyword w is calculated at a given granularity C j The probability of occurrence can be performed as follows:
statistics of keywords w j Number of occurrences at granularity C: traversing the learning resource set D, for each learning resource D i Judging whether the granularity to which the keyword belongs is C, if so, counting the keyword w j In the learning resourceThe number of occurrences;
counting the total keyword number under granularity C: traversing the learning resource set D, for each learning resource D i Judging whether the granularity to which the learning resource belongs is C, if so, counting the total keyword number in the learning resource, namely the total number of all keywords contained in the granularity C;
calculating keyword w j Probability at a given granularity C: keyword w j Dividing the number of occurrences at granularity C by the total number of keywords at granularity C to obtain keyword w j The probability at a given granularity C is formulated as follows:
P(w j |C) = N(w j , C) / N(C)
wherein P (w) j I C) means that given granularity C, keyword w j Probability of occurrence, N (w j, C) Representing keyword w j The number of occurrences at granularity C, N (C), represents the total number of keywords at granularity C.
Wherein, the associating each learning resource with the keyword category to which it belongs includes:
based on the calculated posterior probabilityWill learn resource d i Associated with the granularity with highest posterior probability, i.e., d i Classified as C.
Wherein, the step S109 includes:
step S1091, using one-time thermal coding to represent the target user or target learning resource as a feature vector;
step S1093, assuming M keyword classifications, marking a target feature vector as X_target, wherein X_target [ i ] represents the existence condition of the ith keyword classification in the target resource, 1 represents existence, and 0 represents nonexistence;
in step S1095, the Similarity between the target feature vector x_target and other learning resources is calculated by using a cosine Similarity formula, and if there is another learning resource feature vector denoted as x_i, where x_i [ j ] represents the existence of the j-th keyword category in the resource, the Similarity between the target resource and the learning resource is denoted as Similarity (x_target, x_i).
Wherein, the step S1011 includes:
selecting learning resources with similarity higher than a preset threshold as a candidate resource set;
the candidate resource sets are ordered and filtered based on specified conditions.
Generating a final recommendation result according to the sorted and filtered candidate resource sets;
and displaying the recommendation result to the user.
Third embodiment,
The invention provides the method for determining the granularity of division according to the calculation capability and the storage capability of the dynamic real-time reporting of the tablet personal computer, and the determination of the granularity can be regarded as an optimization problem. The following is a specific step of classifying and recommending according to keywords.
Step 1, data preprocessing:
a. computing power and storage power data, such as CPU performance, memory capacity, etc., of the tablet computer are collected.
b. Keyword data of learning resources is collected.
Step 2, determining granularity:
a. and setting corresponding thresholds or indexes, such as CPU performance thresholds, available memory thresholds and the like, according to the computing capacity and storage capacity data of the tablet personal computer.
b. Based on these thresholds or metrics, the granularity of the division of the keywords is determined. The manner in which the granularity is divided may be determined based on the number of keywords, weights of the keywords, or other characteristics.
Step 3, keyword classification:
a. and classifying the keywords of the learning resources according to the granularity of the division. The classification of keywords may be performed using a clustering algorithm, a text classification algorithm, or the like.
b. Each learning resource is associated with a keyword class to which it belongs.
Step 4, target feature vector representation:
a. for the target user or target learning resource, it is represented as a feature vector. The feature vectors may be represented using One-Hot Encoding (One Encoding) or the like.
b. Assuming that there are M keyword classifications, the target feature vector is denoted as X_target, where X_target [ i ] represents the presence of the ith keyword classification in the target resource (1 represents present, 0 represents absent).
Step 5, similarity calculation:
a. and calculating the similarity of the target feature vector X_target and other learning resources.
b. The calculation may be performed using cosine similarity formula or the like. Assuming that there is another feature vector of the learning resource denoted as x_i, where x_i [ j ] represents the existence of the j-th keyword category in the resource, the Similarity of the target resource and the learning resource is denoted as Similarity (x_target, x_i).
Step 6, selecting candidate resources:
a. and selecting learning resources with similarity higher than a certain threshold value as candidate resources. And screening out learning resources with similarity to the target resources higher than the threshold value as candidate resource sets by setting a similarity threshold value.
Step 7, sequencing and filtering:
a. and sequencing and filtering the candidate resources according to the scoring index or the filtering condition.
b. The ranking can be performed according to indexes such as scores of resources, browsing amount and the like, or the filtering can be performed according to filtering conditions such as release time, authors and the like.
Step 8, generating a recommendation result:
a. and generating a final recommendation result according to the sorted and filtered candidate resources.
b. The recommendation results are presented to the user to assist them in selecting the appropriate learning resources.
Fourth embodiment,
Assume that there is a set of learning resources, each of which is an article. The articles are classified according to the keywords, and the granularity of the division is determined according to the computing capacity and the storage capacity of the tablet computer. In this example, we divide keywords as features, each of which is considered a feature.
Assume that the following four articles and corresponding keywords are:
article A, "machine learning", "deep learning", "neural network"
Article B, "data mining", "clustering", "classification algorithm"
Article C, "natural language processing", "text analysis", "machine translation"
Article D, "computer vision", "image recognition", "target detection"
These articles are represented as feature vectors, where each feature represents a keyword and binary values are used to represent whether the keyword is present in the article. For example, if a keyword is present in the article, the corresponding feature vector has a value of 1, otherwise 0.
For the above example, the following feature vectors may be derived:
article A [1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
Article B [0, 0, 0, 1, 1, 1, 0, 0, 0, 0]
Article C [0, 0, 0, 0, 0, 1, 1, 1, 0]
Article D [0, 0, 0, 0, 0, 0, 0, 0, 1]
Next, the cosine similarity is used to calculate the similarity between learning resources. And calculating the similarity between the target learning resource R_target and other learning resources.
The cosine similarity is calculated as follows:
Similarity(R_target, R_i) = (X_target · X_i) / (||X_target|| * ||X_i||)
where Similarity (r_target, r_i) represents the Similarity between the target learning resource r_target and the learning resource r_i, and x_target and x_i represent their feature vectors, respectively.
The similarity between R_target and article A is calculated, and the following can be obtained:
similarity (r_target, article a) = (x_target article a)/(|x_target article a|)
Assuming that x_target represents a feature vector of the target learning resource r_target, according to the above example, we get:
X_target = [0, 0, 0, 0, 0, 0, 0, 0, 0, 1]
substituting the similarity into a cosine similarity formula to calculate the similarity value.
Similarly, the similarity of R_target to other learning resources may be calculated.
According to the calculation result of the similarity, learning resources with the similarity higher than a certain threshold value can be selected as candidate resources, and the candidate resources are ranked and filtered according to a scoring index or a filtering condition.
And finally, generating a local recommendation result, and displaying the sorted and filtered candidate resources to a user.
Fifth embodiment (V),
The invention also provides an education platform realization system based on the tablet personal computer, which comprises the tablet personal computer and the education platform,
the tablet computer includes:
the acquisition module is used for acquiring the capability information and index information of the tablet personal computer;
the collection module is used for collecting keyword information of a user learning history of the learning application on the tablet computer;
the transmission module is used for uploading the capability information, the index information and the keyword information to the education platform;
the educational platform includes:
a granularity dividing module for determining a division granularity of the keywords based on the capability information, the index information, and the keyword information;
the classification association module is used for classifying and associating all learning resources according to the division granularity;
the similarity calculation module is used for obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and the recommendation module is used for carrying out learning resource recommendation based on the similarity.
Embodiment six,
The disclosed embodiments provide a non-transitory computer storage medium storing computer executable instructions that perform the method steps described in the embodiments above.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local Area Network (AN) or a Wide Area Network (WAN), or can be connected to AN external computer (for example, through the Internet using AN Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The foregoing description of the preferred embodiments of the present invention has been presented for purposes of clarity and understanding, and is not intended to limit the invention to the particular embodiments disclosed, but is intended to cover all modifications, alternatives, and improvements within the spirit and scope of the invention as outlined by the appended claims.
Claims (7)
1. The method for realizing the education platform based on the tablet personal computer is characterized by comprising the following steps of:
step S101, starting a tablet personal computer, and acquiring capability information and index information of the tablet personal computer;
step S103, collecting keyword information of a user learning history of a learning application on the tablet computer;
step S105, uploading the capability information, the index information and the keyword information to the education platform, wherein the education platform determines the division granularity of the keywords based on the capability information, the index information and the keyword information;
step S107, classifying and associating all learning resources on the education platform according to the division granularity;
step S109, obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
step S1011, recommending learning resources based on the similarity;
the capability information of the tablet personal computer comprises the performance and the storage capability of the tablet personal computer, and the index information comprises the threshold value of the performance and the threshold value of the storage capability;
the step S105 specifically includes:
assuming that N keywords need to be classified, the number of keywords is num_keywords, for each keyword i, the CPU performance threshold is cpu_threshold [ i ], the storage capability threshold is memory_threshold [ i ], the weight of the keywords is weight [ i ], cpu_performance represents performance, available_memory represents available storage capability,
wherein, the CPU performance score is expressed as cpu_score [ i ] =f (cpu_performance, cpu_threshold [ i ]);
the memory capacity score is expressed as memory_score [ i ] =g (available_memory, memory_threshold [ i ]);
the keyword number score is expressed as: num_keywords_score=h (num_keywords);
the keyword weight score is expressed as: weight_score [ i ] =k (weight [ i ]);
the composite score for a keyword is expressed as: overlap_score [ i ] =w1×cpu_score [ i ] +w2×memory_score [ i ] +w3×num_keys_score+w4×weight_score [ i ]; wherein w1, w2, w3, w4 are weights of the respective scores;
dividing the keywords into different granularities according to the comprehensive scores of the keywords;
and the CPU performance score, the storage capacity score, the keyword quantity score and the keyword weight score are obtained quantitatively by using a linear function.
2. The method according to claim 1, wherein the step S107 specifically includes: and classifying the keywords of the learning resources according to the division granularity by using a naive Bayesian text classification algorithm, and associating each learning resource with the keyword classification to which the learning resources belong.
3. The method of claim 2, wherein classifying the keywords of the learning resources according to the division granularity using a naive bayesian text classification algorithm comprises:
let C denote a set of granularity, which includes partitioningParticle size of (2); d represents a collection of learning resources, each learning resource being represented as D i The method comprises the steps of carrying out a first treatment on the surface of the W represents a set of keywords, each keyword being represented as W j The method comprises the steps of carrying out a first treatment on the surface of the X represents a feature vector, meaning learning resource d i Medium keyword w j Occurrence of (2);
calculating the prior probability P (C) of each granularity C, namely the probability of occurrence of the granularity C in the whole learning resource set D;
for each keyword w j Calculating the keyword w under the condition of given granularity C j Probability of occurrence;
For a given learning resource d i Predicting the granularity C to which the naive Bayes algorithm belongs by using the naive Bayes algorithm, and calculating a learning resource d by using the following formula according to the assumption that each keyword appears independently of the naive Bayes i Posterior probability of granularity C:
,
Wherein P (d) i ) Is a normalization factor for ensuring that the sum of the posterior probabilities is 1.
4. The method of claim 3, wherein associating each learning resource with the keyword class to which it belongs comprises:
based on the calculated posterior probabilityWill learn resource d i Associated with the granularity with highest posterior probability, i.e., d i Classified as C.
5. The method of claim 1, wherein the step S109 includes:
step S1091, using one-time thermal coding to represent the target user or target learning resource as a feature vector;
step S1093, assuming M keyword classifications, marking a target feature vector as X_target, wherein X_target [ i ] represents the existence condition of the ith keyword classification in the target resource, 1 represents existence, and 0 represents nonexistence;
in step S1095, the Similarity between the target feature vector x_target and other learning resources is calculated by using a cosine Similarity formula, and if there is another learning resource feature vector denoted as x_i, where x_i [ j ] represents the existence of the j-th keyword category in the resource, the Similarity between the target resource and the learning resource is denoted as Similarity (x_target, x_i).
6. The method of claim 1, wherein the step S1011 includes:
selecting learning resources with similarity higher than a preset threshold as a candidate resource set;
sorting and filtering the candidate resource sets based on specified conditions;
generating a final recommendation result according to the sorted and filtered candidate resource sets;
and displaying the recommendation result to the user.
7. An education platform implementation system based on a tablet computer, for implementing the method of any one of claims 1-6, comprising the tablet computer and the education platform, characterized in that,
the tablet computer includes:
the acquisition module is used for acquiring the capability information and index information of the tablet personal computer;
the collection module is used for collecting keyword information of a user learning history of the learning application on the tablet computer;
the transmission module is used for uploading the capability information, the index information and the keyword information to the education platform;
the educational platform includes:
a granularity dividing module for determining a division granularity of the keywords based on the capability information, the index information, and the keyword information;
the classification association module is used for classifying and associating all learning resources according to the division granularity;
the similarity calculation module is used for obtaining the similarity between a target user or a target learning resource and the existing learning resource on the education platform, wherein the target user is a user using the education platform, and the target learning resource is the latest learning resource uploaded to the education platform;
and the recommendation module is used for carrying out learning resource recommendation based on the similarity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311773999.9A CN117454018B (en) | 2023-12-22 | 2023-12-22 | Education platform implementation method and system based on tablet personal computer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311773999.9A CN117454018B (en) | 2023-12-22 | 2023-12-22 | Education platform implementation method and system based on tablet personal computer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117454018A CN117454018A (en) | 2024-01-26 |
CN117454018B true CN117454018B (en) | 2024-03-08 |
Family
ID=89591276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311773999.9A Active CN117454018B (en) | 2023-12-22 | 2023-12-22 | Education platform implementation method and system based on tablet personal computer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117454018B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503025A (en) * | 2015-09-08 | 2017-03-15 | 北京搜狗科技发展有限公司 | Method and system is recommended in a kind of application |
CN108984711A (en) * | 2018-07-09 | 2018-12-11 | 湖南大学 | A kind of personalized APP recommended method based on layering insertion |
CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
CN111414570A (en) * | 2020-03-20 | 2020-07-14 | 读书郎教育科技有限公司 | Flat-panel online learning adaptive learning system and method based on cloud service |
CN114118433A (en) * | 2020-08-26 | 2022-03-01 | 华为技术有限公司 | Recommendation method and device for configuration parameters of equipment |
CN116628339A (en) * | 2023-06-09 | 2023-08-22 | 国信蓝桥教育科技股份有限公司 | Educational resource recommendation method and system based on artificial intelligence |
CN117194743A (en) * | 2023-08-17 | 2023-12-08 | 同方知网数字出版技术股份有限公司 | Progressive learning resource recommendation method and device, storage medium and computer equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11694098B2 (en) * | 2020-06-29 | 2023-07-04 | Forescout Technologies, Inc. | Multiple granularity classification |
-
2023
- 2023-12-22 CN CN202311773999.9A patent/CN117454018B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503025A (en) * | 2015-09-08 | 2017-03-15 | 北京搜狗科技发展有限公司 | Method and system is recommended in a kind of application |
CN108984711A (en) * | 2018-07-09 | 2018-12-11 | 湖南大学 | A kind of personalized APP recommended method based on layering insertion |
CN111414570A (en) * | 2020-03-20 | 2020-07-14 | 读书郎教育科技有限公司 | Flat-panel online learning adaptive learning system and method based on cloud service |
CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
CN114118433A (en) * | 2020-08-26 | 2022-03-01 | 华为技术有限公司 | Recommendation method and device for configuration parameters of equipment |
CN116628339A (en) * | 2023-06-09 | 2023-08-22 | 国信蓝桥教育科技股份有限公司 | Educational resource recommendation method and system based on artificial intelligence |
CN117194743A (en) * | 2023-08-17 | 2023-12-08 | 同方知网数字出版技术股份有限公司 | Progressive learning resource recommendation method and device, storage medium and computer equipment |
Also Published As
Publication number | Publication date |
---|---|
CN117454018A (en) | 2024-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Anastasopoulos et al. | Machine learning for public administration research, with application to organizational reputation | |
CN112131350B (en) | Text label determining method, device, terminal and readable storage medium | |
Stein et al. | Intrinsic plagiarism analysis | |
US10762439B2 (en) | Event clustering and classification with document embedding | |
CN112214670A (en) | Online course recommendation method and device, electronic equipment and storage medium | |
US11429810B2 (en) | Question answering method, terminal, and non-transitory computer readable storage medium | |
US12020267B2 (en) | Method, apparatus, storage medium, and device for generating user profile | |
CN109086265B (en) | Semantic training method and multi-semantic word disambiguation method in short text | |
Huang et al. | Expert as a service: Software expert recommendation via knowledge domain embeddings in stack overflow | |
CN112188312B (en) | Method and device for determining video material of news | |
CN112307336B (en) | Hot spot information mining and previewing method and device, computer equipment and storage medium | |
Ashok et al. | A personalized recommender system using machine learning based sentiment analysis over social data | |
Schofield et al. | Identifying hate speech in social media | |
CN112598405B (en) | Business project data management method and system based on big data | |
CN117056575B (en) | Method for data acquisition based on intelligent book recommendation system | |
Fauzan et al. | Automatic multilabel categorization using learning to rank framework for complaint text on Bandung government | |
Das et al. | Dataset bias: A case study for visual question answering | |
CN117454018B (en) | Education platform implementation method and system based on tablet personal computer | |
CN113220994B (en) | User personalized information recommendation method based on target object enhanced representation | |
CN115510326A (en) | Internet forum user interest recommendation algorithm based on text features and emotional tendency | |
US20170293863A1 (en) | Data analysis system, and control method, program, and recording medium therefor | |
US20200226159A1 (en) | System and method of generating reading lists | |
Xue | Knowledge graph based recommendation by adversarial learning algorithm in application of lifelong education data classification | |
Lee et al. | Exploring a Supervised Learning Based Social Media Business Sentiment Index | |
Soria et al. | Comparative approach of sentiment analysis algorithms to classify social media information gathering in the Spanish language |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |