Digital teaching resource recommendation optimization system based on artificial intelligence
By adopting artificial intelligence-based data collection, feature extraction and hybrid recommendation algorithms in the digital teaching resource recommendation system, the shortcomings of the existing system in accurate recommendation are solved, personalized and intelligent teaching resource recommendations are realized, and learning effect is improved.
Patent Information
- Application Number
- CN202510097108.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-22
- Publication Date
- 2025-05-16
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing digital teaching resource recommendation system has shortcomings in accurately and efficiently recommending resources to users that meet their needs and learning habits. Traditional methods are inefficient and difficult to accurately capture users' personalized needs.
Using a digital teaching resource recommendation optimization system based on artificial intelligence, through the combination of data collection, feature extraction, index construction and resource recommendation models, network crawlers collect user behavior data, combine deep learning and neural network technology to build a hybrid recommendation algorithm and resource recommendation model to achieve personalized recommendation.
It improves the accuracy and diversity of resource recommendations, provides users with personalized and intelligent learning services, and improves the utilization rate and learning effect of teaching resources.
Smart Images
Figure CN120013719A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart teaching, and in particular to a digital teaching resource recommendation and optimization system based on artificial intelligence. Background Art
[0002] With the rapid development of information technology, the application of digital teaching resources in the field of education is becoming more and more extensive. However, faced with a large amount of digital teaching resources, how to accurately and efficiently recommend resources that meet users' needs and learning habits has become an urgent problem to be solved. Traditional resource recommendation methods often rely on manual screening or simple keyword matching, which is not only inefficient, but also difficult to accurately capture users' personalized needs.
[0003] In order to overcome this problem, digital teaching resource recommendation systems based on artificial intelligence have emerged in recent years. Such systems collect and analyze user behavior data, extract user feature information, and then build resource indexes to achieve accurate resource recommendations. However, existing recommendation systems still have some shortcomings. For example, some systems rely only on a single recommendation algorithm, such as collaborative filtering or content recommendation, which limits the accuracy and diversity of recommendation results. In addition, some systems lack the application of deep learning and neural networks in feature extraction and resource index construction, which makes the intelligence of the recommendation system and the recommendation effect need to be improved. Summary of the invention
[0004] The purpose of the present invention is to provide a digital teaching resource recommendation optimization system based on artificial intelligence, which can improve the accuracy of content recommendation.
[0005] To achieve the above object, the present invention provides the following solutions:
[0006] A digital teaching resource recommendation and optimization system based on artificial intelligence, comprising:
[0007] A data collection port is used to extract user behavior data online using a web crawler to obtain target historical data; the behavior data includes learning purpose, learning time, learning progress, interaction frequency and homework completion status;
[0008] A feature extraction unit, used to extract features from the target history data to obtain target attention features; the target attention features are used to describe learning habits, interest preferences and ability levels;
[0009] An index building unit, used to build a resource index according to the target focus feature and the loaded digital teaching resources;
[0010] A resource recommendation unit, configured to construct a resource recommendation model according to a hybrid recommendation algorithm, and to push content using the resource index and the resource recommendation model; the hybrid recommendation algorithm includes a collaborative filtering algorithm and a content recommendation algorithm; the resource recommendation model is constructed by a deep neural network;
[0011] The display terminal is used to visually display the resource index and the corresponding pushed content.
[0012] Optionally, the data acquisition port includes an RS-485 interface connected to the Internet and a LoRa gateway; wherein the LoRa gateway uses LoRa protocol self-organizing network communication to transmit data.
[0013] Optionally, the feature extraction unit specifically includes:
[0014] A preprocessing module is used to preprocess and filter the target historical data to obtain valid data; the preprocessing includes cleaning, conversion and normalization; the data filtering uses a screening algorithm or a Bloom filter to remove duplicate and invalid data; the screening algorithm includes attribute screening, relationship screening and rule screening;
[0015] The feature calculation module is used to extract features from the valid data using the TF-IDF algorithm to obtain corresponding feature vectors, and to aggregate the feature vectors to obtain target focus features.
[0016] Optionally, the preprocessing module also includes an algorithm storage submodule; the algorithm storage submodule stores a screening algorithm and a Bloom filter; wherein the attribute screening includes keyword matching and numerical range screening, the relationship screening includes social relationship screening and reference relationship screening, and the rule screening includes business rule screening and data feature rule screening.
[0017] Optionally, the index building unit specifically includes:
[0018] A resource feature extraction module is used to extract metadata from the loaded digital teaching resources; the metadata includes the resource title, author, abstract, keywords, subject classification and difficulty level;
[0019] The association matching module is used to establish a resource index according to the target focus feature and the metadata.
[0020] Optionally, the resource recommendation unit specifically includes:
[0021] A model building module, used for performing model training based on the hybrid recommendation algorithm and the long short-term memory network, and determining the trained model as a resource recommendation model;
[0022] The recommendation module is used to push content using the resource index and the resource recommendation model.
[0023] Optionally, the model building module specifically includes:
[0024] A training data acquisition submodule is used to acquire training data;
[0025] A model building submodule, used to build a pre-trained model based on the hybrid recommendation algorithm and the long short-term memory network;
[0026] The model training submodule is used to input the training data into the pre-trained model, train the pre-trained model with a gradient descent strategy, and determine the trained model as a resource recommendation model.
[0027] Optionally, the display terminal includes at least one of a personal computer, a laptop computer, a smart phone, a tablet computer and a portable wearable device.
[0028] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:
[0029] The present invention discloses a digital teaching resource recommendation optimization system based on artificial intelligence, the system comprises a data acquisition port, a feature extraction unit, an index construction unit, a resource recommendation unit and a display terminal connected in sequence; wherein the data acquisition port is used to extract the user's behavior data on the Internet using a web crawler to obtain target historical data; the feature extraction unit is used to extract features from the target historical data to obtain target attention features; the index construction unit is used to establish a resource index according to the target attention features and the loaded digital teaching resources; the resource recommendation unit is used to construct a resource recommendation model according to a hybrid recommendation algorithm, and use the resource index and the resource recommendation model to push content; the display terminal is used for content display. The present invention can overcome the shortcomings of the existing recommendation system, improve the accuracy and diversity of resource recommendations, and provide users with more personalized and intelligent learning services. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0031] Figure 1 This is a structural diagram of the digital teaching resource recommendation and optimization system based on artificial intelligence of the present invention. DETAILED DESCRIPTION
[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0033] The purpose of the present invention is to provide a digital teaching resource recommendation optimization system based on artificial intelligence, which can improve the accuracy of content recommendation.
[0034] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0035] like Figure 1 As shown, the present invention provides a digital teaching resource recommendation and optimization system based on artificial intelligence, comprising: a data acquisition port, a feature extraction unit, an index construction unit, a resource recommendation unit and a display terminal connected in sequence.
[0036] A data collection port is used to extract user behavior data online using a web crawler to obtain target historical data; the behavior data includes learning purpose, learning time, learning progress, interaction frequency and homework completion status;
[0037] A feature extraction unit, used to extract features from the target history data to obtain target attention features; the target attention features are used to describe learning habits, interest preferences and ability levels;
[0038] An index building unit, used to build a resource index according to the target focus feature and the loaded digital teaching resources;
[0039] A resource recommendation unit, configured to construct a resource recommendation model according to a hybrid recommendation algorithm, and to push content using the resource index and the resource recommendation model; the hybrid recommendation algorithm includes a collaborative filtering algorithm and a content recommendation algorithm; the resource recommendation model is constructed by a deep neural network;
[0040] The display terminal is used to visually display the resource index and the corresponding pushed content.
[0041] As a specific implementation, the data acquisition port includes an RS-485 interface connected to the Internet and a LoRa gateway; wherein the LoRa gateway uses the LoRa protocol self-organizing network communication to transmit data.
[0042] As a specific implementation, the feature extraction unit specifically includes:
[0043] A preprocessing module is used to preprocess and filter the target historical data to obtain valid data; the preprocessing includes cleaning, conversion and normalization; the data filtering uses a screening algorithm or a Bloom filter to remove duplicate and invalid data; the screening algorithm includes attribute screening, relationship screening and rule screening;
[0044] The feature calculation module is used to extract features from the valid data using the TF-IDF algorithm to obtain corresponding feature vectors, and to aggregate the feature vectors to obtain target focus features.
[0045] Among them, the preprocessing module also includes an algorithm storage submodule; the algorithm storage submodule stores a screening algorithm and a Bloom filter; wherein the attribute screening includes keyword matching and numerical range screening, the relationship screening includes social relationship screening and reference relationship screening, and the rule screening includes business rule screening and data characteristic rule screening.
[0046] As a specific implementation, the index building unit specifically includes:
[0047] A resource feature extraction module is used to extract metadata from the loaded digital teaching resources; the metadata includes the resource title, author, abstract, keywords, subject classification and difficulty level;
[0048] The association matching module is used to establish a resource index according to the target focus feature and the metadata.
[0049] As a specific implementation, the resource recommendation unit specifically includes:
[0050] A model building module, used for performing model training based on the hybrid recommendation algorithm and the long short-term memory network, and determining the trained model as a resource recommendation model;
[0051] The recommendation module is used to push content using the resource index and the resource recommendation model.
[0052] Wherein, the model building module specifically includes:
[0053] A training data acquisition submodule is used to acquire training data;
[0054] A model building submodule, used to build a pre-trained model based on the hybrid recommendation algorithm and the long short-term memory network;
[0055] The model training submodule is used to input the training data into the pre-trained model, train the pre-trained model with a gradient descent strategy, and determine the trained model as a resource recommendation model.
[0056] As a specific implementation, the display terminal includes at least one of a personal computer, a laptop computer, a smart phone, a tablet computer, and a portable wearable device.
[0057] Based on the above technical solution, the following embodiments are provided.
[0058] The system in this embodiment is composed of a data acquisition port, a feature extraction unit, an index construction unit, a resource recommendation unit and a display terminal connected in sequence, aiming to provide users with personalized and intelligent teaching resource recommendation services.
[0059] Data collection port:
[0060] The data collection port is responsible for capturing the user's behavior data from the Internet. In this embodiment, the data collection port is equipped with an RS-485 interface and a LoRa gateway connected to the Internet. The RS-485 interface ensures high-speed and stable data transmission, while the LoRa gateway uses the LoRa protocol for self-organizing network communication to achieve low-power and long-distance data transmission. Through these two interfaces, the data collection port successfully extracts target historical data including learning purpose, learning time, learning progress, interaction frequency and homework completion from major educational platforms, social media and other channels.
[0061] Feature extraction unit:
[0062] The feature extraction unit processes the collected target history data in depth to extract target attention features that describe the user's learning habits, interest preferences and ability level. This unit includes a preprocessing module and a feature calculation module.
[0063] The preprocessing module first cleans, transforms and normalizes the data to eliminate noise, outliers and redundant information in the data. Subsequently, the filtering algorithm (including attribute filtering, relationship filtering and rule filtering) and Bloom filter are used to filter out duplicate and invalid data. Attribute filtering focuses on the keyword matching and value range of the data; relationship filtering analyzes the social relationship and reference relationship of the data; rule filtering is based on business rules and data feature rules. These measures ensure the accuracy and validity of the data.
[0064] The feature calculation module uses the TF-IDF algorithm to extract features from the preprocessed data and obtain the corresponding feature vectors. These feature vectors are processed collectively to form target focus features, which provide an important basis for subsequent resource recommendations.
[0065] Index building unit:
[0066] The index building unit builds a resource index according to the target focus features and the loaded digital teaching resources. The unit includes a resource feature extraction module and an association matching module.
[0067] The resource feature extraction module extracts metadata from digital teaching resources, including key information such as resource title, author, abstract, keywords, subject classification, and difficulty level. These metadata provide a basis for resource classification and indexing.
[0068] The association matching module builds a resource index based on the association between the target focus features and metadata. In this way, when users need learning resources, the system can quickly retrieve content that meets their needs from the resource library.
[0069] Resource recommendation unit:
[0070] The resource recommendation unit is the core part of the system, responsible for content push based on the resource recommendation model built by the hybrid recommendation algorithm and deep neural network. This unit includes a model building module and a recommendation module.
[0071] The model building module first obtains training data, and then builds a pre-trained model based on a hybrid recommendation algorithm (including collaborative filtering algorithm and content recommendation algorithm) and a long short-term memory network (LSTM). Next, the training data is input into the pre-trained model, and the model is trained using a gradient descent strategy until the model achieves satisfactory performance. The trained model is determined as a resource recommendation model for subsequent content push.
[0072] The recommendation module uses resource indexing and resource recommendation models to recommend personalized teaching resources to users based on their current needs and historical behavior data. These resources not only meet the user's learning goals and progress, but also stimulate the user's learning interest and improve learning outcomes.
[0073] Display terminal:
[0074] The display terminal is a window for users to interact with the system. In this embodiment, the display terminal includes at least one of a personal computer, a laptop, a smart phone, a tablet computer, and a portable wearable device. These devices have different screen sizes and interaction methods, but can all display resource indexes and push content through a unified user interface. Users can choose a suitable device for access and operation according to their preferences and needs.
[0075] In summary, the digital teaching resource recommendation and optimization system based on artificial intelligence in this embodiment provides users with personalized and intelligent teaching resource recommendation services through steps such as data collection, feature extraction, index construction, resource recommendation and visual display. The system not only improves the utilization rate of teaching resources and learning effects, but also brings users a more convenient and efficient learning experience.
[0076] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0077] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of the present invention. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A digital teaching resource recommendation and optimization system based on artificial intelligence, characterized in that: include: A data collection port is used to extract user behavior data online using a web crawler to obtain target historical data; the behavior data includes learning purpose, learning time, learning progress, interaction frequency and homework completion status; A feature extraction unit, used to extract features from the target history data to obtain target attention features; the target attention features are used to describe learning habits, interest preferences and ability levels; An index building unit, used to build a resource index according to the target focus feature and the loaded digital teaching resources; A resource recommendation unit, configured to construct a resource recommendation model according to a hybrid recommendation algorithm, and to push content using the resource index and the resource recommendation model; the hybrid recommendation algorithm includes a collaborative filtering algorithm and a content recommendation algorithm; the resource recommendation model is constructed by a deep neural network; The display terminal is used to visually display the resource index and the corresponding pushed content.
2. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 1 is characterized in that: The data acquisition port includes an RS-485 interface connected to the Internet and a LoRa gateway; wherein the LoRa gateway uses the LoRa protocol self-organizing network communication to transmit data.
3. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 1 is characterized in that: The feature extraction unit specifically comprises: A preprocessing module is used to preprocess and filter the target historical data to obtain valid data; the preprocessing includes cleaning, conversion and normalization; the data filtering uses a screening algorithm or a Bloom filter to remove duplicate and invalid data; the screening algorithm includes attribute screening, relationship screening and rule screening; The feature calculation module is used to extract features from the valid data using the TF-IDF algorithm to obtain corresponding feature vectors, and to aggregate the feature vectors to obtain target focus features.
4. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 3 is characterized in that: The preprocessing module also includes an algorithm storage submodule; the algorithm storage submodule stores a screening algorithm and a Bloom filter; wherein the attribute screening includes keyword matching and numerical range screening, the relationship screening includes social relationship screening and reference relationship screening, and the rule screening includes business rule screening and data feature rule screening.
5. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 1 is characterized in that: The index building unit specifically includes: A resource feature extraction module is used to extract metadata from the loaded digital teaching resources; the metadata includes the resource title, author, abstract, keywords, subject classification and difficulty level; The association matching module is used to establish a resource index according to the target focus feature and the metadata.
6. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 1 is characterized in that: The resource recommendation unit specifically includes: A model building module, used for performing model training based on the hybrid recommendation algorithm and the long short-term memory network, and determining the trained model as a resource recommendation model; The recommendation module is used to push content using the resource index and the resource recommendation model.
7. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 6 is characterized in that: The model building module specifically includes: A training data acquisition submodule is used to acquire training data; A model building submodule, used to build a pre-trained model based on the hybrid recommendation algorithm and the long short-term memory network; The model training submodule is used to input the training data into the pre-trained model, train the pre-trained model with a gradient descent strategy, and determine the trained model as a resource recommendation model.
8. The digital teaching resource recommendation and optimization system based on artificial intelligence according to claim 1 is characterized in that: The display terminal includes at least one of a personal computer, a notebook computer, a smart phone, a tablet computer and a portable wearable device.