CN117057519B - Teaching information demonstration method based on convolutional neural network and computer equipment - Google Patents
Teaching information demonstration method based on convolutional neural network and computer equipment Download PDFInfo
- Publication number
- CN117057519B CN117057519B CN202311322465.4A CN202311322465A CN117057519B CN 117057519 B CN117057519 B CN 117057519B CN 202311322465 A CN202311322465 A CN 202311322465A CN 117057519 B CN117057519 B CN 117057519B
- Authority
- CN
- China
- Prior art keywords
- student group
- student
- offline
- time
- real
- 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 32
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 8
- 230000001364 causal effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 7
- 238000009877 rendering Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses a teaching information demonstration method and computer equipment based on a convolutional neural network. One embodiment of the method comprises the following steps: inputting the real-time student group characteristic representation and the offline student group characteristic representation into a student group classification neural network model to obtain first student group classification information; inputting the offline student group characteristic representation, the pseudo real-time student group characteristic representation and the pseudo offline student group characteristic representation into a student group classification neural network model to obtain second student group classification information; generating student population classification information of a target student population based on the first student population classification information and the second student population classification information; and selecting teaching information pages corresponding to the student group classification information from the teaching information page set according to the student group classification information. The embodiment is convenient for demonstrating teaching information meeting the requirements according to student classification information.
Description
Technical Field
The embodiment of the disclosure relates to the field of computers, in particular to a teaching information demonstration method based on a convolutional neural network and computer equipment.
Background
With the increasing popularity of intelligent teaching, students gradually acquire knowledge through teaching pages. At present, when demonstrating teaching information to students, the following modes are generally adopted: the teaching information page is established in advance and is directly displayed to students. However, when demonstrating instructional information to students, there are often the following problems: the categories of the student groups are not considered, so that the displayed teaching information page does not meet the demands of the student groups; when building a tutorial information page, it is often necessary to read resources locally, there is some I/O Input/Output (I/O) consumption, affecting performance and experience.
Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a teaching information demonstration method, a computer device and a computer-readable storage medium based on convolutional neural network to solve the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a teaching information demonstration method based on a convolutional neural network, the method including: respectively generating a real-time student group characteristic representation and an offline student group characteristic representation of a target student group; inputting the real-time student group characteristic representation and the offline student group characteristic representation into a pre-trained student group classification neural network model to obtain first student group classification information, wherein the student group classification neural network model comprises: a real-time student group classification sub-network, an offline student group classification sub-network and a converged student group classification sub-network; inputting the offline student group characteristic representation, the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information; generating student group classification information of the target student group based on the first student group classification information and the second student group classification information; according to the student group classification information, a teaching information page corresponding to the student group classification information is selected from a preset teaching information page set to serve as a target teaching information page; and sending the target teaching information page to an associated teaching information demonstration terminal to demonstrate.
In a second aspect, the present disclosure also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements a method as described in any of the implementations of the first aspect.
In a third aspect, the present disclosure also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method as described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following advantageous effects: according to the teaching information demonstration method based on the convolutional neural network, disclosed by some embodiments, the off-line characteristic deviation is removed by introducing the pseudo real-time characteristic representation and the pseudo off-line characteristic representation, so that the accuracy of the generated student classification information is improved. Therefore, the teaching information meeting the requirements can be conveniently demonstrated according to the student classification information. First, a real-time student population feature representation and an offline student population feature representation of a target student population are generated, respectively. And secondly, inputting the real-time student group characteristic representation and the offline student group characteristic representation into a pre-trained student group classification neural network model to obtain first student group classification information. The student group classification neural network model comprises: a real-time student group classification sub-network, an offline student group classification sub-network and a converged student group classification sub-network. And then, inputting the offline student group characteristic representation, the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information. Then, based on the first student group classification information and the second student group classification information, student group classification information of the target student group is generated. Therefore, the teaching information meeting the demands of students can be conveniently selected according to the student group classification information. And then, according to the student group classification information, selecting a teaching information page corresponding to the student group classification information from a preset teaching information page set as a target teaching information page. And finally, the target teaching information page is sent to an associated teaching information demonstration terminal to be demonstrated. Therefore, by introducing the pseudo real-time characteristic representation and the pseudo offline characteristic representation, the offline characteristic deviation is removed, and the accuracy of the generated student classification information is improved. Therefore, the teaching information meeting the requirements can be conveniently demonstrated according to the student classification information.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flow chart of some embodiments of a convolutional neural network-based teaching information presentation method in accordance with the present disclosure;
fig. 2 is a schematic block diagram of a computer device provided in an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a flow chart of some embodiments of a convolutional neural network-based teaching information presentation method in accordance with the present disclosure. A flow 100 of some embodiments of a convolutional neural network-based teaching information presentation method in accordance with the present disclosure is shown. The teaching information demonstration method based on the convolutional neural network comprises the following steps:
step 101, respectively generating a real-time student group characteristic representation and an offline student group characteristic representation of a target student group.
In some embodiments, an executing body (e.g., computing device) of the teaching information presentation based on the convolutional neural network may generate a real-time student population feature representation and an offline student population feature representation, respectively, of the target student population. Wherein the real-time student population feature representation may be used to characterize the real-time feature. The offline student population feature representation may be used to characterize offline features. For example, the real-time features and the offline features may be input into an embedding layer or a multi-layer perceptron (MLP, multilayer Perceptron), respectively, to obtain a real-time student group feature table and an offline student group feature representation. Wherein the real-time features, i.e. features that change over time, include related features that are within a short period of time up to the request time. Wherein the short period of time is typically on the order of hours or days, e.g. 24 hours, relative to the long period of time corresponding to the offline feature. The real-time feature may be, for example, the number of times the student population views the instructional information within 24 hours of the time of the request. Offline features are features that generally do not change in real-time over time, including related features that are over a long period of time up to the day prior to the requested time. Wherein the long period of time may be on the order of days or months, the offline feature may be, for example, the number/duration of average viewing of certain instructional information within 1 month. The target student population may be individual students at a certain level currently learning a certain discipline.
Step 102, inputting the real-time student group characteristic representation and the offline student group characteristic representation into a pre-trained student group classification neural network model to obtain first student group classification information.
In some embodiments, the executing entity may input the real-time student group feature representation and the offline student group feature representation into a pre-trained student group classification neural network model to obtain the first student group classification information. The student group classification neural network model comprises: a real-time student group classification sub-network, an offline student group classification sub-network and a converged student group classification sub-network. For example, the three sub-networks may be various classification networks, e.g., may include a Softmax layer to enable generation of corresponding sub-classification results from input data. Further, after the three sub-classification results are fused, first student group classification information is obtained. In addition, the fused student population classification sub-network is used for fusing input data, and may include a multi-layer perceptron (MLP) or a recurrent neural network for feature fusion.
In an actual application scenario, the execution subject may input the real-time student group feature representation and the offline student group feature representation into a pre-trained student group classification neural network model to obtain first student group classification information by:
first, inputting the real-time student group characteristic representation into the real-time student group classification sub-network to obtain a first real-time classification result.
Secondly, inputting the offline student group characteristic representation into the offline student group classification sub-network to obtain a first offline classification result.
Thirdly, inputting the real-time student group characteristic representation and the offline student group characteristic representation into the fused student group classification sub-network to obtain a first fused classification result.
Fourth, the first real-time classification result, the first fusion classification result and the first offline classification result are fused to obtain first student group classification information.
And step 103, inputting the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information.
In some embodiments, the executing entity may input the pseudo real-time student group feature representation corresponding to the real-time student group feature representation and the pseudo offline student group feature representation corresponding to the offline student group feature representation into the student group classification neural network model to obtain the second student group classification information. Wherein the pseudo real-time student group feature representation is not a real-time feature, and similarly the pseudo offline student group feature representation is not a real offline feature. For example, the pseudo real-time student population feature representation or pseudo offline student population feature representation may be a random number. In the process, the real-time characteristics are replaced by the pseudo real-time student group characteristic representation, and the real offline characteristics are replaced by the pseudo offline student group characteristic representation, so that the obtained second student group classification information can represent natural direct causal effects of the offline characteristics.
In an actual application scenario, the execution subject may input the pseudo real-time student group feature representation corresponding to the real-time student group feature representation and the pseudo offline student group feature representation corresponding to the offline student group feature representation into the student group classification neural network model to obtain second student group classification information by:
first, generating a pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and a pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation respectively.
Wherein the pseudo real-time student group feature representation corresponding to the real-time student group feature representation and the pseudo offline student group feature representation corresponding to the offline student group feature representation may be generated by the sub-steps of:
and (2) a sub-step 1, obtaining a student group training sample set. Wherein, the student group training sample in the student group training sample set comprises: sample real-time features, sample offline features and sample student population classification information.
And 2, determining average values of sample real-time characteristics corresponding to each student group training sample in the student group training sample set as pseudo real-time student group characteristic representation.
And 3, determining average values of sample offline features corresponding to the student group training samples in the student group training sample set as pseudo offline student group feature representations.
In an actual application scene, the real-time features and the offline features are replaced by adopting the average value of each student group training sample in the student group training sample set, so that the offline feature deviation can be removed in the prediction process, meanwhile, the credibility of the pseudo real-time feature representation and the pseudo offline feature representation is increased, errors caused by mismatching of a random value with an actual situation are avoided, and the accuracy of the generated student group classification information is improved.
Secondly, inputting the pseudo real-time student group characteristic representation into the real-time student group classification sub-network to obtain a second pseudo real-time student group classification result.
Thirdly, inputting the pseudo real-time student group characteristic representation and the pseudo offline student group characteristic representation into the fused student group classification sub-network to obtain a second fused classification result.
Fourth, the pseudo offline student group characteristic representation is input into the offline student group classification sub-network, and a second pseudo offline student group classification result is obtained.
Fifthly, fusing the second pseudo real-time student group classification result, the second fusion classification result and the second pseudo offline student group classification result to obtain second student group classification information.
Step 104, generating student group classification information of the target student group based on the first student group classification information and the second student group classification information.
In some embodiments, the executive may generate the student group classification information of the target student group based on the first student group classification information and the second student group classification information. Wherein, the first student group classification information is obtained through the real-time student group characteristic representation and the offline student group characteristic representation of the target student group, so that the total causal effect of the real-time characteristic representation and the offline characteristic representation of the target student group can be represented. The second student group classification information can represent natural direct causal effect of offline features, and the offline feature deviation can be removed through differencing, so that the accuracy of the generated student group classification information is improved. The first student group classification information and the second student group classification information can be weighted and fused, for example, differenced, in a weighted and summation mode, so that the student group classification information is obtained. The student population classification information may represent a specific category of student population. The student group classification information may represent the grade, class, and current discipline of the student group.
Optionally, for each production tutorial information page instruction, the following processing steps are performed:
and a first processing step, receiving page update data corresponding to the instruction for making the teaching information page, and creating a primary container. The instruction for making the teaching information page may be an instruction for packaging and combining a plurality of teaching information sub-pages. In particular, the authoring tutorial information page instructions may be requests for encapsulation of multiple functions. In practice, the plurality of functions includes, but is not limited to, at least one of: page type judging function, H5 data refreshing function and background login opening function. For example, the produce teaching information page instruction may be a Node service request. The page update data may be request data for a subsequent page update. For example, the page update data may include: attribute data corresponding to custom data attributes (data attributes), functional data, data generated by native root guides, and data generated by top tag fields. The native container may be a container for exposing HTML pages. For example, the primordial container may be, but is not limited to, one of the following: the activity component corresponds to a container and the ViewController corresponds to a container.
And a second processing step of acquiring a webpage container corresponding to the target teaching information webpage link. The target tutorial information web page link may be a link (URL, uniform Resource Locator) of a web page to be opened. Wherein the web page container may be a web container. The web page container may be a container in which a rendering result of a web page portion corresponding to a web page link of the target teaching information is stored in advance. For example, the content stored by the web page container may include: the webview container, offline resources required in the offline package.
Wherein the second processing step may include:
1. a browser kernel component is obtained. The browser kernel component may be a Webkit component.
2. And taking the target teaching information webpage link as input, and executing off-screen loading for offline resources according to the callable interface corresponding to the browser kernel component to obtain loading content. The callable interface may be an interface to load resources off-screen. For example, the callable interface may be an API loadUrl provided by webkit. The offline resource may be an offline package that is pre-stored locally. For example, offline resources include, but are not limited to, at least one of: JS resources, CSS resources, HTML resources. The loading content may be off-screen loaded resource content. In practice, the loading content includes the required portion of the offline resources. For example, the above target teaching information web page link is used as input, and the API loadUrl provided by webkit is called to execute off-screen loading of the offline resource, so as to obtain the loading content.
3. A web page container for the loaded content is generated. The content stored in the webpage container comprises the loading content. The loading content includes: and the source file execution result and the service interface preloading information which correspond to the aging information and meet the preset conditions. The preset condition may be a source file execution result with the aging information corresponding to a size greater than the target value. For example, the target value may be 0.1 milliseconds. In practice, the source file execution results may be code execution results. The source file execution result may include: and (3) carrying out results on source files created by the commonly built floors such as feeds, carrying out results on source files created by the initial page frame, and carrying out results on source files of the sharing component. The service interface preloading information may be a result of preloading the service interface.
And a third processing step of generating a mixed layout page according to the page update data, the native container and the web page container. The hybrid layout page may be a rendered page for a portion of the page resources. The mixed layout page may be a page after the native page and the H5 page are mixed layout. For example, the Hybrid layout page may be a Hybrid page.
Wherein the third processing step may include:
1. and according to the page update data, adjusting page layout information corresponding to the original container to obtain an adjusted original container. Wherein the page layout information may be page element information for a subsequent responsible page layout. In practice, the page layout information may include: native bottom navigation information, top tab information, page immersive information. The page layout information corresponding to the native container can be adjusted according to the expected page layout information included in the page update data, so as to obtain the adjusted native container.
2. And embedding the webpage container into the adjusted original container to obtain an embedded container.
3. And generating a mixed layout page corresponding to the embedded container.
And a fourth processing step, carrying out page local refreshing on the mixed layout page to generate a rendering page corresponding to the target teaching information webpage link as a teaching information page.
Wherein the fourth processing step may include:
1. and sending a predefined teaching information event to an associated teaching information page development processing end, so that the teaching information page development processing end performs page local rendering on the mixed layout page to obtain a rendering result. The teaching information page development processing end can be an H5 processing end. For example, the teaching information page development processing end may be a terminal that processes a target teaching information page. For example, the instructional information event may be a custom event of xRenderReady.
2. And executing the bridge logic aiming at the target bridge mode information, and generating a rendering page aiming at the rendering result as a teaching information page. The target bridge mode information may be mode information corresponding to a JS bridge mode. The bridge logic may be JS (JavaScript) bridge logic. The target bridge mode information may be locally cached information.
For the "when building a tutorial information page" mentioned in the background, it is usually necessary to read resources locally, there is a certain I/O Input/Output (Input/Output) consumption, which affects performance and experience. ". The method can be solved by the following steps: firstly, receiving page update data corresponding to the instruction of the page for producing the teaching information, and creating a primary container. Therefore, a plurality of local hypertext transfer protocol (Hypertext Transfer Protocol, HTTP) requests of the client are packaged to obtain the instruction for making the teaching information page, and a unified interface can be used for returning page update data, so that time is shortened, and user experience is improved. In addition, page load time may be further reduced for synchronous execution of receiving page update data and creating a native container. Then, a web page container corresponding to the target teaching information web page link is acquired. Therefore, the generation time of the webpage container can be greatly shortened by the way of generating the webpage container in advance, and the page loading time is shortened. And generating a mixed layout page according to the page update data, the native container and the webpage container. And finally, carrying out page local refreshing on the mixed layout page to generate a rendering page corresponding to the target teaching information webpage link as a teaching information page. Therefore, the problem of timeliness can be effectively solved and the page content can be fully represented by carrying out page partial refreshing on the mixed layout page. In summary, by making the instruction for the instructional information page not only shortens the time, but also further reduces the page loading time for the synchronous execution of receiving the page update data and creating the proto-container. In addition, by pre-generating the web page container, the page loading time can be reduced. Thus, the corresponding page can be efficiently generated.
Step 105, according to the student group classification information, selecting a teaching information page corresponding to the student group classification information from a preset teaching information page set as a target teaching information page.
In some embodiments, the executing body may select, according to the student group classification information, a teaching information page corresponding to the student group classification information from a preset teaching information page set as a target teaching information page. For example, each teaching information page corresponds to a discipline category. The teaching information page may contain teaching information of the subject to be learned. The teaching information page which is the same as the subject category represented by the student group classification information can be selected from the preset teaching information page set as the target teaching information page.
And step 106, the target teaching information page is sent to an associated teaching information demonstration terminal to be demonstrated.
In some embodiments, the executing body may send the target teaching information page to an associated teaching information presentation terminal to perform presentation. The teaching information presentation terminal may be a display terminal having a display function.
Fig. 2 is a schematic block diagram of a structure of a computer device according to an embodiment of the disclosure. The computer device may be a terminal.
As shown in fig. 2, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program comprises program instructions which, when executed, cause the processor to perform any of a number of teaching information presentation methods based on convolutional neural networks.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a non-volatile storage medium, which when executed by a processor, causes the processor to perform any one of a number of teaching information presentation methods based on convolutional neural networks.
The network interface is used for network communication such as transmitting assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 2 is merely a block diagram of some of the architecture relevant to the disclosed aspects and is not limiting of the computer device to which the disclosed aspects apply, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of: respectively generating a real-time student group characteristic representation and an offline student group characteristic representation of a target student group; inputting the real-time student group characteristic representation and the offline student group characteristic representation into a pre-trained student group classification neural network model to obtain first student group classification information, wherein the student group classification neural network model comprises: a real-time student group classification sub-network, an offline student group classification sub-network and a converged student group classification sub-network; inputting the offline student group characteristic representation, the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information; generating student group classification information of the target student group based on the first student group classification information and the second student group classification information; according to the student group classification information, a teaching information page corresponding to the student group classification information is selected from a preset teaching information page set to serve as a target teaching information page; and sending the target teaching information page to an associated teaching information demonstration terminal to demonstrate.
Embodiments of the present disclosure also provide a computer readable storage medium having a computer program stored thereon, where the computer program includes program instructions, and a method implemented when the program instructions are executed may refer to various embodiments of the teaching information demonstration method based on a convolutional neural network of the present disclosure.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present disclosure are merely for description and do not represent advantages or disadvantages of the embodiments. While the invention has been described with reference to certain preferred embodiments, it will be apparent to one skilled in the art that various changes and substitutions can be made herein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (3)
1. The teaching information demonstration method based on the convolutional neural network is characterized by comprising the following steps of:
respectively generating a real-time student group characteristic representation and an offline student group characteristic representation of a target student group, wherein the real-time student group characteristic representation is used for representing the real-time characteristic, namely, the characteristic which is changed continuously along with time, including the related characteristic which is cut off to a short time period of the request time, and the offline student group characteristic representation is used for representing the offline characteristic, wherein the offline characteristic is the characteristic which is not changed along with time generally and includes the related characteristic which is cut off to a long time period of the previous day of the request time;
inputting the real-time student group characteristic representation and the offline student group characteristic representation into a pre-trained student group classification neural network model to obtain first student group classification information, wherein the student group classification neural network model comprises: the system comprises a real-time student group classification sub-network, an offline student group classification sub-network and a fusion student group classification sub-network, wherein the three sub-networks are classification networks and comprise Softmax layers so as to generate corresponding sub-classification results according to input data, and the fusion student group classification sub-network is used for fusing the input data and comprises a multi-layer perceptron for performing feature fusion;
inputting the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information, wherein the pseudo real-time student group characteristic representation is not a real-time characteristic, the pseudo offline student group characteristic representation is not a real offline characteristic, the real-time characteristic is replaced by the pseudo real-time student group characteristic representation, and the real offline characteristic is replaced by the pseudo offline student group characteristic representation, so that the obtained second student group classification information represents natural direct causal effect of the offline characteristic;
generating student population classification information of the target student population based on the first student population classification information and the second student population classification information;
according to the student group classification information, a teaching information page corresponding to the student group classification information is selected from a preset teaching information page set to serve as a target teaching information page;
the target teaching information page is sent to an associated teaching information demonstration terminal to be demonstrated;
the step of inputting the pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and the pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation into the student group classification neural network model to obtain second student group classification information comprises the following steps:
generating a pseudo real-time student group characteristic representation corresponding to the real-time student group characteristic representation and a pseudo offline student group characteristic representation corresponding to the offline student group characteristic representation respectively;
inputting the pseudo real-time student group characteristic representation into the real-time student group classification sub-network to obtain a second pseudo real-time student group classification result;
inputting the pseudo real-time student group characteristic representation and the pseudo offline student group characteristic representation into the fused student group classification sub-network to obtain a second fused classification result;
inputting the pseudo offline student group characteristic representation into the offline student group classification sub-network to obtain a second pseudo offline student group classification result;
fusing the second pseudo real-time student group classification result, the second fusion classification result and the second pseudo offline student group classification result to obtain second student group classification information;
wherein the generating the pseudo real-time student group feature representation corresponding to the real-time student group feature representation and the pseudo offline student group feature representation corresponding to the offline student group feature representation respectively includes:
obtaining a student population training sample set, wherein the student population training sample in the student population training sample set comprises: sample real-time characteristics, sample offline characteristics and sample student population classification information;
determining the average value of sample real-time characteristics corresponding to each student group training sample in the student group training sample set as pseudo real-time student group characteristic representation;
determining average values of sample offline features respectively corresponding to all student group training samples in the student group training sample set as pseudo offline student group feature representations;
wherein generating student population classification information for the target student population comprises:
and carrying out weighted fusion on the first student group classification information and the second student group classification information in a weighted summation mode to obtain student group classification information, wherein the student group classification information represents a specific class of a student group, the student group classification information represents a grade and a class of the student group, the current school is a subject, and the first student group classification information is obtained through real-time student group feature representation and offline student group feature representation of a target student group and represents the total causal effect of the real-time feature representation and the offline feature representation of the target student group.
2. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of the method of claim 1.
3. A computer readable storage medium, wherein the computer readable storage medium has stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311322465.4A CN117057519B (en) | 2023-10-13 | 2023-10-13 | Teaching information demonstration method based on convolutional neural network and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311322465.4A CN117057519B (en) | 2023-10-13 | 2023-10-13 | Teaching information demonstration method based on convolutional neural network and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117057519A CN117057519A (en) | 2023-11-14 |
| CN117057519B true CN117057519B (en) | 2024-01-23 |
Family
ID=88667817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311322465.4A Active CN117057519B (en) | 2023-10-13 | 2023-10-13 | Teaching information demonstration method based on convolutional neural network and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057519B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100060555A (en) * | 2008-11-27 | 2010-06-07 | 상지대학교산학협력단 | Virtual university using rfid technology and artificial intelligence |
| CN111540244A (en) * | 2020-05-11 | 2020-08-14 | 镇江纵陌阡横信息科技有限公司 | Multi-terminal online teaching system based on big data analysis |
| CN112085099A (en) * | 2020-09-09 | 2020-12-15 | 西南大学 | Distributed student clustering integration method and system |
| CN113988494A (en) * | 2020-07-27 | 2022-01-28 | 上海萧傲文化传播有限公司 | Online education system |
| CN114912518A (en) * | 2022-04-27 | 2022-08-16 | 浙江大学 | Reinforced learning grouping method, device and medium based on user group typical characteristics |
-
2023
- 2023-10-13 CN CN202311322465.4A patent/CN117057519B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100060555A (en) * | 2008-11-27 | 2010-06-07 | 상지대학교산학협력단 | Virtual university using rfid technology and artificial intelligence |
| CN111540244A (en) * | 2020-05-11 | 2020-08-14 | 镇江纵陌阡横信息科技有限公司 | Multi-terminal online teaching system based on big data analysis |
| CN113988494A (en) * | 2020-07-27 | 2022-01-28 | 上海萧傲文化传播有限公司 | Online education system |
| CN112085099A (en) * | 2020-09-09 | 2020-12-15 | 西南大学 | Distributed student clustering integration method and system |
| CN114912518A (en) * | 2022-04-27 | 2022-08-16 | 浙江大学 | Reinforced learning grouping method, device and medium based on user group typical characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117057519A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101512483B (en) | Dynamically generating customized user interfaces | |
| US8156419B2 (en) | Intelligent preloads of views and asynchronous loading of models using the MVC design pattern | |
| CN107229633A (en) | Static page generation method, Web access method and device | |
| US20060068367A1 (en) | System and method for content management in a distributed learning system | |
| AU2014101627A4 (en) | Computer-implemented frameworks and methodologies for generating, delivering and managing adaptive tutorials | |
| CN107832275A (en) | The generation method of intelligent Contract ID, apparatus and system in block chain | |
| AU2015101951A4 (en) | Computer-implemented frameworks and methodologies for enabling adaptive functionality based on a knowledge model | |
| CN111459501B (en) | SVG-based Web configuration picture storage and display system, method and medium | |
| CN106033361A (en) | Method and device for showing application page, and method and device for updating application page data | |
| US20140040363A1 (en) | System and Method for Content Storage and Retrieval | |
| JP2021009665A (en) | Method, apparatus, and device for generating file, and storage medium | |
| US20040205488A1 (en) | Active web page for editing with any browser | |
| CN108763416A (en) | Multimedia file methods of exhibiting, device, computer equipment and storage medium | |
| CN100336031C (en) | A system and method for replaying a predefined path through the internet | |
| CA3074436A1 (en) | Rules-based automated chart description system | |
| CN117057519B (en) | Teaching information demonstration method based on convolutional neural network and computer equipment | |
| US11314840B2 (en) | Thin-layer webpage cloning for off-line demonstration | |
| Lonka | Improving the Initial Rendering Performance of React Applications Through Contemporary Rendering Approaches | |
| US11553029B2 (en) | Method and apparatus for HTML construction using the widget paradigm | |
| CN110618811B (en) | Information presentation method and device | |
| US20130073582A1 (en) | Web search results with live data | |
| US20230177631A1 (en) | Automatically enhancing content items through identifying relationships | |
| CN113282291A (en) | Method, device and equipment for generating small program and storage medium | |
| CN110784543B (en) | Application widget module and access and push method thereof | |
| Yu et al. | Using bayesian networks to implement adaptivity in mobile learning |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 806, 8th Floor, No. 6 Haidian Middle Street, Haidian District, Beijing, 100193 Applicant after: Beijing Layout Future Technology Development Co.,Ltd. Address before: Inside Beijing Diplomatic Language and Culture Center, No. 7 Sanlitun North Street, Chaoyang District, Beijing, 100027 Applicant before: Beijing layout Future Education Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |