CN117131902A - Student intention recognition method based on intelligent teaching and computer equipment - Google Patents
Student intention recognition method based on intelligent teaching and computer equipment Download PDFInfo
- Publication number
- CN117131902A CN117131902A CN202311398104.8A CN202311398104A CN117131902A CN 117131902 A CN117131902 A CN 117131902A CN 202311398104 A CN202311398104 A CN 202311398104A CN 117131902 A CN117131902 A CN 117131902A
- Authority
- CN
- China
- Prior art keywords
- information
- teaching
- student
- click
- teaching page
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000012552 review Methods 0.000 claims description 50
- 230000006399 behavior Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims 1
- 239000013598 vector Substances 0.000 description 17
- 230000008569 process Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure discloses a student intention recognition method and computer equipment based on intelligent teaching. One embodiment of the method comprises the following steps: inputting real-time click data of the teaching page and a history click data sequence of the teaching page into a word embedding network included in the student intention recognition model; inputting the teaching page history click word embedded information sequence into a high-dimensional click feature extraction network to obtain a teaching page high-dimensional click behavior feature information sequence; inputting the high-dimensional click behavior characteristic information sequence of the teaching page into a history click integral characteristic extraction network of the teaching page; inputting the history click integral feature information of the teaching page and the real-time click word embedded information of the teaching page into a feature information cross processing network; and generating student intention identification information according to the teaching page characteristic intersection information. This embodiment shortens the recognition time of student intention. And relevant knowledge information is pushed conveniently according to student intention.
Description
Technical Field
The embodiment of the disclosure relates to the field of computers, in particular to a student intention recognition method based on intelligent teaching and computer equipment.
Background
With the increasing popularity of intelligent teaching, students gradually acquire knowledge through teaching pages. At present, when acquiring knowledge through a teaching page, a teacher usually needs to know learning interests of students one by one to know learning intentions of the students. However, knowing the learning interests of students one by one, there are often the following technical problems: learning interests of students one by one, more time is required to be consumed, and learning progress of the students is influenced; when learning knowledge information is pushed to students, the knowledge information cannot be pushed according to the preference of the students, and pushing resources are wasted.
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 student intention recognition method, a computer device, and a computer-readable storage medium based on intelligent teaching to solve the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a student intention recognition method based on intelligent teaching, the method comprising: collecting real-time click data of a teaching page and a corresponding history click data sequence of the teaching page; inputting the teaching page real-time click data and the teaching page historical click data sequence into a word embedding network included in a predetermined student intention recognition model to obtain teaching page real-time click word embedding information and a teaching page historical click word embedding information sequence, wherein the student intention recognition model further comprises: the high-dimensional click feature extraction network, the teaching page history click integral feature extraction network and the feature information cross processing network; inputting the history click word embedded information sequence of the teaching page into the high-dimensional click feature extraction network to obtain a high-dimensional click behavior feature information sequence of the teaching page; inputting the high-dimensional click behavior feature information sequence of the teaching page into the history click integral feature extraction network of the teaching page to generate history click integral feature information of the teaching page; inputting the history click integral feature information of the teaching page and the real-time click word embedded information of the teaching page into the feature information cross processing network to obtain feature cross information of the teaching page; and generating student intention identification information according to the teaching page characteristic intersection information.
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 student intention recognition method based on intelligent teaching, which is disclosed by the embodiment of the invention, the student intention can be recognized according to the click data of the student on the teaching page. Thus, the recognition time of the intention of the student is shortened. And relevant knowledge information is pushed conveniently according to student intention. Firstly, collecting real-time click data of a teaching page and a corresponding history click data sequence of the teaching page. And secondly, inputting the real-time click data of the teaching page and the historical click data sequence of the teaching page into a word embedding network included in a predetermined student intention recognition model to obtain real-time click word embedding information of the teaching page and a historical click word embedding information sequence of the teaching page. Wherein, the student intention recognition model further comprises: the high-dimensional click feature extraction network and the teaching page history click integral feature extraction network and the feature information cross processing network. Therefore, through the word embedding network, the teaching page real-time click data and the teaching page historical click data sequence can be converted into a word embedding form so as to facilitate subsequent feature extraction. And then, inputting the history click word embedded information sequence of the teaching page into the high-dimensional click feature extraction network to obtain a high-dimensional click behavior feature information sequence of the teaching page. Therefore, through the high-dimensional click feature extraction network, high-dimensional click feature information aiming at the teaching page historical click data sequence can be accurately obtained, so that subsequent student intention identification information generation is more accurate. And then, inputting the high-dimensional click behavior characteristic information sequence of the teaching page into the history click integral characteristic extraction network of the teaching page so as to generate history click integral characteristic information of the teaching page. Therefore, through the teaching page history click integral feature extraction network, integral feature information aiming at a teaching page high-dimensional click behavior feature information sequence can be accurately generated, important buried point feature information influencing student intention recognition is obtained, and subsequent student intention recognition information generation is more accurate. And then, inputting the history clicking integral characteristic information of the teaching page and the real-time clicking word embedded information of the teaching page into the characteristic information cross processing network to obtain the characteristic cross information of the teaching page. And finally, generating student intention identification information according to the teaching page characteristic intersection information. Therefore, the intention of the student can be identified according to the click data of the student on the teaching page. Thus, the recognition time of the intention of the student is shortened. And relevant knowledge information is pushed conveniently according to student intention.
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 student intent recognition method based on intelligent teaching according to 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 student intent recognition method based on intelligent teaching according to the present disclosure. A flow 100 of some embodiments of a student intent recognition method based on intelligent teaching according to the present disclosure is shown. The student intention recognition method based on intelligent teaching comprises the following steps:
and step 101, collecting real-time click data of the teaching page and a corresponding history click data sequence of the teaching page.
In some embodiments, an executive (e.g., computing device) of student intent recognition based on intelligent teaching may collect teaching page real-time click data and corresponding teaching page historical click data sequences by way of a wired or wireless connection. The teaching page real-time click data may be real-time click data corresponding to a student when clicking a target teaching page. Specifically, the real-time click data may include: real-time buried point identification, real-time teaching page identification, real-time knowledge class identification and real-time search word identification. The real-time knowledge class identification may represent a discipline section classification of the knowledge. The teaching page historical click data sequence may be a historical click data sequence corresponding to a student for a preset period of time before clicking on the target teaching page. For example, the teaching page history click data sequence may be a student's click data set within 12 hours before clicking on the target teaching page. For example, clicking on the dataset may include: buried point identification of student click behaviors, teaching page identification, knowledge class identification, search word identification and click time characteristic data.
Optionally, a teaching page real-time click data set and a student intention information set are acquired.
In some embodiments, the executing entity may obtain the teaching page real-time click data set and the student intention information set. Wherein, teaching page real-time click data includes: teaching page real-time click data, a corresponding teaching page historical click data sequence and a corresponding student attribute information set. The real-time click data of one teaching page corresponds to one student intention information.
Optionally, the teaching page real-time clicking data is selected from the teaching page real-time clicking data set and used as target teaching page real-time clicking data, and the following training steps are executed:
firstly, inputting teaching page real-time click data and teaching page historical click data sequences which are included in the target teaching page real-time click data into an initial word embedding network which is included in an initial student intention recognition model to obtain target teaching page real-time click word embedding information and target teaching page historical click word embedding information sequences. The initial student intent recognition model may be an untrained completed student intent recognition model. The initial word embedding network may be an untrained word embedding network.
Secondly, the target teaching page history click word embedded information sequence is input into a high-dimensional click feature extraction network included in the initial student intention recognition model, and a target teaching page high-dimensional click behavior feature information sequence is obtained. The high-dimensional click feature extraction network included in the initial student intent recognition model may be an untrained high-dimensional click behavior feature extraction network.
Thirdly, inputting the high-dimensional click behavior characteristic information sequence of the target teaching page into an initial teaching page historical click integral characteristic extraction network included in the initial student intention recognition model to generate target teaching page historical click integral characteristic information. The initial teaching page history click global feature extraction network may be an untrained teaching page history click global feature extraction network.
Fourth, the history clicking integral feature information of the target teaching page and the real-time clicking word embedded information of the target teaching page are input into an initial feature information cross processing network included in the initial student intention recognition model, and feature cross information of the target teaching page is obtained. The initial feature information cross-processing network may be an untrained feature information cross-processing network.
Fifthly, inputting the student attribute information set included in the real-time click data of the target teaching page into the initial word embedding network to obtain the target student attribute characteristic information set.
Sixthly, carrying out information fusion processing on the target teaching page feature intersection information and the target student attribute feature information set to obtain target fusion feature information.
Seventh, the target fusion feature information is input to an initial intention recognition information output layer included in the initial student intention recognition model to output initial student intention recognition information. The initial intention recognition information output layer may be an untrained intention recognition information output layer.
Eighth, generating student intention loss information according to student intention information corresponding to the target teaching page real-time click data and the initial student intention identification information. And determining the student intention loss information between the student intention information corresponding to the target teaching page real-time click data and the initial student intention identification information by using a cross entropy loss function.
Ninth, in response to determining that the student intention loss information satisfies a preset loss condition, the initial student intention recognition model is determined as a trained student intention recognition model. The preset loss condition may refer to: the value of the student intention loss information representation is larger than or equal to a preset threshold value.
Optionally, in response to determining that the student intention loss information does not meet a preset loss condition, updating model parameters of the initial student intention recognition model to generate an updated student intention recognition model as the initial student intention recognition model, and re-selecting target teaching page real-time click data from the teaching page real-time click data set, and re-executing the training step.
In some embodiments, the executing entity may update model parameters of the initial student intention recognition model in response to determining that the student intention loss information does not satisfy a preset loss condition, to generate an updated student intention recognition model, and re-select target teaching page real-time click data from the teaching page real-time click data set as the initial student intention recognition model, and re-execute the training step.
For the background technology, when learning knowledge information is pushed to students, the knowledge information cannot be pushed according to the preference of the students, so that pushing resources are wasted. ". The method can be solved by the following steps: firstly, inputting teaching page real-time click data and teaching page historical click data sequences included in the target teaching page real-time click data into an initial word embedding network included in an initial student intention recognition model to obtain target teaching page real-time click word embedding information and target teaching page historical click word embedding information sequences. And secondly, inputting the target teaching page history click word embedded information sequence into a high-dimensional click feature extraction network included in the initial student intention recognition model to obtain a target teaching page high-dimensional click behavior feature information sequence. And then, inputting the high-dimensional click behavior characteristic information sequence of the target teaching page into a teaching page historical click integral characteristic extraction network included in the initial student intention recognition model to generate target teaching page historical click integral characteristic information. And then, inputting the historical click integral feature information of the target teaching page and the real-time click word embedded information of the target teaching page into an initial feature information cross processing network included in the initial student intention recognition model to obtain feature cross information of the target teaching page. Then, inputting the student attribute information set included in the real-time click data of the target teaching page into the initial word embedding network to obtain a target student attribute characteristic information set; and carrying out information fusion processing on the target teaching page feature intersection information and the target student attribute feature information set to obtain target fusion feature information. Then, the target fusion feature information is input to an initial intention recognition information output layer included in the initial student intention recognition model to output initial student intention recognition information. And then generating student intention loss information according to the student intention information corresponding to the target teaching page real-time click data and the initial student intention identification information. And finally, in response to determining that the student intention loss information meets a preset loss condition, determining the initial student intention recognition model as a trained student intention recognition model. Therefore, the training student intention recognition model comprises a word embedding network, a high-dimensional click feature extraction network and a teaching page history click integral feature extraction network and feature information cross processing network, so that student intention recognition information can be accurately generated. Therefore, the associated knowledge information can be accurately pushed to the students according to the learning intention of the students, so that the waste of pushing resources is avoided.
And 102, inputting the real-time click data of the teaching page and the historical click data sequence of the teaching page into a word embedding network included in a predetermined student intention recognition model to obtain real-time click word embedding information of the teaching page and a historical click word embedding information sequence of the teaching page.
In some embodiments, the executing body may input the real-time click data of the teaching page and the historical click data sequence of the teaching page into a word embedding network included in a predetermined student intention recognition model, so as to obtain real-time click word embedding information of the teaching page and a historical click word embedding information sequence of the teaching page. Wherein, the student intention recognition model further comprises: the high-dimensional click feature extraction network and the teaching page history click integral feature extraction network and the feature information cross processing network. The student intention recognition model may be a model that generates student intention recognition information. For example, the student intention recognition information may be intention information of the student clicking on the teaching page. For example, the student intention recognition information may be intention information of a student teaching page corresponding to a knowledge point. The word embedding network may be a model for performing word embedding processing on the impact data. For example, the word Embedding network may be an Embedding layer.
The teaching page real-time click word embedding information may be an original vector representation of the teaching page real-time click data. The teaching page historical click word embedding information in the teaching page historical click word embedding information sequence corresponds to student historical click data in the student historical click data sequence one by one. The real-time click data of the teaching page is the same as the teaching page clicked correspondingly by the corresponding student historical click data sequence. The teaching page history click word embedding information in the teaching page history click word embedding information sequence may be an original vector of student history click data. The student historical click data sequence can be a data sequence after data normalization processing according to a time window corresponding to a preset time period.
And step 103, inputting the history click word embedded information sequence of the teaching page into the high-dimensional click feature extraction network to obtain a high-dimensional click behavior feature information sequence of the teaching page.
In some embodiments, the executing body may input the teaching page history click word embedded information sequence into the high-dimensional click feature extraction network to obtain a teaching page high-dimensional click behavior feature information sequence. The high-dimensional click feature extraction network can be a model for generating high-dimensional click behavior feature information of the teaching page. The teaching page high-dimensional click behavior feature information can be higher-order vector characterization of the student historical click data corresponding to the click behavior. The teaching page high-dimensional click behavior characteristic information in the teaching page high-dimensional click behavior characteristic information sequence corresponds to teaching page historical click word embedding information in the teaching page historical click word embedding information sequence one by one. The high-dimensional click feature extraction network may be a multi-layer serial connected recurrent neural network. For example, the high-dimensional click feature extraction network may be a Self-attention network (Self-attention network).
And 104, inputting the high-dimensional click behavior feature information sequence of the teaching page into the history click integral feature extraction network of the teaching page to generate history click integral feature information of the teaching page.
In some embodiments, the executing body may input the high-dimensional click behavior feature information sequence of the teaching page into the history click global feature extraction network of the teaching page to generate history click global feature information of the teaching page. The teaching page history click ensemble feature extraction network may be a network that generates teaching page history click ensemble feature information. The teaching page history click overall characteristic information can represent an overall representation vector of student click behaviors corresponding to the student history click data sequence. For example, the teaching page history click ensemble feature extraction network may be a time decay based attention mechanism network (attention unit with time decay).
And 105, inputting the history clicking integral feature information of the teaching page and the real-time clicking word embedded information of the teaching page into the feature information cross processing network to obtain the feature cross information of the teaching page.
In some embodiments, the executing body may input the history click global feature information of the teaching page and the real-time click word embedding information of the teaching page into the feature information cross processing network to obtain feature cross information of the teaching page. The feature information cross processing network may be a model for performing information cross processing on feature information. The teaching page feature intersection information may include: the teaching page history clicks the cross characteristic information between the integral characteristic information and the real-time clicking word embedded information of the teaching page. For example, the characteristic information cross-processing network may be a multi-layer serial connected convolutional neural network.
In some embodiments, the executing body may input the history click global feature information of the teaching page and the real-time click word embedding information of the teaching page into the feature information cross processing network through the following steps to obtain feature cross information of the teaching page:
firstly, utilizing the characteristic information cross processing network to carry out characteristic information cross multiplication processing on the history click integral characteristic information of the teaching page and the real-time click word embedding information of the teaching page, so as to obtain cross multiplication characteristic information. For example, the above feature information cross processing network may be used to perform a vector cross process on the teaching page history click global feature information corresponding vector and the teaching page real-time click word embedding information corresponding vector, so as to generate a cross vector as the cross feature information.
And secondly, carrying out characteristic information subtraction processing on the history click integral characteristic information of the teaching page and the real-time click word embedded information of the teaching page by utilizing the characteristic information cross processing network to obtain subtracted characteristic information. For example, the above feature information cross processing network may be used to perform a vector subtraction process on the teaching page history click global feature information corresponding vector and the teaching page real-time click word embedding information corresponding vector, so as to generate a subtraction vector as the subtraction feature information.
Thirdly, feature fusion is carried out on the cross feature information and the subtraction feature information so as to generate teaching page feature cross information. Vector stitching can be performed on the vectors corresponding to the cross feature information and the vectors corresponding to the subtraction feature information, so that a stitched vector serving as teaching page feature intersection information is obtained.
And 106, generating student intention identification information according to the teaching page feature intersection information.
In some embodiments, the executing entity may generate student intention identification information according to the teaching page feature intersection information. For example, the teaching page feature intersection information can be decoded through a decryption network included in the student intention recognition model to obtain student intention recognition information.
In an actual application scenario, the execution subject may generate student intention identification information by:
first, a student attribute information set corresponding to the real-time click data of the teaching page is obtained. The student attribute information may be an attribute value corresponding to a student attribute. For example, student attributes may include: student gender, student age, student grade, and student class.
Second, each student attribute information in the student attribute information set is input into the word embedding network to generate student attribute feature information, and a student attribute feature information set is obtained. Wherein the student attribute feature information may characterize feature information of the student attribute. For example, student attribute feature information may be in the form of a vector.
Thirdly, information fusion is carried out on the student attribute characteristic information set and the teaching page characteristic intersection information, and fusion characteristic information is obtained.
Fourth, the fused feature information is input into an intention recognition information output layer included in the student intention recognition model to output student intention recognition information.
Optionally, a set of teaching knowledge review weight information corresponding to the student intention identification information is generated.
In some embodiments, the executing entity may generate a set of teaching knowledge review weight information corresponding to the student intention identification information. Wherein, the student intention identification information includes: review the same class knowledge intent score information and review the same class knowledge intent score information. Wherein, the teaching knowledge review weight information is the weight information of a certain teaching knowledge in the review weight information set. The weight information may be a value between 0 and 1. The teaching knowledge review weight information can represent the importance degree of a certain teaching knowledge corresponding to review. Review of the knowledge of the same category intent score information may refer to review of the importance of knowledge of a certain teaching knowledge of the same category. Review of the knowledge intent score information of the same department may refer to review of the importance of knowledge of a certain teaching knowledge same department.
In an actual application scenario, the execution subject may generate the set of learning knowledge review weight information corresponding to the student intention identification information by:
first, similar teaching knowledge review weight information corresponding to the similar knowledge intent score information is generated. The same kind of knowledge intention score information can be normalized to generate same kind of teaching knowledge review weight information.
Second, generating the review weight information of the peer teaching knowledge corresponding to the review peer knowledge intention score information. The review peer knowledge intent score information may be normalized to generate peer teaching knowledge review weight information.
Thirdly, combining the same class teaching knowledge review weight information and the same class teaching knowledge review weight information into a teaching knowledge review weight information set.
Optionally, the review knowledge information set is generated by the above-described teaching knowledge review weight information set.
In some embodiments, the executing entity may generate the review knowledge information set by using the teaching knowledge review weight information set. Firstly, the executing body can set the number of knowledge points of the corresponding teaching knowledge according to the teaching knowledge review weight information corresponding to each teaching knowledge. Then, for each teaching knowledge, a key knowledge point is set as review knowledge information.
Optionally, sorting the review knowledge information sets to obtain a review knowledge information sequence.
In some embodiments, the executing entity may sort the review knowledge information set to obtain a review knowledge information sequence. For example, the review knowledge information sets may be sorted from more to less according to the number of bytes corresponding to each review knowledge information, so as to obtain a review knowledge information sequence.
Optionally, pushing the review knowledge information sequence to the relevant student terminals.
In some embodiments, the execution body may push the review knowledge information sequence to an associated student terminal.
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 that, when executed, cause the processor to perform any of a number of intelligent teaching-based student intent recognition methods.
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 that, when executed by the processor, causes the processor to perform any of a number of intelligent teaching-based student intent recognition methods.
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: collecting real-time click data of a teaching page and a corresponding history click data sequence of the teaching page; inputting the teaching page real-time click data and the teaching page historical click data sequence into a word embedding network included in a predetermined student intention recognition model to obtain teaching page real-time click word embedding information and a teaching page historical click word embedding information sequence, wherein the student intention recognition model further comprises: the high-dimensional click feature extraction network, the teaching page history click integral feature extraction network and the feature information cross processing network; inputting the history click word embedded information sequence of the teaching page into the high-dimensional click feature extraction network to obtain a high-dimensional click behavior feature information sequence of the teaching page; inputting the high-dimensional click behavior feature information sequence of the teaching page into the history click integral feature extraction network of the teaching page to generate history click integral feature information of the teaching page; inputting the history click integral feature information of the teaching page and the real-time click word embedded information of the teaching page into the feature information cross processing network to obtain feature cross information of the teaching page; and generating student intention identification information according to the teaching page characteristic intersection information.
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 where a method implemented when the program instructions are executed may refer to various embodiments of the present disclosure of a student intention recognition method based on intelligent teaching.
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 (6)
1. An intelligent teaching-based student intention recognition method is characterized by comprising the following steps:
collecting real-time click data of a teaching page and a corresponding history click data sequence of the teaching page;
inputting the teaching page real-time click data and the teaching page historical click data sequence into a word embedding network included in a predetermined student intention recognition model to obtain teaching page real-time click word embedding information and a teaching page historical click word embedding information sequence, wherein the student intention recognition model further comprises: the high-dimensional click feature extraction network, the teaching page history click integral feature extraction network and the feature information cross processing network;
inputting the teaching page history click word embedded information sequence into the high-dimensional click feature extraction network to obtain a teaching page high-dimensional click behavior feature information sequence;
inputting the teaching page high-dimensional click behavior feature information sequence into the teaching page history click integral feature extraction network to generate teaching page history click integral feature information;
inputting the history click integral feature information of the teaching page and the real-time click word embedding information of the teaching page into the feature information cross processing network to obtain feature cross information of the teaching page;
and generating student intention identification information according to the teaching page characteristic intersection information.
2. The method of claim 1, wherein generating student intent identification information from the teaching page feature intersection information comprises:
acquiring a student attribute information set corresponding to the real-time click data of the teaching page;
inputting each student attribute information in the student attribute information set into the word embedding network to generate student attribute characteristic information, and obtaining a student attribute characteristic information set;
information fusion is carried out on the student attribute characteristic information set and the teaching page characteristic intersection information to obtain fusion characteristic information;
and inputting the fusion characteristic information into an intention recognition information output layer included in the student intention recognition model so as to output student intention recognition information.
3. The method according to claim 1, wherein the method further comprises:
generating a teaching knowledge review weight information set corresponding to the student intention identification information;
generating a review knowledge information set through the teaching knowledge review weight information set;
sequencing the review knowledge information set to obtain a review knowledge information sequence;
pushing the review knowledge information sequence to relevant student terminals.
4. A method according to claim 3, wherein the student intent recognition information comprises: reviewing the same kind of knowledge intention score information and the same kind of knowledge intention score information; and
the generating a teaching knowledge review weight information set corresponding to the student intention identification information includes:
generating similar teaching knowledge review weight information corresponding to the similar knowledge intent score information;
generating peer teaching knowledge review weight information corresponding to the review peer knowledge intention score information;
and combining the similar teaching knowledge review weight information and the same family teaching knowledge review weight information into a teaching knowledge review weight information set.
5. A computer device, wherein the computer device comprises 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 according to any of claims 1-4.
6. 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 according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311398104.8A CN117131902B (en) | 2023-10-26 | 2023-10-26 | Student intention recognition method based on intelligent teaching and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311398104.8A CN117131902B (en) | 2023-10-26 | 2023-10-26 | Student intention recognition method based on intelligent teaching and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117131902A true CN117131902A (en) | 2023-11-28 |
| CN117131902B CN117131902B (en) | 2024-02-27 |
Family
ID=88856757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311398104.8A Active CN117131902B (en) | 2023-10-26 | 2023-10-26 | Student intention recognition method based on intelligent teaching and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117131902B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108563749A (en) * | 2018-04-16 | 2018-09-21 | 中山大学 | On-line education system resource recommendation method based on various dimensions information and knowledge network |
| CN109087135A (en) * | 2018-07-25 | 2018-12-25 | 百度在线网络技术（北京）有限公司 | The method for digging and device, computer equipment and readable medium that user is intended to |
| CN110414547A (en) * | 2019-05-07 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A kind of behavioral value method, apparatus, computer equipment and storage medium |
| CN111177575A (en) * | 2020-04-07 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN111931056A (en) * | 2020-08-17 | 2020-11-13 | 北京小川科技有限公司 | Push content recommendation method and device |
| WO2021204017A1 (en) * | 2020-11-20 | 2021-10-14 | 平安科技（深圳）有限公司 | Text intent recognition method and apparatus, and related device |
| CN114331492A (en) * | 2021-11-25 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Recommendation method, device and equipment for media resources and storage medium |
| WO2023279693A1 (en) * | 2021-07-09 | 2023-01-12 | 平安科技（深圳）有限公司 | Knowledge distillation method and apparatus, and terminal device and medium |
-
2023
- 2023-10-26 CN CN202311398104.8A patent/CN117131902B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108563749A (en) * | 2018-04-16 | 2018-09-21 | 中山大学 | On-line education system resource recommendation method based on various dimensions information and knowledge network |
| CN109087135A (en) * | 2018-07-25 | 2018-12-25 | 百度在线网络技术（北京）有限公司 | The method for digging and device, computer equipment and readable medium that user is intended to |
| CN110414547A (en) * | 2019-05-07 | 2019-11-05 | 腾讯科技（深圳）有限公司 | A kind of behavioral value method, apparatus, computer equipment and storage medium |
| CN111177575A (en) * | 2020-04-07 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, electronic equipment and storage medium |
| CN111931056A (en) * | 2020-08-17 | 2020-11-13 | 北京小川科技有限公司 | Push content recommendation method and device |
| WO2021204017A1 (en) * | 2020-11-20 | 2021-10-14 | 平安科技（深圳）有限公司 | Text intent recognition method and apparatus, and related device |
| WO2023279693A1 (en) * | 2021-07-09 | 2023-01-12 | 平安科技（深圳）有限公司 | Knowledge distillation method and apparatus, and terminal device and medium |
| CN114331492A (en) * | 2021-11-25 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Recommendation method, device and equipment for media resources and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘娇;李艳玲;林民;: "人机对话系统中意图识别方法综述", 计算机工程与应用, no. 12 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117131902B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147551B (en) | Multi-category entity recognition model training, entity recognition method, server and terminal | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN111275107A (en) | Multi-label scene image classification method and device based on transfer learning | |
| CN112819023B (en) | Sample set acquisition method, device, computer equipment and storage medium | |
| CN108681541B (en) | Picture searching method and device and computer equipment | |
| CN110929524A (en) | Data screening method, device, equipment and computer readable storage medium | |
| CN111563192A (en) | Entity alignment method and device, electronic equipment and storage medium | |
| CN108959550B (en) | User focus mining method, device, equipment and computer readable medium | |
| CN111259647A (en) | Question and answer text matching method, device, medium and electronic equipment based on artificial intelligence | |
| CN111914159A (en) | Information recommendation method and terminal | |
| CN110807693A (en) | Album recommendation method, device, equipment and storage medium | |
| CN113010785B (en) | User recommendation method and device | |
| CN112667790B (en) | Intelligent question-answering method, device, equipment and storage medium | |
| CN114490964A (en) | Soil fertility knowledge question-answering method, system, equipment and medium based on knowledge map | |
| CN112765985B (en) | Named entity identification method for patent embodiments in specific fields | |
| JP2023540266A (en) | Concept prediction for creating new intents and automatically assigning examples in dialogue systems | |
| CN117131902B (en) | Student intention recognition method based on intelligent teaching and computer equipment | |
| CN117077679A (en) | Named entity recognition method and device | |
| CN111552802A (en) | Text classification model training method and device | |
| CN110717037A (en) | Method and device for classifying users | |
| CN112328881B (en) | Article recommendation method, device, terminal equipment and storage medium | |
| CN111767710B (en) | Indonesia emotion classification method, device, equipment and medium | |
| CN114676237A (en) | Sentence similarity determining method and device, computer equipment and storage medium | |
| CN116991919B (en) | Service data retrieval method combined with platform database and artificial intelligent system | |
| CN114936327B (en) | Element recognition model acquisition method and device, computer equipment and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: Inside Beijing Diplomatic Language and Culture Center, No. 7 Sanlitun North Street, Chaoyang District, Beijing, 100027 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |