CN113177181A

CN113177181A - Online teaching information pushing method and system based on interactive customization plan

Info

Publication number: CN113177181A
Application number: CN202110726160.4A
Authority: CN
Inventors: 郭春林; 施欧军; 胡宇; 周自力
Original assignee: Changsha Douya Culture Technology Co ltd
Current assignee: Changsha Douya Culture Technology Co ltd
Priority date: 2021-06-29
Filing date: 2021-06-29
Publication date: 2021-07-27
Anticipated expiration: 2041-06-29
Also published as: CN113177181B

Abstract

The embodiment of the disclosure provides an online teaching information pushing method and system based on an interactive customization plan, which are characterized in that interactive customization data and training label information of a plurality of reference teaching objects are obtained, interactive intention characteristics corresponding to a plurality of interactive flow data of the reference teaching objects under interactive customization nodes responded by the reference teaching objects are determined according to the interactive customization data of each reference teaching object, the interactive intention characteristics are input into a preset artificial intelligent learning network for migration learning, interest course decision information of the reference teaching objects is obtained, network convergence configuration is carried out on the preset artificial intelligent learning network according to the interest course decision information and the training label information, and an online teaching interest decision network is obtained. Therefore, the depth characteristics of various different interactive customization nodes can be learned, and the online teaching information pushing of the target teaching object based on the online teaching interest decision network has higher prediction accuracy.

Description

Online teaching information pushing method and system based on interactive customization plan

Technical Field

The disclosure relates to the technical field of online education, in particular to an online teaching information pushing method and system based on an interactive customized plan.

Background

With the continuous development of the information society, more and more people choose to learn various knowledge to expand themselves continuously. Because the traditional students and teachers give lessons face to face, both the students and the teachers need to spend a great deal of time and energy on the roads, and the learning effect of many students is poor. Therefore, with the development of the communication era, online education on the network is accepted by a large number of users. For example, online network education is remote teaching between a teacher and students by allowing the teacher to communicate with the students via a network. In the related art, usually, interest points of users (such as teachers or students) are obtained based on an interactive customized plan, and then online teaching information push is performed on a targeted basis, however, prediction accuracy of online teaching information push on target teaching objects in the related art still needs to be improved.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, the present disclosure is directed to providing an online teaching information pushing method and system based on an interactive customized plan.

In a first aspect, the present disclosure provides an online teaching information pushing method based on an interactive customization plan, applied to an online teaching service platform, where the online teaching service platform is in communication connection with a plurality of online teaching service terminals, and the method includes:

acquiring interactive customization data of a plurality of reference teaching objects responding to a plurality of interactive customization nodes for interactive customization in a first interactive course time sequence range, and network convergence configuration label information of preset interest course labels of each reference teaching object in a second interactive course time sequence range at the interactive customization nodes responded by the reference teaching object; the interaction customizing nodes comprise a target interaction customizing node and a plurality of subordinate interaction customizing nodes;

aiming at each reference teaching object, determining interaction intention characteristics respectively corresponding to various interaction flow data of the reference teaching object under an interaction customization node responded by the reference teaching object according to the interaction customization data of the reference teaching object in a first interaction course time sequence range;

inputting the interaction intention characteristics of each reference teaching object into a preset artificial intelligence learning network to perform transfer learning from the target interaction customized node to the plurality of interaction customized nodes, and acquiring interest course decision information of the reference teaching object at the interaction customized node responded by the reference teaching object;

and performing network convergence configuration on the preset artificial intelligent learning network according to the interest course decision information of each reference teaching object at the interactive customization node responded by the reference teaching object and the network convergence configuration label information of the preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object, acquiring an online teaching interest decision network, and pushing online teaching information of the target teaching object based on the online teaching interest decision network.

In a second aspect, an embodiment of the present disclosure further provides an online teaching information pushing system based on an interactive customization plan, where the online teaching information pushing system based on the interactive customization plan includes an online teaching service platform and a plurality of online teaching service terminals in communication connection with the online teaching service platform;

the online teaching service platform is used for:

According to any one of the aspects, in the embodiment provided by the disclosure, a plurality of reference teaching object interactive customization data and training label information are obtained, interactive intention features corresponding to a plurality of types of interactive flow data of a reference teaching object under an interactive customization node responded by the reference teaching object are determined according to the interactive customization data of each reference teaching object, the interactive intention features are input into a preset artificial intelligent learning network for migration learning, interest course decision information of the reference teaching object is obtained, and network convergence configuration is performed on the preset artificial intelligent learning network according to the interest course decision information and the training label information, so that an online teaching interest decision network is obtained. Therefore, the online teaching interest decision network configured by network convergence can learn the depth characteristics of various different interaction customization nodes based on a transfer learning mode, and online teaching information pushing on a target teaching object based on the online teaching interest decision network has higher prediction accuracy.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present disclosure, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of an online teaching information pushing system based on an interactive customized plan according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart of an online teaching information pushing method based on an interactive customized plan according to an embodiment of the present disclosure;

fig. 3 is a block diagram schematically illustrating a structure of an online teaching service platform for implementing the online teaching information pushing method based on the interactive customized plan according to the embodiment of the present disclosure.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification, the terms "a", "an" and/or "the" are not intended to be inclusive of the singular, but rather are intended to be inclusive of the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Fig. 1 is a scene schematic diagram of an online teaching information pushing system 10 based on an interactive customized plan according to an embodiment of the present disclosure. The online teaching information pushing system 10 based on the interactive customized plan may include an online teaching service platform 100 and an online teaching service terminal 200 communicatively connected to the online teaching service platform 100. The online education information push system 10 based on the interactive customized plan shown in fig. 1 is only one possible example, and in other possible embodiments, the online education information push system 10 based on the interactive customized plan may also include only at least some of the components shown in fig. 1 or may also include other components.

In a possible design idea, the online teaching service platform 100 and the online teaching service terminal 200 in the online teaching information push system 10 based on the interactive customization plan can cooperatively execute the online teaching information push method based on the interactive customization plan described in the following method embodiment, and the detailed description of the method embodiment can be referred to in the specific steps of the online teaching service platform 100 and the online teaching service terminal 200.

In order to solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of an online teaching information pushing method based on an interactive customized plan according to an embodiment of the present disclosure, where the online teaching information pushing method based on the interactive customized plan according to the embodiment may be executed by the online teaching service platform 100 shown in fig. 1, and the online teaching information pushing method based on the interactive customized plan is described in detail below.

Step S101: the method comprises the steps of obtaining interaction customization data of each first reference teaching object in a plurality of first reference teaching objects responding to a target interaction customization node in a first interaction course time sequence range for online interaction customization, and obtaining network convergence configuration label information of each first reference teaching object in a second interaction course time sequence range based on the target interaction customization node for generating a preset interest course label.

Step S102: and acquiring interaction customization data of each second reference teaching object in the plurality of second reference teaching objects for online interaction customization based on the corresponding slave interaction customization node in the first interaction course time sequence range, and network convergence configuration tag information of preset interest course tags of each second reference teaching object in the second interaction course time sequence range at the corresponding slave interaction customization node.

Here, step S101 and step S102 have no execution order.

After the interactive customization data and the training label information are obtained in step S101, step S102 is executed to determine interactive intention characteristics corresponding to various interactive stream data under each interactive customization node.

Step S102: and aiming at each reference teaching object, determining interaction intention characteristics respectively corresponding to various interaction flow data of the reference teaching object under the interaction customization nodes responded by the reference teaching object according to the interaction customization data of the reference teaching object in the first interaction course time sequence range.

In one possible design idea, the interaction intention characteristics comprise a source domain interaction intention characteristic and a target domain interaction intention characteristic; the plurality of interaction flow data includes: a plurality of baseline interaction flow data and a plurality of derivative interaction flow data.

The source domain interaction intention characteristics are interaction intention characteristics of a first reference teaching object corresponding to the target interaction customization nodes; the target domain interaction intention characteristics are interaction intention characteristics of the second reference teaching objects which are interactively customized in response to the subordinate interaction customizing nodes.

The plurality of types of interaction stream data in step S102 include, in terms of type, reference interaction stream data and derivative interaction stream data; the reference interactive stream data can be various according to the specific content of the interactive stream; the derived interaction flow data can also be divided into a plurality of derived interaction flow data according to different interaction modes.

The interactive intention characteristics respectively corresponding to the multiple types of interactive flow data determined for each reference teaching object comprise: interaction intention characteristics for the reference interaction flow data, and corresponding interaction intention characteristics for each of the derived interaction flow data.

Aiming at different reference teaching objects which respond to the business of the target interaction customizing node and the subordinate interaction customizing nodes, the interaction intention characteristics which are respectively corresponding to various interaction flow data of each reference teaching object under the interaction customizing node responded by the reference teaching object can be obtained by adopting the following modes:

a: for the first reference teaching objects, the source domain interaction intention characteristics of each first reference teaching object can be obtained by adopting the following modes:

and for each first reference teaching object, constructing source domain interaction intention characteristics respectively corresponding to each kind of reference interaction flow data and each kind of derivative interaction flow data of the first reference teaching object under the target interaction customization nodes based on interaction customization data of the first reference teaching object under the target interaction customization nodes.

For example, the following steps may be adopted to obtain interaction intention characteristics respectively corresponding to a plurality of types of interaction flow data of each first reference teaching object under the target interaction customized node:

step S201: and for each first reference teaching object, determining mapping direction values of each type of reference interaction flow data and each type of derivative interaction flow data of the first reference teaching object under the target interaction customization node according to interaction customization data of the first reference teaching object under the target interaction customization node.

Step S202: and determining source domain interaction intention characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data of the first reference teaching object under the target interaction customizing node according to mapping direction quantities of the first reference teaching object under a plurality of preset interaction flow data characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data under the target interaction customizing node.

Here, each type of reference interaction stream data corresponds to a plurality of preset interaction stream data characteristics, and the preset interaction stream data characteristics corresponding to different reference interaction stream data may be different.

The generated value of each element in the interaction intention characteristic corresponding to certain interaction flow data is a mapping direction quantity value of the first reference teaching object under a plurality of preset interaction flow data characteristics corresponding to the interaction flow data under the target interaction customization node.

B: for the second reference teaching objects, the target domain interaction intention characteristics of each second reference teaching object can be obtained by adopting the following modes:

and for each second reference teaching object, constructing target domain interaction intention characteristics respectively corresponding to each type of benchmark interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customizing node based on the interaction customizing data of the second reference teaching object under the corresponding subordinate interaction customizing node.

For example, the following steps may be adopted to obtain the interaction intention characteristics corresponding to the various interaction flow data of each second reference teaching object under the subordinate interaction customizing node to which the second reference teaching object responds:

step S301: for each second reference teaching object, determining mapping direction quantities of each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node according to interaction customization data of the second reference teaching object under the corresponding subordinate interaction customization node;

step S302: and determining target domain interaction intention characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node according to mapping direction quantities of each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node.

Here, each derivative interaction flow data also corresponds to a plurality of preset interaction flow data characteristics, and the preset interaction flow data characteristics corresponding to different derivative interaction flow data may also be different.

In another embodiment of the present invention, before the source domain interaction intention feature and the target domain interaction intention feature are constructed, the mapping direction values of the first reference teaching object under the target interaction customization node under the plurality of preset interaction flow data features respectively corresponding to each type of the reference interaction flow data and each type of the derivative interaction flow data, and/or the mapping direction values of the second reference teaching object under the slave interaction customization node responding to the second reference teaching object under the plurality of preset interaction flow data features respectively corresponding to each type of the reference interaction flow data and each type of the derivative interaction flow data.

After the final source domain interaction intention characteristics and target domain interaction intention characteristics are obtained through the above steps, the online teaching interest decision network training method provided by the embodiment of the present invention further includes the following steps S103 and S104:

step S103: inputting the interaction intention characteristics of each reference teaching object into a preset artificial intelligence learning network to perform transfer learning from the target interaction customization nodes to the plurality of subordinate interaction customization nodes, and acquiring interest course decision information of the reference teaching object at the interaction customization nodes responded by the reference teaching object.

Wherein, predetermine artificial intelligence learning network includes: the system comprises a global splicing network unit, a prediction unit, a first slave splicing network unit corresponding to the reference interactive flow data and a second slave splicing network unit corresponding to the derivative interactive flow data.

Here, after determining interaction intention features respectively corresponding to a plurality of kinds of interaction flow data under the interaction customization nodes responded by each reference teaching object, constructing a multi-layer AI unit to perform nonlinear change of the interaction intention features on the extracted interaction intention features, excavating complex nonlinear relations among the interaction intention features, performing feature splicing on the interaction intention features, and performing network convergence configuration on the preset artificial intelligent learning network in response to the spliced interaction intention features, so that the obtained preset artificial intelligent learning network has a higher network convergence configuration learning effect.

Here, the feature splicing is performed in response to the hierarchical splicing method in the embodiment of the present invention, for example, the first slave splicing network unit may be invoked to perform feature splicing on the interaction intention features respectively corresponding to the multiple reference interaction stream data, then the second slave splicing network unit may be invoked to perform feature splicing on the interaction intention features respectively corresponding to the multiple derivative interaction stream data, and finally the two splicing features of the global splicing network unit may be responded to perform feature splicing.

For example, the embodiment of the present invention obtains interest course decision information of a target interaction customization node to which each first reference teaching object responds based on the following manner:

step S501: responding to the first subordinate splicing network unit to perform feature splicing on source domain interaction intention features respectively corresponding to multiple kinds of reference interaction flow data of the first reference teaching object under the target interaction customized node aiming at the condition that the reference teaching object is a first reference teaching object, and acquiring a first source domain splicing interaction intention feature corresponding to the first reference teaching object;

step S502: calling the second subordinate splicing network unit, performing feature splicing on the source domain interaction intention features respectively corresponding to the multiple kinds of derived interaction flow data of the first reference teaching object under the target interaction customized node, and acquiring a second source domain splicing interaction intention feature corresponding to the first reference teaching object;

step S503: calling the global splicing network unit to perform feature splicing on the first source domain splicing interactive intention feature and the second source domain splicing interactive intention feature to obtain a target interactive intention feature of the first reference teaching object;

step S504: inputting the target interaction intention characteristics of the first reference teaching object into the prediction unit, and acquiring interest course decision information of the first reference teaching object at the target interaction customization node.

The embodiment of the invention obtains the interest course decision information of the subordinate interactive customization nodes responded by each second reference teaching object based on the following modes:

step S601: calling a first subordinate splicing network unit aiming at the condition that the reference teaching object is a second reference teaching object, and performing feature splicing on the target domain interaction intention features respectively corresponding to the multiple kinds of benchmark interaction flow data of the second reference teaching object under the subordinate interaction customization nodes responded by the second reference teaching object to obtain a first target domain splicing interaction intention feature corresponding to the second reference teaching object;

step S602: calling the second subordinate splicing network unit, performing feature splicing on the target domain interaction intention features respectively corresponding to the multiple kinds of derived interaction flow data of the second reference teaching object under the subordinate interaction customizing nodes responded by the second reference teaching object, and acquiring a second target domain splicing interaction intention feature corresponding to the second reference teaching object;

step S603: calling the global splicing network unit to perform feature splicing on the first target domain splicing interactive intention feature and the second target domain splicing interactive intention feature to obtain a target interactive intention feature of the second reference teaching object;

step S604: inputting the target interaction intention characteristics of the second reference teaching object into the prediction unit, and acquiring interest course decision information of the second reference teaching object at the slave interaction customization node.

And after obtaining the interest course decision information of the reference teaching object at each interactive customization node, executing the step S104 to obtain an online teaching interest decision network.

Step S104: and performing network convergence configuration on the preset artificial intelligent learning network according to the interest course decision information of each reference teaching object at the interactive customization node responded by the reference teaching object and the network convergence configuration label information of the preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object, acquiring an online teaching interest decision network, and pushing online teaching information of the target teaching object based on the online teaching interest decision network.

In a possible design idea, the embodiment of the invention obtains an online teaching interest decision network based on the following ways:

step S701: performing network convergence configuration on the preset artificial intelligent learning network according to interest course decision information of each reference teaching object at the interactive customization node responded by the reference teaching object and network convergence configuration label information of a preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object;

step S702: and taking the preset artificial intelligence learning network subjected to network convergence configuration for multiple times as the online teaching interest decision network.

In a possible design idea, the embodiment of the present invention specifically obtains an online teaching interest decision network based on the following ways:

step S801: and taking any one of the reference teaching objects which do not meet the network convergence requirement in the network convergence configuration as a target reference teaching object.

Step S802: and determining a network convergence evaluation index of the target reference teaching object in the network convergence configuration according to the interest course decision information of the target reference teaching object at the interactive customization node responded by the target reference teaching object and the network convergence configuration label information of the preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object.

According to the interest course decision information of the target reference teaching object at the target interaction customization node and the network convergence configuration label information of the reference teaching object generating the preset interest course label at the target interaction customization node, the network convergence evaluation index of the target reference teaching object at the target interaction customization node configured by the network convergence is obtained, and the network convergence evaluation index of the target reference teaching object configured by the network convergence is obtained according to the interest course decision information of the target reference teaching object at the target interaction customization node.

The larger the network convergence evaluation index is, the more inaccurate the prediction effect of the current artificial intelligence learning network on the current reference teaching object is. On the contrary, the smaller the network convergence evaluation index is, the more accurate the prediction effect of the current artificial intelligence learning network on the current reference teaching object is.

Step S803: and adjusting the weight configuration information of the preset artificial intelligent learning network according to the network convergence evaluation index of the target reference teaching object in the network convergence configuration.

For example, when adjusting the parameters of the preset artificial intelligence learning network based on the network convergence evaluation index, the following method can be adopted:

aiming at the condition that the target reference teaching object is a first target reference teaching object, updating the weight configuration information of the preset artificial intelligent learning network by a first updating weight template according to the network convergence evaluation index of the target reference teaching object in the current network convergence configuration;

according to the situation that the target reference teaching object is a second target reference teaching object, updating the weight configuration information of the preset artificial intelligent learning network by using a second updated weight template according to the network convergence evaluation index of the target reference teaching object in the current network convergence configuration;

wherein the first updated weight template is larger than the second updated weight template.

It should be noted here that the first updated weight templates in the network convergence configurations in different training phases may be the same or different; the second updated weight template may be the same or different in the network convergence configuration at different training phases.

Based on the design, the main influence factors of the network convergence evaluation indexes of the target interaction customized nodes on the adjustment of the weight configuration information can be ensured, and the network convergence evaluation indexes of the subordinate interaction customized nodes can be used as subordinate influence elements to have certain influence on the adjustment of the weight configuration information. The model trained in this way is simultaneously influenced by the data of a plurality of interactive customization nodes, namely, the transfer learning is carried out.

Step S804: and taking the target reference teaching object as a reference teaching object meeting the network convergence requirement.

Step S805: detecting whether a reference teaching object which does not meet the network convergence requirement exists in the current training stage; if yes, jumping to step S806; if not, it jumps to step S808.

Step S806: and taking any one of the reference teaching objects which do not meet the network convergence requirement in the current training stage as a new target reference teaching object.

Step S807: and obtaining interest course decision information of the new target reference teaching object at the interactive customization node responded by the new target reference teaching object by using the preset artificial intelligence learning network after the network weight is updated, and returning to the step S702 again.

Step S808: and finishing the network convergence configuration of the preset artificial intelligence learning network.

And acquiring an online teaching interest decision network through multiple network convergence configurations of a preset artificial intelligence learning network.

After the network convergence configuration of the preset artificial intelligence learning network is completed, the embodiment of the invention obtains the online teaching interest decision network through the following three ways:

the first method is as follows: detecting whether the network convergence configuration reaches a preset iteration number or not; if so, stopping network convergence configuration of the preset artificial intelligence learning network, and taking the preset artificial intelligence learning network obtained by the last network convergence configuration as an online teaching interest decision network.

In a possible design idea, a preset iteration number of training is preset during network convergence configuration, if it is detected that the current network convergence configuration reaches the preset iteration number, the network convergence configuration of the preset artificial intelligent learning network is stopped, and the preset artificial intelligent learning network obtained by the last network convergence configuration is used as an online teaching interest decision network.

The second method comprises the following steps: calling a test data set to verify the preset artificial intelligence learning network obtained by the network convergence configuration at the time; if the test is concentrated, the joint network convergence evaluation index is not larger than the number of the test data of the preset joint network convergence evaluation index threshold value, occupies the percentage of the total number of the test data in the test set, and is larger than the preset first percentage threshold value, the network convergence configuration of the preset artificial intelligent learning network is stopped, and the preset artificial intelligent learning network obtained by the last network convergence configuration is used as the online teaching interest decision network.

The third method comprises the following steps: sequentially configuring the joint network convergence evaluation indexes of all the reference teaching objects for the network convergence, and comparing the joint network convergence evaluation indexes with the joint network convergence evaluation indexes of the corresponding reference teaching objects in the previous training stage; if the combined network convergence evaluation index of the current network convergence configuration reference teaching object is larger than the number of the reference teaching objects corresponding to the combined network convergence evaluation index of the reference teaching object in the previous training stage, and the percentage of the number of all the reference teaching objects reaches a preset second percentage threshold, stopping the network convergence configuration of the preset artificial intelligent learning network, and taking the preset artificial intelligent learning network obtained by the last network convergence configuration as an online teaching interest decision network.

Here, the training process is a process of continuously reducing the joint network convergence evaluation index, but too many times of network convergence configuration may cause the joint network convergence evaluation index not to be reduced or increased, so that a model obtained by the current network convergence configuration with the minimum joint network convergence evaluation index can be selected as an online teaching interest decision network.

In the online teaching interest decision network training method provided by the embodiment of the invention, when the online teaching interest decision network training is carried out, interactive customization data for interactive customization of a plurality of reference teaching objects based on a plurality of interactive customization nodes in a first interactive course time sequence range is obtained, and network convergence configuration label information of preset interest course labels of each reference teaching object in each interactive customization node in a second interactive course time sequence range is obtained; the plurality of interactive customization nodes comprise a target interactive customization node and a plurality of subordinate interactive customization nodes; aiming at each reference teaching object, determining interaction intention characteristics of the reference teaching object under each interaction customization node, which correspond to various interaction flow data under the interaction customization nodes one by one, according to interaction customization data of the reference teaching object in a first interaction course time sequence range; inputting interaction intention characteristics of the reference teaching object under each interaction customization node, which correspond to various interaction flow data of the interaction customization nodes respectively, into a preset artificial intelligence learning network for transfer learning, and acquiring interest course decision information of the reference teaching object at each interaction customization node; and performing network convergence configuration on a preset artificial intelligent learning network according to the interest course decision information of each reference teaching object at each interactive customization node and the network convergence configuration label information of the preset interest course label of the reference teaching object at each interactive customization node, so as to obtain the online teaching interest decision network. The method can enable the online teaching interest decision network configured by network convergence to learn the depth characteristics of various different interaction customization nodes based on a transfer learning mode, and has higher accuracy by detecting whether the interaction flow data of the user belongs to the preset interest course label based on the online teaching interest decision network.

In a possible design idea, an embodiment of the present invention further provides an online teaching information pushing method based on an interactive customized plan, including:

step S901: and when the target teaching object generates interactive flow data based on the target interactive customization node, acquiring interactive flow data information of the target teaching object for online interactive customization based on the target interactive customization node within a third interactive course time sequence range.

Step S902: and determining interaction intention characteristics of the target teaching object under the target interaction customizing node, which are in one-to-one correspondence with various interaction flow data under the target interaction customizing node, according to interaction flow data information of the target teaching object for performing online interaction customizing based on the target interaction customizing node within the third interaction course time sequence range.

In a possible design idea, referring to the method in step S102 in the present invention, the interaction intention characteristics of the target teaching object under the target interaction customized node, which correspond to the various interaction flow data under the target interaction customized node one to one, are determined.

Step S903: and inputting the interaction intention characteristics corresponding to the various interaction flow data under the target interaction customizing node one by one into the online teaching interest decision network, and acquiring the metric value of the interaction flow data of the target teaching object which belongs to the preset interest course label based on the target interaction customizing node.

Step S904, a target interest course label corresponding to the target teaching object is obtained based on a metric value of interaction flow data of the target teaching object in the target interaction customization node, which belongs to a preset interest course label.

Step S905, carrying out on-line teaching information pushing on the target teaching object based on the target interest course label corresponding to the target teaching object.

The embodiment of the invention provides an online teaching information pushing method based on an interactive customization plan, which comprises the steps of acquiring interactive customization data of a plurality of reference teaching objects for interactive customization based on a plurality of interactive customization nodes in a first interactive course time sequence range and network convergence configuration label information of each reference teaching object for generating a preset interest course label at each interactive customization node in a second interactive course time sequence range during online teaching interest decision network training; the plurality of interactive customization nodes comprise a target interactive customization node and a plurality of subordinate interactive customization nodes; aiming at each reference teaching object, determining interaction intention characteristics of the reference teaching object under each interaction customization node, which correspond to various interaction flow data under the interaction customization nodes one by one, according to interaction customization data of the reference teaching object in a first interaction course time sequence range; inputting interaction intention characteristics of the reference teaching object under each interaction customization node, which correspond to various interaction flow data of the interaction customization nodes respectively, into a preset artificial intelligence learning network for transfer learning, and acquiring interest course decision information of the reference teaching object at each interaction customization node; and performing network convergence configuration on a preset artificial intelligent learning network according to the interest course decision information of each reference teaching object at each interactive customization node and the network convergence configuration label information of the preset interest course label of the reference teaching object at each interactive customization node, so as to obtain the online teaching interest decision network. The method can enable the online teaching interest decision network configured by network convergence to learn the depth characteristics of various different interaction customization nodes based on a transfer learning mode, and has higher accuracy by detecting whether the interaction flow data of the user belongs to the preset interest course label based on the online teaching interest decision network.

In a possible design idea, for step S906, a reference interest course topic list corresponding to a target interest course tag corresponding to the target teaching object may be obtained; acquiring content data of each candidate course corresponding to the reference interest course topic list, and converting the content data of the course into target content hotspot distribution information based on a preset content hotspot tracking model, wherein the content hotspot tracking model is obtained by performing hotspot tracking learning based on the acquired content data of the reference course; matching user portrait hotspot distribution information corresponding to a preset target user portrait label with the target content hotspot distribution information to obtain first matching information; if the first pairing information is successful, determining that the course content data comprises the target user portrait label, and pushing the course content data to the target teaching object for online teaching information; if the first pairing information is pairing failure, performing derivative hotspot expansion on the user portrait hotspot distribution information to obtain at least one derivative expansion hotspot content hotspot distribution information; pairing each derived extended hotspot content hotspot distribution information with the target content hotspot distribution information to obtain at least one piece of second pairing information; if the at least one piece of second pairing information contains target second pairing information, clustering the target content hotspot distribution information to obtain at least one hotspot clustering data, wherein the target second pairing information is one piece of second pairing information which is successfully paired; determining hotspot clustering data matched with derived extended hotspot content hotspot distribution information corresponding to the target second pairing information in the at least one hotspot clustering data, and replacing the derived extended hotspot content hotspot distribution information included in the hotspot clustering data with the user portrait hotspot distribution information to obtain target hotspot clustering data;

determining a frequent confidence coefficient of the target hotspot clustering data based on a preset frequent pattern item model, wherein the frequent pattern item model is obtained by training based on a training database in a first target frequent item node library; obtaining a confidence degree range corresponding to the clustering measurement parameter based on the clustering measurement parameter of the target hotspot clustering data and pre-established measurement parameter-confidence degree mapping information, wherein the measurement parameter-confidence degree mapping information is established based on the frequent pattern item model and a test database in the first target frequent item node library; judging whether the frequent confidence coefficient belongs to the confidence coefficient range; if the frequent confidence degree belongs to the confidence degree range, determining the confidence degree that the target content hot spot distribution information belongs to a plurality of preset hot spot labels based on a preset hot spot label decision network to obtain a hot spot label vector of the target content hot spot distribution information, wherein the hot spot label decision network is obtained by training based on a hot spot label decision data set including the plurality of hot spot labels in a second target frequent item node library; calculating the matching degree of the user portrait hotspot distribution information and each hotspot tag in the plurality of hotspot tags to obtain matching degree vectors of the target portrait tag and the plurality of hotspot tags, and normalizing the matching degree vectors to obtain normalized vectors; calculating the correlation degree of the hotspot tag vector and the normalized vector, and taking the correlation degree as the distribution correlation degree of the user portrait hotspot distribution information and the target content hotspot distribution information; calculating the reference values of the user portrait hotspot distribution information and the target content hotspot distribution information based on the distribution correlation degree and the frequent confidence degree; judging whether the reference value is greater than a preset reference value or not; and if the reference value is greater than or equal to the preset reference value, determining that the course content data comprises the target user portrait label.

If the target second matching information does not exist in the at least one second matching information, determining that the course content data does not include the target user portrait label; if the frequent confidence does not belong to the confidence range, determining that the course content data does not include the target user portrait label; and if the reference value is smaller than the preset reference value, determining that the course content data comprises the target user portrait label.

Fig. 3 illustrates a hardware structure of an online teaching service platform 100 for implementing the above-mentioned online teaching information pushing method based on an interactive customization plan, according to an embodiment of the present disclosure, as shown in fig. 3, the online teaching service platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

In a specific implementation process, one or more processors 110 execute machine-readable execution instructions stored in a machine-readable storage medium 120, so that the processors 110 may execute the online education information pushing method based on the interactive customization plan according to the above method embodiment, the processors 110, the machine-readable storage medium 120, and the communication unit 140 are connected through a bus 130, and the processors 110 may be configured to control the transceiving action of the communication unit 140, so as to perform data transceiving with the online education service terminal 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the online teaching service platform 100, which implement principles and technical effects similar to each other, and details of this embodiment are not described herein again.

In addition, the embodiment of the disclosure also provides a readable storage medium, a machine readable execution instruction is preset in the readable storage medium, and when the processor executes the machine readable execution instruction, the online teaching information pushing method based on the interactive customized plan is realized.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the embodiments herein. Various modifications, improvements and adaptations to the embodiments described herein may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the embodiments of the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the embodiments of the present description may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of embodiments of the present description may be carried out entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the embodiments of the present specification may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for operation of various portions of the embodiments of the present description may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, VisualBasic, Fortran2003, Perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or processing device. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

In addition, unless explicitly stated in the claims, the order of processing elements and sequences, use of numbers and letters, or use of other names in the embodiments of the present specification are not intended to limit the order of the processes and methods in the embodiments of the present specification. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing processing device or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more embodiments of the invention. This method of disclosure, however, is not intended to imply that more features are required than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are possible within the scope of the embodiments of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. An online teaching information pushing method based on an interactive customization plan is characterized by being applied to an online teaching service platform, wherein the online teaching service platform is in communication connection with a plurality of online teaching service terminals, and the method comprises the following steps:

2. The method for pushing on-line teaching information based on interactive customized plan according to claim 1, wherein the reference teaching object comprises: a first reference teaching object and a second reference teaching object;

the method for obtaining interaction customization data of a plurality of reference teaching objects responding to a plurality of interaction customization nodes in a first interaction course time sequence range for interaction customization, and network convergence configuration label information of preset interest course labels of each reference teaching object in a second interaction course time sequence range at the interaction customization nodes responded by the reference teaching object comprises the following steps:

acquiring interaction customization data of each first reference teaching object in a plurality of first reference teaching objects responding to the target interaction customization node within a first interaction course time sequence range for online interaction customization, and network convergence configuration tag information of each first reference teaching object in a second interaction course time sequence range based on the target interaction customization node for generating a preset interest course tag;

and acquiring interaction customization data for online interaction customization of each second reference teaching object in the plurality of second reference teaching objects based on the corresponding slave interaction customization node in the first interaction course time sequence range, and network convergence configuration tag information of preset interest course tags of each second reference teaching object in the second interaction course time sequence range at the corresponding slave interaction customization node.

3. The online teaching information pushing method based on the interaction customized plan as claimed in claim 2, wherein the interaction intention characteristics comprise a source domain interaction intention characteristic and a target domain interaction intention characteristic; the plurality of interaction flow data includes: a plurality of baseline interaction flow data and a plurality of derivative interaction flow data;

the method comprises the following steps of aiming at each reference teaching object, determining interaction intention characteristics respectively corresponding to various interaction flow data of the reference teaching object under an interaction customization node responded by the reference teaching object according to the interaction customization data of the reference teaching object in a first interaction course time sequence range, and comprises the following steps:

for each first reference teaching object, constructing source domain interaction intention characteristics respectively corresponding to each kind of reference interaction flow data and each kind of derivative interaction flow data of the first reference teaching object under the target interaction customization nodes based on interaction customization data of the first reference teaching object under the target interaction customization nodes;

4. The method for pushing online education information based on interaction customization plan according to claim 3, wherein for each first reference education object, based on the interaction customization data of the first reference education object under the target interaction customization node, constructing source domain interaction intention features corresponding to each kind of benchmark interaction flow data and each kind of derivative interaction flow data of the first reference education object under the target interaction customization node respectively comprises:

for each first reference teaching object, determining mapping direction quantities of each kind of reference interaction flow data and each kind of derivative interaction flow data of the first reference teaching object under the target interaction customization node according to interaction customization data of the first reference teaching object under the target interaction customization node;

determining source domain interaction intention characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data of the first reference teaching object under the target interaction customizing node according to mapping direction quantities of the first reference teaching object under a plurality of preset interaction flow data characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data under the target interaction customizing node;

for each second reference teaching object, constructing, based on the interaction customization data of the second reference teaching object at the subordinate interaction customization node to which the second reference teaching object responds, target domain interaction intention features respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object at the subordinate interaction customization node to which the second reference teaching object responds, including:

for each second reference teaching object, determining mapping direction quantities of each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node according to interaction customization data of the second reference teaching object under the corresponding subordinate interaction customization node;

and determining target domain interaction intention characteristics respectively corresponding to each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node according to mapping direction quantities of each type of reference interaction flow data and each type of derivative interaction flow data of the second reference teaching object under the corresponding subordinate interaction customization node.

5. The online teaching information pushing method based on the interactive customized plan according to claim 3, wherein the preset artificial intelligence learning network comprises: the system comprises a global splicing network unit, a prediction unit, a first slave splicing network unit corresponding to the reference interactive flow data and a second slave splicing network unit corresponding to the derivative interactive flow data;

inputting the interaction intention characteristics of each reference teaching object into a preset artificial intelligence learning network to perform transfer learning from the target interaction customized node to the plurality of interaction customized nodes, and acquiring interest course decision information of the reference teaching object at the interaction customized node to which the reference teaching object responds, wherein the method comprises the following steps:

responding to the first subordinate splicing network unit to perform feature splicing on source domain interaction intention features respectively corresponding to multiple kinds of reference interaction flow data of the first reference teaching object under the target interaction customized node aiming at the condition that the reference teaching object is a first reference teaching object, and acquiring a first source domain splicing interaction intention feature corresponding to the first reference teaching object;

calling the second subordinate splicing network unit, performing feature splicing on the source domain interaction intention features respectively corresponding to the multiple kinds of derived interaction flow data of the first reference teaching object under the target interaction customized node, and acquiring a second source domain splicing interaction intention feature corresponding to the first reference teaching object;

calling the global splicing network unit to perform feature splicing on the first source domain splicing interactive intention feature and the second source domain splicing interactive intention feature to obtain a target interactive intention feature of the first reference teaching object; inputting the target interaction intention characteristics of the first reference teaching object into the prediction unit, and acquiring interest course decision information of the first reference teaching object at the target interaction customized node;

calling a first subordinate splicing network unit aiming at the condition that the reference teaching object is a second reference teaching object, and performing feature splicing on the target domain interaction intention features respectively corresponding to the multiple kinds of benchmark interaction flow data of the second reference teaching object under the subordinate interaction customization nodes responded by the second reference teaching object to obtain a first target domain splicing interaction intention feature corresponding to the second reference teaching object;

calling the second subordinate splicing network unit, performing feature splicing on the target domain interaction intention features respectively corresponding to the multiple kinds of derived interaction flow data of the second reference teaching object under the subordinate interaction customizing nodes responded by the second reference teaching object, and acquiring a second target domain splicing interaction intention feature corresponding to the second reference teaching object;

calling the global splicing network unit to perform feature splicing on the first target domain splicing interactive intention feature and the second target domain splicing interactive intention feature to obtain a target interactive intention feature of the second reference teaching object;

inputting the target interaction intention characteristics of the second reference teaching object into the prediction unit, and acquiring interest course decision information of the second reference teaching object at the slave interaction customization node.

6. The method as claimed in claim 1, wherein the obtaining an online education interest decision network by performing network convergence configuration on the preset artificial intelligence learning network according to interest course decision information of each reference education object at the interactive customization node to which the reference education object responds and network convergence configuration tag information of a preset interest course tag occurring at the interactive customization node to which the reference education object responds includes:

performing network convergence configuration on the preset artificial intelligent learning network according to interest course decision information of each reference teaching object at the interactive customization node responded by the reference teaching object and network convergence configuration label information of a preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object;

and taking the preset artificial intelligence learning network subjected to network convergence configuration for multiple times as the online teaching interest decision network.

7. The method as claimed in claim 6, wherein the step of performing network convergence configuration on the preset artificial intelligent learning network to obtain the online teaching interest decision network according to interest course decision information of each reference teaching object at the interactive customization node to which the reference teaching object responds and network convergence configuration tag information of a preset interest course tag occurring at the interactive customization node to which the reference teaching object responds comprises:

taking any one of the reference teaching objects which do not meet the network convergence requirement in the network convergence configuration as a target reference teaching object, and determining the network convergence evaluation index of the target reference teaching object in the network convergence configuration according to interest course decision information of the target reference teaching object at the interactive customization node responded by the target reference teaching object and network convergence configuration label information of a preset interest course label of the reference teaching object at the interactive customization node responded by the reference teaching object;

adjusting the weight configuration information of the preset artificial intelligent learning network according to the network convergence evaluation index configured by the target reference teaching object in the network convergence;

taking the target reference teaching object as a reference teaching object meeting the network convergence requirement, taking any other reference teaching object in the reference teaching objects meeting the network convergence requirement obtained in the current training stage as a new target reference teaching object, using the preset artificial intelligent learning network after network weight updating to obtain interest course decision information of the new target reference teaching object at the interactive customization node responded by the new target reference teaching object, and returning again the interest course decision information according to the interactive customization node responded by the target reference teaching object, the reference teaching object generates network convergence configuration label information of a preset interest course label at an interactive customization node responded by the reference teaching object, and a network convergence evaluation index of the target reference teaching object in the current network convergence configuration is determined; until all reference teaching objects finish the network convergence configuration in the current training stage, finishing the network convergence configuration of the preset artificial intelligent learning network;

and acquiring the online teaching interest decision network through multiple network convergence configurations of the preset artificial intelligence learning network.

8. The method for pushing the on-line teaching information based on the interactive customized plan as claimed in any one of claims 1 to 7, wherein the step of pushing the on-line teaching information to the target teaching object based on the on-line teaching interest decision network comprises:

when a target teaching object generates interactive flow data based on a target interactive customization node, acquiring interactive flow data information of the target teaching object for online interactive customization based on the target interactive customization node within a third interactive course time sequence range;

according to the interactive flow data information of the target teaching object which is subjected to online interactive customization based on the target interactive customization node within the third interactive course time sequence range, determining interactive intention characteristics of the target teaching object under the target interactive customization node, which are in one-to-one correspondence with various interactive flow data under the target interactive customization node;

inputting interaction intention characteristics corresponding to a plurality of kinds of interaction flow data under the target interaction customizing node one by one into the online teaching interest decision network, and acquiring a metric value of interaction flow data of the target teaching object, which belongs to a preset interest course label and occurs on the basis of the target interaction customizing node;

acquiring a target interest course label corresponding to the target teaching object based on a metric value of interaction flow data of the target teaching object in a target interaction customization node;

and carrying out online teaching information pushing on the target teaching object based on the target interest course label corresponding to the target teaching object.

9. The method for pushing the on-line teaching information based on the interactive customized plan as claimed in claim 8, wherein the step of pushing the on-line teaching information to the target teaching object based on the target interest course tag corresponding to the target teaching object includes:

acquiring a reference interest course theme list corresponding to a target interest course label corresponding to the target teaching object;

acquiring content data of each candidate course corresponding to the reference interest course topic list, and converting the content data of the course into target content hotspot distribution information based on a preset content hotspot tracking model, wherein the content hotspot tracking model is obtained by performing hotspot tracking learning based on the acquired content data of the reference course;

matching user portrait hotspot distribution information corresponding to a preset target user portrait label with the target content hotspot distribution information to obtain first matching information;

if the first pairing information is successful, determining that the course content data comprises the target user portrait label, and pushing the course content data to the target teaching object for online teaching information;

if the first pairing information is pairing failure, performing derivative hotspot expansion on the user portrait hotspot distribution information to obtain at least one derivative expansion hotspot content hotspot distribution information;

pairing each derived extended hotspot content hotspot distribution information with the target content hotspot distribution information to obtain at least one piece of second pairing information;

if the at least one piece of second pairing information contains target second pairing information, clustering the target content hotspot distribution information to obtain at least one hotspot clustering data, wherein the target second pairing information is one piece of second pairing information which is successfully paired;

determining hotspot clustering data matched with derived extended hotspot content hotspot distribution information corresponding to the target second pairing information in the at least one hotspot clustering data, and replacing the derived extended hotspot content hotspot distribution information included in the hotspot clustering data with the user portrait hotspot distribution information to obtain target hotspot clustering data;

determining a frequent confidence coefficient of the target hotspot clustering data based on a preset frequent pattern item model, wherein the frequent pattern item model is obtained by training based on a training database in a first target frequent item node library;

obtaining a confidence degree range corresponding to the clustering measurement parameter based on the clustering measurement parameter of the target hotspot clustering data and pre-established measurement parameter-confidence degree mapping information, wherein the measurement parameter-confidence degree mapping information is established based on the frequent pattern item model and a test database in the first target frequent item node library;

judging whether the frequent confidence coefficient belongs to the confidence coefficient range;

if the frequent confidence degree belongs to the confidence degree range, determining the confidence degree that the target content hot spot distribution information belongs to a plurality of preset hot spot labels based on a preset hot spot label decision network to obtain a hot spot label vector of the target content hot spot distribution information, wherein the hot spot label decision network is obtained by training based on a hot spot label decision data set including the plurality of hot spot labels in a second target frequent item node library;

calculating the matching degree of the user portrait hotspot distribution information and each hotspot tag in the plurality of hotspot tags to obtain matching degree vectors of the target portrait tag and the plurality of hotspot tags, and normalizing the matching degree vectors to obtain normalized vectors;

calculating the correlation degree of the hotspot tag vector and the normalized vector, and taking the correlation degree as the distribution correlation degree of the user portrait hotspot distribution information and the target content hotspot distribution information;

calculating the reference values of the user portrait hotspot distribution information and the target content hotspot distribution information based on the distribution correlation degree and the frequent confidence degree;

judging whether the reference value is greater than a preset reference value or not;

if the reference value is larger than or equal to the preset reference value, determining that the course content data comprises the target user portrait label, and pushing the course content data to the target teaching object for online teaching information; and

if the target second matching information does not exist in the at least one second matching information, determining that the course content data does not include the target user portrait label; if the frequent confidence does not belong to the confidence range, determining that the course content data does not include the target user portrait label; and if the reference value is smaller than the preset reference value, determining that the course content data comprises the target user portrait label, and pushing the course content data to the target teaching object for online teaching information.

10. The online teaching information pushing system based on the interactive customization plan is characterized by comprising an online teaching service platform and a plurality of online teaching service terminals in communication connection with the online teaching service platform;

the online teaching service platform is used for: