CN112182413A

CN112182413A - Intelligent recommendation method and server based on big teaching data

Info

Publication number: CN112182413A
Application number: CN202011374623.7A
Authority: CN
Inventors: 陈国镇; 韩高强; 罗龙; 刘栋梁
Original assignee: Sunmnet Technology Co ltd
Current assignee: Sunmnet Technology Co ltd
Priority date: 2020-12-01
Filing date: 2020-12-01
Publication date: 2021-01-05
Anticipated expiration: 2040-12-01
Also published as: CN112182413B

Abstract

The invention relates to the technical field of intelligent recommendation based on big teaching data, in particular to an intelligent recommendation method and a server based on big teaching data. According to the method, data item statistical data are divided into a series of label clustering data in advance, and then each label clustering data is subjected to teaching establishment portrait classification through a target behavior analysis deep learning network so as to identify the type of the teaching establishment portrait to which each label clustering data belongs, so that the accuracy of teaching recommendation strategy updating is improved, and a teaching establishment portrait classification result is further obtained.

Description

Intelligent recommendation method and server based on big teaching data

Technical Field

The invention relates to the technical field of intelligent recommendation based on big teaching data, in particular to an intelligent recommendation method and a server based on big teaching data.

Background

The teaching big data analysis process needs a large amount of education basic data to be provided, the education basic data of colleges and universities generally have the problems of missing, difficult acquisition and unavailable use at present, the requirements of concomitant acquisition and instantaneity analysis are provided for the education basic data at present, the condition of the application of the teaching data of colleges and universities is combined, the localization and enrichment of the teaching data are an important development direction in the future, the construction of data acquisition terminal equipment is enhanced, a data analysis processing platform is introduced, the localization and enrichment of the data are realized, and more analysis results can be generated. Therefore, how to improve the pertinence of teaching recommendation, realize artificial intelligence application in teaching, and then realize artificial intelligence application in teaching, really provide accurate propelling movement of educational service, be the technical problem that this field is urgent to solve.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, an object of the present invention is to provide an intelligent recommendation method and a server based on big teaching data, wherein before updating a teaching recommendation policy, data item statistical data is divided into a series of tag clustering data in advance, and then each tag clustering data is subjected to teaching creation portrait classification through a target behavior analysis deep learning network, so as to identify a teaching creation portrait type to which each tag clustering data belongs, thereby improving accuracy of updating the teaching recommendation policy. In addition, after the teaching establishment portrait type to which each label cluster data belongs is identified through the target behavior analysis deep learning network, a teaching establishment portrait classification result is obtained, so that the label cluster data meeting a preset portrait template are detected to exist in the label cluster data, a teaching recommendation strategy item with reference significance possibly carried by a target data item can be rapidly determined, and then after targeted strategy updating is carried out, the follow-up teaching recommendation data amount with low confidence coefficient is reduced, and the pertinence of teaching recommendation is improved.

In a first aspect, the invention provides an intelligent recommendation method based on big teaching data, which is applied to a server, wherein the server is in communication connection with a plurality of teaching data capturing devices, and the method comprises the following steps:

acquiring data item statistical data containing a target data item in teaching capture big data of teaching arrangement distribution of teaching plan arrangement information issued to the plurality of teaching data capture devices, and performing label clustering processing on the data item statistical data to obtain label clustering data corresponding to the data item statistical data;

acquiring a target behavior analysis deep learning network corresponding to the data item statistical data, extracting a first description component and a second description component from the tag clustering data through the target behavior analysis deep learning network, and generating teaching behavior feature distribution of the first description component and the second description component to obtain teaching behavior feature distribution associated with the data item statistical data;

according to the teaching behavior feature distribution and the target behavior analysis deep learning network, performing teaching establishment portrait classification on the label clustering data to obtain a teaching establishment portrait classification result corresponding to the label clustering data;

and if the teaching establishment portrait classification result indicates that the data item statistical data contains label clustering data meeting a preset portrait template, determining the target data item as a teaching recommendation strategy item, and updating the teaching recommendation strategy of the server based on the teaching recommendation strategy item and the label clustering data meeting the preset portrait template corresponding to the teaching recommendation strategy item.

In a possible implementation manner of the first aspect, the step of obtaining data item statistical data including a target data item from teaching capture big data of teaching layout distribution in which teaching planning layout information is issued to the plurality of teaching data capture devices, and performing label clustering processing on the data item statistical data to obtain label clustering data corresponding to the data item statistical data includes:

responding to an arrangement plan distribution request aiming at teaching arrangement distribution, and outputting an arrangement plan distribution table corresponding to the teaching arrangement distribution;

starting a data statistics process associated with the teaching layout distribution, capturing at least one data item statistic data of the teaching layout distribution in a data statistics interval corresponding to the data statistics process, outputting the captured at least one data item statistic data to the layout plan distribution table, and determining the at least one data item statistic data displayed on the layout plan distribution table as a data item statistic data list associated with the teaching layout distribution; the data item statistics manifest comprises at least one data item statistic;

acquiring teaching layout distributed data item statistical data from at least one data item statistical data of the data item statistical data list, and performing teaching behavior label analysis on the teaching layout distributed data item statistical data to obtain a teaching behavior label analysis result;

if the analysis result of the teaching behavior tag indicates that target data which belong to the marked teaching behavior tag exist in the data item statistical data of the teaching arrangement distribution, determining the topological ring information of the teaching behavior topological ring of the teaching arrangement distribution in the data item statistical data of the teaching arrangement distribution based on the target data, and intercepting the topological ring information from the data item statistical data of the teaching arrangement distribution;

taking the teaching behavior topology circle distributed in the teaching arrangement as a target data item in the topology circle information, and taking the relation statistical data corresponding to the target data item in the topology circle information as data item statistical data; the target data items are teaching behavior topological rings distributed in the teaching layout;

and acquiring a clustering strategy for performing label clustering processing on the data item statistical data, and performing label clustering processing on the data item statistical data based on the clustering strategy to obtain label clustering data corresponding to the data item statistical data.

In a possible implementation manner of the first aspect, the number of the tag clustering data is multiple;

the step of obtaining a target behavior analysis deep learning network corresponding to the data item statistical data, extracting a first description component and a second description component from the tag clustering data through the target behavior analysis deep learning network, and generating teaching behavior feature distribution of the first description component and the second description component to obtain teaching behavior feature distribution associated with the data item statistical data includes:

acquiring a target behavior analysis deep learning network corresponding to the data item statistical data; the target behavior analysis deep learning network comprises: the behavior analysis module comprises a first behavior analysis module and a second behavior analysis module;

extracting time sequence teaching behavior characteristics from each label clustering data through the first behavior analysis module, and respectively determining the extracted time sequence teaching behavior characteristics of each label clustering data as first description components;

extracting a null sequence teaching behavior feature from each label clustering data through the second behavior analysis module, and respectively determining the extracted null sequence teaching behavior feature of each label clustering data as a second description component;

and performing teaching behavior feature distribution generation on the first description component of each label clustering data and the second description component corresponding to the label clustering data to obtain the teaching behavior feature distribution feature of each label clustering data, and determining the teaching behavior feature distribution feature of each label clustering data as the teaching behavior feature distribution associated with the data item statistical data.

In a possible implementation manner of the first aspect, the target behavior analysis deep learning network includes: a classification module; the classification module has the function of predicting and classifying the teaching establishment portrait type to which the label clustering data corresponding to the data item statistical data belongs;

the step of carrying out teaching establishment portrait classification on the label clustering data according to the teaching behavior feature distribution and the target behavior analysis deep learning network to obtain a teaching establishment portrait classification result corresponding to the label clustering data comprises the following steps:

inputting the teaching behavior feature distribution to the classification module in the target behavior analysis deep learning network, and determining the matching degree between the teaching behavior feature distribution and a plurality of comparison behavior feature distributions in the classification module by the classification module; the matching degree is used for representing the confidence degree that the teaching behavior feature distribution and each comparison behavior feature distribution belong to the same teaching establishment portrait type respectively;

acquiring a comparison behavior feature distribution with the maximum matching degree with the teaching behavior feature distribution from the comparison behavior feature distributions based on the matching degree, and taking the comparison behavior feature distribution with the maximum matching degree as a target comparison behavior feature distribution;

and taking the teaching recommendation label corresponding to the target comparison behavior characteristic distribution as a target teaching establishment portrait type corresponding to the teaching behavior characteristic distribution, and determining a teaching establishment portrait classification result after classifying the label clustering data in the data item statistical data based on the target teaching establishment portrait type and the maximum matching degree associated with the target teaching establishment portrait type.

In a possible implementation manner of the first aspect, one tag clustering data corresponds to one teaching creation portrait classification result; the teaching recommendation labels corresponding to the comparison behavior characteristic distribution comprise teaching key feedback label information;

if the teaching creation portrait classification result indicates that tag clustering data meeting a preset portrait template exists in the data item statistical data, determining the target data item as a teaching recommendation strategy item, including:

acquiring a preset portrait template corresponding to the target behavior analysis deep learning network;

if the teaching establishment portrait type belongs to the teaching establishment portrait classification result of the teaching key feedback label information in the teaching establishment portrait classification result, determining label clustering data corresponding to the target teaching establishment portrait type in the label clustering data as the label clustering data meeting the preset portrait template;

and determining the target data item contained in the data item statistical data as a teaching recommendation strategy item.

In a possible implementation manner of the first aspect, the step of updating the teaching recommendation policy of the server based on the teaching recommendation policy item and the tag cluster data that satisfies a preset portrait template and corresponds to the teaching recommendation policy item includes:

extracting teaching recommendation information corresponding to each target label cluster classification target in label cluster data meeting a preset portrait template corresponding to the teaching recommendation strategy item, and extracting teaching visit dispute information of the teaching recommendation information in parallel while acquiring an original teaching visit result list associated with the teaching recommendation information during teaching visit from a teaching visit filling form of the teaching recommendation information;

determining teaching visit update item information used for carrying out update analysis on the original teaching visit result list based on the extracted teaching visit dispute information, extracting update parameter types of a plurality of update items to be used and update linkage switching information among different update items from the teaching visit update item information, and carrying out teaching visit processing on the plurality of update items to be used according to the update parameter types and the update linkage switching information to obtain update containers of at least two target update items;

updating and analyzing the original teaching visit result list through an updating container of the target updating project to obtain a candidate teaching visit result list;

determining new teaching visit library updating data of the candidate teaching visit result list according to target teaching visit dispute information determined from a thread teaching visit record of a preset virtual teaching visit thread, and determining new teaching visit library extension data of the candidate teaching visit result list according to the determined teaching visit type in the candidate teaching visit result list;

performing key label clustering classification target extraction on the candidate teaching visit result list based on the new teaching visit library updating data and the new teaching visit library extension data to obtain a key label clustering classification target set;

and updating the teaching recommendation strategy of the server based on the key label clustering classification target set.

In a possible implementation manner of the first aspect, the step of extracting, in parallel, the teaching visit dispute information of the teaching recommendation information while obtaining an original teaching visit result list associated with the teaching recommendation information at the time of teaching visit from the teaching visit filling form of the teaching recommendation information includes:

generating new teaching visit template front information corresponding to the form template information of the teaching visit filling form, sending the new teaching visit template front information through a software development interface pre-established with the teaching visit filling form, and detecting whether a new teaching visit state of the teaching recommendation information is in an enabled state while sending the new teaching visit template front information;

when the new teaching visit state is detected to be in the starting state, associating teaching visit distribution software with a new teaching visit task corresponding to the teaching recommendation information so that the new teaching visit task corresponding to the teaching recommendation information synchronously feeds back an original teaching visit result list obtained by querying from the teaching visit filling form based on the front information of the new teaching visit template and the teaching visit dispute information extracted from the record information corresponding to the new teaching visit state through the teaching visit distribution software;

when the new teaching visit state is detected to be in a non-enabled state, generating teaching visit distribution software according to a new teaching visit calling sequence of the new teaching visit state in a delayed mode and issuing the teaching visit distribution software to a new teaching visit task corresponding to the teaching recommendation information, enabling the new teaching visit task corresponding to the teaching recommendation information to start the new teaching visit state according to the teaching visit distribution software and extract the teaching visit dispute information from record information corresponding to the new teaching visit state, enabling the new teaching visit task corresponding to the teaching recommendation information to obtain an original teaching visit result list from the teaching visit filling form according to the teaching visit distribution software in a delayed mode based on the front information of the new teaching visit template, and synchronously receiving the teaching visit dispute information and the original teaching visit result list fed back by the new teaching visit task corresponding to the teaching recommendation information And (4) listing the fruits.

In a possible implementation manner of the first aspect, the step of determining, based on the extracted teaching visit dispute information, teaching visit update item information used for performing update analysis on the original teaching visit result list, and extracting update parameter types of a plurality of update items to be used and update linkage switching information between different update items from the teaching visit update item information includes:

determining a plurality of dispute subject distributions with different dispute problem labels from the teaching interview dispute information, and constructing a first update subject content and a second update subject content according to the dispute subject distributions, wherein the first update subject content is a global update subject content, and the second update subject content is a specific object update subject content;

mapping record member information corresponding to any one first update project record information in the first update subject content to second update project record information on a corresponding node in the second update subject content, and determining teaching visit associated information of the record member information in the second update project record information;

determining commonly used dispute points of the teaching visit dispute information in a set member range based on member matching parameters between the teaching visit associated information and target record member information in the second updated project record information, analyzing a dispute resolution template corresponding to the dispute points and generating the teaching visit updated project information according to information characteristics indicated by the dispute resolution template;

listing the teaching visit updating item information in a stack structure to obtain a plurality of initial updating items, determining a teaching visit processing level of each initial updating item according to the stack level of the teaching visit updating item information, sequencing the initial updating items according to the descending order of the teaching visit processing levels, and selecting a target number of initial updating items which are sequenced in the front as updating items to be used;

and aiming at each update project to be used, determining a content configuration parameter and a content editing parameter of update configuration data of the update project, determining an update content service of the update project according to the content configuration parameter, and extracting an update parameter type from the update content service according to the content editing parameter.

In a possible implementation manner of the first aspect, the step of performing update analysis on the original teaching visit result list through an update container of the target update item to obtain a candidate teaching visit result list includes:

determining an updatable unit of the original teaching visit result list from an update container of the target update project; the updatable unit is used for representing an updatable node of the original teaching visit result list in the teaching recommendation information;

determining index teaching visit parameters of the original teaching visit result list according to the updatable nodes in the updatable units, and acquiring target index teaching visit parameters with index analysis characteristics of preset duration in the index teaching visit parameters;

and updating and analyzing the original teaching visit result list according to an inverse matrix of a distribution matrix corresponding to the updatable unit, and updating and analyzing a target teaching visit control item corresponding to a teaching visit behavior corresponding to an index analysis feature of preset duration of the target index teaching visit parameter in the original teaching visit result list by using the target index teaching visit parameter in a teaching visit processing process to obtain the candidate teaching visit result list.

For example, in one possible implementation manner of the first aspect, the target behavior analysis deep learning network is obtained by training in the following manner:

acquiring training sample information associated with a sample object and a teaching recommendation label of the training sample information; the training sample information comprises first sample information and second sample information used for training an initial behavior analysis deep learning network; the teaching recommendation label of the training sample information comprises: non-teaching key feedback label information corresponding to the first sample information and teaching key feedback label information corresponding to the second sample information;

performing label clustering processing on the training sample information to obtain index performance sample data corresponding to the training sample information;

extracting a first sample characteristic and a second sample characteristic from the index performance sample data through the initial behavior analysis deep learning network, and performing characteristic teaching behavior characteristic distribution generation on the first sample characteristic and the second sample characteristic to obtain a sample teaching behavior characteristic distribution characteristic associated with the training sample information;

training the initial behavior analysis deep learning network based on the sample teaching behavior feature distribution feature, the non-teaching key feedback label information and the teaching key feedback label information, and determining the trained initial behavior analysis deep learning network as a target behavior analysis deep learning network for predicting a target object in a target image.

For example, in a possible implementation manner of the first aspect, the step of obtaining training sample information associated with a sample object and a teaching recommendation label of the training sample information includes:

acquiring initial data item statistical data containing a sample object, taking the initial data item statistical data as first sample information for training an initial behavior analysis deep learning network, and determining label information of the first sample information as non-teaching key feedback label information;

acquiring an object identification model having an association relation with the initial behavior analysis deep learning network, and determining target data item statistical data associated with the initial data item statistical data through the object identification model;

generating superposed data item statistical data containing the target data item statistical data based on the target data item statistical data and the initial data item statistical data, taking the superposed data item statistical data as second sample information for training the initial behavior analysis deep learning network, and determining label information of the second sample information as teaching key feedback label information;

and determining the first sample information and the second sample information as training sample information, and using the non-teaching key feedback label information and the teaching key feedback label information as teaching recommendation labels of the training sample information.

In a second aspect, an embodiment of the present invention further provides an intelligent recommendation apparatus based on big teaching data, which is applied to a server, where the server is in communication connection with multiple teaching data capture devices, and the apparatus includes:

the acquisition module is used for acquiring data item statistical data containing target data items in teaching capture big data of teaching arrangement distribution of teaching plan arrangement information issued to the plurality of teaching data capture devices, and performing label clustering processing on the data item statistical data to obtain label clustering data corresponding to the data item statistical data;

the generation module is used for acquiring a target behavior analysis deep learning network corresponding to the data item statistical data, extracting a first description component and a second description component from the label clustering data through the target behavior analysis deep learning network, and generating teaching behavior feature distribution of the first description component and the second description component to obtain teaching behavior feature distribution associated with the data item statistical data;

the analysis module is used for carrying out teaching establishment portrait classification on the label clustering data according to the teaching behavior feature distribution and the target behavior analysis deep learning network to obtain a teaching establishment portrait classification result corresponding to the label clustering data;

and the updating module is used for determining the target data item as a teaching recommendation strategy item if the teaching creation portrait classification result indicates that the data item statistical data contains label clustering data meeting a preset portrait template, and updating the teaching recommendation strategy of the server based on the teaching recommendation strategy item and the label clustering data meeting the preset portrait template corresponding to the teaching recommendation strategy item.

In a third aspect, an embodiment of the present invention further provides an intelligent recommendation system based on big teaching data, where the intelligent recommendation system based on big teaching data includes a server and multiple teaching data capture devices in communication connection with the server;

the server is configured to:

In a fourth aspect, an embodiment of the present invention further provides a server, where the server includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one instructional data capturing device, the machine-readable storage medium is configured to store a program, instructions, or code, and the processor is configured to execute the program, instructions, or code in the machine-readable storage medium to perform the instructional big data based intelligent recommendation method in the first aspect or any possible implementation manner of the first aspect.

In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed, the computer executes the method for intelligently recommending based on big teaching data in the first aspect or any one of the possible implementations of the first aspect.

Based on any one of the above aspects, when acquiring data item statistical data including a target data item, the present invention may perform tag clustering processing on the data item statistical data to divide the data item statistical data into one or more indexes, where the number of the divided indexes is not limited. It should be understood that the embodiment of the present invention may collectively refer to the relationship statistics data corresponding to each index as tag cluster data. In addition, it is understood that the target data item herein may be an operation item of a certain analysis interaction node in a teaching visit tracking scenario, and optionally, the target data item herein may also be an operation item of a certain teaching network in an identification recognition scenario, where a specific type of the target data item will not be limited herein. Furthermore, the statistical data of the data items can be given to a trained target behavior analysis deep learning network, so that a first description component and a second description component are extracted from the partitioned label clustering data through the target behavior analysis deep learning network, and then the extracted first description component and the extracted second description component can be subjected to teaching behavior feature distribution generation processing to obtain teaching behavior feature distribution associated with the statistical data of the data items; it can be understood that, after the teaching behavior feature distribution generation processing is performed on the first description component and the second description component extracted from each label clustering data, the accuracy of classifying the teaching establishment image types to which each label clustering data belongs can be improved. Furthermore, the label clustering data can be subjected to teaching to establish portrait classification according to teaching behavior feature distribution and a target behavior analysis deep learning network so as to obtain teaching establishment portrait classification results corresponding to the data item statistical data. It can be understood that the teaching creation portrait classification result in the embodiment of the present invention may include a teaching creation portrait classification result corresponding to each tag clustering data, so that when it is detected that a teaching creation portrait classification result corresponding to tag clustering data satisfying a preset portrait template exists in the teaching creation portrait classification results, it may be determined that tag clustering data satisfying the preset portrait template exists in data item statistical data, and thus, the target data item may be indirectly determined to be a teaching recommendation policy item. Therefore, before the teaching recommendation strategy is updated, the embodiment of the invention can divide the statistical data of the data item into a series of label cluster data in advance, and can further perform teaching establishment portrait classification on each label cluster data through the target behavior analysis deep learning network so as to identify the teaching establishment portrait type to which each label cluster data belongs, thereby improving the accuracy of the teaching recommendation strategy updating. In addition, after the teaching establishment portrait type to which each label cluster data belongs is identified through the target behavior analysis deep learning network, the teaching establishment portrait type to which each label cluster data belongs can be collectively referred to as a teaching establishment portrait classification result corresponding to the data item statistical data, and therefore when the label cluster data meeting a preset portrait template is detected to exist, the target data item can be rapidly determined to be a teaching recommendation strategy item with reference significance, and further after targeted strategy updating is carried out, the amount of subsequent teaching recommendation data with low confidence coefficient is reduced, and the pertinence of teaching recommendation is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, 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 invention, 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 intelligent recommendation system based on big teaching data according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of an intelligent recommendation method based on big teaching data according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a functional module of an intelligent recommendation device based on big teaching data according to an embodiment of the present invention;

fig. 4 is a schematic block diagram of structural components of a server for implementing the intelligent recommendation method based on big teaching data according to an embodiment of the present invention.

Detailed Description

The present invention is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the apparatus embodiments or the system embodiments.

Fig. 1 is an interaction diagram of an intelligent recommendation system 10 based on big teaching data according to an embodiment of the present invention. The intelligent tutorial big data based recommendation system 10 can include a server 100 and a tutorial data capture device 200 communicatively coupled to the server 100. The intelligent tutorial big data based recommendation system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the intelligent tutorial big data based recommendation system 10 may include only one of the components shown in fig. 1 or may include other components.

In this embodiment, the server 100 and the teaching data capturing device 200 in the intelligent recommendation system 10 based on big teaching data can cooperatively execute the intelligent recommendation method based on big teaching data described in the following method embodiments, and the detailed description of the method embodiments below can be referred to for the execution steps of the specific server 100 and the teaching data capturing device 200.

In order to solve the technical problem in the foregoing background art, fig. 2 is a schematic flowchart of an intelligent recommendation method based on big teaching data according to an embodiment of the present invention, where the intelligent recommendation method based on big teaching data according to the present embodiment may be executed by the server 100 shown in fig. 1, and the intelligent recommendation method based on big teaching data is described in detail below.

Step S110 is to acquire data item statistical data including a target data item from the teaching capture big data of the teaching layout distribution for which the teaching planning layout information is issued to the plurality of teaching data capture devices 200, and perform label clustering processing on the data item statistical data to obtain label clustering data corresponding to the data item statistical data.

And step S120, acquiring a target behavior analysis deep learning network corresponding to the data item statistical data, extracting a first description component and a second description component from the label clustering data through the target behavior analysis deep learning network, and generating teaching behavior characteristic distribution of the first description component and the second description component to obtain teaching behavior characteristic distribution associated with the data item statistical data.

And step S130, according to the teaching behavior feature distribution and the target behavior analysis deep learning network, performing teaching building portrait classification on the label clustering data to obtain a teaching building portrait classification result corresponding to the label clustering data.

And step S140, if the teaching establishment portrait classification result indicates that the statistical data of the data items contains the label clustering data meeting the preset portrait template, determining the target data item as a teaching recommendation strategy item, and updating the teaching recommendation strategy of the server based on the teaching recommendation strategy item and the label clustering data meeting the preset portrait template corresponding to the teaching recommendation strategy item.

In this embodiment, when the data item statistical data including the target data item is obtained, tag clustering processing may be performed on the data item statistical data to divide the data item statistical data into one or more tag clusters, where the number of the divided tag clusters is not limited. It should be understood that, in the embodiment of the present invention, the relationship statistical data corresponding to each tag cluster may be collectively referred to as tag cluster data. In addition, it is understood that the target data item herein may be a data item of a certain visiting node in a teaching visiting scene, and optionally, the target data item herein may also be an operation item identifying a certain teaching network in the scene, and a specific type of the target data item will not be limited herein.

Furthermore, the statistical data of the data items can be sent to a trained target behavior analysis deep learning network, so that a first description component and a second description component are extracted from the partitioned label clustering data through the target behavior analysis deep learning network, and then the extracted first description component and the extracted second description component can be subjected to teaching behavior feature distribution generation processing to obtain teaching behavior feature distribution associated with the statistical data of the data items.

It can be understood that, after the teaching behavior feature distribution generation processing is performed on the first description component and the second description component extracted from each label clustering data, the accuracy of classifying the teaching establishment image types to which each label clustering data belongs can be improved. Furthermore, the label clustering data can be subjected to teaching to establish portrait classification according to teaching behavior feature distribution and a target behavior analysis deep learning network so as to obtain teaching establishment portrait classification results corresponding to the data item statistical data.

It can be understood that the teaching creation portrait classification result in the embodiment of the present invention may include a teaching creation portrait classification result corresponding to each tag clustering data, so that when it is detected that a teaching creation portrait classification result corresponding to tag clustering data satisfying a preset portrait template exists in the teaching creation portrait classification results, it may be determined that tag clustering data satisfying the preset portrait template exists in data item statistical data, and thus, the target data item may be indirectly determined to be a teaching recommendation policy item.

Therefore, before the teaching recommendation strategy is updated, the embodiment of the invention can divide the statistical data of the data item into a series of label cluster data in advance, and can further perform teaching establishment portrait classification on each label cluster data through the target behavior analysis deep learning network so as to identify the teaching establishment portrait type to which each label cluster data belongs, thereby improving the accuracy of the teaching recommendation strategy updating. In addition, after the teaching establishment portrait type to which each label cluster data belongs is identified through the target behavior analysis deep learning network, the teaching establishment portrait type to which each label cluster data belongs can be collectively referred to as a teaching establishment portrait classification result corresponding to the data item statistical data, and therefore when the label cluster data meeting a preset portrait template is detected to exist, the target data item can be rapidly determined to be a teaching recommendation strategy item with reference significance, and further after targeted strategy updating is carried out, the amount of subsequent teaching recommendation data with low confidence coefficient is reduced, and the pertinence of teaching recommendation is improved.

In a possible implementation manner, for step S110, in the process of obtaining data item statistical data of a target data item from teaching capture big data of teaching layout distribution that issues teaching planning layout information to a plurality of teaching data capture devices 200, and performing tag clustering processing on the data item statistical data to obtain tag clustering data corresponding to the data item statistical data, the following exemplary sub-steps may be implemented.

And a substep S111 of outputting an arrangement plan allocation table corresponding to the teaching arrangement distribution in response to the arrangement plan allocation request for the teaching arrangement distribution.

And a substep S112, starting a data statistics process associated with the teaching layout distribution, capturing at least one data item statistic data of the teaching layout distribution within a data statistics interval corresponding to the data statistics process, outputting the captured at least one data item statistic data to a layout plan distribution table, and determining the at least one data item statistic data displayed on the layout plan distribution table as a data item statistic data list associated with the teaching layout distribution.

In this embodiment, the data item statistics list may include at least one data item statistic.

It should be noted that the data statistics interval corresponding to the data statistics process may be flexibly set according to actual operation conditions of different cloud services, and the data statistics interval may be understood as a captured directory range or a captured service data range, which is not specifically limited herein.

And a substep S113, acquiring the statistical data of the teaching layout distributed data items from at least one statistical data of the data items in the statistical data list of the data items, and analyzing the teaching behavior tags of the statistical data of the teaching layout distributed data items to obtain a teaching behavior tag analysis result.

And a substep S114, if the analysis result of the teaching behavior tag indicates that target data belonging to the marked teaching behavior tag exists in the data item statistical data of the teaching layout distribution, determining the topology ring information of the teaching behavior topology ring of the teaching layout distribution in the data item statistical data of the teaching layout distribution based on the target data, and intercepting the topology ring information from the data item statistical data of the teaching layout distribution.

And a substep S115, taking the teaching behavior topology circle distributed in the teaching layout as a target data item in the topology circle information, and taking the relation statistical data corresponding to the target data item in the topology circle information as data item statistical data. The target data items are teaching behavior topological circles distributed in teaching arrangement.

And a substep S116, acquiring a clustering strategy for performing label clustering processing on the data item statistical data, and performing label clustering processing on the data item statistical data based on the clustering strategy to obtain label clustering data corresponding to the data item statistical data.

In one possible implementation manner, the number of tag cluster data may be multiple for step S120. Therefore, in the process of obtaining the teaching behavior feature distribution associated with the data item statistical data by obtaining the target behavior analysis deep learning network corresponding to the data item statistical data, extracting the first description component and the second description component from the tag clustering data through the target behavior analysis deep learning network, and generating the teaching behavior feature distribution by performing the teaching behavior feature distribution on the first description component and the second description component, the following exemplary sub-steps can be implemented.

And a substep S121, obtaining a target behavior analysis deep learning network corresponding to the data item statistical data.

For example, the target behavior analysis deep learning network may include: the device comprises a first behavior analysis module and a second behavior analysis module. It can be understood that the first behavior analysis module and the second behavior analysis module may be different network model layers arranged in parallel in the target behavior analysis deep learning network, and are used for extracting different network circle features.

And a substep S122, extracting time sequence teaching behavior characteristics from each label clustering data through a first behavior analysis module, and respectively determining the extracted time sequence teaching behavior characteristics of each label clustering data as first description components.

And a substep S123 of extracting the empty sequence teaching behavior characteristics from each label clustering data through a second behavior analysis module, and respectively determining the extracted empty sequence teaching behavior characteristics of each label clustering data as second description components.

And a substep S124, performing teaching behavior feature distribution generation on the first description component of each label clustering data and the second description component of the corresponding label clustering data to obtain the teaching behavior feature distribution feature of each label clustering data, and determining the teaching behavior feature distribution feature of each label clustering data as the teaching behavior feature distribution associated with the data item statistical data.

In one possible implementation, for step S130, the target behavior analysis deep learning network may include: and (5) a classification module. For example, the classification module has a function of performing predictive classification on teaching creation portrait types to which tag cluster data corresponding to data item statistics belong. Therefore, in a possible implementation manner, in the process of analyzing the deep learning network according to the teaching behavior feature distribution and the target behavior, performing teaching creation portrait classification on the label clustering data to obtain a teaching creation portrait classification result corresponding to the label clustering data, the following exemplary substeps can be implemented.

And the substep S131, inputting the teaching behavior feature distribution into a classification module in the target behavior analysis deep learning network, and determining the matching degree between the teaching behavior feature distribution and a plurality of comparison behavior feature distributions in the classification module by the classification module.

The matching degree can be used for representing the confidence degree that the teaching behavior feature distribution and each comparison behavior feature distribution belong to the same teaching establishment portrait type.

And a substep S132 of obtaining a comparison behavior feature distribution having the greatest matching degree with the teaching behavior feature distribution among the plurality of comparison behavior feature distributions based on the matching degrees, and taking the comparison behavior feature distribution having the greatest matching degree as a target comparison behavior feature distribution.

And a substep S133 of using the teaching recommendation label corresponding to the target comparison behavior feature distribution as a target teaching creation portrait type corresponding to the teaching behavior feature distribution, and determining a teaching creation portrait classification result after classifying label clustering data in the data item statistical data based on the target teaching creation portrait type and the maximum matching degree associated with the target teaching creation portrait type.

Based on the above description, for step S140, one label cluster data corresponds to one teaching creation portrait classification result, and a plurality of teaching recommendation labels corresponding to the comparison behavior feature distribution include teaching key feedback label information. Thus, in one possible implementation, in determining the target data item as the teaching recommendation policy item if the teaching creation portrait classification result indicates that tag cluster data satisfying the preset portrait template exists in the data item statistics, the following exemplary sub-steps may be implemented.

And a substep S141 of obtaining a preset portrait template corresponding to the target behavior analysis deep learning network.

And a substep S142, if the teaching establishment portrait type belongs to the teaching establishment portrait classification result of the teaching key feedback label information in the teaching establishment portrait classification result, determining label clustering data corresponding to the target teaching establishment portrait type in the label clustering data as the label clustering data meeting the preset portrait template.

In substep S143, the target data item included in the data item statistics is determined as a teaching recommendation policy item.

Further, in a possible implementation manner, still referring to step S141, in the process of updating the teaching recommendation policy of the server based on the teaching recommendation policy item and the tag cluster data corresponding to the teaching recommendation policy item and satisfying the preset portrait template, the following exemplary sub-steps may be implemented.

And a substep S144, extracting teaching recommendation information corresponding to each target label cluster classification target in label cluster data meeting the preset portrait template corresponding to the teaching recommendation strategy item, and extracting teaching visit dispute information of the teaching recommendation information in parallel while acquiring an original teaching visit result list associated with the teaching recommendation information during teaching visit from a teaching visit filling form of the teaching recommendation information.

And a substep S145, determining teaching visit update item information used for updating and analyzing the original teaching visit result list based on the extracted teaching visit dispute information, extracting update parameter types of a plurality of update items to be used and update linkage switching information among different update items from the teaching visit update item information, and performing teaching visit processing on the plurality of update items to be used according to the update parameter types and the update linkage switching information to obtain update containers of at least two target update items.

And a substep S146, updating and analyzing the original teaching visit result list through an updating container of the target updating project to obtain a candidate teaching visit result list.

And a substep S147, determining new teaching visit library updating data of the candidate teaching visit result list according to the target teaching visit dispute information determined from the thread teaching visit record of the preset virtual teaching visit thread, and determining new teaching visit library extension data of the candidate teaching visit result list according to the determined teaching visit type in the candidate teaching visit result list.

And a substep S148, performing key label clustering classification target extraction on the candidate teaching visit result list based on the updated data of the new teaching visit library and the expanded data of the new teaching visit library to obtain a key label clustering classification target set.

And a substep S144, updating the teaching recommendation strategy of the server based on the key label clustering classification target set.

For example, in a possible implementation manner, for the sub-step S144, while obtaining the original teaching visit result list associated with the teaching recommendation information at the time of the teaching visit from the teaching visit filling form of the teaching recommendation information, the following exemplary embodiments may be implemented to extract the teaching visit dispute information of the teaching recommendation information in parallel.

(1) Generating new teaching visit template front information corresponding to the form template information of the teaching visit filling form, sending the new teaching visit template front information through a software development interface pre-established with the teaching visit filling form, and detecting whether the new teaching visit state of the teaching recommendation information is in an enabled state or not while sending the new teaching visit template front information.

(2) And when the new teaching visit state is detected to be in the starting state, associating teaching visit distribution software with the new teaching visit task corresponding to the teaching recommendation information so that the original teaching visit result list obtained by querying the teaching visit filling form based on the front information of the new teaching visit template and the teaching visit dispute information extracted from the record information corresponding to the new teaching visit state are synchronously fed back by the teaching visit distribution software through the new teaching visit task corresponding to the teaching recommendation information.

(3) When detecting that the new teaching visit state is not started, generating teaching visit distribution software according to the call sequence of the new teaching visit state in a delayed manner and sending the teaching visit distribution software to a new teaching visit task corresponding to the teaching recommendation information, so that the new teaching visit task corresponding to the teaching recommendation information starts a new teaching visit state according to the teaching visit distribution software and the teaching visit dispute information extracted from the record information corresponding to the new teaching visit state, and the new teaching visit task corresponding to the teaching recommendation information is inquired from the teaching visit filling form based on the front information of the new teaching visit template in a delayed manner according to the teaching visit distribution software to obtain an original teaching visit result list, and the teaching visit dispute information and the original teaching visit result list fed back by the new teaching visit task corresponding to the teaching recommendation information are synchronously received.

For example, in a possible implementation manner, for the sub-step S145, in the process of determining, based on the extracted teaching visit dispute information, teaching visit update item information for performing update analysis on the original teaching visit result list, and extracting update parameter types of a plurality of update items to be used and update linkage switching information between different update items from the teaching visit update item information, the following exemplary implementation manner may be implemented.

(1) And determining a plurality of dispute subject distributions with different dispute problem labels from the teaching interview dispute information, and constructing a first update subject content and a second update subject content according to the dispute subject distributions.

The first updating subject content is global updating subject content, and the second updating subject content is specific object updating subject content.

(2) And mapping the record member information corresponding to any one first updating project record information in the first updating subject content to second updating project record information on a corresponding node in the second updating subject content, and determining teaching visit associated information of the record member information in the second updating project record information.

(3) And determining commonly used dispute points of the teaching visit dispute information in a set member range based on member matching parameters between the teaching visit associated information and target record member information in the second updated project record information, analyzing dispute resolution templates corresponding to the dispute points, and generating teaching visit updated project information according to information characteristics indicated by the dispute resolution templates.

(4) The method comprises the steps of listing teaching visit updating project information in a stack structure to obtain a plurality of initial updating projects, determining a teaching visit processing level of each initial updating project according to the stack level of the teaching visit updating project information, sequencing the initial updating projects according to the sequence of the teaching visit processing levels from large to small, and selecting a target number of initial updating projects which are sequenced in the front as updating projects to be used.

(5) And aiming at each update project to be used, determining a content configuration parameter and a content editing parameter of update configuration data of the update project, determining an update content service of the update project according to the content configuration parameter, and extracting an update parameter type from the update content service according to the content editing parameter.

Illustratively, in one possible implementation manner, for the sub-step S146, in the process of performing update analysis on the original teaching visit result list through the update container of the target update item to obtain the candidate teaching visit result list, the following exemplary implementation manner may be implemented.

(1) And determining an updatable unit of the original teaching visit result list from the updating container of the target updating project.

The updating unit is used for representing the updatable nodes of the original teaching visit result list in the teaching recommendation information.

(2) And determining the index teaching visit parameters of the original teaching visit result list according to the updatable nodes in the updatable unit, and acquiring the target index teaching visit parameters of the index analysis characteristics with preset duration in the index teaching visit parameters.

(3) And updating and analyzing the original teaching visit result list according to the inverse matrix of the distribution matrix corresponding to the updatable unit, and updating and analyzing a target teaching visit control item corresponding to the teaching visit behavior corresponding to the index analysis feature with preset duration of the target index teaching visit parameter in the original teaching visit result list by adopting the target index teaching visit parameter in the teaching visit processing process to obtain a candidate teaching visit result list.

Illustratively, for example, in one possible implementation, the target behavior analysis deep learning network provided in the present embodiment is obtained by training in the following manner:

(1) training sample information associated with the sample object and a teaching recommendation label of the training sample information are obtained.

For example, the training sample information includes first sample information and second sample information for training the initial behavior analysis deep learning network. The teaching recommendation label of the training sample information comprises: the non-teaching key feedback label information corresponding to the first sample information and the teaching key feedback label information corresponding to the second sample information.

(2) And performing label clustering processing on the training sample information to obtain index performance sample data corresponding to the training sample information.

(3) Extracting a first sample characteristic and a second sample characteristic from index performance sample data through an initial behavior analysis deep learning network, and performing characteristic teaching behavior characteristic distribution generation on the first sample characteristic and the second sample characteristic to obtain a sample teaching behavior characteristic distribution characteristic associated with training sample information.

(4) Training an initial behavior analysis deep learning network based on the sample teaching behavior feature distribution feature, the non-teaching key feedback label information and the teaching key feedback label information, and determining the trained initial behavior analysis deep learning network as a target behavior analysis deep learning network for predicting a target object in a target image.

Illustratively, for example, in (1), in the process of obtaining training sample information associated with a sample object and a teaching recommendation label of the training sample information, initial data item statistical data including the sample object may be first obtained, the initial data item statistical data may be used as first sample information for training an initial behavior analysis deep learning network, and label information of the first sample information may be determined as non-teaching key feedback label information.

Then, an object recognition model having an association relation with the initial behavior analysis deep learning network is obtained, and target data item statistical data associated with the initial data item statistical data is determined through the object recognition model. And then, based on the target data item statistical data and the initial data item statistical data, generating superposed data item statistical data containing the target data item statistical data, taking the superposed data item statistical data as second sample information for training the initial behavior analysis deep learning network, and determining label information of the second sample information as teaching key feedback label information.

Therefore, the first sample information and the second sample information can be determined as training sample information, and the non-teaching key feedback label information and the teaching key feedback label information can be used as teaching recommendation labels of the training sample information.

Fig. 3 is a schematic diagram of functional modules of an intelligent recommendation device 300 based on big teaching data according to an embodiment of the present disclosure, in this embodiment, the intelligent recommendation device 300 based on big teaching data may be divided into the functional modules according to a method embodiment executed by the server 100, that is, the following functional modules corresponding to the intelligent recommendation device 300 based on big teaching data may be used to execute the method embodiments executed by the server 100. The intelligent recommendation device 300 based on big teaching data may include an obtaining module 310, a generating module 320, an analyzing module 330, and an updating module 340, and the functions of the functional modules of the intelligent recommendation device 300 based on big teaching data are described in detail below.

The obtaining module 310 is configured to obtain data item statistical data including a target data item from teaching capture big data of teaching layout distribution in which teaching layout information is issued to a plurality of teaching data capture devices 200, and perform tag clustering processing on the data item statistical data to obtain tag clustering data corresponding to the data item statistical data. The obtaining module 310 may be configured to perform the step S110, and the detailed implementation of the obtaining module 310 may refer to the detailed description of the step S110.

The generating module 320 is configured to obtain a target behavior analysis deep learning network corresponding to the data item statistical data, extract a first description component and a second description component from the tag clustering data through the target behavior analysis deep learning network, and generate teaching behavior feature distribution for the first description component and the second description component to obtain teaching behavior feature distribution associated with the data item statistical data. The generating module 320 may be configured to perform the step S120, and the detailed implementation of the generating module 320 may refer to the detailed description of the step S120.

And the analysis module 330 is configured to analyze the deep learning network according to the teaching behavior feature distribution and the target behavior, perform teaching setup portrait classification on the tag clustering data, and obtain a teaching setup portrait classification result corresponding to the tag clustering data. The analysis module 330 may be configured to perform the step S130, and the detailed implementation of the analysis module 330 may refer to the detailed description of the step S130.

And the updating module 340 is configured to determine the target data item as a teaching recommendation policy item if the teaching creation portrait classification result indicates that the statistical data of the data item includes tag clustering data meeting the preset portrait template, and update the teaching recommendation policy of the server based on the teaching recommendation policy item and the tag clustering data meeting the preset portrait template corresponding to the teaching recommendation policy item. The updating module 340 may be configured to perform the step S140, and the detailed implementation of the updating module 340 may refer to the detailed description of the step S140.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules may all be implemented in software invoked by a processing element. Or may be implemented entirely in hardware. And part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the obtaining module 310 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the processing element of the apparatus calls and executes the functions of the obtaining module 310. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

Fig. 4 is a schematic diagram illustrating a hardware structure of a server 100 for implementing the intelligent recommendation method based on instructional big data according to the embodiment of the disclosure, and as shown in fig. 4, the server 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, at least one processor 110 executes computer-executable instructions stored in the machine-readable storage medium 120 (for example, the obtaining module 310, the generating module 320, the analyzing module 330, and the updating module 340 included in the intelligent recommendation device 300 based on instructional big data shown in fig. 3), so that the processor 110 may execute the intelligent recommendation method based on instructional big data according to the above method embodiment, where the processor 110, the machine-readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control transceiving actions of the transceiver 140, so as to transceive data with the instructional data capture device 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the server 100, which implement similar principles and technical effects, and this embodiment is not described herein again.

In the embodiment shown in fig. 4, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The machine-readable storage medium 120 may comprise high-speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.

The bus 130 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus 130 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus.

In addition, the embodiment of the invention also provides a readable storage medium, wherein the readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the intelligent recommendation method based on the big teaching data is realized.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in 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 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. 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 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 this description may be performed 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 present description may be represented as a computer product, including computer-readable program content, embodied in one or more computer-readable media.

The computer storage medium may comprise a propagated data signal with the computer program content embodied therein, for example, on a 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, or device. Program content 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 content required for the operation of various portions of this specification 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 content may run entirely on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer or entirely on the remote computer or server. 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).

Additionally, the order in which the elements and lists are processed, the use of letters and numbers, or other designations in this specification are not intended to limit the order of the processes and methods in this specification, unless otherwise specified in the claims. 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 server or mobile device.

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

Finally, it should be understood that the examples in this specification are only intended to illustrate the principles of the examples in this specification. Other variations are also possible within the scope of this 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 intelligent recommendation method based on big teaching data is applied to a server, the server is in communication connection with a plurality of teaching data capturing devices, and the method comprises the following steps:

2. The intelligent recommendation method based on teaching big data according to claim 1, wherein the step of obtaining data item statistics data including target data items in teaching captured big data of teaching layout distribution of teaching layout information issued to the plurality of teaching data capturing devices, and performing label clustering processing on the data item statistics data to obtain label clustering data corresponding to the data item statistics data comprises:

3. The intelligent recommendation method based on big teaching data as claimed in claim 1, wherein the number of the tag clustering data is plural;

4. The intelligent recommendation method based on instructional big data according to claim 1, wherein the target behavior analysis deep learning network comprises: a classification module; the classification module has the function of predicting and classifying the teaching establishment portrait type to which the label clustering data corresponding to the data item statistical data belongs;

5. The intelligent recommendation method based on big teaching data as claimed in claim 4, wherein a label cluster data corresponds to a teaching creation portrait classification result; the teaching recommendation labels corresponding to the comparison behavior characteristic distribution comprise teaching key feedback label information;

6. The intelligent recommendation method based on teaching big data according to any one of claims 1-5, wherein the step of updating the teaching recommendation strategy of the server based on the teaching recommendation strategy item and the tag cluster data corresponding to the teaching recommendation strategy item and meeting a preset portrait template comprises:

7. The intelligent recommendation method based on big teaching data as claimed in claim 6, wherein said step of extracting the dispute information of the teaching visit of the teaching recommendation information in parallel while obtaining the original teaching visit result list associated with the teaching recommendation information at the time of teaching visit from the teaching visit filling form of the teaching recommendation information comprises:

8. The intelligent recommendation method based on big teaching data as claimed in claim 6, wherein the step of determining updated teaching visit item information for performing update analysis on the original teaching visit result list based on the extracted teaching visit dispute information, and extracting update parameter types of a plurality of update items to be used and update linkage switching information between different update items from the updated teaching visit item information comprises:

9. The intelligent recommendation method based on big teaching data as claimed in claim 6, wherein the step of performing update analysis on the original teaching visit result list through the update container of the target update item to obtain a candidate teaching visit result list comprises:

10. A server, comprising a processor, a machine-readable storage medium, and a network interface, wherein the machine-readable storage medium, the network interface, and the processor are connected by a bus system, the network interface is configured to be communicatively connected with at least one instructional data capture device, the machine-readable storage medium is configured to store a program, instructions, or code, and the processor is configured to execute the program, instructions, or code in the machine-readable storage medium to perform the instructional big data based intelligent recommendation method of any one of claims 1 to 9.