Content reservation and recommendation method for AI online education

Abstract

The invention discloses a content reservation and recommendation method for AI online education, and the method comprises the steps: enabling a server to sequentially transmit an original video stream to all student ends through a preset number of other routers and a gateway router for a recorded broadcast course or a delayed live broadcast course; sending the generated content directory information and preset recommendation information to all student ends, wherein the gateway router has the functions of a gateway and a router; according to the method, the content points are reserved based on the recommendation information, and the playing speed is adaptively adjusted in the course playing process, so that the individuation and efficiency of learning are improved; according to the method, after each appointment content is played, the question is provided for the student to answer, and the learning effect of the student is improved and interactive feedback is realized by judging the answering accuracy and sending the detailed solution video stream to the student end.

Description

Technical Field

[0001] The present invention belongs to the technical field of online education, and particularly relates to a method for content reservation and recommendation in AI online education. Background Art

[0002] In the online education scenario, each student has different concerns about the course content and hopes to achieve personalized education, that is, it is necessary to achieve course content positioning, speed-adjustable playback, understanding degree assessment, and on-demand detailed explanation of key content according to the content concerns of different students.

[0003] Currently, some recorded or live courses also provide course content introductions and catalogs to help students better understand the courses. Students can make reservations for the entire course, but do not support making reservations for partial content within the course, nor support intelligent speed adjustment during playback based on whether the student is concerned about the content. It is impossible to make smaller-granularity course content reservations and adaptive playback based on reservations according to different student situations, lacking flexibility and personalization in course viewing. In addition, it does not support interactive feedback for content points and on-demand detailed explanation of key content. Summary of the Invention

[0004] The purpose of the present invention is to propose a method for content reservation and recommendation in AI online education to solve the problems raised in the background art.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] A method for content reservation and recommendation in AI online education proposed by the present invention includes:

[0007] For recorded courses or delayed live courses, while the server sends the original video stream to all student terminals through a preset number of other routers and gateway routers in sequence, it sends the generated content directory information and preset recommendation information to all student terminals, where the gateway router has the functions of a gateway and a router;

[0008] Each student makes content reservations on the corresponding student terminal based on the preset recommendation information as needed;

[0009] When each student terminal plays the course, it detects whether it is the reserved content and makes an adaptive adjustment of the playback speed;

[0010] After each student terminal finishes playing a content point, the server sends questions related to the current content point to the student terminal for the students to answer. The student terminal pauses the playback of the original video stream and determines whether the accuracy rate of the students' answers reaches a first threshold. If it reaches the first threshold, the original video stream is continued to be played. If it does not reach the first threshold, a detailed video stream request for the corresponding content point is sent to the server, and the gateway router stops sending the original video stream to the student terminals that do not reach the first threshold.

[0011] After the server receives the detailed video stream requests for each content point, it sends a first response message to the corresponding student terminal.

[0012] Each corresponding student terminal parses the received first response message. When the status of the first response message is accepted, a corresponding detailed video stream request message is sent to the server according to the parsed content.

[0013] Then the server forwards the detailed video stream to the gateway router of the corresponding student terminal through a preset number of other routers.

[0014] The gateway router of each student terminal sends the detailed video stream to the student terminals that do not reach the first threshold and caches the original video stream. When the cache space utilization rate of the gateway router is greater than a third threshold, a cache request message is sent to other routers upstream adjacent to it.

[0015] Preferably, the content directory information includes recorded broadcast content directory information and live broadcast content directory information.

[0016] For recorded broadcast courses, the complete audio of the course is identified and content points and key content points are marked to form recorded broadcast content directory information. The recorded broadcast content directory information includes: directory ID, course ID, course type, creation time, content point serial number, content point name, content point type, content point description, content point start timestamp, content point end timestamp, and whether each content point is a key content point.

[0017] For delayed live broadcast courses, the course introduction of the teacher is identified and content points and key content points are marked to form live broadcast content directory information. The live broadcast content directory information includes: directory ID, course ID, course type, creation time, content point serial number, content point name, content point type, content point description, and whether each content point is a key content point.

[0018] Preferably, each student makes content reservations based on preset recommendation information on the corresponding student terminal as needed, including:

[0019] For recorded courses, the preset recommended information includes at least three pieces of recommended information: recommendation based on the student's own historical appointment content point preferences, recommendation based on key content points, and recommendation based on historical playback content points of other student terminals;

[0020] For delayed live courses, the preset recommended information includes at least three pieces of recommended information: recommendation based on the student's own historical appointment content point preferences, recommendation based on key content points, and recommendation based on real-time appointment information of other student terminals;

[0021] Each student makes an appointment or not for the content according to the recommended information as needed;

[0022] Among them, for the recommendation based on real-time appointment information of other student terminals, each student terminal sends the appointment content point information to the teacher terminal and all other student terminals, and the student terminal counts the received appointment content point information, calculates the appointment rate of each content point, and uses the content points with the appointment rate exceeding the preset recommended threshold as the recommendation of real-time appointment information of other student terminals.

[0023] Preferably, when each student terminal plays a recorded course or a delayed live course, it detects whether it is an appointed content and makes an adaptive adjustment of the playback speed, including:

[0024] For recorded courses, the student terminal detects the current playback time point. If the current playback time point is between the start timestamp and the end timestamp of the appointed content, it plays at a reduced speed according to the first preset speed; otherwise, it plays at an accelerated speed according to the second preset speed;

[0025] For delayed live courses, the student terminal dynamically extracts the audio of the currently played video stream and performs text extraction. Through natural language processing technology, it vectorizes the extracted text and the appointed content of the current student terminal respectively, and calculates the difference between the two vectors. If the difference is less than the second threshold, it plays at a reduced speed according to the first preset speed; otherwise, it plays at an accelerated speed according to the second preset speed;

[0026] When a student does not make an appointment for all content points, the corresponding student terminal makes an adaptive adjustment of the playback speed according to the recommendation of key content points;

[0027] For recorded courses, when a student does not make an appointment for all content points and there are no key content points, the corresponding student terminal makes an adaptive adjustment of the playback speed according to the recommendation of historical playback content points of other student terminals.

[0028] Preferably, the detailed video stream request includes a message ID, a message type, a student ID, a creation time, a course ID, and a content point detailed video stream ID;

[0029] The first response information includes a message ID, a message type, a student ID, a creation time, a response status, a multicast group address, an original video stream port, and a detailed explanation video stream port;

[0030] The fields of the detailed explanation video stream request message include a message type, a checksum, a multicast group address, an original video stream port, and a detailed explanation video stream port. Among them, the student side adds the original video stream port and the detailed explanation video stream port in the parsed first response information to the IGMP v2 message to form the detailed explanation video stream request message.

[0031] Preferably, when the student side sends a detailed explanation video stream request message to the server, it is forwarded to the server through the gateway server and other routers. After receiving the detailed explanation video stream request message, the gateway server parses it and records the original video stream port and the detailed explanation video stream port. The gateway router receives the original video stream and the detailed explanation video stream and distinguishes the original video stream and the detailed explanation video stream according to the destination port number information of the video stream based on the ACL access control list rules on the gateway router.

[0032] Preferably, between each student side and the server, there is a gateway router located at the student side, and n other routers. The n other routers are sequentially represented as the first router P1, the second router P2,..., the nth router Pn from the gateway router to the server direction;

[0033] When the gateway router caches the original video stream, it records the time point t1 when the caching of the original video stream starts and stores it in the mapping table, and continuously monitors whether the cache space utilization rate is greater than the third threshold. When it is greater than the third threshold, it sends a cache request message to the first router P1 adjacent upstream of it;

[0034] After receiving the cache request message, the first router P1 decides whether to accept the cache request according to its own cache space;

[0035] When the first router P1 accepts the cache request, it sends the accepted second response information to the gateway router. The gateway router records the IP address of the first router P1 in the accepted second response information, and records the time point t2 when the first router P1 starts caching the original video stream and stores it in the mapping table. At the same time, the gateway router itself stops caching the original video stream, and the first router P1 starts caching the original video stream at the time point t2;

[0036] When the first router P1 rejects the cache request, it sends the rejected second response information to the gateway router. The gateway router stops sending the detailed explanation video stream to the student side that has not reached the first threshold, and resends the original video stream to the student side that has not reached the first threshold.

[0037] Preferably, when the first router P1 caches the original video stream, it continuously monitors whether the cache space utilization rate is greater than the third threshold, and when it is greater than the third threshold, it sends a cache request message to the second router P2 adjacent to its upstream;

[0038] After receiving the cache request message, the second router P2 decides whether to accept the cache request according to its own cache space;

[0039] When the second router P2 accepts the cache request, it simultaneously sends the accepted third response information to the first router P1 adjacent to its downstream and the gateway router. The gateway router records the IP address of the second router P2 in the accepted third response information, and records the time point t3 when the second router P2 starts caching the original video stream and stores it in the mapping table. At the same time, the first router P1 stops caching the original video stream by itself, and the second router P2 starts caching the original video stream at the time point t3;

[0040] When the second router P2 rejects the cache request, it only sends the rejected third response information to the first router P1 adjacent to its downstream, and the first router P1 sends the rejected second response information to the gateway router. At this time, the gateway router stops sending the detailed video stream to the student terminals that do not reach the first threshold, and resends the original video stream to the student terminals that do not reach the first threshold;

[0041] When the cache space utilization rate of one of the n other routers, say another router Px, is always less than the third threshold, it stops sending cache request messages to the other routers adjacent to its upstream, and the gateway router records the time point t(x + 1) when the other router Px starts caching the original video stream and stores it in the mapping table;

[0042] Among them, the mapping table stores the mapping relationship between the time points when the original video stream starts caching and the cache devices, and the cache devices are each router.

[0043] Preferably, the content reservation and recommendation method of the AI online education further includes: when the playing of the detailed video stream request ends at the student terminal, the corresponding student terminal sends an original video stream request message to the gateway router;

[0044] After receiving the original video stream request message, the gateway router selects the earliest time point t1 for recording the original video stream according to the mapping table, and sends the original video stream with the start time point t1 to the corresponding student terminal;

[0045] When the gateway router sends the original video stream to the time point t2, according to the mapping table, the gateway router sends an original video stream request message to the first router P1, which is the cache device corresponding to the cache start time point t2;

[0046] After the first router P1 receives the original video stream request information, it forwards the original video stream with the start time point t2 to the corresponding student end through the gateway router;

[0047] When the network router forwards the original video stream to the time point t3, according to the mapping table, the network router sends the original video stream request information to the second router P2, which is a caching device corresponding to the caching start time point t3;

[0048] After the second router P2 receives the original video stream request information, it forwards the original video stream with the start time point t3 to the corresponding student end through the gateway router;

[0049] And so on, until after other routers Px receive the original video stream request information, they forward the original video stream with the start time point t(x + 1) to the corresponding student end through the gateway router.

[0050] Preferably, the content reservation and recommendation method of the AI online education further includes: after each router sends the original video stream to the corresponding student end, it clears the cache of the sent original video stream;

[0051] After the gateway router clears the cache, when it monitors that the cache space utilization rate of the gateway router is less than the fourth threshold, it sends a stop caching request message to other routers Px that are caching the latest data of the original video stream;

[0052] After other routers Px receive the stop caching request message from the gateway router, if they accept the stop caching, then other routers Px stop caching the original video stream and send a stop caching request response message with the response status of acceptance to the gateway router;

[0053] After the gateway router receives the stop caching request response message of acceptance, it resumes caching the remaining uncached original video stream.

[0054] Compared with the prior art, the beneficial effects of the present invention are:

[0055] 1. This method reserves content points based on recommendation information and adaptively adjusts the playback speed during the course of playing the course, thereby improving the personalization and efficiency of learning;

[0056] 2. After each reserved content is played, this method provides questions for students to answer, and through the judgment of the answer accuracy rate and sending a detailed explanation video stream to the student end, it improves the learning effect of students and realizes interactive feedback;

[0057] 3. For students who need a detailed explanation, while each router forwards the detailed explanation video, it caches the original video data, ensuring that after the students finish watching the detailed explanation video, they can seamlessly continue to watch the original video, improving the continuity and fluency of learning. In addition, each router can also send cache requests to the upstream routers according to the usage of the cache space, realizing the dynamic allocation and optimization of cache resources;

[0058] 4. Based on the IGMPv2 message, this method adds new fields to obtain the detailed explanation video stream request message, and uses the new fields to identify the specific content points of the request, enhancing the flexibility and practicality of the protocol; and by identifying the specific content points of the request, it enhances the flexibility and practicality of the protocol and sends the corresponding video streams respectively, which not only retains the efficiency of multicast, reduces the network complexity, but also realizes the differentiation of different video streams by the gateway router, avoiding the limitation that all members receive the same content in traditional multicast, and providing technical support for personalized learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flowchart of the content reservation and recommendation method for AI online education of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0061] As Figure 1 shown, a content reservation and recommendation method for AI online education is provided. First of all, it should be noted that: recorded courses refer to pre-recorded video courses, and students can watch or listen to the course content through the Internet at any time and any place; delayed live courses refer to live courses but the server sends the original video stream with a slight delay (such as 5 minutes), and the student side can watch the course almost in real time, and at the same time, the content that has not been played can be cached locally, which can be used for accelerated playback.

[0062] The content reservation and recommendation method for this AI online education includes:

[0063] Step 1. For recorded courses or delayed live courses, while the server sends the original video stream to all student terminals through a preset number of other routers and gateway routers in sequence (that is, while the server sends the original video stream to all student terminals through each router on the network link between the server and the student terminals (including the gateway router on the student terminal side and other routers upstream of it)), the generated content directory information and preset recommendation information are sent to all student terminals, where the gateway router has the functions of a gateway and a router;

[0064] Among them, the recorded courses or delayed live courses on the teacher side send video streams in a multicast manner through the server, and each student side receives the video streams for playback; between each student side and the server, there is a gateway router located on the student side and n other routers, and the n other routers are successively represented as the first router P1, the second router P2,..., the nth router Pn from the gateway router to the server direction (where the adjacent upstream other router of a certain other router is the other router adjacent to and closer to the server side of this certain other router).

[0065] Among them, the content directory information includes recorded content directory information (statically generated in advance) and live content directory information (dynamically generated in real time);

[0066] For recorded courses, the complete audio of the course is recognized in advance (the text can be extracted through speech recognition technology and the content points and key content points can be extracted through natural language processing technology, which belongs to the prior art and will not be described in detail), and the content points and key content points are marked (where the recognition of key content points means that the teacher specifically points out as key content during the explanation. For example, when the teacher says "Next, we will introduce the working principle of the large model. This part of the content is very important. Please listen carefully", then "the working principle of the large model" is not only marked as a content point but also marked as a key content point), forming the recorded content directory information, and the recorded content directory information includes: directory ID, course ID, course type (delayed live course or recorded course), creation time, content point serial number, content point name, content point type, content point description, content point start timestamp, content point end timestamp, and whether each content point is a key content point;

[0067] For delayed live courses, the course introduction of the teacher is recognized and the content points and key content points are marked (after the teacher starts the delayed live course, first introduce the content of this course in general (at this time, you can first click the "voice input" button of the course introduction on the teacher side, and then click "end input" after the general introduction is completed, so as to complete the segment marking of the introduction part)), forming the live content directory information (for example, when the teacher introduces at the beginning of the course live broadcast "Today, our course has three parts. First, we will introduce the basic concept of the large model, then introduce the working principle of the large model, and finally introduce the application scenario of the large model. Among them, the working principle of the large model is the key content", then the content directory information is marked as: 1. Basic concept of the large model; 2. Working principle of the large model (key content); 3. Application scenario of the large model), and the live content directory information includes: directory ID, course ID, course type, creation time, content point serial number, content point name, content point type (such as basic concept, technical principle, development trend, application scenario, etc.), content point description, and whether each content point is a key content point.

[0068] Step 2. Each student makes content reservations on the corresponding student side based on the preset recommended information as needed, including:

[0069] For recorded courses, the preset recommended information includes at least three recommended information: recommended based on the student's own historical reservation content point preferences, recommended based on key content points, and recommended based on the historical playback content points of other student sides.

[0070] For delayed live courses, the preset recommended information includes at least three recommended information: recommended based on the student's own historical reservation content point preferences, recommended based on key content points, and recommended based on the real-time reservation information of other student sides.

[0071] Each student makes content reservations (can reserve multiple or one) or not according to the recommended information (on their respective student sides) as needed.

[0072] Among them, the recommendation based on the student's own historical reservation content point preferences: Analyze the student's preferences based on the student's historical reservation content points, and label the student's learning preferences through data profiling. For example, the learning preference labels are basic concepts, technical principles, development trends, application scenarios, etc. Match the content point types of the content points in this course with the student's learning preference labels, and recommend the content points with successful matches to the student.

[0073] Among them, the recommendation based on key content points: That is, the content points emphasized by the teacher.

[0074] Among them, the recommendation based on the historical playback content points of other student sides: Among all the content points of the current recorded course, recommend the content points whose historical playback rate (the ratio of the number of students who have played back this content point to the total number of students who have watched the recorded course historically) exceeds the recommended threshold (such as 50%).

[0075] Among them, for the recommendation based on the real-time reservation information of other student sides, each student side sends the reservation content point information to the teacher side and all other student sides (while receiving the content reservation information of other student sides), and the student side counts the received reservation content point information, dynamically calculates the reservation rate of each content point (that is, the ratio of the number of students who have reserved the current content point to the total number of students), and uses the content points whose reservation rate exceeds the preset recommended threshold (such as 40%) as the recommendation of the real-time reservation information of other student sides; among them, after receiving and summarizing the content reservation information of all student sides, the teacher side displays the reservation situation (that is, displays the current reservation rate of each content point), and the teacher can understand the overall attention of the students in this course to the content points, and can adjust the detailed degree of content explanation in the subsequent explanation. For example, introduce the content points with high reservation rates in more detail, and appropriately streamline the content points with low reservation rates and non-important knowledge points.

[0076] It should be noted that after this reservation, students can also make or cancel reservations for the reserved content points that have not reached the playback point during the subsequent course viewing process (for the content points that have already been played, cancellation of reservations is not allowed).

[0077] Step 3: When each student terminal plays the course (recorded course or delayed live course), it detects whether it is reserved content and makes an adaptive adjustment to the playback speed (when the student terminal initially views the course, it plays at the normal speed, i.e., 1x speed), including:

[0078] For recorded courses, the student terminal detects the current playback time point. If the current playback time point is between the start timestamp and the end timestamp of the reserved content, it plays at a reduced speed according to the first preset speed (such as 0.9x speed); otherwise, it plays at an increased speed according to the second preset speed (such as 1.1x speed).

[0079] For delayed live courses, the student terminal dynamically extracts the audio of the currently played video stream and performs text extraction (text can be extracted through speech recognition technology). Through natural language processing technology, the extracted text and the reserved content of the current student terminal (for each student terminal, the reserved content on each student terminal is the content reserved by the corresponding student) are vectorized, and the difference between the two vectors is calculated. If the difference is less than the second threshold (the smaller the difference, the higher the similarity between the two vectors), it plays at a reduced speed according to the first preset speed; otherwise, it plays at an increased speed according to the second preset speed.

[0080] When a student has not reserved any content points, the corresponding student terminal makes an adaptive adjustment to the playback speed according to the recommended key content points (the specific adaptive adjustment process is the same as the adaptive adjustment in this Step 3).

[0081] For recorded courses, when a student has not reserved any content points and there are no key content points, the corresponding student terminal makes an adaptive adjustment to the playback speed according to the recommended historical playback content points of other student terminals (the specific adaptive adjustment process is the same as the adaptive adjustment in this Step 3).

[0082] Step 4. For recorded courses or delayed live courses, after each content point is played on each student terminal, the server sends questions related to the current content point to the student terminal for the students to answer (the number of questions can be set according to actual needs, such as 3 - 5, and the questions are displayed in a pop - up window on the student terminal), pauses the playback of the original video stream on the student terminal, and determines whether the accuracy rate of the students' answers reaches the first threshold (such as 60%). If it reaches the first threshold, the original video stream continues to be played. If it does not reach the first threshold, a detailed video stream request for the corresponding content point is sent to the server (when the student terminal determines that the answer accuracy rate is lower than the first threshold, the student terminal will prompt the student that "in view of the fact that your answer accuracy rate for the current content point is lower than 60%, the system will explain this part of the content in detail again!". After the student confirms, the student terminal sends a detailed video stream request for the corresponding content point to the server), and the gateway router stops sending the original video stream to the student terminals that do not reach the first threshold (and caches the original video stream). Among them, the detailed video stream request includes the message ID, message type, student ID, creation time, course ID, and content point detailed video stream ID.

[0083] It should be noted that the transmission of the detailed video stream request and the subsequent first response information detailed video stream request message between the server and the student terminal is forwarded through the gateway router and other routers.

[0084] Step 5. After receiving the detailed video stream requests for each content point, the server sends the first response information to the corresponding student terminal; the first response information includes the message ID, message type, student ID, creation time, response status (accepted or rejected), multicast group address, original video stream port, and detailed video stream port;

[0085] Among them, when the response status in the first response information is accepted, an accepted response message (response status is 1) is sent, notifying the student terminal that it will send the original video stream and the detailed video stream with the multicast group address G. The original video stream uses port Port1 (such as 5004), and the detailed video stream uses port Port2 (such as 5005); then, the server sends two streams using the same multicast group address (G) but different UDP ports according to the first response information. The original normal - playing video uses Port1, and the detailed - explanation video uses Port2.

[0086] When the response status in the first response information is rejected, a rejected response message (response status is 0) is sent, notifying the student terminal to reject the detailed video stream request. In the first response information, the multicast group address, original video stream port, and detailed video stream port are all set to 0.

[0087] Step 6: Each corresponding student terminal parses the first response message. When the status of the first response message is "accepted", a corresponding detailed video stream request message is sent to the server according to the parsed content;

[0088] Among them, the fields of the detailed video stream request message include message type (i.e., Type, which is an existing field in the IGMPv2 message. A new type is added to the IGMP v2 message, and the value is 0x18), checksum (i.e., Checksum, which is an existing field in the IGMPv2 message, the checksum, calculate the message checksum and fill it into this field), multicast group address (i.e., Group Address, which is an existing field in the IGMPv2 message), original video stream port (i.e., Original VideoPort, which is a newly added field), and detailed video stream port (i.e., Detailed VideoPort, which is a newly added field). The student terminal adds the original video stream port and the detailed video stream port in the parsed first response message to the IGMP v2 message to form a detailed video stream request message (IGMPv2: IGMPv2 (Internet Group Management Protocol version 2) is a network protocol used for communication between hosts (referring to student terminals) and adjacent routers to report the multicast groups that the hosts want to join or leave, so that the routers can know which multicast traffic needs to be forwarded on the network. It manages multicast group members by sending IGMP query and report messages to ensure that only interested receivers can receive multicast data).

[0089] Among them, when the student terminal sends a detailed video stream request message to the server, it is forwarded to the server through the gateway server and each other router. After receiving the detailed video stream request message, the gateway server parses it and records the original video stream port and the detailed video stream port (i.e., after receiving the student terminal's detailed video stream request message, the gateway router parses it and updates its multicast forwarding list, recording the multicast group address as G, the original video stream port as Port1, and the detailed video stream port as Port2).

[0090] Step 7: After receiving the detailed video stream request message, the server forwards the detailed video stream to the gateway router of the corresponding student terminal through a preset number of other routers;

[0091] It should be noted that the gateway router and other routers use the multicast routing protocol to maintain the forwarding routing information of the multicast group. The detailed video stream with the multicast group address G sent by the server is forwarded through the routing information by other routers and finally sent to the gateway router (the original video stream is also forwarded through the routing information by other routers and finally sent to the gateway router);

[0092] The gateway router receives the original video stream and the detailed video stream, and differentiates the original video stream and the detailed video stream according to the video stream ports in the ACL access control list rules (after the gateway router receives the original video stream and the detailed video stream, based on the five-tuple (source IP address, destination IP address, source port number, destination port number, protocol type) filtering method, the original video stream and the detailed video stream are identified and differentiated through the ACL rules (server IP and video stream port)).

[0093] Step 8: The gateway routers of each student terminal send the detailed video stream to the student terminals that have not reached the first threshold (to the student terminals corresponding to the students who have not reached the first threshold), cache the original video stream, and when the cache space utilization rate of the gateway router is greater than the third threshold, a cache request message is sent to other routers upstream adjacent to it.

[0094] Among them, when the gateway router caches the original video stream, it records the time point t1 when the caching of the original video stream starts and stores it in the mapping table, continuously monitors whether the cache space utilization rate is greater than the third threshold (such as 70%), and when it is greater than the third threshold, a cache request message is sent to the first router P1 upstream adjacent to it;

[0095] After receiving the cache request message, the first router P1 decides whether to accept the cache request according to its own cache space (for example, when its own cache space is already greater than the third threshold, the cache request is rejected);

[0096] When the first router P1 accepts the cache request, it sends the accepted second response message to the gateway router, and the gateway router records the IP address of the first router P1 in the accepted second response message, and records the time point t2 when the first router P1 starts caching the original video stream and stores it in the mapping table, and the gateway router itself stops caching the original video stream, and at the same time the first router P1 starts caching the original video stream at the time point t2;

[0097] When the first router P1 rejects the cache request, it sends the rejected second response message to the gateway router, and the gateway router stops sending the detailed video stream to the student terminals that have not reached the first threshold, and resends the original video stream to the student terminals that have not reached the first threshold (and sends the reason, such as "Since the video stream cannot be cached continuously, to ensure the normal playback of the course, the detailed video stream is interrupted this time);

[0098] Similarly, when the first router P1 caches the original video stream, it continuously monitors whether the cache space utilization rate is greater than the third threshold, and when it is greater than the third threshold, a cache request message is sent to the second router P2 upstream adjacent to it;

[0099] After receiving the cache request message, the second router P2 decides whether to accept the cache request according to its own cache space;

[0100] When the second router P2 accepts the caching request, it simultaneously sends the accepted third response information to the first router P1 and the gateway router adjacent to its downstream. The gateway router records the IP address of the second router P2 in the accepted third response information, and records the time point t3 when the second router P2 starts caching the original video stream and stores it in the mapping table. At the same time, the first router P1 stops caching the original video stream by itself, and the second router P2 starts caching the original video stream at the time point t3;

[0101] When the second router P2 rejects the caching request, it only sends the rejected third response information to the first router P1 adjacent to its downstream. The first router P1 sends the rejected second response information to the gateway router. At this time, the gateway router stops sending the detailed video stream to the student terminals that do not reach the first threshold, and resends the original video stream to the student terminals that do not reach the first threshold;

[0102] And so on, until among the n other routers, the cache space utilization rate of one other router Px is always less than the third threshold, then stop sending the caching request message to the other routers adjacent to its upstream. The gateway router records the time point t(x + 1) when the other router Px starts caching the original video stream and stores it in the mapping table (in this embodiment, when the second router P2 caches the original video stream, the cache space utilization rate does not exceed the third threshold, that is, the original video stream has been cached in the second router P2);

[0103] Among them, the mapping table stores the mapping relationship between each time point when the original video stream starts caching and the caching device, and the caching device is each router.

[0104] The content reservation and recommendation method for AI online education further includes: when the detailed video stream request ends in the student terminal (or the student terminal actively exits the content point detailed video playback), the corresponding student terminal sends the original video stream request information to the gateway router;

[0105] After receiving the original video stream request information, the gateway router selects the earliest time point t1 for recording the original video stream according to the mapping table, and sends the original video stream with the start time point t1 to the corresponding student terminal;

[0106] When the gateway router sends the original video stream to the time point t2, according to the mapping table, the gateway router sends the original video stream request information to the first router P1, which is the caching device corresponding to the cache start time point t2;

[0107] After receiving the original video stream request information, the first router P1 forwards it through the gateway router and sends the original video stream with the start time point t2 to the corresponding student terminal;

[0108] When the gateway router forwards the original video stream to time point t3, according to the mapping table, the gateway router sends the original video stream request information to the cache device, the second router P2, corresponding to the cache start time point t3.

[0109] After receiving the original video stream request information, the second router P2 forwards the original video stream with the start time point t3 to the corresponding student side through the gateway router.

[0110] And so on, until after other routers Px receive the original video stream request information, they forward the original video stream with the start time point t(x + 1) to the corresponding student side through the gateway router.

[0111] The content reservation and recommendation method for AI online education further includes: after each router (including the gateway router and other routers) sends the original video stream to the corresponding student side, it clears the cache of the sent original video stream.

[0112] After the gateway router clears the cache, when it monitors that the cache space utilization rate of the gateway router is less than the fourth threshold (where the fourth threshold is less than the third threshold), it sends a stop caching request message to other routers Px that are caching the latest data of the original video stream (in this embodiment, it sends a stop caching request message to the second router P2).

[0113] After other routers Px receive the stop caching request message from the gateway router, if they accept the stop caching, then other routers Px stop caching the original video stream and send a stop caching request response message with an accepted response status to the gateway router.

[0114] After the gateway router receives the accepted stop caching request response message, it resumes caching the remaining uncached original video stream.

[0115] Finally, return to step 3 and continue to execute in the order of the steps.

[0116] In another embodiment, the present application further includes a content reservation and recommendation device for AI online education, including a processor and a memory storing a number of computer instructions. When the computer instructions are executed by the processor, the steps of the method in steps 1 - 3 are implemented.

[0117] This method makes reservations for content points based on recommended information and adaptively adjusts the playback speed during the course of playing the course, thereby improving the personalization and efficiency of learning. After each reserved content is played, this method provides questions for students to answer, and by judging the accuracy rate of the answers and sending a detailed video stream to the student side, it improves the learning effect of students and realizes interactive feedback. For students who need detailed explanations, while each router forwards the detailed explanation video, it caches the original video data, ensuring that after the student finishes watching the detailed explanation video, they can seamlessly continue to watch the original video, enhancing the continuity and smoothness of learning. In addition, each router can also send cache requests to the upstream routers according to the usage of the cache space, realizing the dynamic allocation and optimization of cache resources. This method is based on IGMPv2 packets, adds a new field to obtain the detailed video stream request packet, and uses the new field to identify the specific content point of the request, enhancing the flexibility and practicality of the protocol. And by identifying the specific content point of the request, it enhances the flexibility and practicality of the protocol and sends the corresponding video streams respectively, which not only retains the high efficiency of multicast, reduces the network complexity, but also realizes the differentiation of different video streams by the gateway router, and can avoid the limitation that all members receive the same content in traditional multicast, providing technical support for personalized learning.

[0118] It should be understood that although Figure 1 the steps in the flowchart of Figure 1 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover,

[0119] The above-described embodiments only represent several implementation manners of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A content reservation and recommendation method for AI online education, characterized in that: The content reservation and recommendation method for the AI online education includes: For recorded courses or delayed live courses, while the server sends the original video stream to all student terminals sequentially through a preset number of other routers and gateway routers, it also sends the generated content directory information and preset recommendation information to all student terminals, where the gateway router has the functions of a gateway and a router; Each student makes content reservations based on the preset recommendation information on the corresponding student terminal as needed; When each student terminal plays a course, it detects whether it is the reserved content and makes an adaptive adjustment to the playback speed; After each student terminal finishes playing a content point, the server sends a question related to the current content point to the student terminal for the student to answer, and the student terminal pauses the playback of the original video stream, and determines whether the accuracy rate of the student's answer reaches the first threshold. If it reaches the first threshold, the original video stream continues to be played. If it does not reach the first threshold, a detailed video stream request for the corresponding content point is sent to the server, and the gateway router stops sending the original video stream to the student terminals that do not reach the first threshold; After the server receives the detailed video stream requests for each content point, it sends a first response message to the corresponding student terminal; Each corresponding student terminal parses the received first response message, and when the status of the first response message is accepted, it sends a corresponding detailed video stream request message to the server according to the parsed content; Then the server forwards the detailed video stream to the gateway router of the corresponding student terminal through a preset number of other routers; The gateway router of each student terminal sends the detailed video stream to the student terminals that do not reach the first threshold, caches the original video stream, and when the usage rate of the cache space of the gateway router is greater than the third threshold, it sends a cache request message to the other routers adjacent upstream; 2. The content reservation and recommendation method for AI online education according to claim 1, characterized in that: The content directory information includes recorded content directory information and live content directory information; For recorded courses, the complete audio of the course is identified and content points and key content points are marked to form recorded content directory information, and the recorded content directory information includes: directory ID, course ID, course type, creation time, content point serial number, content point name, content point type, content point description, content point start timestamp, content point end timestamp, and whether each content point is a key content point; For delayed live courses, the teacher's course introduction is identified and content points and key content points are marked to form live content directory information, and the live content directory information includes: directory ID, course ID, course type, creation time, content point serial number, content point name, content point type, content point description, and whether each content point is a key content point.

3. The content reservation and recommendation method for AI online education according to claim 2, characterized in that: The process that each student makes content reservations based on the preset recommendation information on the corresponding student terminal as needed includes: For recorded courses, the preset recommendation information includes at least three recommendation information: recommendation based on the student's own historical reservation content point preferences, recommendation based on key content points, and recommendation based on the historical playback content points of other student terminals; For delayed live courses, the preset recommended information includes at least three pieces of recommended information: recommended based on the student's own historical appointment content point preferences, recommended based on key content points, and recommended based on real-time appointment information of other student terminals; Each student makes content appointments or not according to the recommended information as needed; Among them, for the recommendation based on real-time appointment information of other student terminals, each student terminal sends the appointment content point information to the teacher terminal and all other student terminals, and the student terminal counts the received appointment content point information, calculates the appointment rate of each content point, and takes the content points with the appointment rate exceeding the preset recommended threshold as the recommendation of real-time appointment information of other student terminals.

4. The content reservation and recommendation method for AI online education according to claim 3, characterized in that: When each student terminal plays a recorded course or a delayed live course, it detects whether it is an appointed content and makes an adaptive adjustment of the playback speed, including: For a recorded course, the student terminal detects the current playback time point. If the current playback time point is between the start timestamp and the end timestamp of the appointed content, it plays at a reduced speed according to the first preset speed; otherwise, it plays at an accelerated speed according to the second preset speed; For a delayed live course, the student terminal dynamically extracts the audio of the currently played video stream and performs text extraction. Through natural language processing technology, it vectorizes the extracted text and the appointed content of the current student terminal respectively, and calculates the difference between the two vectors. If the difference is less than the second threshold, it plays at a reduced speed according to the first preset speed; otherwise, it plays at an accelerated speed according to the second preset speed; When a student has not made an appointment for all content points, the corresponding student terminal makes an adaptive adjustment of the playback speed according to the recommendation of key content points; For a recorded course, when a student has not made an appointment for all content points and there are no key content points, the corresponding student terminal makes an adaptive adjustment of the playback speed according to the recommendation of the historical playback content points of other student terminals.

5. The content reservation and recommendation method for AI online education according to claim 1, characterized in that: The detailed video stream request includes a message ID, a message type, a student ID, a creation time, a course ID, and a content point detailed video stream ID; The first response information includes a message ID, a message type, a student ID, a creation time, a response status, a multicast group address, an original video stream port, and a detailed video stream port; The fields of the detailed video stream request packet include a packet type, a checksum, a multicast group address, an original video stream port, and a detailed video stream port. Among them, the student terminal adds the original video stream port and the detailed video stream port in the parsed first response information to the IGMP v2 packet to form a detailed video stream request packet.

6. The content reservation and recommendation method for AI online education according to claim 1, characterized in that: When the student terminal sends a detailed video stream request packet to the server, it is forwarded to the server through the gateway server and each other router. After receiving the detailed video stream request packet, the gateway server parses it and records the original video stream port and the detailed video stream port. The gateway router receives the original video stream and the detailed video stream, and distinguishes the original video stream and the detailed video stream according to the destination port number information of the video stream based on the ACL access control list rules on the gateway router.

7. The content reservation and recommendation method for AI online education according to claim 1, characterized in that: Between each student terminal and the server, there is a gateway router located at the student terminal, and n other routers. The n other routers are sequentially represented as the first router P1, the second router P2,..., the nth router Pn from the gateway router to the server direction; When the gateway router performs the original video stream caching, it records the time point t1 when the original video stream starts caching and stores it in the mapping table, and continuously monitors whether the cache space utilization rate is greater than the third threshold. When it is greater than the third threshold, it sends a cache request message to the first router P1 adjacent to its upstream; After receiving the cache request message, the first router P1 decides whether to accept the cache request according to its own cache space; When the first router P1 accepts the cache request, it sends the accepted second response information to the gateway router. The gateway router records the IP address of the first router P1 in the accepted second response information, and records the time point t2 when the first router P1 starts caching the original video stream and stores it in the mapping table. At the same time, the gateway router itself stops caching the original video stream, and the first router P1 starts caching the original video stream at the time point t2; When the first router P1 rejects the cache request, it sends the rejected second response information to the gateway router. The gateway router stops sending the detailed video stream to the student terminals that do not reach the first threshold, and resends the original video stream to the student terminals that do not reach the first threshold.

8. The content reservation and recommendation method for AI online education according to claim 7, characterized in that: When the first router P1 performs the original video stream caching, it continuously monitors whether the cache space utilization rate is greater than the third threshold. When it is greater than the third threshold, it sends a cache request message to the second router P2 adjacent to its upstream; After receiving the cache request message, the second router P2 decides whether to accept the cache request according to its own cache space; When the second router P2 accepts the cache request, it simultaneously sends the accepted third response information to the first router P1 and the gateway router adjacent to its downstream. The gateway router records the IP address of the second router P2 in the accepted third response information, and records the time point t3 when the second router P2 starts caching the original video stream and stores it in the mapping table. At the same time, the first router P1 itself stops caching the original video stream, and the second router P2 starts caching the original video stream at the time point t3; When the second router P2 rejects the cache request, it only sends the rejected third response information to the first router P1 adjacent to its downstream. The first router P1 sends the rejected second response information to the gateway router. At this time, the gateway router stops sending the detailed video stream to the student terminals that do not reach the first threshold, and resends the original video stream to the student terminals that do not reach the first threshold; When the cache space utilization rate of one of the n other routers, say the other router Px, is always less than the third threshold, it stops sending the cache request message to the other router adjacent to its upstream. The gateway router records the time point t(x + 1) when the other router Px starts caching the original video stream and stores it in the mapping table; Among them, the mapping table stores the mapping relationship between each time point when the original video stream starts caching and the caching device, and the caching device is each router.

9. The content reservation and recommendation method for AI online education according to claim 8, characterized in that: The content reservation and recommendation method for the AI online education further includes: after the detailed video stream request ends playing on the student side, the corresponding student side sends the original video stream request information to the gateway router; After receiving the original video stream request information, the gateway router selects the earliest time point t1 for the original video stream record according to the mapping table, and sends the original video stream with the start time point t1 to the corresponding student side; When the gateway router sends the original video stream to the time point t2, according to the mapping table, the gateway router sends the original video stream request information to the first router P1 of the caching device corresponding to the caching start time point t2; After receiving the original video stream request information, the first router P1 sends the original video stream with the start time point t2 to the corresponding student side through the gateway router; When the network router forwards the original video stream to the time point t3, according to the mapping table, the network router sends the original video stream request information to the second router P2 of the caching device corresponding to the caching start time point t3; After receiving the original video stream request information, the second router P2 sends the original video stream with the start time point t3 to the corresponding student side through the gateway router; And so on, until after other routers Px receive the original video stream request information, they send the original video stream with the start time point t(x + 1) to the corresponding student side through the gateway router.

10. The content reservation and recommendation method for AI online education according to claim 9, characterized in that: The content reservation and recommendation method for the AI online education further includes: after each router sends the original video stream to the corresponding student side, it clears the cache of the sent original video stream; After the gateway router clears the cache, when it monitors that the cache space utilization rate of the gateway router is less than the fourth threshold, it sends a stop caching request message to other routers Px that are caching the latest data of the original video stream; After receiving the stop caching request message from the gateway router, if other routers Px accept to stop caching, then other routers Px stop caching the original video stream, and send a stop caching request response message with the response status of acceptance to the gateway router; After receiving the stop caching request response message of acceptance, the gateway router resumes caching the remaining uncached original video stream.

Images