Intelligent scheduling method and system for learning resources

Abstract

The invention discloses a learning resource intelligent scheduling method and system, and relates to the technical field of resource scheduling, and the method comprises the steps: determining a plurality of target student terminals, building a scheduling graph between the plurality of target student terminals and a learning resource database, marking a user portrait of each target student terminal in a corresponding sub-graph, and carrying out the scheduling of the plurality of target student terminals; establishing an implicit relationship between the sub-atlas of each target student terminal and the learning resource database; actively providing the learning resource data in the learning resource database to the target student end through the capturing community based on the involved relationship; and updating the sub-atlas of the target student terminal in real time, and when the sub-atlas of the target student terminal changes, replacing the grabbing community where the target student terminal is located. According to the invention, multi-type data scheduling can be carried out on multiple target student terminals, and the students can switch among multiple capture communities, so that the method has good flexibility, and data provision is more flexible and accurate.

Description

Technical Field

[0001] This invention relates to the field of resource scheduling technology, specifically to a learning resource intelligent scheduling method and system. Background Technology

[0002] Traditional education models primarily rely on "standardized supply" (such as uniform textbooks and a uniform pace). However, as society's demand for diversified talent increases, individual differences among learners are receiving more and more attention. For example, some learners have different learning foundations, interests, and goals. Within the same group, some learners need to consolidate basic knowledge, some want to learn advanced content in advance, and others have different professional interests. Traditional education models cannot differentiate resource allocation, and due to the large number of learners, complex data exchange can easily lead to system crashes, making it impossible to guarantee the stability of resource allocation. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for intelligent scheduling of learning resources to address the shortcomings in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an intelligent scheduling method for learning resources, comprising the following steps: Multiple target student clients are identified, and a scheduling graph is established between these target student clients and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student clients, and multiple crawling communities. Each target student's user profile is marked in the corresponding sub-graph, and the connection between each target student's sub-graph and the learning resource database is established. Based on the relationship, learning resource data from the learning resource database is proactively provided to target students by crawling the community. The subgraph of the target student is updated in real time. When the subgraph of the target student changes, the crawling community of the target student is changed.

[0005] In a preferred embodiment, the step of identifying multiple target student terminals and establishing a scheduling graph between the multiple target student terminals and the learning resource database includes: The learning resource data in the learning resource database is divided into multiple resource pools according to type, and the type is used as the label for the corresponding resource pool.

[0006] Multiple resource points are configured according to resource pools, and the resource points are interconnected with their corresponding resource pools. By connecting multiple resource points, the main graph is obtained. Multiple type points are set for each target student, and the multiple type points are connected to obtain a sub-map; A crawling community is set up for each resource point.

[0007] In a preferred embodiment, the step of setting up a crawling community for each resource point includes: A distribution body is set up for each resource point. The distribution body includes the main resource and multiple mapping surfaces. The distribution body is connected to the corresponding resource point. Multiple tentacles are set for the corresponding distribution body. Each tentacle includes a contact point and a connecting line between the contact point and the distribution body, establishing a one-to-one correspondence between the contact point and the mapping surface. Consider a distribution entity and its corresponding connected tentacles as a single grabbing community.

[0008] In a preferred embodiment, the step of setting up a distribution body for each resource point includes: A storage space is set up for each resource point, and the storage space is divided into multiple virtual spaces in a ring. After the ring partitioning, the data plane is set as the primary resource in the internal space of the storage space, and the data plane is set as the mapping plane in the edge space of the storage space after the ring partitioning. Set up a transport plane between the mapping plane and the main resource and make it correspond. The transport plane consists of multiple transport points, which include nodes and virtual machines. Adjacent transport points are connected to each other. The main resource is mapped to multiple mapping surfaces for data range. The main resource and multiple mapping surfaces are divided into corresponding data ranges according to the number of transfer points, resulting in multiple main data range surfaces in the main resource and the same number of corresponding mapping data range surfaces in the mapping surfaces. Connect the transport point to the corresponding mapping data range in the mapping surface and the main data range in the main resource one-to-one to obtain the distribution body.

[0009] In a preferred embodiment, the step of marking the user profile of each target student in a corresponding sub-graph and establishing the connection between the sub-graph of each target student and the learning resource database includes: For each target student, a user profile is collected, converted into a type, and marked in the corresponding type point; Each target student's marked type point is triggered and connected to the corresponding type's resource pool to obtain the relationship.

[0010] In a preferred embodiment, the step of proactively providing learning resource data from the learning resource database to the target student based on the association relationship includes: Based on the relationship, the tentacles corresponding to the resource pool are connected to the corresponding target student terminals, wherein the contact points of the tentacles are connected to the target student terminals; The learning resource data in the resource pool is transmitted to the main resource of the distribution point through the resource point and laid on the data surface of the main resource; By using the transfer point, the learning resource data of the master data range in the corresponding master resource is copied and provided to the mapping data range in the corresponding mapping surface; When a transfer point is unable to copy the learning resource data in the corresponding master data scope, it is designated as an abnormal transfer point. A virtual machine of a transfer point adjacent to the abnormal transfer point is randomly selected and connected to the node of the abnormal transfer point. The virtual machine of the adjacent transfer point copies the learning resource data of the master data scope corresponding to the abnormal transfer point and provides it to the mapping data scope in the corresponding mapping surface. The learning resource data in the mapped data range is provided to the corresponding target student through touchpoints.

[0011] In a preferred embodiment, the step of real-time updating of the sub-graphe of the target student terminal, and changing the crawling community of the target student terminal when the sub-graphe of the target student terminal changes, includes: Real-time collection of user profiles from the target student's end; and updating the sub-graph by marking type points based on the real-time collected user profiles. If the updated subgraph has changed labels, establish a connection between the changed and labeled type points and the corresponding resource pools. Based on the relationship, connect the crawling communities corresponding to the changes and marked type points on the target student's end, and connect the tentacles of the crawling communities corresponding to the changes and marked type points to the target student's end.

[0012] This invention also provides an intelligent scheduling system for learning resources, comprising: The module is used to identify multiple target student terminals and establish a scheduling graph between the multiple target student terminals and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student terminals, and multiple crawling communities. The connection module, connected to the construction module, is used to mark the user profile of each target student in the corresponding sub-graph and establish the connection between the sub-graph of each target student and the learning resource database. The scheduling module, connected to the connection module, is used to proactively provide learning resource data from the learning resource database to the target students based on the relationship between them and the community. The update module, connected to the scheduling module, is used to update the subgraph of the target student in real time. When the subgraph of the target student changes, the crawling community in which the target student is located is changed.

[0013] The technical effects and advantages provided by the present invention in the above technical solution are as follows: 1. This invention can schedule multiple types of data for multiple target student terminals, and students can switch between multiple crawling communities, which has good flexibility and the data provided is more flexible and accurate. 2. When a large number of target students use the system, the present invention is less likely to experience system overload or crashes, and has good data stability. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0015] Figure 1 This is a flowchart of the method of the present invention.

[0016] Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figure 1 As shown in this embodiment, a learning resource intelligent scheduling method includes the following steps: S1. Identify multiple target student terminals and establish a scheduling graph between the multiple target student terminals and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student terminals, and multiple crawling communities. S2. Mark the user profile of each target student in the corresponding sub-graph and establish the connection between the sub-graph of each target student and the learning resource database. S3. Based on the relationship, the learning resource data in the learning resource database is proactively provided to the target students by crawling the community. S4. Update the subgraph of the target student in real time. When the subgraph of the target student changes, change the crawling community in which the target student is located.

[0019] As described in steps S1-S4 above, the system can allocate multiple types of data to multiple target student terminals, and students can switch between multiple crawling communities, which provides good flexibility and more flexible data provision. Furthermore, when multiple target student terminals are using the system, there is less likelihood of system access overload or crashes, resulting in good data stability.

[0020] In one embodiment, step S1, which involves identifying multiple target student terminals and establishing a scheduling graph between the multiple target student terminals and the learning resource database, includes: S11. Divide the learning resource data in the learning resource database into multiple resource pools according to their types, and use the type as the label of the corresponding resource pool (the learning resource database is a cloud database, and the resource pool is a storage space divided in the cloud database, with each storage space used to store learning resource data of the corresponding type).

[0021] S12. Configure multiple resource points according to the resource pool. The resource points are interconnected with the corresponding resource pools. Connect the multiple resource points to obtain the main graph (the resource points configured for the corresponding resource pools are network ports. One resource pool corresponds to one network port. Multiple network ports are interconnected. The resource points can represent the data types of the resource pools in the learning resource database. They can also be used to obtain data from the resource pools in the future. Then the main graph is obtained). S13. Set multiple type points for each target student terminal, and connect the multiple type points to obtain a sub-graph (the number of type points is the same as the number of types used to classify learning resource data. Here, the type points are network nodes, which can be used to point the target student terminal to the resource pool. The subsequent connection between the network nodes and the resource pool cannot transmit data. It is only used to determine the resource pool corresponding to the target student terminal. The determination of the corresponding resource pool is based on the type of the target student terminal. This type includes the learner's knowledge level, learning progress, interest preferences, and error types, etc. All the above data about learners are classified by type. For example, knowledge level can be described by academic level type, and interest preferences can include the learner's favorite resources, such as tool-type courses or technology-type data. Different types are used to classify the data in the learning resource database. The type of the type point is also the same as the type used to classify learning resource data). S14. Set up a crawling community for each resource point.

[0022] In one embodiment, step S14, which involves setting up a crawling community for each resource point, includes: S141. A distribution body is set up for each resource point, wherein the distribution body includes the main resource and multiple mapping surfaces, and the distribution body is connected to the corresponding resource point. S142. Multiple tentacles are set for the corresponding distribution body, wherein the tentacles include contact points and connecting lines between the contact points and the distribution body, and a one-to-one correspondence between the contact points and the mapping surface is established. S143. Treat a distributor and its corresponding connected tentacles as a grabbing community.

[0023] In one embodiment, step S141, which sets up a distribution body for each resource point, includes: S1411. Set up a storage space for each resource point, and divide the storage space into multiple virtual spaces in a ring. S1412. After the ring partitioning, set the data plane as the main resource in the internal space of the storage space, and set the data plane as the mapping plane in the edge space of the storage space after the ring partitioning. S1413. Set up a transport surface and correspondence between the mapping surface and the main resource. The transport surface consists of multiple transport points, which include nodes and virtual machines. Adjacent transport points are interconnected. S1414. Assign data ranges to the main resource and multiple mapping surfaces respectively. Divide the main resource and multiple mapping surfaces into corresponding data ranges according to the number of transfer points, so as to obtain multiple main data range surfaces in the main resource and the number of corresponding mapping data range surfaces in the mapping surfaces. S1415. Connect the transport point to the corresponding mapping data range in the mapping surface and the main data range in the main resource one-to-one to obtain the distribution body.

[0024] As described in steps S11-S14 above, the learning resource database collects multi-type learning resource data about corresponding student groups based on big data. The data is categorized according to its type, such as humanities and social sciences, natural sciences, and tools. Each major category includes multiple subcategories; for example, the humanities and social sciences category includes knowledge data related to college Chinese, ideological and political theory, history, philosophy, and art appreciation. This data differentiation into various subcategories results in multiple resource pools. Each resource pool stores corresponding types of learning resource data. To better recommend data based on student user profiles, corresponding resource points are set for each resource pool. One resource point corresponds to one resource pool, serving as the output network port for transmitting data from the resource pool. The resource points of multiple resource pools are interconnected as a fixed network, referred to as the main graph. The type of resource pool is marked on the resource point. This further enhances the targeted scheduling and recommendation of learning resource data.

[0025] Each resource point is assigned a storage space, which is divided into ring-shaped sections. Essentially, a central section is designated to receive learning resource data transmitted from the corresponding resource point. Multiple smaller storage spaces, serving as virtual spaces, are then created outside this central section. Within the ring-shaped storage space, a data plane is designated as the primary resource. At the edge of the ring-shaped storage space, data planes are designated as mapping planes. The primary resource storage locations are distributed according to the data planes. The mapping planes undergo the same operation, but reside in different virtual spaces. A transport plane is established between the mapping plane and the primary resource, corresponding to each other. The storage space for the transport plane is located at [location missing]. Each transport plane consists of multiple transport points. The system consists of transport points, including nodes and virtual machines. Adjacent transport points are interconnected to form transport surfaces. After transferring data from the resource pool to the main resource of the distribution body, there is a need to distribute resources to multiple target student terminals. To avoid data corruption and instability caused by multiple target student terminals simultaneously accessing the data, the learning resource data on the main resource is copied according to the target student terminals to be allocated. Specifically, the main resource is mapped to multiple mapping surfaces for data range. For example, the main resource is divided into 8 main data range surfaces. Since the data surface of the main resource is the same as the data surface of multiple mapping surfaces, the multiple mapping surfaces are also divided into 8 mapping data range surfaces according to the same division method. To replicate the learning resource data from the main resource, the mapping surfaces need to be mapped one-to-one with the eight main data surfaces. The number of transport points is also eight. The mapping surfaces and main resource are divided based on the number of transport points. This results in multiple main data surfaces in the main resource and corresponding mapping data surfaces in the mapping surfaces. Transport points include nodes and virtual machines. Nodes are network nodes set up in the storage space between the main resource and the mapping surfaces, serving as network placement points for virtual machines. Through these network nodes, multiple virtual machines can connect to each other. After the learning resource data from the main resource is in place... There is a one-to-one connection between the transfer points and the 8 mapped data ranges and 8 main data ranges. The virtual machines on the transfer points copy the learning resource data in the corresponding main data range and then provide it to the corresponding mapped data range. Since there are many transfer points, when one of them is unusable, it can be moved to the node of the unusable transfer point through an adjacent transfer point to replace the unusable virtual machine in copying the learning resource data in the corresponding main data range until the copying of learning resource data in all main resources is completed. The mapped surface serves as the data providing space for the tentacles. Subsequently, the learning resource data in the corresponding mapped surface is provided to the target student through the tentacles, completing the resource scheduling based on the student user profile.

[0026] The distribution body is equipped with multiple tentacles, each consisting of a contact point and a connecting line between the contact point and the distribution body. A one-to-one correspondence is established between the contact point and the mapping surface. One tentacle is used to connect to one target student end. The mapping surface corresponding to a tentacle that is not connected to a target student end will not copy the learning resource data from the main resource. Only the mapping surface corresponding to a tentacle connected to a target student end will copy the learning resource data from the main resource. This ensures the stability and bias of the learning resource data recommendation. When a large number of students use the system, the distribution of learning resource data can be stably carried out without being overloaded or crashing.

[0027] In one embodiment, step S2, which involves marking the user profile of each target student in a corresponding sub-graph and establishing the connection between the sub-graph of each target student and the learning resource database, includes: S21. Collect user profiles for each target student, convert the user profiles into types, and mark them in the type points of the corresponding types; S22. Connect the type point marked on each target student terminal with the corresponding type of resource pool to obtain the connection relationship.

[0028] In one embodiment, step S3, which involves proactively providing learning resource data from the learning resource database to the target student based on the association relationship through community crawling, includes: S31. Connect the tentacles corresponding to the resource pool to the corresponding target student terminals according to the linkage relationship. The touch points of the tentacles are connected to the target student terminals (the touch point, as a network node, can be bound to the target student terminal, and the distribution body establishes a communication relationship with the touch point and the target student terminal through the connection line). S32. Transmit the learning resource data in the resource pool to the main resource of the distribution point through the resource point, and lay it on the data surface of the main resource; S33. Copy the learning resource data of the master data range in the corresponding master resource through the transfer point and provide it to the mapping data range in the corresponding mapping surface; S34. When a transfer point is unable to copy the learning resource data in the corresponding master data scope, it is designated as an abnormal transfer point. A virtual machine of a transfer point adjacent to the abnormal transfer point is randomly selected and connected to the node of the abnormal transfer point. The virtual machine of the adjacent transfer point copies the learning resource data of the master data scope corresponding to the abnormal transfer point and provides it to the mapping data scope in the corresponding mapping surface. (After the virtual machine of the adjacent transfer point completes the copying task, the virtual machine returns to its original position, and a new virtual machine is configured to replace the virtual machine of the abnormal transfer point. Since the data in the resource library is subsequently improved, updated, and changed, the transfer point needs to transfer the data to the mapping data scope in a timely manner. This is recommended for the target student end.) S35. Provide the learning resource data in the mapped data range to the corresponding target student terminal through the touch point.

[0029] As described in steps S31-S35 above, each target student client actively acquires data from various resource pools, and their historical usage reveals their preferences and weaknesses. Based on this data, a user profile is created. The data corresponding to these preferences and weaknesses is then categorized according to the same rules as the resource pool classification, such as humanities and social sciences, natural sciences, and tools. Subsequently, the resource pools are linked through sub-graphs based on the user profiles. This is a referencing relationship used to understand the resource pool corresponding to the target student client. This facilitates the subsequent recommendation of data from the resource pools to the target student client through a distribution mechanism, enabling the allocation of multiple types of data across multiple target student clients. Students can switch between multiple data scraping communities, providing greater flexibility and more flexible data provision. Furthermore, even with multiple target student clients using the system, there is less likelihood of system overload or crashes, demonstrating good data stability.

[0030] In one embodiment, step S4, which involves updating the sub-graphe of the target student in real time and changing the crawling community to which the target student belongs when the sub-graphe of the target student changes, includes: S41. Collect user profiles of target students in real time, and update the type points of the sub-graph based on the collected user profiles. S42. If the updated sub-map has changed labels, establish a connection between the changed and labeled type points and the corresponding resource pools. S43. Connect the crawling communities corresponding to the changed and marked type points on the target student end according to the relationship, and connect the tentacles of the crawling communities corresponding to the changed and marked type points to the target student end.

[0031] As described in steps S41-S43 above, since students' learning progress and direction are constantly changing, for example, if a student currently has weaknesses in basic knowledge, the learning resources categorized for the current target student will be biased towards data on technical knowledge. After strengthening these areas, the weakness will no longer be the student's learning problem. Therefore, the target student can disconnect from the crawling community corresponding to this type of resource pool and no longer focus on this type of learning resource data. If a student generates new types based on their user profile during the learning process, such as a preference for data on a certain research direction, then a connection is established between this type and the distribution body in the corresponding resource point. The target student can also actively acquire data from different types of resource pools. This is considered active acquisition. When not actively acquiring data, the platform provides biased data based on the target student's different types of crawling communities. A target student can have multiple types, and user profiles are complex and changeable. A target student can connect to multiple crawling communities to actively receive learning resource data provided by the distribution body.

[0032] Example 2, please refer to Figure 2 As shown in this embodiment, a learning resource intelligent scheduling system includes: The module is used to identify multiple target student terminals and establish a scheduling graph between the multiple target student terminals and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student terminals, and multiple crawling communities. The connection module, connected to the construction module, is used to mark the user profile of each target student in the corresponding sub-graph and establish the connection between the sub-graph of each target student and the learning resource database. The scheduling module, connected to the connection module, is used to proactively provide learning resource data from the learning resource database to the target students based on the relationship between them and the community. The update module, connected to the scheduling module, is used to update the subgraph of the target student in real time. When the subgraph of the target student changes, the crawling community in which the target student is located is changed.

[0033] It should be noted that the system can allocate multiple types of data to multiple target student terminals, and students can switch between multiple crawling communities, which provides good flexibility and data provision. Furthermore, when multiple target student terminals are using the system, there is less likelihood of system access overload or crashes, indicating good data stability.

[0034] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for intelligent scheduling of learning resources, characterized in that, Includes the following steps: Multiple target student clients are identified, and a scheduling graph is established between these target student clients and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student clients, and multiple crawling communities. Each target student's user profile is marked in the corresponding sub-graph, and the connection between each target student's sub-graph and the learning resource database is established. Based on the relationship, learning resource data from the learning resource database is proactively provided to target students by crawling the community. The subgraph of the target student is updated in real time. When the subgraph of the target student changes, the crawling community of the target student is changed.

2. The intelligent scheduling method for learning resources according to claim 1, characterized in that, The steps of identifying multiple target student terminals and establishing a scheduling graph between the multiple target student terminals and the learning resource database include: The learning resource data in the learning resource database is divided into multiple resource pools according to type, and the type is used as the label for the corresponding resource pool. Multiple resource points are configured according to resource pools, and the resource points are interconnected with their corresponding resource pools. By connecting multiple resource points, the main graph is obtained. Multiple type points are set for each target student, and the multiple type points are connected to obtain a sub-map; A crawling community is set up for each resource point.

3. The intelligent scheduling method for learning resources according to claim 2, characterized in that, The step of setting up community crawling for each resource point includes: A distribution body is set up for each resource point. The distribution body includes the main resource and multiple mapping surfaces. The distribution body is connected to the corresponding resource point. Multiple tentacles are set for the corresponding distribution body. Each tentacle includes a contact point and a connecting line between the contact point and the distribution body, establishing a one-to-one correspondence between the contact point and the mapping surface. Consider a distribution entity and its corresponding connected tentacles as a single grabbing community.

4. The intelligent scheduling method for learning resources according to claim 3, characterized in that, The step of setting up a distribution body for each resource point includes: A storage space is set up for each resource point, and the storage space is divided into multiple virtual spaces in a ring. After the ring partitioning, the data plane is set as the primary resource in the internal space of the storage space, and the data plane is set as the mapping plane in the edge space of the storage space after the ring partitioning. Set up a transport plane between the mapping plane and the main resource and make it correspond. The transport plane consists of multiple transport points, which include nodes and virtual machines. Adjacent transport points are connected to each other. The main resource is mapped to multiple mapping surfaces for data range. The main resource and multiple mapping surfaces are divided into corresponding data ranges according to the number of transfer points, resulting in multiple main data range surfaces in the main resource and the same number of corresponding mapping data range surfaces in the mapping surfaces. Connect the transport point to the corresponding mapping data range in the mapping surface and the main data range in the main resource one-to-one to obtain the distribution body.

5. The intelligent scheduling method for learning resources according to claim 4, characterized in that, The step of marking the user profile of each target student in the corresponding sub-graph and establishing the connection between the sub-graph of each target student and the learning resource database includes: For each target student, a user profile is collected, converted into a type, and marked in the corresponding type point; Each target student's marked type point is triggered and connected to the corresponding type's resource pool to obtain the relationship.

6. The intelligent scheduling method for learning resources according to claim 5, characterized in that, The step of proactively providing learning resource data from the learning resource database to target students by crawling the community based on the relationship includes: Based on the relationship, the tentacles corresponding to the resource pool are connected to the corresponding target student terminals, wherein the contact points of the tentacles are connected to the target student terminals; The learning resource data in the resource pool is transmitted to the main resource of the distribution point through the resource point and laid on the data surface of the main resource; By using the transfer point, the learning resource data of the master data range in the corresponding master resource is copied and provided to the mapping data range in the corresponding mapping surface; When a transfer point is unable to copy the learning resource data in the corresponding master data scope, it is designated as an abnormal transfer point. A virtual machine of a transfer point adjacent to the abnormal transfer point is randomly selected and connected to the node of the abnormal transfer point. The virtual machine of the adjacent transfer point copies the learning resource data of the master data scope corresponding to the abnormal transfer point and provides it to the mapping data scope in the corresponding mapping surface. The learning resource data in the mapped data range is provided to the corresponding target student through touchpoints.

7. The intelligent scheduling method for learning resources according to claim 1, characterized in that, The step of updating the subgraph of the target student's terminal in real time, and changing the crawling community of the target student's terminal when the subgraph of the target student's terminal changes, includes: Real-time collection of user profiles from the target student's end; and updating the sub-graph by marking type points based on the real-time collected user profiles. If the updated subgraph has changed labels, establish a connection between the changed and labeled type points and the corresponding resource pools. Based on the relationship, connect the crawling communities corresponding to the changes and marked type points on the target student's end, and connect the tentacles of the crawling communities corresponding to the changes and marked type points to the target student's end.

8. A learning resource intelligent scheduling system, used to implement the learning resource intelligent scheduling method according to any one of claims 1-7, characterized in that, include: The module is used to identify multiple target student terminals and establish a scheduling graph between the multiple target student terminals and the learning resource database. The scheduling graph includes a main graph, multiple sub-graphs corresponding to the target student terminals, and multiple crawling communities. The connection module, connected to the construction module, is used to mark the user profile of each target student in the corresponding sub-graph and establish the connection between the sub-graph of each target student and the learning resource database. The scheduling module, connected to the connection module, is used to proactively provide learning resource data from the learning resource database to the target students based on the relationship between them and the community. The update module, connected to the scheduling module, is used to update the subgraph of the target student in real time. When the subgraph of the target student changes, the crawling community in which the target student is located is changed.

Images