Heterogeneous graph information mining method for online learning video recommendation

Abstract

The embodiment of the invention discloses a heterogeneous graph information mining method for online learning video recommendation, which comprises the following steps of: constructing a heterogeneous graph comprising a user node, a video node and a label node, and performing multi-hop aggregation on initial features of each node in the heterogeneous graph by utilizing a multilayer graph attention network, and recommending videos to the users according to the final features of the nodes. Dividing the plurality of users into a first user for complete watching, a second user for non-watching and a third user for partial watching according to the actual watching condition of the recommended video by the users; and determining a target second user whose change between the final feature and the initial feature is less than a set threshold, and updating a second sub-graph structure of the target second user in the heterogeneous graph according to the first user and / or the third user. According to the embodiment, the actual watching condition of the recommended video by the user can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the fields of artificial intelligence and educational technology, and in particular to a heterogeneous graph information mining method for online learning video recommendation. Background Art

[0002] With the rapid development of Internet technology, online learning platforms have become an important way for learners to acquire knowledge. However, faced with a massive amount of learning video resources, how to accurately recommend content that meets learners' interests and needs is a common problem.

[0003] In the prior art, some patent applications have explored methods for recommending short videos and course content, such as "Short Video Recommendation Method and System Based on Heterogeneous Graph Neural Network with Multimodal Data Integration" (CN202411211539.1) and "Heterogeneous Graph Neural Network Course Recommendation Method and System Based on Attention Mechanism" (CN202310588836.7). However, none of these methods mention how to conduct targeted information mining to improve users' viewing of recommended videos when users' actual viewing of recommended videos is not good. Summary of the invention

[0004] The embodiment of the present invention provides a heterogeneous graph information mining method for online learning video recommendation to solve the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a heterogeneous graph information mining method for online learning video recommendation, comprising:

[0006] Obtain user information, video resource information and learning topic tags of the online learning platform;

[0007] Based on the acquired content, a heterogeneous graph including user nodes, video nodes and label nodes is constructed; the heterogeneous graph is input into a multi-layer graph attention network, the initial features of each node are multi-hop aggregated, and videos are recommended to each user based on the final features of each node;

[0008] According to actual viewing conditions of the recommended videos by the users, the multiple users are divided into a first user who has watched the recommended videos completely, a second user who has not watched the recommended videos, and a third user who has watched the recommended videos partially.

[0009] Determine a target second user whose final feature has a change with the initial feature that is less than a set threshold, and a target first user whose initial feature is most similar to the target second user; update a second subgraph structure of the target second user in the heterogeneous graph according to a first subgraph structure of the target first user in the heterogeneous graph, so as to improve the actual viewing situation of the recommended video by the target second user;

[0010] In case of update failure, a target third user is determined whose initial feature similarity with the target first user and the target second user is greater than another threshold; the third subgraph structure of the target third user in the heterogeneous graph is updated according to the first subgraph structure, and the second subgraph structure is updated according to the updated third subgraph structure; the updated heterogeneous graph is used to re-input the multi-layer graph attention network to re-recommend new videos to each user.

[0011] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0012] one or more processors;

[0013] a memory for storing one or more programs,

[0014] When the one or more programs are executed by the one or more processors, the one or more processors implement the heterogeneous graph information mining method for online learning video recommendation described in any embodiment.

[0015] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the heterogeneous graph information mining method for online learning video recommendation described in any embodiment.

[0016] In summary, the embodiment of the present invention provides a heterogeneous graph information mining method for online learning video recommendation, which constructs a heterogeneous graph by integrating learners, learning videos and label information, uses the graph attention network to accurately calculate vectors and update weights, and deeply extracts features and modeling relationships. Finally, a multi-layer perceptron is used to generate prediction probabilities to achieve accurate and personalized recommendations for video resources, effectively improving learning experience and efficiency. After the recommendation is completed, the actual viewing of the recommended video by the user is recorded, and users whose aggregation and transformation of user features by the multi-layer GAT network is not large are selected from the users who have never watched the video as improvement objects. At the same time, users who are similar to the user but have better viewing conditions are used as reference objects, and the information data of the improvement objects are targetedly mined with reference to their information structure in the heterogeneous graph, so as to capture more information that can accurately reflect the complex rules of users watching videos, further improve the accuracy of recommended videos, and improve users' actual viewing of recommended videos. In particular, in order to improve the effectiveness of sub-graph updating, this embodiment further divides users with better viewing conditions into users who have watched the entire program and users who have watched partially, and together with users who have not watched the program, they form a three-level user system. Through the mutual cooperation of the first-level sub-graph updating and the two-level sub-graph gradual updating, the user information data is effectively mined. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a heterogeneous graph information mining method for online learning video recommendation provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of recommending online learning video resources based on a heterogeneous graph provided by an embodiment of the present invention;

[0020] Figure 3 is a comparison diagram of a first sub-image and a second sub-image provided by an embodiment of the present invention;

[0021] Figure 4 is a comparison diagram of a simplified first sub-graph and a simplified second sub-graph provided by an embodiment of the present invention;

[0022] Figure 5 is a comparison diagram of a current first sub-image and a current second sub-image provided by an embodiment of the present invention;

[0023] Figure 6 is a comparison diagram of the remaining part of the current first sub-image and the current second sub-image provided by an embodiment of the present invention;

[0024] Figure 7 is another comparison diagram of the remaining part of the current first sub-image and the current second sub-image provided by an embodiment of the present invention;

[0025] Figure 8 is another comparison diagram of the remaining part of the current first sub-image and the current second sub-image provided by an embodiment of the present invention;

[0026] Fig. 9 is a comparison diagram of the simplified first sub-graph and the new simplified second sub-graph provided by the embodiment of the present invention;

[0027] Fig.10 is a schematic diagram comparing the first sub-image and the new second sub-image provided by an embodiment of the present invention;

[0028] Fig.11 is a comparison diagram of a new current first sub-image and a new current second sub-image provided by an embodiment of the present invention;

[0029] Fig.12 is a comparison diagram of the remaining part of the new current first sub-image and the new current second sub-image provided by an embodiment of the present invention;

[0030] Fig.13 is a comparison diagram of the remaining part of the new current first sub-image and the supplemented new simplified second sub-image provided by an embodiment of the present invention;

[0031] Fig.14 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0033] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0034] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0035] Figure 1 is a flow chart of a heterogeneous graph information mining method for online learning video recommendation provided by an embodiment of the present invention. The method is executed by an electronic device, such as Figure 1 As shown, the method specifically includes:

[0036] S110, obtaining user information, video resource information and learning topic tags of the online learning platform.

[0037] User information includes user age, identity, hobbies, courses ordered, historical video click behavior, historical viewing behavior, etc. Video resource information includes the title, content, summary, overview, course system, and hierarchical position of the learning video. Learning topic tags are used to summarize course content, course knowledge points, etc., and can be extracted from titles at all levels in the course system.

[0038] This embodiment uses the information data accumulated by the online learning platform as the data source of the entire method. Generally speaking, these information data are relatively large, and some key information can be extracted from them for subsequent operations.

[0039] S120. Construct a heterogeneous graph including user nodes, video nodes and label nodes based on the acquired content, wherein the edge between the user node and the label node is used to represent the association relationship between the user and the label, the edge between the video node and the label node is used to represent the association relationship between the video and the label, and the edge between the user node and the video node is used to represent the interactive relationship between the user and the video.

[0040] Based on the content obtained in the previous step, this embodiment constructs a heterogeneous graph including user nodes U, video nodes V, and label nodes T, where each user node corresponds to a user, each video node corresponds to a learning video, and each label node corresponds to a label. According to user behaviors such as video clicks and video views, edges between user nodes and video nodes can be established, such as establishing edges between videos that users have watched; according to user information, the user's preferred learning topic can be determined, and an edge can be established between the user node and the preferred learning topic label node; according to the text similarity between the video resource information and the label, the learning topic to which the video belongs can be determined, and an edge can be established between the user node and the learning topic label node.

[0041] Figure 2 A heterogeneous graph with a three-part graph structure is shown in FIG. x 、v y and t z represent user nodes, video nodes, and label nodes respectively. x, y, and z are node indexes. The user-video edge E UV Represents the interactive relationship between users and videos, user-label edge E UT Represents the association between users and tags, video-tag edge E VTRepresents the association between videos and tags. These nodes and edges form a complex heterogeneous graph structure. This heterogeneous graph structure fully captures the rich data information in the online learning platform. Compared with the traditional single relationship graph, it can better alleviate the data sparsity problem of new users or new videos. Because through the introduction of label nodes, even if new users or new videos do not have enough historical interaction data, they can find potential similar users or videos with the help of the association with the label, thus providing a basis for subsequent recommendations. At the same time, it perceives and learns the relationship between different types of nodes from multiple dimensions, which helps to deeply explore the potential information of the data and improve the accuracy and diversity of recommendations.

[0042] S130, inputting the heterogeneous graph into a multi-layer graph attention network, performing multi-hop aggregation on the initial features of each node according to the graph structure, and recommending at least one video to each user according to the final features of each node.

[0043] This embodiment uses a neural network model based on a multi-layer graph attention network (GAT) and a multi-layer perceptron (MLP) to process the above heterogeneous graph. The multi-layer GAT is used to update the node vector and aggregate the neighbor information to accurately capture the complex relationship between nodes. The MLP is used for final prediction to further improve the accuracy of video recommendation. The model can be pre-trained based on a large number of heterogeneous graphs. The model input is a heterogeneous graph within a period of time (including the initial features and connection relationships of each node in the graph), and the output is the viewing probability of each user for each video in the future. When constructing samples in model training, a heterogeneous graph within a historical period of time can be selected as input, and the viewing probability can be calculated based on the number of views of each video by each user in another historical period after the historical period. The viewing probability is used as output to fully train the model.

[0044] In a specific implementation, the data processing process of the heterogeneous graph in the model may include the following steps:

[0045] Step 1: Generate initial features of each node based on the acquired content. Optionally, encode the user's age, identity, hobbies, courses ordered, etc. as initial features of the user node; encode the acquired video information as initial features of the video node, and encode the tag content as initial features of the tag node. The type information can be encoded using ont-hot, hashing, etc., and the text information can be encoded using text embedding, which is not specifically limited in this embodiment. Figure 2 , each node has a corresponding feature vector, and the initial feature encoding method of the same type of nodes is the same.

[0046] Step 2: Input the initial features and connection relationships of each node into the multi-layer graph attention network. In the multi-layer graph attention network, update the feature vector of each node according to the feature vectors of adjacent nodes, and update repeatedly to complete multi-hop aggregation. This step uses multi-layer GAT to update the node vector. The core idea of ​​GAT is to dynamically assign weights to neighboring nodes through the attention mechanism, so as to more accurately capture the complex relationship between nodes. Specifically, in each hop feature aggregation, for each node i, update the node vector according to the following formula:

[0047]

[0048] in, is the updated feature vector of node i, N(i) represents the set of all neighboring nodes of node i, W is the learnable weight matrix, is the current feature vector of each node in the union of its neighbor nodes and node i, is a nonlinear activation function; a ij is the attention coefficient or weight distribution matrix, which is used to measure the importance of different nodes to the target node. It is calculated as follows:

[0049]

[0050] in, is a learnable attention vector, is the current feature vector of each node in the union of neighbor nodes and node i, || represents the vector concatenation operation, and LeakyReLU() is the activation function. The updated node feature vector will be used as the current feature vector of node i in the next hop aggregation.

[0051] Through multi-layer GAT, we can gradually aggregate neighbor information of more hops. Assuming that the multi-layer GAT has L layers, the final vector of node i after passing through L layers of GAT is expressed as . GAT dynamically assigns weights to each neighbor node through the attention mechanism, so that the model can more accurately capture the complex relationships between nodes. By gradually aggregating multi-hop neighbor information, the global structural information in the graph can be captured more comprehensively. For online learning video recommendations, the model can better understand the user's potential interests and the comprehensive characteristics of the video, thereby improving the accuracy and coverage of the recommendation. In particular, in this embodiment, the final features output by the same node after passing through multiple layers of GAT are set to have the same dimension as the initial features input to GAT.

[0052] Step 3: Input the final features of each node into the multi-layer perceptron to predict the probability of each user watching each video. This step introduces MLP for final prediction based on the graph neural network. The input of MLP is the node vector updated by multi-layer GAT. , the output is the probability of each user watching each prediction Optionally, the MLP consists of K fully connected layers, the activation function of each layer is ReLU, and the activation function of the output layer is Sigmoid, then the prediction score It can be expressed as:

[0053]

[0054] Among them, W k and b k are the weight matrix and bias term of the kth layer, k=1,2,…,K.

[0055] By introducing MLP, we can give full play to the advantages of graph neural network in capturing node relationships and MLP in nonlinear fitting, and achieve complementary advantages. This combination not only improves the accuracy of prediction, but also enhances the generalization ability of the model.

[0056] Step 4: Recommend at least one video with the highest viewing probability to each user. For each user, recommend the first few videos with the highest predicted viewing probability to the user.

[0057] S140: According to actual viewing conditions of the recommended videos by the users, multiple users are divided into a group of users who have watched the recommended videos completely, a group of users who have not watched the recommended videos, and a group of users who have watched the recommended videos partially.

[0058] After recommending a specific video to a user, this embodiment records the actual viewing situation of each user for the recommended video in the future. If the user has watched any one or more recommended videos completely, the user is divided into a group of users who have watched them completely; if the user has not watched all the recommended videos, the user is divided into a group of users who have not watched them; if the user has watched any one or more recommended videos but has not watched them to the end, the user is divided into a group of users who have watched them partially. For the convenience of distinction and description, each user in the above three groups of users is referred to as the first user, the second user and the third user respectively. The above viewing situation reflects the accuracy of the video recommendation. When the test accuracy of the recommendation model (i.e., the above neural network model composed of multi-layer GAT and MLP) is relatively stable, the viewing situation also reflects whether the input model heterogeneous graph has extracted enough effective information from a large amount of information data to learn the complex rules of users watching videos.

[0059] S150: Determine a target second user whose final feature has a change with the initial feature that is less than a certain threshold, and a target first user whose pre-aggregation feature is most similar to that of the target second user.

[0060] The final feature here refers to the aggregated feature output of the last layer in the multi-layer GAT network. , the initial feature refers to the initial feature input into the multi-layer GAT network. In this embodiment, the same dimension is set for the final feature and the initial feature of the same user node, and the difference between the final feature and the initial feature of the node is used to reflect the degree of mining of the global relationship of the node by the multi-layer GAT network, and the difference is also used to reflect whether the heterogeneous graph provides sufficient effective information about the mining of the node relationship.

[0061] In a specific implementation, first, for each second user, the similarity between the initial feature and the final feature of the current second user is calculated. ,Will The second user whose value is less than a certain threshold is taken as the target second user. The initial features and final features of the target second user do not change much, indicating that the multi-layer GAT network does not aggregate enough effective information for the initial features of the user. When the test accuracy of the model is relatively stable, this may be due to the fact that the heterogeneous graph does not contain much effective information about the user (for example, the number of edges or nodes related to the user in the heterogeneous graph is too small, or the number of effective edges or nodes is too small). The multi-layer GAT network does not fully aggregate the information of neighbor nodes, resulting in poor actual viewing of recommended videos by users.

[0062] Then, the similarity between the initial features of each first user and the initial features of the target second user is calculated respectively, and the first user with the greatest similarity is selected as the target first user. The user itself has the highest similarity with the initial features of the target second user, indicating that the two users have the most similar information, and the target first user can be used as a reference node for subsequently expanding the relevant information of the target second user in the heterogeneous graph.

[0063] S160: Update the subgraph structure of the target second user in the heterogeneous graph according to the subgraph structure of the target first user in the heterogeneous graph, so as to improve actual viewing conditions of the recommended video by the target second user.

[0064] This step uses the interaction information and association information of the target first user in the heterogeneous graph as a reference to expand the interaction information and association information of the target second user in the heterogeneous graph. For the sake of distinction and description, in this embodiment, the subgraph corresponding to the target first user is called the first subgraph, and the subgraph corresponding to the target second user is called the second subgraph.

[0065] In a specific implementation, the process may include the following steps:

[0066] Step 1: extracting from the heterogeneous graph a first subgraph that diffuses outwards with the target first user as the center, and a second subgraph that diffuses outwards with the target second user as the center. Figure 3An extracted subgraph is shown as an example, wherein U1 represents the target first user, V11, V12, and V13 respectively represent different video nodes in the first subgraph, U12 represents the user node in the first subgraph, and T11, T12, and T13 respectively represent different label nodes in the first subgraph; U2 represents the target second user, V21 represents the video node in the second subgraph, U22 represents the user node in the second subgraph, and T21 and T23 respectively represent different label nodes in the second subgraph.

[0067] Step 2: Simplify the node attributes in each subgraph into node types to obtain a simplified first subgraph and a simplified second subgraph, where the node types include user, video, and tag. Through node simplification, nodes of the same type are regarded as the same node, for example, multiple user nodes are regarded as the same U node without distinguishing which user they are. Figure 3 For example, the simplified first subgraph and second subgraph are as follows Figure 4 As shown, U, V and T represent user nodes, video nodes and tag nodes respectively. The different colors in the nodes are for the convenience of description in subsequent operations and do not represent the differences between the nodes.

[0068] Step 3: Initialize N to 1 and loop through the following operations:

[0069] S1-10, from the simplified first subgraph and the second subgraph, extract the central node and the nearest neighboring nodes in the first N layers, as well as the edges between the extracted nodes, to form the current first subgraph and the current second subgraph respectively. Taking N=1 as an example, from Figure 4 The current first sub-image and the current second sub-image extracted from Figure 5 shown.

[0070] S1-20. Remove the same parts as those in the current second subgraph from the current first subgraph. Optionally, first, remove the central node and the first N-1 layers of neighboring nodes and the first N-1 layers of edges from the current first subgraph. When N=1, only two central nodes are the same nodes, so only the central node can be removed, and the remaining parts are as follows: Figure 6 shown.

[0071] Then, the following operations are performed in sequence for each neighbor node in the Nth layer of the current second subgraph:

[0072] If the remaining part of the current first subgraph (excluding the part that has been removed for the previous neighbor node) has only one node that is the same as the current neighbor node, remove the same node and the edges connected to it that are of the same type as the current neighbor node from the remaining part, where the edge types include the edge between the user and the tag, the edge between the video and the tag, and the edge between the user and the video. Figure 6 For example, the first-layer neighbor nodes of the current second subgraph include a V node and a T node. For the V node (i.e., the blue V node), there is only one V node in the remaining part of the current first subgraph. Therefore, the white V node and the user-video edge (i.e., the blue edge) of the same type as the edge (user-video edge) connected to the white V node and the blue V node are removed from the remaining part of the current first subgraph. The two subgraphs after removal are as follows Figure 7 shown.

[0073] If there are multiple nodes identical to the current neighbor node in the remaining part of the current first subgraph (excluding the part that has been removed for the previous neighbor node), select the node whose initial vector is most similar to the current neighbor node as the final identical node from these identical nodes, and remove the final identical node and the edges connected to it that are of the same type as the edges connected to the current neighbor node from the remaining part. Figure 7 There is another neighbor node T (i.e., green T node) in the first layer of the current second subgraph in , and there are two T nodes (red T node and blue T node) in the remaining part of the corresponding current first subgraph. Then calculate the similarity between the initial vector of the red T node and the initial vector of the green T node, and the similarity between the initial vector of the blue T node and the initial vector of the green T node, select the T node with the highest similarity from the red and blue T nodes, and remove the node and its connected user-label edge of the same type as the edge connected to the green T node from Figure 7 Assuming that the red T node has a high similarity, the two subgraphs after removal are as follows Figure 8 shown.

[0074] If the remaining part of the current first subgraph (excluding the part that has been removed for the previous neighbor node) does not have a node that is the same as the current neighbor node, indicating that the current neighbor node is a part that is larger than the current first subgraph, the current neighbor node is marked as a retrieval failed node.

[0075] S1-30, respectively determine the removed nodes connected to each remaining node and the remaining isolated edge in the current first subgraph, and extract the node determined to be the same as the removed node in S1-20 from the current second subgraph as the target node; extract the information data of the target node from the information data accumulated on the online learning platform, and retrieve the nodes of the same type as each remaining node and / or the same relationship as each remaining isolated edge from the information data of the target node, and add them to the simplified second subgraph. S1-30 is explained below for each remaining node and remaining isolated edge in the current first subgraph:

[0076] For each remaining node in the current first subgraph, perform the following operations respectively: determine the removed nodes adjacent to the current remaining node, extract the target node determined to be the same as the removed node in S1-20 from the current second subgraph; extract the information data of the target node from the large amount of information data accumulated on the online learning platform, and retrieve the node of the same type as the current remaining node from the information data of the target node, add it to the simplified second subgraph, and add the corresponding edge between the supplemented node and the target node, and use the supplemented node as the node that is the same as the current remaining node in S1-20 of the next cycle. Figure 8 For example, there is only one remaining node in the remaining part of the current first subgraph, that is, the blue T node. For this node, determine the removed nodes adjacent to the blue T node, that is, Figure 5 Then, extract the target node that is determined to be the same as the yellow U node in S1-20 from the current second subgraph (the same nodes here are nodes of the same type, and different colors are only for ease of description and do not mean that the nodes are different), that is, Figure 8 The gray U node in the figure is retrieved from the information data of the gray U node, and the node of the same type as the blue T node is retrieved, that is, the T node associated with the target second user is searched, and added to the simplified second subgraph. The result after addition is as follows Fig. 9 As shown, the purple T nodes are supplementary nodes.

[0077] Finally, if no nodes of the same type as the current remaining nodes can be retrieved from a large amount of information data, the remaining nodes are also marked as failed retrieval nodes of this round of loop. For the sake of distinction and description, the failed retrieval nodes in the current second subgraph marked in S1-20 are called second failed retrieval nodes, corresponding to the part of the current second subgraph that is larger than the current first subgraph; the failed retrieval nodes in the current first subgraph marked in S1-30 are called first failed retrieval nodes, corresponding to the part of the current first subgraph that is larger than the current second subgraph but no comparable nodes are retrieved from the information data of the current second subgraph.

[0078] For each remaining orphan edge in the current first subgraph, perform the following operations respectively: determine the two removed nodes connected to the current remaining orphan edge, extract the target node determined in S1-20 to be the same as the two removed nodes from the current second subgraph; retrieve the relationship of the same type as the current remaining orphan edge from the information of the two target nodes, and add it to the simplified second subgraph. Among them, an orphan edge refers to an edge whose two endpoints have been removed. The above operations are Figure 4-Figure 9 This does not exist in the example shown for N=1 and will be explained in the next cycle for N=2.

[0079] S1-40, restore each node in the new simplified second subgraph to complex attributes, and merge the restored graph into the overall heterogeneous graph. This step performs the opposite operation of the simplification operation in step 2 on the new simplified second subgraph, that is, further distinguishing the same nodes into different nodes of the same type. The restored new second subgraph is as follows Fig.10 After restoration, a fusion operation is performed to add the newly added nodes and edges in the new second subgraph to the heterogeneous graph. If the newly added nodes are already in the heterogeneous graph, there is no need to add them again. Just add edges between the existing nodes. Finally, node disambiguation is performed to obtain the fused heterogeneous graph.

[0080] S1-50, input the fused heterogeneous graph into the first N layers of the multi-layer graph attention network to obtain a new aggregation feature of the target second user. Under the guidance of the target first user, the fused heterogeneous graph re-mines the information data of the target second user and extracts more information; this step uses the new data to recalculate the aggregation features of the target second user to verify whether the information mined this time can aggregate more effective information for user features. In particular, since each layer of the GAT network corresponds to the information aggregation of a layer of neighboring nodes, the aggregation features processed by the first N layers of the multi-layer GAT are taken here.

[0081] S1-60, if the change between the new aggregated features and the initial features of the target second user is greater than the set threshold (or another independent threshold), it indicates that the multi-layer GAT network has effectively aggregated the user's neighbor information, so that the user's initial features have been fully transformed, and the cycle from S1-10 to S1-60 can be terminated. Otherwise, if the change between the new aggregated features and the initial features of the target second user is less than the set threshold or independent threshold, N is increased by 1, and the cycle from S1-10 to S1-60 is restarted according to the simplified first subgraph and the new simplified second subgraph until N reaches the number of layers of the first subgraph or the second subgraph.

[0082] In this embodiment, the latter case is taken as an example. Fig. 9 , take N=2, and restart a new cycle of S1-10 to S1-60. First, in S1-10, extract the central node and its nearest neighbor nodes in the first N layers, as well as the edges between the extracted nodes, from the simplified first subgraph and the new simplified second subgraph, respectively, to form a new current first subgraph and a new current second subgraph, respectively, as shown in Fig.11 shown.

[0083] In S1-20, the same parts as those in the new current second subgraph are removed from the new current first subgraph. Specifically, first remove the central node and the first-layer neighbor nodes, as well as the first-layer edges, from the new current first subgraph. Since the first-layer neighbor nodes of the two new current subgraphs, except for the nodes that failed to be retrieved, have been supplemented in the previous cycle, they can all find the same neighbor nodes as themselves, and the nodes that failed to be retrieved will no longer look for the same neighbor nodes as themselves through subsequent operations, so the entire layer can be removed. Then, perform the following operations for the second-layer neighbor nodes according to different situations:

[0084] Case 1: If there is no failed retrieval node in the previous cycle, then the following operations are performed in sequence for the second-layer neighbor nodes in the new current second subgraph: If there is only one node in the remaining part of the new current first subgraph that is identical to the current neighbor node A in the second layer of the new current second subgraph, remove the identical node and the edges connected to the identical node that are of the same type as the current neighbor node A from the remaining part; If there are multiple identical nodes in the remaining part of the new current first subgraph that are identical to the current neighbor node A, select the node with the most similar initial vector to the current neighbor node from these identical nodes as the final identical node, and remove the final identical node and the edges connected to it that are of the same type as the current neighbor node from the remaining part; If there is no node identical to the current neighbor node A in the remaining part of the new current first subgraph, mark the current neighbor node as the second failed retrieval node in this cycle. Fig.11 For example, the remaining part after removal is as follows Fig.12 shown.

[0085] Case 2: If there is a retrieval failure node in the previous cycle, then in the new current first subgraph, the node in the second-layer neighbor node that is only connected to the first retrieval failure node in the previous cycle is marked as the first retrieval failure node in this cycle and removed; at the same time, in the new current second subgraph, the node in the second-layer neighbor node that is only connected to the second retrieval failure node in the previous cycle is marked as the second retrieval failure node in this cycle and removed; then, for each other neighbor node B remaining in the second-layer neighbor node of the new current second subgraph, the following operations are performed in sequence: If the remaining part of the new current first subgraph (excluding the part that has been removed for the previous neighbor node and the first retrieval failure node in this cycle, the same below) is connected to the current neighbor node B being processed If there is only one identical node, the identical node and the edges connected to the identical node that are of the same type as the edges connected to the current neighbor node B are removed from the remaining part of the new current first subgraph; if there are multiple identical nodes as the current neighbor node B in the remaining part of the new current first subgraph, select the node whose initial vector is most similar to the current neighbor node B from these identical nodes as the final identical node, and remove the final identical node and the edges connected to it that are of the same type as the edges connected to the current neighbor node B from the remaining part of the new current first subgraph; if there is no identical node as the current neighbor node B in the remaining part of the new current first subgraph, mark the current neighbor node as the second failed retrieval node in this round of loop. In this case, for the neighbor nodes of the current layer, first remove the branches extending from the part in the previous round of loop that did not retrieve suitable nodes from a large amount of information data to add, and at the same time remove the part that is larger than the new current first subgraph in the new current second subgraph, and then search for the identical nodes in the new current first subgraph for the remaining neighbor nodes and remove them. The operation in this case is Fig.11 and Fig.12 It is not shown in the example, but can be executed in the second round and subsequent cycles.

[0086] In S1-30, for the gray V node among the remaining nodes, its adjacent removed nodes are Fig. 9 The red T node in the new current second subgraph corresponds to the green T node. The information data of the green T node (i.e., T21) is extracted from the large amount of information data on the online learning platform, and the nodes of the same type as the gray V node (i.e., the video associated with T21) are retrieved from it. For example, Fig.13 The red V node in is added to the new simplified second subgraph, and the corresponding edge is added. Similarly, similar operations are performed on the other remaining green V node, and finally the Fig.13 The purple V node in is added to the new simplified second subgraph.

[0087] For the remaining isolated edges (for easy distinction, Fig.11 and Fig.12 The edge is displayed in bold red in the figure, and the two removed nodes (i.e. Fig. 9 The blue U node and the red T node in the second subgraph are extracted from the current second subgraph, and the target node (i.e. Fig. 9 The white U node and the green T node in the graph); extract the information data of the two target nodes from the large amount of information data accumulated on the online learning platform, and determine the relationship of the same type as the current remaining isolated edge, that is, determine whether there is an association relationship between the white U node and the green T node, and add it to the new simplified second subgraph, such as Fig.13 shown.

[0088] Then, operations from S1-40 to S1-60 are performed again, and the cycle is repeated until N reaches the maximum number of neighbor layers of the first subgraph or the second subgraph.

[0089] S170: If the update fails, determine a target third user whose initial feature similarity with the target first user and the target second user is greater than another threshold; update the subgraph structure of the target third user in the heterogeneous graph according to the first subgraph structure, and then update the second subgraph structure according to the updated third subgraph structure.

[0090] Optionally, if no node of the same type as the remaining nodes or the same relationship as the remaining isolated edges is retrieved after all cycles, that is, the structure of the second subgraph has not changed, then the update can be judged to have failed; or the updated heterogeneous graph is re-input into the multi-layer graph attention network, the initial features of each node are multi-hop aggregated according to the new graph structure, and new videos are re-recommended to each user, and the actual viewing of the new recommended video by the user is recorded. If the actual viewing of the recommended video by the target second user has not been improved (for example, no recommended video has been watched), it indicates that the structure of the second subgraph has not changed in a way that is conducive to video recommendation, and the update can also be judged to have failed. This indicates that it is difficult to directly find useful information for reference between the target second user and the target first user. At this time, this embodiment re-updates the second subgraph with the help of the third user, first updates the subgraph structure of the third user according to the subgraph structure of the first user, and then updates the subgraph structure of the second user according to the subgraph structure updated by the third user. Since the viewing situation of the third user is between that of the first user and the second user, compared with directly comparing the effective information of the first user and the second user in the heterogeneous graph, the effective information of the third user in the heterogeneous graph is more comparable with that of the first user and the second user. It is easier to update successfully by using step-by-step analogy, and finally the gradual update of the subgraph structure is realized.

[0091] Specifically, first determine a third user whose initial features are similar to those of the target first user and the target second user, referred to as the target third user, and extract a subgraph that can spread outward from the target third user as the center from the heterogeneous graph, referred to as the third subgraph. Then, for all operations on the target second user and the second subgraph in S160, replace the execution objects with the target third user and the third subgraph, re-execute all steps of S160, and finally obtain the updated third subgraph structure. Finally, for all operations on the target first user and the first subgraph in S160, replace the execution objects with the target third user and the updated third subgraph, re-execute all steps of S160, and finally obtain the updated second subgraph and the final fused heterogeneous graph.

[0092] S180, re-inputting the final fused heterogeneous graph into the multi-layer graph attention network, performing multi-hop aggregation on the initial features of each node according to the new graph structure, and recommending at least one new video to each user according to the new final features of each node.

[0093] If there are multiple target second users, the above operations can be performed for each target second user in turn, and the subgraph structure of each target second user in the heterogeneous graph can be updated in turn. After the update is completed, the new heterogeneous graph is re-input into the multi-layer GAT and MLP for processing, and the probability of each user watching each video is re-predicted, and at least one new video with the highest viewing probability is recommended to each user. In this recommendation, since more effective information is provided for the target second user, it is at least helpful to improve the actual viewing of the recommended video by the target second user.

[0094] It should be noted that the user information involved in this application is information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0095] In summary, this embodiment provides a heterogeneous graph information mining method for online learning video recommendation. By integrating learners, learning videos and label information to construct a heterogeneous graph, the graph attention network is used to accurately calculate vectors and update weights, and the features and modeling relationships are deeply extracted. Finally, a multi-layer perceptron is used to generate prediction scores to achieve accurate and personalized recommendations for video resources, effectively improving the learning experience and efficiency. After the recommendation is completed, the actual viewing of the recommended video by the user is recorded, and users whose aggregation and transformation of user features by the multi-layer GAT network is not large are selected from the users who have never watched the video as improvement objects. At the same time, users who are similar to the user but have better viewing conditions are used as reference objects. The information data of the improvement object is targeted and mined with reference to its information structure in the heterogeneous graph, so as to capture more information that can accurately reflect the complex rules of users watching videos, further improve the accuracy of recommended videos, and improve users' actual viewing of recommended videos. In particular, in order to improve the effectiveness of sub-graph updating, this embodiment further divides users with better viewing conditions into users who have watched the entire program and users who have watched partially, and together with users who have not watched the program, they form a three-level user system. Through the mutual cooperation of the first-level sub-graph updating and the two-level sub-graph gradual updating, the user information data is effectively mined.

[0096] Fig.14 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Fig.14 As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Fig.14 A processor 60 is taken as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Fig.14 The example of connecting through bus is taken in the following.

[0097] The memory 61 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the heterogeneous graph information mining method for online learning video recommendation in the embodiment of the present invention. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned heterogeneous graph information mining method for online learning video recommendation.

[0098] The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0100] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the heterogeneous graph information mining method for online learning video recommendation of any embodiment.

[0101] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0102] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0103] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0104] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A heterogeneous graph information mining method for online learning video recommendation, characterized in that: include: Obtain user information, video resource information and learning topic tags of the online learning platform; Based on the acquired content, a heterogeneous graph including user nodes, video nodes and label nodes is constructed; the heterogeneous graph is input into a multi-layer graph attention network, the initial features of each node are multi-hop aggregated, and videos are recommended to each user based on the final features of each node; According to actual viewing conditions of the recommended videos by the users, the multiple users are divided into a first user who has watched the recommended videos completely, a second user who has not watched the recommended videos, and a third user who has watched the recommended videos partially. Determine a target second user whose final feature has a change with the initial feature that is less than a set threshold, and a target first user whose initial feature is most similar to the target second user; update a second subgraph structure of the target second user in the heterogeneous graph according to a first subgraph structure of the target first user in the heterogeneous graph, so as to improve the actual viewing situation of the recommended video by the target second user; In the case of update failure, determining a target third user whose initial feature similarity with the target first user and the target second user is greater than another threshold; updating the third subgraph structure of the target third user in the heterogeneous graph according to the first subgraph structure, and then updating the second subgraph structure according to the updated third subgraph structure; The updated heterogeneous graph is used to re-input the multi-layer graph attention network to re-recommend new videos to each user.

2. The method according to claim 1, characterized in that The heterogeneous graph is input into a multi-layer graph attention network, the initial features of each node are aggregated in multiple hops, and videos are recommended to each user according to the final features of each node, including: Generate initial features of each node according to the acquired content; Inputting the initial features and connection relationships of each node into a multi-layer graph attention network, in which the features of each node are updated multiple times according to the features of adjacent nodes to complete multi-hop feature aggregation; The final features of each node are input into the multi-layer perceptron to predict the probability of each user watching each video; Recommend the video with the highest viewing probability to each user.

3. The method according to claim 2, characterized in that The step of determining a target second user whose final feature has a change from an initial feature that is less than a set threshold, and a target first user whose initial feature is most similar to the target second user, comprises: For each second user, respectively calculate the similarity between the initial feature and the final feature of the current second user, and take the second user whose difference between 1 and the similarity is less than a set threshold as the target second user; The similarities between the initial features of each first user and the initial features of the target second user are calculated respectively, and the first user with the greatest similarity is selected as the target first user.

4. The method according to claim 2, characterized in that: The updating of the second subgraph structure of the target second user in the heterogeneous graph according to the first subgraph structure of the target first user in the heterogeneous graph comprises: Extracting, from the heterogeneous graph, a first subgraph that diffuses outwards with the target first user as the center, and a second subgraph that diffuses outwards with the target second user as the center; Simplify the node attributes in each subgraph into node types, where node types include users, videos, and tags; Initialize N to 1 and loop through the following operations: S1-10, extracting the central node and the first N layers of neighboring nodes closest to it, and the edges between the extracted nodes from the simplified first subgraph and the second subgraph, respectively, to form the current first subgraph and the current second subgraph; S1-20, removing the same portion as the current second sub-image from the current first sub-image; S1-30, respectively determine the removed nodes connected to each remaining node and the remaining isolated edge in the current first subgraph, and extract the target node determined to be the same as the removed node in S1-20 from the current second subgraph, retrieve the nodes of the same type as each remaining node and / or the same relationship as each remaining isolated edge from the information of the target node, and add them to the simplified second subgraph; S1-40, restoring each node in the new simplified second subgraph to a complex attribute, and integrating the restored graph into the overall heterogeneous graph; S1-50, inputting the fused heterogeneous graph into the first N layers of the multi-layer graph attention network to obtain an aggregated feature of the target second user; S1-60. If the change between the aggregated feature and the initial feature of the target second user is greater than the set threshold, terminate the loop from S1-10 to S1-60; otherwise, increase N by 1, and restart the loop from S1-10 to S1-60 according to the new simplified second subgraph until N reaches the maximum number of neighbor node layers of the first subgraph or the second subgraph.

5. The method according to claim 4, characterized in that S1-20, including: Remove the central node and the first N-1 layers of neighboring nodes, and the first N-1 layers of edges from the current first subgraph; For each neighbor node in the Nth layer of the current second subgraph, perform the following operations in sequence: S1-21. If there is only one node identical to the current neighbor node in the remaining part of the current first subgraph, remove the identical node and the edges connected to it that are of the same type as the edges connected to the current neighbor node from the remaining part; S1-22. If there are multiple nodes identical to the current neighbor node in the remaining part of the current first subgraph, select a node whose initial vector is most similar to the current neighbor node from the multiple identical nodes as the final identical node, and remove the final identical node and the edges connected to it that are of the same type as the edges connected to the current neighbor node from the remaining part; The edge types include edges between users and tags, edges between videos and tags, and edges between users and videos.

6. The method according to claim 4, characterized in that S1-30 includes: The following operations are performed for each remaining node: determine the removed nodes adjacent to the current remaining node, extract the target node determined in S1-20 to be the same as the removed node from the current second subgraph; retrieve nodes of the same type as the current remaining node from the information of the target node, add them to the simplified second subgraph, and add corresponding edges between the added nodes and the target node; The following operations are performed for each remaining isolated edge: determine the two removed nodes connected to the current remaining isolated edge, extract the target nodes determined in S1-20 to be the same as the two removed nodes from the current second subgraph; retrieve the relationship of the same type as the current remaining isolated edge from the information of the two target nodes, and add it to the simplified second subgraph.

7. The method according to claim 4, characterized in that Before determining the target third user that is most similar to the initial feature of the target second user in the case of update failure, the method further includes: If any node of the same type as the remaining nodes or any relationship of the same type as the remaining isolated edges is not retrieved in S1-30 of all loops, it is determined that the update has failed.

8. The method according to claim 1, characterized in that Before determining the target third user that is most similar to the initial feature of the target second user in the case of update failure, the method further includes: Re-inputting the updated heterogeneous graph into the multi-layer graph attention network, and re-recommending new videos to each user, and recording the user's actual viewing of the newly recommended videos; If the updated heterogeneous graph fails to improve the actual viewing situation of the recommended video by the target second user, it is determined that the update fails.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the heterogeneous graph information mining method for online learning video recommendation as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the heterogeneous graph information mining method for online learning video recommendation described in any one of claims 1-8 is implemented.

Images