Data enhancement method and related device

Abstract

The invention discloses a data enhancement method and a related device, and the method comprises the steps: obtaining a to-be-enhanced sequence which comprises a plurality of object nodes and directed edges used for connecting the object nodes; according to the potential object nodes corresponding to the object nodes, a directed graph comprising a plurality of weighted directed edges is determined, and the weighted directed edges are used for pointing to the potential object nodes corresponding to the object nodes from the object nodes; the weight carried by the weighted directed edge is used for indicating the probability that the user selects the potential object corresponding to the target object after selecting the target object. And traversing the directed graph according to the weight carried by the weighted directed edge to obtain a target enhanced sequence corresponding to the to-be-enhanced sequence. Therefore, according to the weight capable of representing the probability that the user selects the object, the directed graph obtained by mining the potential information of the session is traversed, the target enhancement sequence with higher accuracy is obtained, and when the target enhancement sequence is used for sequence recall, the object related to the user can be predicted more accurately.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a data enhancement method and related devices. Background Art

[0002] With the rapid development of e-commerce platforms, social media, streaming services and other platforms, the amount of interactive data generated by users every day has exploded. These platforms have accumulated a large amount of user behavior data, such as clicks, shopping, browsing records, etc. By analyzing users' interests and preferences, they provide users with objects with a high probability of interest, such as short videos and products, thereby improving user experience, increasing user stickiness and conversion rate.

[0003] In the related art, objects of interest to users are predicted through sequence recall. Sequence recall refers to the process of predicting objects of interest to users from a large set of candidate objects by analyzing the user's historical behavior sequence in a recommendation task.

[0004] However, the accuracy of historical behavior sequences used for sequence recall in related technologies is low. Summary of the invention

[0005] In view of the above problems, the present application provides a data enhancement method and related devices for improving the accuracy of historical behavior sequences.

[0006] Based on this, this application discloses the following technical solutions: In a first aspect, an embodiment of the present application provides a data enhancement method, the method comprising: Acquire a sequence to be enhanced, the sequence to be enhanced comprising a plurality of object nodes and directed edges for connecting the object nodes, the sequence to be enhanced being used to indicate the order in which the user selects objects in a session; Determining a directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes, wherein the weighted directed edges are used to point from the object nodes to the potential object nodes corresponding to the object nodes, and the weights carried by the weighted directed edges are used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object; The directed graph is traversed according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edges, the higher the probability of traversing to the object node pointed to by the weighted directed edges.

[0007] Optionally, determining a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes to obtain a directed graph includes: Determine directed edges to be weighted corresponding to each of the object nodes, wherein the directed edges to be weighted are used to point from the object nodes to potential object nodes corresponding to the object nodes; Acquire a correspondence relationship between the association degree and the weight, in which the higher the association degree is, the greater the weight is; Acquire multiple association degrees between each of the potential object nodes and the corresponding object node; The weights corresponding to the directed edges to be weighted are determined according to the corresponding relationship, so as to obtain a directed graph including a plurality of the weighted directed edges.

[0008] Optionally, the method further comprises: Determine the basic weights corresponding to the directed edges to be weighted according to the corresponding relationship; Acquire a collaborative filtering model, wherein the collaborative filtering model is used to determine the similarity between two objects, wherein the similarity is used to indicate the frequency of simultaneous occurrence of the two objects corresponding to the directed edge to be weighted, and the higher the frequency, the higher the similarity; Determine the similarities corresponding to each of the directed edges to be weighted according to the collaborative filtering model; The basic weight is adjusted according to the similarities corresponding to each of the directed edges to be weighted, so as to obtain the weight corresponding to each of the directed edges to be weighted.

[0009] Optionally, the degree of association between the potential object node and the corresponding object node is determined by the distance between the window where the potential object node is located and the window where the corresponding object node is located. The smaller the distance, the higher the degree of association. The potential object nodes corresponding to each of the object nodes are determined in the following manner: Obtaining a preset window range, where the preset window range is used to indicate the object distribution range determined by the current recommendation algorithm; For a target object node among the multiple object nodes, determining a potential object distribution range of the target object node according to a position of the target object node and a preset window range; Determine an object node located in the potential object distribution range among the plurality of object nodes as a potential object node of the target object node; Each of the object nodes is used as the target object node to obtain potential object nodes corresponding to each of the object nodes.

[0010] Optionally, determining a directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes includes: Determining an initial directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes; According to the behavior data of the user selecting the object, a discard operation is performed on the initial directed graph to obtain the directed graph, wherein the discard operation is used to discard the object nodes or weighted directed edges included in the initial directed graph.

[0011] Optionally, performing a discard operation on the initial directed graph according to the behavior data of the user selecting the object to obtain the directed graph includes: Obtaining an interval time threshold and an interval time of each pair of object nodes connected by the weighted directed edge; If the interval time of the object node pair exceeds the interval time threshold, determining the first probability of the discard operation according to the timeout degree of the interval time exceeding the interval time threshold, the higher the timeout degree, the higher the first probability; The discard operation is performed on the weighted directed edges connecting the object node pairs in the initial directed graph according to the first probability.

[0012] Optionally, performing a discard operation on the initial directed graph according to the behavior data of the user selecting the object to obtain the directed graph includes: Acquire a probability prediction model, wherein the probability prediction model is used to predict the probability that the user terminates the interaction after selecting the object; According to the characteristic data of the user and the characteristic data corresponding to each of the object nodes, prediction is performed by the probability prediction model to obtain second probabilities corresponding to each of the object nodes; For each of the object nodes in the initial directed graph, the discard operation is performed on the object node corresponding to the second probability according to the second probability.

[0013] Optionally, if the sequence to be enhanced includes a first sequence to be enhanced and a second sequence to be enhanced, the directed graph includes a first directed graph and a second directed graph, wherein the first directed graph is obtained according to the first sequence to be enhanced, and the second directed graph is obtained according to the second sequence to be enhanced, then the directed graph is traversed according to the weight carried by the weighted directed edge to obtain a target enhanced sequence corresponding to the sequence to be enhanced, including: Traversing the first directed graph according to the weights carried by the weighted directed edges in the first sequence to be enhanced to obtain a first enhanced sequence; Traversing the second directed graph according to the weights carried by the weighted directed edges in the second sequence to be enhanced to obtain a second enhanced sequence; A first identifier is assigned to the first enhanced sequence, and a second identifier is assigned to the second enhanced sequence to obtain a first target enhanced sequence corresponding to the first sequence to be enhanced and a second target enhanced sequence corresponding to the second sequence to be enhanced, wherein the first identifier and the second identifier are used to characterize a session order corresponding to the first sequence to be enhanced and the second sequence to be enhanced.

[0014] In a second aspect, an embodiment of the present application provides a data enhancement device, the device comprising: an acquisition unit, a composition unit and a traversal unit; The acquisition unit is used to acquire a sequence to be enhanced, wherein the sequence to be enhanced includes a plurality of object nodes and directed edges for connecting the object nodes, and the sequence to be enhanced is used to indicate the order in which the user selects objects in a session; The graph forming unit is used to determine a directed graph including a plurality of weighted directed edges according to the potential object nodes corresponding to the respective object nodes, wherein the weighted directed edges are used to point from the object nodes to the potential object nodes corresponding to the object nodes, and the weights carried by the weighted directed edges are used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object; The traversal unit is used to traverse the directed graph according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge.

[0015] In a third aspect, an embodiment of the present application provides a computer device, wherein the computer device includes a processor and a memory: The memory is used to store a computer program and transmit the computer program to the processor; The processor is configured to execute the method described in the first aspect according to the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method described in the first aspect above.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product comprising a computer program, which, when executed on a computer device, enables the computer device to execute the method described in the first aspect above.

[0018] It can be seen from the above technical solutions that the present application has at least the following beneficial effects: A session is a series of interactive behaviors of a user within a preset time. This application performs data enhancement on the sequence to be enhanced by mining the potential information in the session, thereby improving the accuracy of the upstream data of the recommendation task. Obtain a sequence to be enhanced, the sequence to be enhanced includes multiple object nodes and directed edges for connecting the object nodes, and the sequence to be enhanced is used to indicate the order in which the user selects objects in the session. According to the potential object nodes corresponding to each object node, a directed graph including multiple weighted directed edges is determined, the weighted directed edges are used to point from the object node to the potential object node corresponding to the object node, and the weights carried by the weighted directed edges are used to indicate the probability of the user selecting the potential object corresponding to the target object after selecting the target object, so that the association relationship between the object node and the potential object node corresponding to the object node in the session can be established through the weighted directed edges, and the sequence to be enhanced is expanded into a directed graph that better reflects the user's interactive behavior. The directed graph is traversed according to the weights carried by the weighted directed edges to obtain the target enhancement sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge. Therefore, according to the weights that can characterize the probability of the user selecting an object, the directed graph obtained by mining the potential information of the session is traversed to obtain a target enhancement sequence with higher accuracy, so that when the target enhancement sequence is used for sequence recall, objects related to the user can be predicted more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of a data enhancement method provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for determining a weighted directed edge provided in an embodiment of the present application; Figure 3 A schematic diagram of a process of discarding weighted directed edges provided in an embodiment of the present application; Figure 4 A schematic diagram of a process of discarding an object node provided in an embodiment of the present application; Figure 5 A flowchart of a scenario of an application data enhancement method provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of a data enhancement device provided in an embodiment of the present application; Figure 7A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0022] In the related art, objects of interest to users are predicted through sequence recall. Current sequence recall models usually use existing user historical behavior sequences for prediction. This approach implies the assumption that the user historical behavior sequences are "strictly ordered", that is, each choice of the user for an object is made without being influenced by objective factors and is a choice made in accordance with subjective will. The order of the user historical behavior sequences generated in the session is the order of the user's subjective choices.

[0023] However, only using the existing user history behavior sequence for prediction does not take into account the potential information in the session. For example, when a user is scrolling through short videos in a waterfall flow, the user may have the same interest in the short videos within the preset window, but due to the display order in the window, the user can only select the short video that is displayed first. The existing user history behavior sequence is difficult to reflect the potential information in the session, resulting in low accuracy.

[0024] Although there are some methods in the prior art to perform data enhancement on existing user historical behavior sequences, such as Self-Supervised Graph Learning (SGL), most of them are based on random masking, cropping, and replacement of existing sequences, lacking reliable evidence and also unable to reflect the potential information in the session.

[0025] Based on this, the embodiment of the present application provides a data enhancement method and related devices, which expand the sequence to be enhanced into a directed graph that can better reflect the user's interactive behavior by mining the potential information in the conversation. According to the weight that can characterize the probability of the user selecting an object, the directed graph obtained by mining the potential information of the conversation is traversed to obtain a target enhancement sequence with higher accuracy, so that when the target enhancement sequence is used for sequence recall, it can more accurately predict the objects related to the user.

[0026] The data enhancement method provided in this application can be applied to computer devices with data enhancement capabilities, such as terminal devices and servers. Specifically, the terminal device can be a desktop computer, a laptop computer, a mobile phone, and a tablet computer; the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0027] See also Figure 1 , which is a flow chart of the data enhancement method provided in the embodiment of the present application. For the convenience of description, the following embodiment is introduced by taking the execution subject of the data enhancement method as a server as an example. Figure 1 As shown, the data enhancement method includes S101-S103.

[0028] S101: Acquire a sequence to be enhanced.

[0029] A session is a series of user interaction behaviors within a preset duration. Interaction behavior is the process of users selecting objects within the preset duration. Objects are entities or content that can interact with users. For example, objects can be short videos, products, other users' homepages, etc. Correspondingly, interaction behaviors are clicking on products, browsing short videos, clicking on user homepages, etc. Each session will generate a corresponding user historical behavior sequence.

[0030] In the related art, data enhancement operations such as node dropout, edge dropout, and random walk are usually only performed on the original user historical behavior sequence. For example, SGL performs the above data enhancement operations on the existing user-item bipartite graph (including the user historical behavior sequences generated by all sessions), but fails to perform data enhancement on the user's interactive behavior in each session. The embodiment of the present application provides a data enhancement method for expanding the user historical behavior sequence based on the potential information corresponding to the interactive behavior in the session, so as to enhance the accuracy of the user historical behavior sequence, which is described in detail below.

[0031] The sequence to be enhanced is at least one user historical behavior sequence that has not been data enhanced, which is used to indicate the order in which the user selects objects in the session. The sequence to be enhanced includes multiple object nodes and directed edges for connecting object nodes. Object nodes are nodes used to refer to objects in the graph structure. According to the order in which the user selects objects, the directed edges point from the previous object node to the next object node.

[0032] For example, in a session, the user clicked on product A, product C, product B, and product D in turn, then A->C->B->D is a user historical behavior sequence (sequence to be enhanced). Among them, A, C, B, and D are the object nodes corresponding to the four products respectively, and the arrows are used to indicate the directed edges connecting adjacent object nodes.

[0033] In a possible implementation, the existing user historical behavior sequence can be preprocessed to obtain a more representative sequence to be enhanced. The following uses three preprocessing methods as examples for explanation: (1) Filter out repeated object nodes in the user's historical behavior sequence. That is, for multiple repeated object nodes, only one object node is retained. This method is usually used in scenarios where users can view multiple object selections as one interactive behavior, such as when browsing short videos.

[0034] (2) Filter out “unpopular” object nodes. That is, among multiple object nodes, delete the object nodes whose appearance frequency is less than the frequency threshold. The object nodes whose appearance frequency is less than the frequency threshold are used to reflect the objects with a low probability of user interest. By filtering these nodes, the data noise in the user’s historical behavior sequence can be reduced.

[0035] (3) Filter out short sequences, that is, remove user historical behavior sequences whose length is less than a preset length threshold, so that when user historical behavior sequences are used for downstream tasks such as predicting objects of interest to users, they can provide richer contextual information and improve prediction accuracy.

[0036] After data preprocessing of the existing user historical behavior sequence, the data is divided into a training set, a validation set, and a test set. The training set can be determined as the sequence to be enhanced for subsequent data enhancement steps.

[0037] All data collected by this application (such as user historical behavior sequences and sequences to be enhanced) are collected with the consent and authorization of the object to which the data belongs (such as users, institutions or enterprises), and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0038] The following describes the steps of data enhancement by taking a sequence to be enhanced as an example.

[0039] S102: Determine a directed graph including a plurality of weighted directed edges according to the potential object nodes corresponding to the respective object nodes.

[0040] In a session, the user selects object A and then object B. In addition to the object B that the user actually selects, there may be multiple potential objects for object A, that is, objects that are not actually selected by the user as the next object but have a high probability of being interested in by the user are potential objects. Potential object nodes are nodes used to refer to potential objects in the graph structure.

[0041] The embodiments of the present application do not specifically limit how to determine the potential object nodes corresponding to each object node. For example, in the sequence to be enhanced A->C->B->D, the user actually selects C after selecting A in the current window of the terminal (the window currently displayed to the user), and D is within the preset window range based on A. Based on the current recommendation algorithm, D and A are associated, then a directed edge to be weighted can be added from A to D. The directed edge to be weighted is a weighted directed edge that has not yet been weighted. This process will be described in detail in A3-A4 later and will not be repeated here. Still taking the sequence to be enhanced A->C->B->D as an example, if the feature information of B is highly associated with the feature information of A, such as repeated keywords, the same labels, etc., then a directed edge to be weighted can be added from A to C.

[0042] It should be noted that the above operation of adding directed edges to be weighted is an additional operation based on retaining the directed edges of the original sequence to be enhanced, that is, the selection path of the original sequence to be enhanced is expanded, reflecting the potential interaction behavior of the user. In addition to expanding the directed edges, it is also necessary to perform weighting operations on each directed edge, that is, to perform weighting operations on the original directed edges and the newly expanded directed edges to be weighted, so as to convert each directed edge into a weighted directed edge.

[0043] The weighted directed edge is used to point from the object node to the potential object node corresponding to the object node. The weight carried by the weighted directed edge is used to indicate the probability of the user selecting the potential object corresponding to the target object after selecting the target object. The target object is one of the multiple objects corresponding to the sequence to be enhanced. For example, if the user has a higher probability of selecting the potential object F corresponding to the target object E after selecting the target object, the weight carried by the weighted directed edge connecting the E node and the F node is greater.

[0044] Therefore, by expanding directed edges and performing weighting operations, a directed graph including a plurality of weighted directed edges is obtained, and the directed graph is a graph obtained by expanding the sequence to be enhanced according to the potential information of the session.

[0045] S103: Traversing the directed graph according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced.

[0046] Among them, the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge, and the target enhancement sequence is the user historical behavior sequence after data enhancement.

[0047] By traversing the directed graph, one or more enhanced sequences can be obtained, and the enhanced sequences are candidate sequences of the target enhanced sequence. If an enhanced sequence is obtained, a traversal actual node can be determined from multiple object nodes, and then the traversal can be started according to the weights of the weighted directed edges for the convenient actual node.

[0048] If multiple enhancement sequences are obtained, a traversal start node set can be constructed for the n object nodes included in the directed graph, and then each traversal start node in the traversal node set is traversed according to the weight of the weighted directed edge to obtain multiple enhancement sequences, and one of the multiple enhancement sequences is determined as the target enhancement sequence. As an implementation method, an enhancement sequence can be randomly selected from multiple enhancement sequences to be determined as the target enhancement sequence to enhance robustness. As another implementation method, the enhancement sequence with the largest number of object nodes in multiple enhancement sequences can be determined as the target enhancement sequence to improve the ability of the target enhancement data to reflect context information. As an implementation method, n can be the window size.

[0049] Specifically, starting from traversing the actual nodes, each object node corresponds to one or more weighted directed edges pointing to one or more object nodes. The enhanced sequence can be obtained by traversing the directed graph according to the following rules: (1) Do not traverse nodes repeatedly (2) If there is a weighted directed edge from node x to node y, the probability of jumping from node x to node y is: ,in is the weight carried by the weighted directed edge between the x node and the y node, It is the sum of the weights carried by multiple weighted directed edges corresponding to the x node.

[0050] (3) If there is no next object node to traverse, the traversal is terminated.

[0051] Therefore, by traversing the directed graph according to the weights carried by the weighted directed edges, it is possible to determine the potential information in the session corresponding to the sequence to be enhanced. The potential information includes the potential objects selected by the user and the probability of the user selecting the next object, so as to obtain a target enhancement sequence that can more fully reflect the user's interactive behavior, thereby improving the accuracy of the user's historical behavior sequence.

[0052] By inputting the target enhancement sequence into the sequence recall model and executing the downstream tasks corresponding to the sequence recall model, the user's preferred objects can be predicted more accurately, thereby improving the user's experience when the user's preferred objects are recommended to the user.

[0053] It can be seen from the above technical solution that the present application performs data enhancement on the sequence to be enhanced by mining the potential information in the session, thereby improving the accuracy of the upstream data of the recommendation task. Obtain a sequence to be enhanced, the sequence to be enhanced includes multiple object nodes and directed edges for connecting the object nodes, and the sequence to be enhanced is used to indicate the order in which the user selects objects in the session. According to the potential object nodes corresponding to each object node, a directed graph including multiple weighted directed edges is determined, and the weighted directed edges are used to point from the object node to the potential object node corresponding to the object node. The weights carried by the weighted directed edges are used to indicate the probability of the user selecting the potential object corresponding to the target object after selecting the target object, so that the association relationship between the object node and the potential object node corresponding to the object node in the session can be established through the weighted directed edges, and the sequence to be enhanced is expanded into a directed graph that can better reflect the user's interactive behavior. The directed graph is traversed according to the weights carried by the weighted directed edges to obtain the target enhancement sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge. Therefore, according to the weights that can characterize the probability of the user selecting an object, the directed graph obtained by mining the potential information of the session is traversed to obtain a target enhancement sequence with higher accuracy, so that when the target enhancement sequence is used for sequence recall, objects related to the user can be predicted more accurately.

[0054] The embodiment of the present application does not specifically limit how to determine the weighted directed edge. The following is an example for explanation, see A1-A4: A1: Determine the directed edges to be weighted corresponding to each object node.

[0055] The directed edge to be weighted is used to point from the object node to the potential object node corresponding to the object node. The potential object node having an association relationship with the object node is determined, and the directed edge to be weighted is added from the object node to the potential object node corresponding to the object node.

[0056] A2: Obtain the corresponding relationship between the degree of association and the weight.

[0057] Among them, in this correspondence, the higher the degree of association, the greater the weight. As mentioned above, the weight is used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object, that is, the higher the degree of association between the target object (target object node) and the potential object (potential object node), the higher the probability that the user selects the potential object corresponding to the target object after selecting the target object.

[0058] A3: Obtain multiple association degrees between each potential object node and the corresponding object node. This application does not specifically limit the method of obtaining the association degree, and the following two methods are used as examples for explanation: Acquisition method 1: In the current recommendation algorithm, the object that the user is interested in will be displayed in the current window or a window close to the current window. Based on this, the object nodes within the preset window range in the sequence to be enhanced can be determined as potential object nodes.

[0059] Specifically, a preset window range is obtained, and the preset window range is used to indicate the object distribution range determined by the current recommendation algorithm, that is, the preset window range is the object distribution range recommended by the current recommendation algorithm. Taking the target object node among multiple object nodes as an example, the potential object distribution range of the target object node is determined according to the position of the target object node and the preset window range. For example, if the preset window range is 2, the window adjacent to the current window and the current window, centered on the current window, constitute the potential object distribution range. The object nodes located in the potential object distribution range among the multiple object nodes are determined as potential object nodes of the target object node. Then, each object node is taken as the target object node, and the above steps are executed to obtain the potential object nodes corresponding to each object node.

[0060] Therefore, by utilizing the recommended object distribution characteristics of the current recommendation algorithm, potential objects are determined according to the distance between the window where each object node is located and the current window, and the potential object nodes corresponding to each object node are determined more accurately with low technical implementation complexity.

[0061] The degree of association between a potential object node and a corresponding object node is determined by the distance between the window where the potential object node is located and the window where the corresponding object node is located. The smaller the distance, the higher the degree of association. For example, if the object node and its corresponding potential object node are both distributed in the current window, the degree of association is high. If the object node is in the current window and its corresponding potential object node is distributed in an adjacent window, the degree of association is lower than that in the same window.

[0062] Acquisition method 2: If each object node is pre-added with a label that can reflect the object category or object characteristics, the degree of association between the object node and its corresponding potential object node can be determined based on the co-occurrence of the labels. For example, the number of labels that are the same between the object node and its corresponding potential object node is counted. The more the number of labels that are the same, the higher the degree of association.

[0063] A4: Determine the weights corresponding to the directed edges to be weighted according to the corresponding relationship, and obtain a directed graph including multiple weighted directed edges.

[0064] According to the correspondence between the degree of association and the weight, the multiple degrees of association between each potential object node and the corresponding object node are transformed to obtain the weight of each directed edge to be weighted connecting the potential object node and the object node, thereby achieving weighting of each directed edge to be weighted and obtaining a directed graph including multiple weighted directed edges.

[0065] Taking the scenario of acquisition method 1 in A3 as an example, if the preset window range is 2, for node x, with node x as the center, the weight carried by the weighted directed edge between node x and node y can be determined by the following formula:

[0066] in, is the weight of the weighted directed edge between node x and node y, and k is used to indicate that the window where node y is located is within the k-fold window range centered on node x. For example, if node x and node y are in the same window, k is 1; if node y is in the adjacent window to the window where node x is located, k is 2.

[0067] Therefore, by determining the weight that can reflect the degree of potential selection tendency of the user according to the degree of association between the object nodes, a directed graph including multiple weighted directed edges that can reflect the potential selection tendency of the user in the session is obtained, thereby improving the accuracy of the target enhancement sequence.

[0068] Furthermore, since users may not have the same inclination towards objects in the same window, based on the above-mentioned determination of weights according to the window positions of object nodes, the present application embodiment provides a specific implementation method for adjusting weights based on similarity, see B1-B4: B1: Determine the basic weights corresponding to each directed edge to be weighted according to the corresponding relationship.

[0069] The basic weight is the weight that has not been adjusted. By executing the weight confirmation steps A1-A4, the basic weight corresponding to each directed edge to be weighted is determined.

[0070] B2: Obtain collaborative filtering model.

[0071] The collaborative filtering model is used to determine the similarity between two objects. The similarity is used to indicate the frequency of co-occurrence of two objects corresponding to the directed edge to be weighted. The higher the frequency, the higher the similarity.

[0072] B3: Determine the similarity corresponding to each directed edge to be weighted based on the collaborative filtering model.

[0073] The similarity corresponding to the directed edge to be weighted is the similarity of the two object nodes corresponding to the directed edge to be weighted. Specifically, the collaborative filtering model can obtain an offline maintained similarity matrix by counting the frequency of simultaneous appearance of each object node pair in each object node in the sequence to be enhanced or other user historical behavior sequence, and sorting the frequency. An object node pair is composed of two object nodes. The similarity matrix is ​​used to characterize the similarity of different object node pairs. The higher the frequency of the object node pair, the higher the similarity of the object node pair. According to the similarity of the object node pair, the similarity of the directed edge to be weighted corresponding to the object node pair is determined.

[0074] By taking values ​​of the object node pairs corresponding to the x node and the y node in the offline maintained similarity matrix, the similarity between the x node and the y node can be determined.

[0075] As an implementation method, the collaborative filtering model normalizes the similarities included in the similarity matrix to a range of 0-1.

[0076] B4: The basic weight is adjusted according to the similarities corresponding to each directed edge to be weighted, so as to obtain the weight corresponding to each directed edge to be weighted.

[0077] The basic weight can be adjusted by the following formula:

[0078] in, is the weight of the directed edge to be weighted corresponding to the x node and the y node, is the basic weight of the directed edge to be weighted corresponding to the x node and the y node, is the similarity between node x and node y.

[0079] Therefore, by adjusting the basic weight of the weighted directed edge based on similarity, the weight can reflect not only the association relationship between objects, but also the degree of similarity between objects. For objects with strong association and high similarity, users will have a stronger tendency to choose them. By adjusting the basic weight, potential information in the conversation can be mined from more dimensions, thereby improving the accuracy of the directed graph.

[0080] The following is an example to illustrate the process of determining the weighted directed edge. Figure 2 , Figure 2 A flow chart of determining a weighted directed edge provided in an embodiment of the present application, firstly, the window size is set to 2 according to the display situation of the actual scene, the window size is used to indicate the range of the window that can display the object, the preset window range is 2, with the target object node as the center, and the window where each object node is located is determined according to the window size. The window is located in the k-window range centered on the target object node, then the formula is used The basic weight of the directed edge to be weighted corresponding to the 1-fold window range is calculated as 1, and the basic weight of the directed edge to be weighted corresponding to the 2-fold window range is calculated as 1 / 2. Then, based on the similarity matrix Sim obtained from the collaborative filtering model of items (a kind of object), the similarity corresponding to each directed edge to be weighted is determined, and the formula is used to calculate the similarity matrix Sim. The weights are adjusted to obtain the weights corresponding to the directed edges to be weighted. Thus, each weighted directed edge is determined.

[0081] As can be seen from the foregoing, the directed graph is obtained by expanding the sequence to be enhanced through S101-S102, so that the directed graph can more accurately reflect the user interaction behavior. The embodiment of the present application provides an implementation method for reprocessing the directed graph: According to the potential object nodes corresponding to each object node, an initial directed graph including a plurality of weighted directed edges is determined. That is, the initial directed graph is obtained through the relevant steps of S102-S103, and the initial directed graph is a directed graph without performing a discard operation. According to the behavior data of the user selecting the object, a discard operation is performed on the initial directed graph to obtain a directed graph. Among them, the discard operation is used to discard the object nodes or weighted directed edges included in the initial directed graph.

[0082] By analyzing the behavioral data of users' object selection, we can determine which object nodes or weighted directed edges in the initial directed graph are difficult to represent the users' preferred objects, and thus discard the object nodes or weighted directed edges that are difficult to represent the users' preferred objects. This can result in a directed graph that can more accurately reflect the users' object selection tendencies and improve the accuracy of the target enhancement sequence.

[0083] The following uses two discarding methods as examples to illustrate.

[0084] See C1-C3 for discarding method 1: C1: Obtain the interval time threshold and the interval time of each pair of object nodes connected by weighted directed edges.

[0085] The interval time threshold is an upper limit of the interval time that can reflect the user's continuous selection of objects in the session. The embodiment of the present application does not specifically limit the size of the interval time threshold, and those skilled in the art can set it according to actual needs. An object node pair is composed of two object nodes, and the interval time of the object node pair connected by a weighted directed edge is the interval time between two objects selected continuously by the user.

[0086] C2: If the interval time between the object node pairs exceeds the interval time threshold, a first probability of a discard operation is determined according to the timeout degree of the interval time exceeding the interval time threshold.

[0087] The higher the timeout degree is, the higher the first probability is. The timeout degree is the degree to which the interval time exceeds the interval time threshold, and the first probability is the probability of performing a discard operation on the weighted directed edge.

[0088] As can be seen from the foregoing, the weighted directed edge is used to point from the object node to the potential object node corresponding to the object node. The weight carried by the weighted directed edge is used to indicate the probability of the user selecting the potential object corresponding to the target object after selecting the target object, that is, the weighted directed edge can reflect the connection between the user's selection of two objects. If the interval time of the object node pair connected by the weighted directed edge exceeds the interval threshold, it means that when the user selects the two corresponding objects, the interval time is long and the connection degree is small. Then, the first probability of the discard operation can be determined according to the timeout degree.

[0089] For example, the first probability can be determined by the following formula:

[0090] Where P1 is the first probability, T is the interval time between object node pairs, is the interval time threshold, Used to indicate that x is rounded down.

[0091] C3: performing a discard operation on the weighted directed edges connecting the object node pairs in the initial directed graph according to the first probability.

[0092] It should be noted that not only can the discard operation be performed on the weighted directed edges by executing C1-C3, but the above-mentioned steps of determining the discard probability according to the interval time corresponding to the directed edge and performing the discard operation according to the discard probability can also be performed on the original directed edges. The embodiments of the present application are not limited here.

[0093] See also Figure 3 , Figure 3 A schematic diagram of a process of discarding weighted directed edges provided in an embodiment of the present application, for T greater than or equal to The object node pair is discarded and its corresponding directed edge is discarded.

[0094] Therefore, by performing a discard operation on directed edges for connecting object node pairs with longer intervals according to the first probability, directed edges corresponding to object node pairs with smaller correlations can be screened out, and directed edges that more accurately reflect the directionality of user selections can be obtained, thereby improving the accuracy of the target enhancement sequence.

[0095] For discarding method 2, see D1-D3: D1: Obtain the probability prediction model.

[0096] Taking into account that users will terminate the interaction after selecting certain objects (such as vulgar short videos, etc.), discarding method 2 improves the accuracy of the target enhancement sequence by discarding object nodes that may cause users to terminate the interaction.

[0097] The probability prediction model is used to predict the probability that the user terminates the interaction after selecting an object. The probability prediction model is trained through the feature data of the user and the feature data of the object node that causes the user to terminate the interaction.

[0098] D2: According to the feature data of the user and the feature data corresponding to each object node, prediction is performed through a probability prediction model to obtain a second probability corresponding to each object node.

[0099] By combining the feature data of each object node with the feature data of the user, a plurality of sample pairs are obtained, and each sample pair is input into the probability prediction model to obtain the second probability of each object node. The second probability corresponding to the object node is the probability of predicting that the user will terminate the interaction after selecting the object corresponding to the object node.

[0100] D3: For each object node in the initial directed graph, a discard operation is performed on the object node corresponding to the second probability according to the second probability.

[0101] Taking the initial directed graph as a linear user historical behavior sequence as an example, the discard operation is performed on the i-th object node, which includes at least two cases: Case 1 is to skip the i-th object node. That is, in the initial directed graph, originally the pointers were from the i-1th object node to the i-th node, and from the i-th object node to the i+1th object node. If the i-th object node is skipped, the pointers are directly from the i-1th object node to the i+1th object node, where i is a positive integer.

[0102] Case 2 is to directly delete the i-th object node and the corresponding directed edge, that is, to obtain the first subsequence and the second subsequence, the first subsequence uses the i-1-th object node as the end object node, and the second subsequence uses the i+1-th object node as the start object node.

[0103] See also Figure 4 , Figure 4 A flowchart of discarding an object node provided in an embodiment of the present application. The second probability of a user terminating interaction on an object is estimated to be P through consumption termination probability estimation (a probability prediction model), and the object node is deactivated (discarded) according to probability P.

[0104] Therefore, the probability prediction model obtained through pre-training predicts the second probability of each object causing the user to terminate the interaction, and each object node is discarded according to the second probability, so that the object nodes with a higher probability of causing the user to terminate the interaction are more easily discarded. Such object nodes are difficult to provide information about the user's preference for selecting objects. By discarding such object nodes, the target enhanced sequence can provide more accurate information that can reflect the user's preference for selecting objects when used for sequence recall, thereby improving the accuracy of sequence recall.

[0105] It should be noted that the above discard operation performed on the initial directed graph can also be used for the enhanced sequence obtained by traversing the directed graph. After performing the discard operation on the enhanced sequence, the target enhanced sequence is obtained, and the embodiment of the present application does not limit this. The discard operation can be performed by performing discard mode 1, performing discard mode 2, performing discard mode 1 and discard mode 2 in sequence, or performing discard mode 2 and discard mode 1 in sequence, and the embodiment of the present application does not limit this.

[0106] The above embodiment is to obtain a target enhanced sequence by data enhancement based on a sequence to be enhanced corresponding to a session, and the user historical behavior sequence used for sequence recall usually includes target enhanced sequences corresponding to multiple sessions. Based on this, the embodiment of the present application provides a method for allocating session identifiers: If the sequence to be enhanced includes a first sequence to be enhanced and a second sequence to be enhanced, correspondingly, the first sequence to be enhanced is expanded to obtain a first directed graph, and the second sequence to be enhanced is expanded to obtain a second directed graph, then the first directed graph is traversed according to the weights carried by the weighted directed edges in the first sequence to be enhanced to obtain the first enhanced sequence. The second directed graph is traversed according to the weights carried by the weighted directed edges in the second sequence to be enhanced to obtain the second enhanced sequence. That is, the first sequence to be enhanced and the second sequence to be enhanced from two different sessions can be data enhanced according to the above data enhancement steps to obtain the first enhanced sequence and the second enhanced sequence.

[0107] Then, a first identifier is assigned to the first enhanced sequence, and a second identifier is assigned to the second enhanced sequence, to obtain a first target enhanced sequence corresponding to the first sequence to be enhanced and a second target enhanced sequence corresponding to the second sequence to be enhanced. The first identifier and the second identifier are used to characterize the order of the sessions corresponding to the first sequence to be enhanced and the second sequence to be enhanced. For example, the session time corresponding to the first sequence to be enhanced is later, and the session time corresponding to the second sequence to be enhanced is earlier, then the first identifier is 1, and the second identifier is 2, to reflect that the session corresponding to the first sequence to be enhanced precedes the session corresponding to the second sequence to be enhanced.

[0108] Therefore, by assigning identifiers to the enhanced sequences corresponding to the user's successive sessions, the data set for sequence recall composed of multiple target enhanced sequences can characterize the temporal correlation between different sessions, thereby enriching the data feature level used for sequence recall and improving the accuracy of sequence recall.

[0109] See Table 1, which is an example of a system that applies the above-mentioned data enhancement method. The system includes a data preparation module, an integrated composition module, a session enhancement module, a sequence generation module, an embedding identification module and a model training module.

[0110]

[0111] Figure 5 A flowchart of a scenario of an application data enhancement method provided in an embodiment of the present application. Figure 5 Further explain the data enhancement process of this system.

[0112] (1) The data preparation module obtains user sequence (user historical behavior sequence) 1 and user sequence (user historical behavior sequence) 2, and performs data preprocessing to obtain sequences to be enhanced corresponding to multiple sessions.

[0113] (2) The integrated graph composition module includes a jump operator, a deactivation operator, and a jump-out operator. The jump operator is used to establish weighted directed edges between each object node and its corresponding potential object node based on a preset window range. The weight is obtained by adjusting the basic weight, which is determined according to the window position corresponding to the object node. Then, the similarity of each object node pair is obtained based on the similarity matrix maintained by the collaborative filtering model of the item, and the basic weight is adjusted. The deactivation operator is used to discard directed edges whose time interval exceeds the time interval threshold in a longer session according to the first probability. The jump-out operator is used to predict the second probability of the user terminating consumption (an interactive behavior) after selecting each object node based on the termination consumption probability estimation model (a probability prediction model), and discard each object node according to the second probability. Thus, based on the three operators and the offline trained model, the enhanced sequence is expanded to obtain multiple directed graphs including weighted directed edges.

[0114] (3) The session enhancement module traverses each directed graph to obtain multiple enhancement sequences corresponding to the session, and randomly selects one enhancement sequence as the enhancement result of the session.

[0115] (4) The sequence generation module concatenates multiple enhancement results to obtain a target enhancement sequence, which includes the enhancement results of multiple sessions.

[0116] (5) The embedding identification module assigns session identifiers according to the order of the sessions. The session ID for the later enhanced sequence is 1, and the session ID for the earlier enhanced sequence is 2. Thus, a data set after data enhancement is obtained.

[0117] (6) The model training module uses the data augmented dataset, selects the sequence recall model, and introduces session embedding in the embedding layer for modeling.

[0118] See also Figure 2 , Figure 2 A data enhancement device provided in an embodiment of the present application, the device 600 includes an acquisition unit 601, a composition unit 602 and a traversal unit 603; The acquisition unit 601 is used to acquire a sequence to be enhanced, wherein the sequence to be enhanced includes a plurality of object nodes and directed edges for connecting the object nodes, and the sequence to be enhanced is used to indicate the order in which the user selects objects in a session; The graph forming unit 602 is used to determine a directed graph including a plurality of weighted directed edges according to the potential object nodes corresponding to the respective object nodes, wherein the weighted directed edges are used to point from the object nodes to the potential object nodes corresponding to the object nodes, and the weights carried by the weighted directed edges are used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object; The traversal unit 603 is used to traverse the directed graph according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge.

[0119] It can be seen from the above technical solution that a session is a series of interactive behaviors of a user within a preset time length. The present application performs data enhancement on the sequence to be enhanced by mining the potential information in the session, thereby improving the accuracy of the upstream data of the recommendation task. The data enhancement device provided in the embodiment of the present application includes an acquisition unit, a composition unit, and a traversal unit. The sequence to be enhanced is acquired by the acquisition unit, and the sequence to be enhanced includes a plurality of object nodes and directed edges for connecting the object nodes. The sequence to be enhanced is used to indicate the order in which the user selects objects in the session. The composition unit determines a directed graph including a plurality of weighted directed edges according to the potential object nodes corresponding to each object node, and the weighted directed edges are used to point from the object node to the potential object node corresponding to the object node. The weights carried by the weighted directed edges are used to indicate the probability of the user selecting the potential object corresponding to the target object after selecting the target object, so that the association relationship between the object node and the potential object node corresponding to the target object in the session can be established through the weighted directed edges, and the sequence to be enhanced is expanded into a directed graph that better reflects the user's interactive behavior. The traversal unit traverses the directed graph according to the weights carried by the weighted directed edges to obtain the target enhancement sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge. Thus, according to the weights that can characterize the probability of the user selecting an object, the directed graph obtained by mining the potential information of the session is traversed to obtain a more accurate target enhancement sequence, so that when the target enhancement sequence is used for sequence recall, it can more accurately predict the objects related to the user.

[0120] As a possible implementation manner, the composition unit is specifically used for: Determine directed edges to be weighted corresponding to each of the object nodes, wherein the directed edges to be weighted are used to point from the object nodes to potential object nodes corresponding to the object nodes; Acquire a correspondence relationship between the association degree and the weight, in which the higher the association degree is, the greater the weight is; Acquire multiple association degrees between each of the potential object nodes and the corresponding object node; The weights corresponding to the directed edges to be weighted are determined according to the corresponding relationship, so as to obtain a directed graph including a plurality of the weighted directed edges.

[0121] As a possible implementation manner, the device further includes a weight adjustment unit, which is used to: Determine the basic weights corresponding to the directed edges to be weighted according to the corresponding relationship; Acquire a collaborative filtering model, wherein the collaborative filtering model is used to determine the similarity between two objects, wherein the similarity is used to indicate the frequency of simultaneous occurrence of the two objects corresponding to the directed edge to be weighted, and the higher the frequency, the higher the similarity; Determine the similarities corresponding to each of the directed edges to be weighted according to the collaborative filtering model; The basic weight is adjusted according to the similarities corresponding to each of the directed edges to be weighted, so as to obtain the weight corresponding to each of the directed edges to be weighted.

[0122] As a possible implementation, the degree of association between the potential object node and the corresponding object node is determined by the distance between the window where the potential object node is located and the window where the corresponding object node is located. The smaller the distance, the higher the degree of association. The potential object nodes corresponding to each of the object nodes are determined by: Obtaining a preset window range, where the preset window range is used to indicate the object distribution range determined by the current recommendation algorithm; For a target object node among the multiple object nodes, determining a potential object distribution range of the target object node according to a position of the target object node and a preset window range; Determine an object node located in the potential object distribution range among the plurality of object nodes as a potential object node of the target object node; Each of the object nodes is used as the target object node to obtain potential object nodes corresponding to each of the object nodes.

[0123] As a possible implementation manner, the composition unit is specifically used for: Determining an initial directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes; According to the behavior data of the user selecting the object, a discard operation is performed on the initial directed graph to obtain the directed graph, wherein the discard operation is used to discard the object nodes or weighted directed edges included in the initial directed graph.

[0124] As a possible implementation manner, the composition unit is specifically used for: Obtaining an interval time threshold and an interval time of each pair of object nodes connected by the weighted directed edge; If the interval time of the object node pair exceeds the interval time threshold, determining the first probability of the discard operation according to the timeout degree of the interval time exceeding the interval time threshold, the higher the timeout degree, the higher the first probability; The discard operation is performed on the weighted directed edges connecting the object node pairs in the initial directed graph according to the first probability.

[0125] As a possible implementation manner, the composition unit is specifically used for: Acquire a probability prediction model, wherein the probability prediction model is used to predict the probability that the user terminates the interaction after selecting the object; According to the characteristic data of the user and the characteristic data corresponding to each of the object nodes, prediction is performed by the probability prediction model to obtain second probabilities corresponding to each of the object nodes; For each of the object nodes in the initial directed graph, the discard operation is performed on the object node corresponding to the second probability according to the second probability.

[0126] As a possible implementation manner, if the sequence to be enhanced includes a first sequence to be enhanced and a second sequence to be enhanced, the directed graph includes a first directed graph and a second directed graph, wherein the first directed graph is obtained according to the first sequence to be enhanced, and the second directed graph is obtained according to the second sequence to be enhanced, then the traversal unit is specifically used to: Traversing the first directed graph according to the weights carried by the weighted directed edges in the first sequence to be enhanced to obtain a first enhanced sequence; Traversing the second directed graph according to the weights carried by the weighted directed edges in the second sequence to be enhanced to obtain a second enhanced sequence; A first identifier is assigned to the first enhanced sequence, and a second identifier is assigned to the second enhanced sequence to obtain a first target enhanced sequence corresponding to the first sequence to be enhanced and a second target enhanced sequence corresponding to the second sequence to be enhanced, wherein the first identifier and the second identifier are used to characterize a session order corresponding to the first sequence to be enhanced and the second sequence to be enhanced.

[0127] See also Figure 7 , the embodiment of the present application further provides a computer device, the computer device comprising a memory 701 and a processor 702: The memory is used to store a computer program and transmit the computer program to the processor; The processor is configured to execute the method of the above method embodiment according to the computer program.

[0128] An embodiment of the present application further provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method of the above method embodiment.

[0129] The embodiment of the present application also provides a computer program product including a computer program, which, when executed on a computer device, enables the computer device to execute the method of the above method embodiment.

[0130] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0131] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0132] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0133] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0134] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0135] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data enhancement method, characterized in that: The method comprises: Acquire a sequence to be enhanced, the sequence to be enhanced comprising a plurality of object nodes and directed edges for connecting the object nodes, the sequence to be enhanced being used to indicate the order in which the user selects objects in a session; Determining a directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes, wherein the weighted directed edges are used to point from the object nodes to the potential object nodes corresponding to the object nodes, and the weights carried by the weighted directed edges are used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object; The directed graph is traversed according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edges, the higher the probability of traversing to the object node pointed to by the weighted directed edges.

2. The method according to claim 1, characterized in that The step of determining a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes to obtain a directed graph includes: Determine directed edges to be weighted corresponding to each of the object nodes, wherein the directed edges to be weighted are used to point from the object nodes to potential object nodes corresponding to the object nodes; Acquire a correspondence relationship between the association degree and the weight, in which the higher the association degree is, the greater the weight is; Acquire multiple association degrees between each of the potential object nodes and the corresponding object node; The weights corresponding to the directed edges to be weighted are determined according to the corresponding relationship, so as to obtain a directed graph including a plurality of the weighted directed edges.

3. The method according to claim 2, characterized in that The method further comprises: Determine the basic weights corresponding to the directed edges to be weighted according to the corresponding relationship; Acquire a collaborative filtering model, wherein the collaborative filtering model is used to determine the similarity between two objects, wherein the similarity is used to indicate the frequency of simultaneous occurrence of the two objects corresponding to the directed edge to be weighted, and the higher the frequency, the higher the similarity; Determine the similarities corresponding to each of the directed edges to be weighted according to the collaborative filtering model; The basic weight is adjusted according to the similarities corresponding to each of the directed edges to be weighted, so as to obtain the weight corresponding to each of the directed edges to be weighted.

4. The method according to claim 2, characterized in that: The degree of association between the potential object node and the corresponding object node is determined by the distance between the window where the potential object node is located and the window where the corresponding object node is located. The smaller the distance, the higher the degree of association. The potential object nodes corresponding to each of the object nodes are determined in the following manner: Obtaining a preset window range, where the preset window range is used to indicate the object distribution range determined by the current recommendation algorithm; For a target object node among the multiple object nodes, determining a potential object distribution range of the target object node according to a position of the target object node and a preset window range; Determine an object node located in the potential object distribution range among the plurality of object nodes as a potential object node of the target object node; Each of the object nodes is used as the target object node to obtain potential object nodes corresponding to each of the object nodes.

5. The method according to claim 1, characterized in that The step of determining a directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes comprises: Determining an initial directed graph including a plurality of weighted directed edges according to the potential object nodes respectively corresponding to the object nodes; According to the behavior data of the user selecting the object, a discard operation is performed on the initial directed graph to obtain the directed graph, wherein the discard operation is used to discard the object nodes or weighted directed edges included in the initial directed graph.

6. The method according to claim 5, characterized in that The step of performing a discard operation on the initial directed graph according to the behavior data of the user selecting the object to obtain the directed graph includes: Obtaining an interval time threshold and an interval time of each pair of object nodes connected by the weighted directed edge; If the interval time of the object node pair exceeds the interval time threshold, determining the first probability of the discard operation according to the timeout degree of the interval time exceeding the interval time threshold, the higher the timeout degree, the higher the first probability; The discard operation is performed on the weighted directed edges connecting the object node pairs in the initial directed graph according to the first probability.

7. The method according to claim 5, characterized in that The step of performing a discard operation on the initial directed graph according to the behavior data of the user selecting the object to obtain the directed graph includes: Acquire a probability prediction model, wherein the probability prediction model is used to predict the probability that the user terminates the interaction after selecting the object; According to the characteristic data of the user and the characteristic data corresponding to each of the object nodes, prediction is performed by the probability prediction model to obtain second probabilities corresponding to each of the object nodes; For each of the object nodes in the initial directed graph, the discard operation is performed on the object node corresponding to the second probability according to the second probability.

8. The method according to claim 1, characterized in that If the sequence to be enhanced includes a first sequence to be enhanced and a second sequence to be enhanced, and the directed graph includes a first directed graph and a second directed graph, wherein the first directed graph is obtained according to the first sequence to be enhanced, and the second directed graph is obtained according to the second sequence to be enhanced, then traversing the directed graph according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced includes: Traversing the first directed graph according to the weights carried by the weighted directed edges in the first sequence to be enhanced to obtain a first enhanced sequence; Traversing the second directed graph according to the weights carried by the weighted directed edges in the second sequence to be enhanced to obtain a second enhanced sequence; A first identifier is assigned to the first enhanced sequence, and a second identifier is assigned to the second enhanced sequence to obtain a first target enhanced sequence corresponding to the first sequence to be enhanced and a second target enhanced sequence corresponding to the second sequence to be enhanced, wherein the first identifier and the second identifier are used to characterize a session order corresponding to the first sequence to be enhanced and the second sequence to be enhanced.

9. A data enhancement device, characterized in that: The device comprises: an acquisition unit, a composition unit and a traversal unit; The acquisition unit is used to acquire a sequence to be enhanced, wherein the sequence to be enhanced includes a plurality of object nodes and directed edges for connecting the object nodes, and the sequence to be enhanced is used to indicate the order in which the user selects objects in a session; The graph forming unit is used to determine a directed graph including a plurality of weighted directed edges according to the potential object nodes corresponding to the respective object nodes, wherein the weighted directed edges are used to point from the object nodes to the potential object nodes corresponding to the object nodes, and the weights carried by the weighted directed edges are used to indicate the probability that the user selects the potential object corresponding to the target object after selecting the target object; The traversal unit is used to traverse the directed graph according to the weights carried by the weighted directed edges to obtain a target enhanced sequence corresponding to the sequence to be enhanced, wherein the greater the weight carried by the weighted directed edge, the higher the probability of traversing to the object node pointed to by the weighted directed edge.

10. A computer device, characterized in that: The computer device comprises a processor and a memory: The memory is used to store a computer program and transmit the computer program to the processor; The processor is configured to execute the method according to any one of claims 1 to 8 according to the computer program.

Images