A modeling method and user behavior prediction method based on user behavior data

Abstract

The present invention discloses a modeling method and a user behavior prediction method based on user behavior data, which are applied to the field of artificial intelligence, including: constructing a hybrid relationship network based on the user's historical behavior data, and determining a hybrid relationship matrix containing implicit relationships and explicit relationships based on the hybrid relationship network; constructing a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; obtaining a feature extraction model based on the hybrid relationship matrix and the multi-perspective data matrix, and obtaining user behavior features based on the feature extraction model; and constructing a user behavior prediction model based on a prediction model and user behavior features. The present invention obtains more significant and diverse user behavior features based on a hybrid relationship matrix containing implicit relationships and explicit relationships, and a multi-perspective data matrix, which can characterize the differences between different perspectives and the consistency of the same perspective, so that the constructed prediction model is more reliable and accurate.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a modeling method based on user behavior data and a user behavior prediction method. Background Art

[0002] Game user behavior modeling mainly mines and explores big data through a variety of statistical analysis methods, such as the current time series behavior modeling method based on relationship networks. It constructs a relationship network by statistically analyzing the interactive relationships between users, and uses the relationship network and user feature data as model inputs, which are passed into the time series model to predict future user behavior trends, thereby constructing a user behavior model. However, this method ignores the potential characteristics of users, resulting in inaccurate predictions of the constructed user behavior prediction model. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a modeling method and device based on user behavior data, a user behavior prediction method and device, an electronic device and a storage medium, which solves the problem in the prior art that the relationship network and user feature data cannot fully characterize user behavior, thereby resulting in unreliable user behavior prediction models and inaccurate predictions.

[0004] In order to solve the above technical problems, the present invention provides a modeling method based on user behavior data, comprising:

[0005] Constructing a hybrid relationship network according to the historical behavior data of the user, and determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network;

[0006] Constructing a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data;

[0007] Obtaining a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtaining user behavior features according to the feature extraction model;

[0008] A user behavior prediction model is constructed based on the prediction model and the user behavior characteristics.

[0009] Optionally, a hybrid relationship network is constructed based on the user's historical behavior data, including:

[0010] Build a node set based on user data;

[0011] The edge set is constructed based on the behavioral relationship data between users;

[0012] The preference label data between users is used as the implicit relationship component;

[0013] Use user attention behavior data as explicit relationship components;

[0014] Obtaining a mixed relationship weight set according to the implicit relationship component and the explicit relationship component;

[0015] The hybrid relationship network is constructed by the node set, the edge set and the hybrid relationship weight set.

[0016] Optionally, the preference tag data between users is used as an implicit relationship component, including:

[0017] The expression formula of the implicit relationship component is: ;

[0018] Represents the preference label relationship value of the new user; and They represent the short-term relationship value of answering likes and the long-term relationship value of answering likes labels respectively; , and is the preset positive hyperparameter;

[0019] Indicates user With users The preference label relationship value is calculated as follows: ;

[0020] Indicates user and users The number of commonly preferred tags; Indicates user The number of preference tags.

[0021] Optionally, determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network includes:

[0022] The initial mixed relationship matrix in the mixed relationship weight set is decomposed by using a robust principal component analysis method, and the optimal solution of the optimization problem is solved by using an augmented Lagrange multiplier method, a singular value decomposition and a soft threshold to obtain a low-rank relationship matrix and a sparse matrix;

[0023] The low-rank relationship matrix is ​​used as the mixed relationship matrix.

[0024] Optionally, obtaining a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtaining user behavior features according to the feature extraction model includes:

[0025] Inputting the mixed relationship matrix and the multi-view data matrix into a multi-view autoencoder, and training the multi-view autoencoder based on a loss function to obtain the feature extraction model; the multi-view graph autoencoder includes an encoder and a dual decoder;

[0026] The user behavior feature is obtained based on the feature extraction model.

[0027] Optionally, constructing a multi-view data matrix based on the user behavior data and economic behavior data in the historical behavior data includes:

[0028] Dividing the user behavior data into m user behavior subsets;

[0029] Dividing the economic behavior data into m economic behavior subsets;

[0030] The user behavior subset and the economic behavior subset are spliced ​​together to obtain A data matrix representing the time domain characteristics;

[0031] Using Fourier transform to obtain frequency domain features from the historical behavior data, and obtaining a data matrix representing the frequency domain features;

[0032] The multi-view data matrix is ​​obtained based on the data matrix representing the time domain characteristics and the data matrix representing the frequency domain characteristics.

[0033] The present invention also provides a user behavior prediction method, comprising:

[0034] Obtain the user behavior data to be predicted;

[0035] The user behavior data is input into the user behavior prediction model obtained by the above-mentioned modeling method based on user behavior data to predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model.

[0036] The present invention also provides a modeling device based on user behavior data, comprising:

[0037] A hybrid relationship matrix acquisition module, used to construct a hybrid relationship network according to the historical behavior data of the user, and determine a hybrid relationship matrix containing implicit relationships and explicit relationships according to the hybrid relationship network;

[0038] A multi-perspective data matrix acquisition module, used to construct a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data;

[0039] A user behavior feature acquisition module, used to obtain a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtain user behavior features according to the feature extraction model;

[0040] The user behavior prediction model construction module is used to construct a user behavior prediction model based on the prediction model and the user behavior characteristics.

[0041] The present invention also provides a user behavior prediction device, comprising:

[0042] A data acquisition module, used to acquire user behavior data to be predicted;

[0043] The prediction module is used to input the user behavior data into the user behavior prediction model obtained by the above-mentioned modeling method based on user behavior data to predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model.

[0044] The present invention also provides an electronic device, comprising:

[0045] Memory for storing computer programs;

[0046] A processor is used to implement the steps of the above-mentioned modeling method based on user behavior data and / or user behavior prediction method when executing the computer program.

[0047] The present invention also provides a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of the above-mentioned modeling method based on user behavior data are implemented.

[0048] It can be seen that the present invention constructs a hybrid relationship network based on the historical behavior data of the user, and determines a hybrid relationship matrix containing implicit relationships and explicit relationships based on the hybrid relationship network; constructs a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; obtains a feature extraction model based on the hybrid relationship matrix and the multi-perspective data matrix, and obtains user behavior features based on the feature extraction model; and obtains a user behavior prediction model based on the prediction model and the user behavior features. The present invention constructs a hybrid relationship network based on the explicit relationships in the behavior data and the implicit relationships in the user behavior data, and forms a multi-perspective data matrix with the user behavior data and the economic behavior data, and obtains user behavior features based on the hybrid relationship matrix containing implicit relationships and explicit relationships, and the multi-perspective data matrix. The user behavior features obtained in this way are discriminative, can characterize the differences between different perspectives and the consistency of the same perspective, can enhance the prediction effect of the prediction model, and make the constructed prediction model more reliable and accurate.

[0049] In addition, the present invention also provides a modeling device based on user behavior data, a user behavior prediction method and device, an electronic device and a storage medium, which also have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0051] Figure 1 A flowchart of a modeling method based on user behavior data provided by an embodiment of the present invention;

[0052] Figure 2 An example diagram of a low-rank relationship matrix acquisition process provided by an embodiment of the present invention;

[0053] Figure 3 A flowchart of a method for acquiring user behavior characteristics provided by an embodiment of the present invention;

[0054] Figure 4 A flowchart of a modeling method based on user behavior data provided by an embodiment of the present invention;

[0055] Figure 5 A flowchart of a user behavior prediction method provided by an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of the structure of a modeling device based on user behavior data provided by an embodiment of the present invention;

[0057] Figure 7 A schematic diagram of the structure of a user behavior prediction device provided by an embodiment of the present invention;

[0058] Figure 8 A schematic diagram of the structure of a modeling device based on user behavior data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 are within the scope of protection of the present invention.

[0060] Please refer to Figure 1 , Figure 1 A flowchart of a modeling method based on user behavior data provided by an embodiment of the present invention. The method may include:

[0061] S101: constructing a hybrid relationship network according to the historical behavior data of the user, and determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network.

[0062] The executor of this embodiment is a terminal. This embodiment does not limit the type of terminal, as long as it can complete the operation of the modeling method based on user behavior data. This embodiment collects historical behavior data of a large number of users related to the internal system of the game. It can be understood that the historical behavior data collected from a large number of users includes historical behavior data corresponding to each user. For example, answering behavior data, consumption behavior data, and behavior data associated with the internal system of the game. Furthermore, this embodiment can also group users according to specified attributes (such as region, age, label field, etc.), and model different groups of users separately, so as to obtain user behavior prediction models of various fixed attributes, and behavior prediction will be more accurate and detailed.

[0063] This embodiment constructs a hybrid relationship network with implicit and explicit relationships based on historical behavior data, and obtains a hybrid relationship matrix with implicit and explicit relationships based on the network. The hybrid relationship network is a network model that combines multiple relationship inductive biases, and aims to improve the performance of deep learning models by constructing and processing different types of node and edge relationships.

[0064] Furthermore, the above-mentioned construction of a hybrid relationship network based on the user's historical behavior data may include the following steps:

[0065] Step 21: Construct a node set based on user data;

[0066] Step 22: construct an edge set based on the behavioral relationship data between users;

[0067] Step 23: Use the preference label data between users as implicit relationship components;

[0068] Step 24: Use the user attention behavior data as the explicit relationship component;

[0069] Step 25: Obtain a mixed relationship weight set according to the implicit relationship component and the explicit relationship component;

[0070] Step 26: A hybrid relationship network is constructed by the node set, edge set and hybrid relationship weight set.

[0071] Specifically, suppose there is Different users, build a mixed relationship network ,in represents a node set, i.e., a user set, that is, the user data in step 21 are individual users; represents an edge set, where Indicates that from the user To User relationship; Represents the mixed relationship weight set, that is, the initial mixed relationship weight matrix, where Indicates that from the user To User The mixed relationship weight of . Since the mixed relationship network has directionality, and May not be equal. For mixed relationship weights , which is composed of the explicit relationship component and implicit relationship components For specific calculations, please refer to Figure 2 , Figure 2 An example diagram of a low-rank relationship matrix acquisition process provided by an embodiment of the present invention. Figure 2 It can be seen that the explicit relationship component directly uses the user attention behavior data, while the implicit relationship component mainly uses the preference label data between users. Specifically, assuming that user Followed users , then the explicit relationship component ; Assume that the user Followed users , then the explicit relationship component ; Assume that the user and users If they are related, then the explicit relationship weight The implicit relationship component mainly uses the preference labels between users, which can specifically include the following steps:

[0072] The expression formula of implicit relationship component is: ;

[0073] Represents the preference label relationship value of the new user, because Choosing only once represents the user's general preference, which is assumed to be a stable component that does not change over time; and They represent the short-term relationship value of answering likes and the long-term relationship value of answering likes labels respectively; , and is the preset positive hyperparameter;

[0074] Indicates user With users The preference label relationship value is calculated as follows: ;

[0075] Indicates user and users The number of commonly preferred tags; Indicates user The number of preference labels; Indicates user The preference tag set is specifically composed of new user preference tags and answer like tags.

[0076] user To User The weight of the mixed relationship The formula expression is: .

[0077] At present, time series behavior modeling based on relationship networks basically only utilizes the explicit relationship features of users, and the utilization rate of implicit relationship features is not high, which indirectly weakens the prediction effect of the behavior prediction model. However, when constructing a hybrid relationship network, this embodiment fully explores the explicit relationship components of user attention behaviors and the implicit relationship components of preference tags between users, further enhancing the hybrid relationship network.

[0078] Furthermore, the above-mentioned determination of the hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network may specifically include the following steps:

[0079] Step 31: using a robust principal component analysis method to perform matrix decomposition on the initial mixed relationship matrix in the mixed relationship weight set, and using an augmented Lagrange multiplier method, a singular value decomposition and a soft threshold to solve the optimal solution of the optimization problem, to obtain a low-rank relationship matrix and a sparse matrix;

[0080] Step 32: Use the low-rank relationship matrix as a mixed relationship matrix.

[0081] Specifically, this embodiment further considers the impact of outliers on the hybrid relationship network, and uses a noise suppression algorithm to weaken the damage of outliers to the hybrid relationship network, so that a more significant relationship network can be obtained, and a more representative hybrid relationship matrix can be obtained, such as Figure 2 As shown. Assuming that the mixed relationship matrix has a good data structure, that is, it is low-rank, and only a small part is contaminated by noise or outliers, that is, it is sparse, so the mixed relationship network calculated above is decomposed using robust principal component analysis to specifically optimize the following problems:

[0082] ;

[0083] ;

[0084] represents the initial mixed relationship matrix; represents a low-rank relationship matrix; represents a sparse matrix; Represents the nuclear norm of the low-rank relationship matrix; Represents a sparse matrix norm; is a regularization parameter used to balance the weights of low-rank components and sparse components. In order to solve the above optimization problem, it is necessary to construct a Lagrangian function with a penalty term , using the augmented Lagrange multiplier method, combined with singular value decomposition and soft thresholding method to solve the optimal low-rank relationship matrix and sparse matrices . Where Y is the Lagrange multiplier corresponding to the equality constraint ALS=0, and u is the coefficient of the penalty function, which is used to control the influence of the equality constraint on the objective function. The low-rank mixing matrix obtained by solving Instead of the hybrid relational network calculated above , and input it to the next stage feature extraction model, which not only ensures the global data structure, but also suppresses the damage of some abnormal noise to the network.

[0085] S102: Construct a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data.

[0086] This embodiment does not limit the specific construction process of the multi-view data matrix, nor does it limit the features in the multi-view data matrix. It only needs to satisfy the requirement of constructing the multi-view data matrix based on user behavior data and economic behavior data.

[0087] Furthermore, the above-mentioned construction of a multi-view data matrix based on the user behavior data and the economic behavior data in the historical behavior data may specifically include the following steps:

[0088] Step 41: Divide the user behavior data into m user behavior subsets;

[0089] Step 42: Divide the economic behavior data into m economic behavior subsets;

[0090] Step 43: Combine the user behavior subset and the economic behavior subset to obtain A data matrix representing the time domain characteristics;

[0091] Step 44: Use Fourier transform to obtain frequency domain features from historical behavior data to obtain a data matrix representing the frequency domain features;

[0092] Step 45: Obtain a multi-view data matrix based on the data matrix representing the time domain characteristics and the data matrix representing the frequency domain characteristics.

[0093] Specifically, we screened out two categories of answering behavior data (including answering time, answering accuracy, etc.) and economic behavior data (number of props purchased, recharge amount, etc.) from a large amount of user behavior data. Each behavior category is divided into The data matrix of each perspective extracts a behavior subset from each of the answering behavior category and the economic behavior category for feature splicing, so we get A data matrix representing time domain characteristics. Use Fourier transform to mine frequency domain information from time series data (i.e. historical behavior data). Assume that the length is The time series data matrix , the data matrix representing the time domain characteristics obtained after Fourier transform The data matrix representing the time domain features is spliced ​​into the data matrix representing the frequency domain features to obtain a multi-view data matrix containing both time domain features and frequency domain features.

[0094] S103: Obtain a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtain user behavior features according to the feature extraction model.

[0095] This embodiment further obtains a user behavior feature with a deeper level of representation based on the mixed relationship matrix obtained in step S101 and the multi-view data matrix obtained in step S102. This embodiment does not limit the specific feature extraction model.

[0096] Furthermore, obtaining the user behavior features based on the hybrid relationship matrix and the multi-view data matrix may specifically include the following steps:

[0097] Step 51: inputting the mixed relationship matrix and the multi-view data matrix into the multi-view autoencoder, and training the multi-view autoencoder based on the loss function to obtain a feature extraction model; the multi-view graph autoencoder includes an encoder and a dual decoder;

[0098] Step 52: Obtain user behavior features based on the feature extraction model.

[0099] Specifically, the feature extraction model of this embodiment is a multi-view autoencoder composed of an encoder based on a graph convolutional neural network and a dual decoder. The multi-view data matrix is , the low-rank relationship matrix (i.e., mixed relationship matrix) is , then The output of a graph convolutional neural network layer is represented as ,in , is the unit matrix, ensuring that its multiplication with the feature matrix does not ignore the node’s own features. yes The degree matrix of , represents a nonlinear activation function, represents the element in the i-th row and j-th column of the low-rank relationship matrix, It is The weight matrix of the layer, , .

[0100] This embodiment takes into account that the decoder of the original graph autoencoder reconstructs the adjacency matrix from the encoded features in the form of inner products, which may lose the feature information of the data itself, causing the feature extraction model to ignore the intrinsic characteristics of the learning data. Therefore, in this embodiment, the double decoder, one of the decoders reconstructs the behavioral features of the potential representation user i , and obtain the reconstructed multi-view data matrix , another decoder uses the inner product form to reconstruct the low-rank relationship matrix and obtains the reconstructed mixed relationship matrix , the formula is expressed as ,in, represents a nonlinear activation function. The final loss function of the multi-view image autoencoder is:

[0101] ;

[0102] ;

[0103] To reconstruct the loss of the multi-view data matrix, is the loss of reconstructing the mixture relationship matrix, is the consistency loss, is the regularization term, is the i-th multi-view data matrix, For the i-th reconstructed multi-view data matrix, is the mixed relationship matrix, To reconstruct the hybrid relationship matrix, and represents the encoder output, which are the behavior characteristics of user i and user j respectively, m represents the number of subsets, is the weight, The Frobenius norm of a matrix is ​​a matrix norm used to measure the size of the matrix elements; Represents the penalty term coefficient to prevent the model from overfitting.

[0104] During the training process of the multi-view autoencoder, the optimal parameters are obtained by optimizing the loss function. Since the multi-view graph encoder shares network parameters, after the training is completed, User behavior characteristics Splice to get the final user behavior characteristics . Figure 3 A flowchart of a method for acquiring user behavior characteristics provided in an embodiment of the present invention.

[0105] S104: constructing a user behavior prediction model based on the prediction model and user behavior characteristics.

[0106] This embodiment does not limit the prediction model. For example, the prediction model in this embodiment can be a long short-term memory network of an attention mechanism. By adding an attention layer between the long short-term memory network and the fully connected layer, more attention can be paid to relevant main information in the prediction to ensure the accuracy of the prediction. The output of the feature extraction model, that is, the user behavior characteristics, is input into the long short-term memory network of the attention mechanism to predict future user behavior trends. Furthermore, when new users accumulate to a certain extent, the hybrid relationship network can be reconstructed, and the feature extraction model and the prediction model can be retrained, that is, the previously constructed hybrid relationship network, feature extraction model and prediction model can be adjusted, and optimized and updated to achieve further accurate prediction of the future economic trends of each group.

[0107] The modeling method based on user behavior data provided by the embodiment of the present invention is applied, by constructing a hybrid relationship network according to the user's historical behavior data, and determining a hybrid relationship matrix containing implicit relationships and explicit relationships according to the hybrid relationship network; constructing a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; obtaining a feature extraction model based on the hybrid relationship matrix and the multi-perspective data matrix, and obtaining user behavior features according to the feature extraction model; and obtaining a user behavior prediction model based on the prediction model and the user behavior features. This method constructs a hybrid relationship network based on the explicit relationships in the behavior data and the implicit relationships in the user behavior data, and combines the user behavior data and the economic behavior data into a multi-perspective data matrix, and obtains user behavior features based on the hybrid relationship matrix containing implicit relationships and explicit relationships, and the multi-perspective data matrix. The user behavior features obtained in this way are discriminative, can characterize the differences between different perspectives and the consistency of the same perspective, can enhance the prediction effect of the prediction model, and make the constructed prediction model more reliable and accurate. In addition, the explicit relationship component of the user attention behavior data is combined with the implicit relationship component of the preference label data between users to construct a hybrid relationship network, and the low-rank relationship matrix is ​​obtained by robust principal component analysis, which not only strengthens the connection and structural characteristics of the relationship network, but also suppresses the damage of outliers to the relationship network. In addition, based on the combination of answering behavior and consumption behavior into multi-perspective time domain features, Fourier transform is performed to obtain multi-perspective frequency domain features, and dual graph autoencoders are used for feature extraction. The user behavior features obtained in this way can retain the intuitive features of the time domain and can also mine the discriminative features of the frequency domain; and the long short-term memory network with attention mechanism is used as the user behavior prediction model, which can pay more attention to the relevant main information in the prediction and ensure the accuracy of the prediction; and the user behavior prediction model is trained based on the user behavior features obtained by the above method, which can enhance the behavior prediction effect of the behavior user behavior prediction model and make the user behavior prediction model more reliable.

[0108] In order to make the present invention easier to understand, please refer to Figure 4 , Figure 4 A flowchart of a modeling method based on user behavior data provided by an embodiment of the present invention may specifically include:

[0109] Obtain user behavior data, group the user behavior data based on user attributes, and obtain various groups. Feature extraction mainly includes inputting the low-rank relationship matrix and the multi-view data matrix into the multi-view graph autoencoder to extract features and mine user behavior features with more hierarchical representations. Among them, the low-rank relationship matrix is ​​obtained by robust principal component analysis of the mixed relationship matrix, and the multi-view data matrix includes both time domain features and frequency domain features. User behavior prediction is performed based on the user behavior features obtained by feature extraction, and the future behavior trend of users in this group is predicted. Combined with the relevant behavior analysis of the game economic system, the economic trend of the overall users in the corresponding group can be obtained.

[0110] Please refer to Figure 5 , Figure 5 A flowchart of a user behavior prediction method provided by an embodiment of the present invention. The method may include:

[0111] Step 201: Obtaining user behavior data to be predicted;

[0112] Step 202: Input the user behavior data into the user behavior prediction model obtained by the above-mentioned modeling method based on the user behavior data to predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model.

[0113] The user behavior data to be predicted is input into the user behavior prediction model obtained by the above-mentioned user behavior data modeling method to predict the future behavior of the user. In actual application, the user behavior data of a group can be input into the feature extraction model corresponding to the group to obtain the user behavior characteristics of the group. By inputting the user behavior characteristics into the prediction model, the future behavior trend of the users in the group can be predicted. Combined with the relevant behavior analysis of the game economic system, the economic trend of the overall users in the corresponding group can be obtained.

[0114] The user behavior prediction method provided by the embodiment of the present invention is applied to predict the user's future behavior by inputting the acquired user behavior data to be predicted into the user behavior prediction model obtained by the above-mentioned modeling method based on user behavior data. The user behavior prediction model includes a feature extraction model and a prediction model. The feature extraction model in the behavior prediction model of this method can extract more representative and discriminative user behavior features, so that the behavior prediction model has better prediction effect and the prediction result is more reliable.

[0115] The following is an introduction to a modeling device based on user behavior data provided in an embodiment of the present invention. The modeling device based on user behavior data described below and the modeling method based on user behavior data described above can refer to each other.

[0116] Please refer to Figure 6, Figure 6 A schematic diagram of a structure of a modeling device based on user behavior data provided by an embodiment of the present invention may include:

[0117] A hybrid relationship matrix acquisition module 100 is used to construct a hybrid relationship network according to the historical behavior data of the user, and determine a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network;

[0118] A multi-perspective data matrix acquisition module 200, used to construct a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data;

[0119] A user behavior feature acquisition module 300, used to obtain a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtain user behavior features according to the feature extraction model;

[0120] The user behavior prediction model building module 400 is used to build a user behavior prediction model based on the prediction model and the user behavior characteristics.

[0121] Based on the above embodiment, the mixed relationship matrix acquisition module 100 may include:

[0122] A node set construction unit, used to construct a node set according to user data;

[0123] An edge set construction unit, used to construct an edge set according to the behavioral relationship data between users;

[0124] An implicit relationship component unit, used to use the preference label data between users as implicit relationship components;

[0125] An explicit relationship component unit, used to take the user attention behavior data as an explicit relationship component;

[0126] A mixed relationship weight set construction unit, used to obtain a mixed relationship weight set according to the implicit relationship component and the explicit relationship component;

[0127] A hybrid relationship network construction unit is used to construct the hybrid relationship network from the node set, the edge set and the hybrid relationship weight set.

[0128] Based on the above embodiment, the implicit relationship component unit may include:

[0129] The expression formula of the implicit relationship component is: ;

[0130] Represents the preference label relationship value of the new user; and They represent the short-term relationship value of answering likes and the long-term relationship value of answering likes labels respectively; , and is the preset positive hyperparameter;

[0131] Indicates user With users The preference label relationship value is calculated as follows: ;

[0132] Indicates user and users The number of commonly preferred tags; Indicates user The number of preference tags.

[0133] Based on the above embodiment, the mixed relationship matrix acquisition module 100 may include:

[0134] A decomposition unit, used to perform matrix decomposition on the initial mixed relationship matrix in the mixed relationship weight set by using a robust principal component analysis method, and to solve the optimal solution of the optimization problem by using an augmented Lagrange multiplier method, a singular value decomposition and a soft threshold to obtain a low-rank relationship matrix and a sparse matrix;

[0135] A mixed relationship matrix determining unit is used to use the low-rank relationship matrix as the mixed relationship matrix.

[0136] Based on any of the above embodiments, the user behavior feature acquisition module 300 may include:

[0137] A training unit, configured to input the mixed relationship matrix and the multi-view data matrix into a multi-view autoencoder, and train the multi-view autoencoder based on a loss function to obtain the feature extraction model; the multi-view graph autoencoder includes an encoder and a dual decoder;

[0138] A user behavior feature acquisition unit is used to obtain the user behavior feature based on the feature extraction model.

[0139] Based on the above embodiment, the multi-view data matrix acquisition module 200 may include:

[0140] A user behavior subset division unit, used for dividing the user behavior data into m user behavior subsets;

[0141] An economic behavior subset division unit, used for dividing the economic behavior data into m economic behavior subsets;

[0142] A splicing unit is used to splice the user behavior subset and the economic behavior subset to obtain A data matrix representing the time domain characteristics;

[0143] A frequency domain extraction unit, used to obtain frequency domain features from the historical behavior data using Fourier transform to obtain a data matrix representing the frequency domain features;

[0144] A multi-view data matrix acquisition unit is used to obtain the multi-view data matrix based on the data matrix representing the time domain characteristics and the data matrix representing the frequency domain characteristics.

[0145] It should be noted that the order of the modules and units in the above-mentioned modeling device based on user behavior data can be changed without affecting the logic.

[0146] The modeling device based on user behavior data provided by the embodiment of the present invention is applied, through the hybrid relationship matrix acquisition module 100, used to build a hybrid relationship network according to the user's historical behavior data, and determine the hybrid relationship matrix containing implicit relationships and explicit relationships according to the hybrid relationship network; the multi-perspective data matrix acquisition module 200, used to build a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; the user behavior feature acquisition module 300, used to obtain a feature extraction model based on the hybrid relationship matrix and the multi-perspective data matrix, and obtain user behavior features according to the feature extraction model; the user behavior prediction model construction module 400, used to construct a user behavior prediction model based on the prediction model and the user behavior features. This device constructs a hybrid relationship network based on the explicit relationship in the behavior data and the implicit relationship of the user behavior data, and forms a multi-perspective data matrix with the user behavior data and the economic behavior data, and obtains user behavior features based on the hybrid relationship matrix containing implicit relationships and explicit relationships, and the multi-perspective data matrix. The user behavior features obtained in this way are discriminative, can characterize the differences between different perspectives and the consistency of the same perspective, can enhance the prediction effect of the prediction model, and make the constructed prediction model more reliable and accurate. In addition, the explicit relationship component of the user attention behavior data is combined with the implicit relationship component of the preference label data between users to construct a hybrid relationship network, and the low-rank relationship matrix is ​​obtained by robust principal component analysis, which not only strengthens the connection and structural characteristics of the relationship network, but also suppresses the damage of outliers to the relationship network. In addition, based on the combination of answering behavior and consumption behavior into multi-perspective time domain features, Fourier transform is performed to obtain multi-perspective frequency domain features, and dual graph autoencoders are used for feature extraction. The user behavior features obtained in this way can retain the intuitive features of the time domain and can also mine the discriminative features of the frequency domain; and the long short-term memory network with attention mechanism is used as the user behavior prediction model, which can pay more attention to the relevant main information in the prediction and ensure the accuracy of the prediction; and the user behavior prediction model is trained based on the user behavior features obtained by the above method, which can enhance the behavior prediction effect of the behavior user behavior prediction model and make the user behavior prediction model more reliable.

[0147] The user behavior prediction device provided by an embodiment of the present invention is introduced below. The user behavior prediction device described below and the user behavior prediction method described above can be referenced to each other.

[0148] Please refer to Figure 7 , Figure 7 A schematic diagram of the structure of a user behavior prediction device provided by an embodiment of the present invention may include:

[0149] A data acquisition module 500 is used to acquire user behavior data to be predicted;

[0150] The prediction module 600 is used to input the user behavior data into the user behavior prediction model obtained by the above-mentioned modeling method based on user behavior data to predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model.

[0151] The embodiment of the present invention is applied to provide a user behavior prediction device, which is used to obtain the user behavior data to be predicted through the data acquisition module 500; the prediction module 600 is used to input the user behavior data into the user behavior prediction model obtained by the above-mentioned modeling method based on the user behavior data, and predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model. The feature extraction model in the behavior prediction model of the present device can extract more representative and discriminative user behavior features, so that the behavior prediction model has better prediction effect and the prediction result is more reliable.

[0152] The electronic device provided by the embodiment of the present invention is introduced below. The electronic device described below and the modeling method based on user behavior data and / or the user behavior prediction method described above can be referenced to each other.

[0153] Please refer to Figure 8 , Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention may include:

[0154] A memory 10, used for storing computer programs;

[0155] The processor 20 is used to execute a computer program to implement the above-mentioned modeling method based on user behavior data.

[0156] The memory 10 , the processor 20 , and the communication interface 31 all communicate with each other via the communication bus 32 .

[0157] In the embodiment of the present invention, the memory 10 is used to store one or more programs, and the program may include program code, and the program code includes computer operation instructions. In the embodiment of the present invention, the memory 10 may store programs for implementing the following functions:

[0158] Constructing a hybrid relationship network according to the historical behavior data of the user, and determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network;

[0159] Construct a multi-perspective data matrix based on user behavior data and economic behavior data in historical behavior data;

[0160] Obtaining a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtaining user behavior features according to the feature extraction model;

[0161] A user behavior prediction model is constructed based on the prediction model and user behavior characteristics;

[0162] and / or;

[0163] Obtain the user behavior data to be predicted;

[0164] The user behavior data is input into the user behavior prediction model obtained by the above-mentioned modeling method based on the user behavior data to predict the user's future behavior. The user behavior prediction model includes a feature extraction model and a prediction model.

[0165] In a possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.

[0166] In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include an NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0167] The processor 20 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device, a microprocessor or any conventional processor, etc. The processor 20 may call a program stored in the memory 10 .

[0168] The communication interface 31 may be an interface of a communication module, and is used to connect to other devices or systems.

[0169] Of course, it should be noted that Figure 7 The structure shown does not constitute a limitation on the modeling device based on user behavior data in the embodiment of the present invention. In actual applications, the modeling device based on user behavior data may include: Figure 7 More or fewer components than shown, or combinations of certain components.

[0170] The storage medium provided in an embodiment of the present invention is introduced below. The storage medium described below and the modeling method based on user behavior data described above can be referenced to each other.

[0171] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned modeling method based on user behavior data are implemented.

[0172] The storage medium may be a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0173] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the 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.

[0174] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0175] Finally, it should be noted that, in this article, relationships such as first and second, etc. are used only 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", "comprises" or any other variations are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes 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.

[0176] The above is a detailed introduction to a modeling method and device based on user behavior data, a user behavior prediction method and device, an electronic device and a storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A modeling method based on user behavior data, characterized in that: include: Constructing a hybrid relationship network according to the historical behavior data of the user, and determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network; Constructing a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; Obtaining a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtaining user behavior features according to the feature extraction model; A user behavior prediction model is constructed based on the prediction model and the user behavior characteristics.

2. The modeling method based on user behavior data according to claim 1 is characterized in that: Build a hybrid relationship network based on the user's historical behavior data, including: Build a node set based on user data; The edge set is constructed based on the behavioral relationship data between users; The preference label data between users is used as the implicit relationship component; Use user attention behavior data as explicit relationship components; Obtaining a mixed relationship weight set according to the implicit relationship component and the explicit relationship component; The hybrid relationship network is constructed by the node set, the edge set and the hybrid relationship weight set.

3. The modeling method based on user behavior data according to claim 2 is characterized in that: The preference label data between users is used as implicit relationship components, including: The expression formula of the implicit relationship component is: ; Represents the preference label relationship value of the new user; and They represent the short-term relationship value of answering likes and the long-term relationship value of answering likes labels respectively; , and is the preset positive hyperparameter; Indicates user With users The preference label relationship value is calculated as follows: ; Indicates user and users The number of commonly preferred tags; Indicates user The number of preference tags.

4. The modeling method based on user behavior data according to claim 2, characterized in that: Determining a hybrid relationship matrix including implicit relationships and explicit relationships according to the hybrid relationship network includes: The initial mixed relationship matrix in the mixed relationship weight set is decomposed by using a robust principal component analysis method, and the optimal solution of the optimization problem is solved by using an augmented Lagrange multiplier method, a singular value decomposition and a soft threshold to obtain a low-rank relationship matrix and a sparse matrix; The low-rank relationship matrix is ​​used as the mixed relationship matrix.

5. The modeling method based on user behavior data according to any one of claims 1 to 4, characterized in that: Obtaining a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtaining user behavior features according to the feature extraction model, including: Inputting the mixed relationship matrix and the multi-view data matrix into a multi-view autoencoder, and training the multi-view autoencoder based on a loss function to obtain the feature extraction model; the multi-view graph autoencoder includes an encoder and a dual decoder; The user behavior feature is obtained based on the feature extraction model.

6. The modeling method based on user behavior data according to claim 1, characterized in that: A multi-perspective data matrix is ​​constructed based on the user behavior data and economic behavior data in the historical behavior data, including: Dividing the user behavior data into m user behavior subsets; Dividing the economic behavior data into m economic behavior subsets; The user behavior subset and the economic behavior subset are spliced ​​together to obtain A data matrix representing the time domain characteristics; Using Fourier transform to obtain frequency domain features from the historical behavior data, and obtaining a data matrix representing the frequency domain features; The multi-view data matrix is ​​obtained based on the data matrix representing the time domain characteristics and the data matrix representing the frequency domain characteristics.

7. A user behavior prediction method, characterized in that: include: Obtain the user behavior data to be predicted; The user behavior data is input into a user behavior prediction model obtained by the modeling method based on user behavior data according to any one of claims 1 to 6 to predict the user's future behavior, wherein the user behavior prediction model includes a feature extraction model and a prediction model.

8. A modeling device based on user behavior data, characterized in that: include: A hybrid relationship matrix acquisition module, used to construct a hybrid relationship network according to the historical behavior data of the user, and determine a hybrid relationship matrix containing implicit relationships and explicit relationships according to the hybrid relationship network; A multi-perspective data matrix acquisition module, used to construct a multi-perspective data matrix based on the user behavior data and economic behavior data in the historical behavior data; A user behavior feature acquisition module, used to obtain a feature extraction model based on the mixed relationship matrix and the multi-view data matrix, and obtain user behavior features according to the feature extraction model; The user behavior prediction model construction module is used to construct a user behavior prediction model based on the prediction model and the user behavior characteristics.

9. A user behavior prediction device, characterized in that: include: A data acquisition module, used to acquire user behavior data to be predicted; A prediction module is used to input the user behavior data into a user behavior prediction model obtained by the modeling method based on user behavior data as described in any one of claims 1 to 6 to predict the user's future behavior, wherein the user behavior prediction model includes a feature extraction model and a prediction model.

10. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the modeling method based on user behavior data and / or the user behavior prediction method as described in any one of claims 1 to 7 when executing the computer program.

Images