Service recommendation method, system and equipment based on feature crossing and storage medium

Abstract

The invention relates to the technical field of business field data prediction recommendation, in particular to a service recommendation method, system and device based on feature crossing and a storage medium. In order to solve the problem of low service recommendation accuracy in the prior art, the method comprises the following steps: firstly, constructing a user interaction graph structure, a service interaction graph structure and a user service interaction graph structure, and respectively carrying out graph convolution processing to obtain user interaction features, service interaction features and user service interaction features; then, performing feature cross processing on the target user feature, the target service feature and the user service interaction feature to obtain a user service cross enhanced feature; then, carrying out aggregation processing on the user interaction features, the service interaction features and the user service cross enhancement features to obtain comprehensive cross features; and finally, based on the comprehensive cross characteristics, calculating a recommendation value, and when the recommendation value is greater than a recommendation value threshold, recommending the target service to the target user, thereby enhancing the accuracy of service recommendation and improving the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction and recommendation in the commercial field, and specifically to a service recommendation method, system, device and storage medium based on feature intersection. Background Art

[0002] Modern people pursue experience and relaxation, and tend to enrich their lives and relieve stress through travel. As a result, some commercial platforms for recommending travel services have emerged. These commercial platforms integrate a large amount of travel service information and recommend it to customers, which improves the convenience and selectivity of customers' travel. However, with the continuous increase in travel service data, customers find it difficult to make decisions in the face of massive data, and the difficulty of customer selection increases, which can easily reduce the efficiency of travel service order transactions, and at the same time reduce user experience and reduce consumption of travel commercial content.

[0003] In the existing technology, in order to ensure the quality of tourism services, customers are often inclined to recommend tourism services with higher scores. Tourism services with higher scores may have better quality, but they may not necessarily meet the current customer preferences. In addition, this recommendation model has the disadvantage of uneven resource allocation, which can easily cause crowding in offline tourism production areas, which will reduce user experience. In addition, some recommendation methods attempt to learn the relationship between users and services through neural networks to improve the targeted ability of service recommendations. However, these recommendation methods usually rely on shallow interactions between features and cannot obtain deeper implicit relationships between users and services, such as user interest preferences, potential attributes of services, etc., resulting in low accuracy of service recommendations, reduced user interest, and affected user experience. Summary of the invention

[0004] The purpose of the present invention is to provide a service recommendation method, system, device and storage medium based on feature intersection.

[0005] The technical solution of the present invention is as follows:

[0006] A service recommendation method based on feature intersection includes the following operations:

[0007] S1. The users and services that have interacted with the target user are regarded as similar users and similar services respectively; the graph structures of the target user and similar users, the graph structures of the target service and similar services, and the graph structures of the target user, similar users, target service and similar services are respectively constructed to obtain the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure; the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure are respectively processed by graph convolution to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service;

[0008] S2. The target user and the target service are embedded to obtain target user features and target service features; among the target user features, target service features and user service interaction features, the features with dimensions exceeding the dimension threshold are subjected to dimensionality reduction processing, and then subjected to feature cross processing to obtain user service cross enhancement features;

[0009] S3. Aggregate the user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; obtain a recommendation value based on the comprehensive cross-features, target user features and target service features; if the recommendation value is greater than the recommendation value threshold, recommend the target service to the target user.

[0010] In the adjacency matrix of the user interaction graph structure in S1, the value of each position is the social relationship degree between users, and the social relationship degree is the weighted sum of user social intimacy, user behavior similarity and user location similarity between users; user social intimacy is based on the mutual attention behavior and social interaction behavior between users; user behavior similarity is based on the historical service query behavior and historical service use behavior between users; user location similarity is based on the real-time geographic location and permanent geographic location between users.

[0011] In the adjacency matrix of the service interaction graph structure in S1, the value of each position is the social correlation between services, and the social correlation is the weighted sum of the collaborative filtering relationship, functional correlation and content similarity between services; the collaborative filtering relationship is based on the user's simultaneous use frequency and user rating correlation between services; the functional correlation is based on the functional complementarity relationship and service upstream and downstream relationship between services; the content similarity is based on the subject similarity and service attribute similarity between services.

[0012] The specific operation of feature cross-processing in S2 is: cross-aggregate the target user features, target service features and user service interaction features after dimensionality reduction to obtain cross-aggregated features; after the cross-aggregated features are processed by the ReLU activation function several times, they are concatenated with the cross-aggregated features to obtain user service cross-enhanced features.

[0013] The cross-aggregation operation can be achieved through the following formula:

[0014]

[0015] H z is the cross-aggregation feature, b0 is the global bias term, α is the cross coefficient, X i is the feature of the i-th dimension in the target user feature, X j is the feature of the jth dimension in the target service feature, X k is the feature of the kth dimension in the user-service interaction feature, I, J, K are the total number of dimensions of the target user feature, target service feature, and user-service interaction feature, respectively, and v ij is the latent vector of the features of the i-th dimension in the target user features and the features of the j-th dimension in the target service features, v ik is the latent vector of the feature of the i-th dimension in the target user feature and the feature of the k-th dimension in the user-service interaction feature, v jk is the latent vector of the feature of the jth dimension in the target service feature and the feature of the kth dimension in the user service interaction feature, 〈〉 is the dot product processing of the vector, w1, w2, w3, w4 are the first cross weight, the second cross weight, the third cross weight and the fourth cross weight.

[0016] The aggregation operation in S3 is implemented by the following formula: f =(U·V)⊙H z , H f is a comprehensive cross-feature, U, V, H z They are user interaction features, service interaction features and user-service cross-enhancement features respectively.

[0017] In S3, the recommended value is obtained through the following formula:

[0018] y=f(W1X u +W2X s +W3(X u ⊙X s )+W4Z+B),

[0019] y is the recommended value, Z, X u , X sare comprehensive cross-features, target user features, and target service features, respectively. W1, W2, W3, and W4 are the first recommendation weight, the second recommendation weight, the third recommendation weight, and the fourth recommendation weight, respectively. B is the recommendation bias, and f() is the activation function.

[0020] A service recommendation system based on feature intersection, used to implement the above-mentioned service recommendation method based on feature intersection, comprising:

[0021] The user interaction feature, service interaction feature and user service interaction feature generation modules are used to respectively regard users and services that have interacted with the target user as similar users and similar services; respectively construct the graph structure of the target user and similar users, the graph structure of the target service and similar services, and the graph structure of the target user, similar users, target service and similar services to obtain the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure; the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure are respectively processed by graph convolution to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service;

[0022] The user service cross-enhanced feature generation module is used to embed the target user and the target service to obtain the target user feature and the target service feature; among the target user feature, the target service feature and the user service interaction feature, the feature with the dimension exceeding the dimension threshold is subjected to dimensionality reduction processing, and then subjected to feature cross-processing to obtain the user service cross-enhanced feature;

[0023] The recommendation module is used to aggregate user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; obtain a recommendation value based on the comprehensive cross-features, target user features and target service features; if the recommendation value is greater than the recommendation value threshold, recommend the target service to the target user.

[0024] A service recommendation device based on feature intersection includes a processor and a memory, wherein the processor implements the above-mentioned service recommendation method based on feature intersection when executing a computer program stored in the memory.

[0025] A computer-readable storage medium is used to store a computer program, wherein the computer program implements the above-mentioned service recommendation method based on feature intersection when executed by a processor.

[0026] The beneficial effects of the present invention are:

[0027] The present invention provides a service recommendation method based on feature intersection. First, similar users and similar services that can indirectly reflect the personality characteristics and preference characteristics of the target user are obtained, and the target user and the target service are combined to construct a user interaction graph structure, a service interaction graph structure, and a user service interaction graph structure that reflect the interaction relationship between users, between user services, and between services. Then, the graphs are processed by convolution to obtain user interaction features that are convenient for identifying the social relationship and influence between users and convenient for improving the personalized recommendation and social network analysis effect, and service interaction features that can analyze the relationship between services, reveal the strength of the relationship between the target service and similar users, and are convenient for analyzing the attraction of the target service to the target user, and are convenient for capturing the complex relationship between users and services, helping to understand users. The method uses the user service interaction characteristics of preference and service satisfaction to identify the target user's preference; then, the features whose dimensions exceed the dimension threshold in the target user characteristics, target service characteristics and user service interaction characteristics are subjected to dimensionality reduction processing, and then feature cross processing is performed to cross-combine information of different dimensions to capture the potential relationship between features, and obtain user service cross-enhanced features that can more accurately identify the target user's preference; subsequently, the user interaction characteristics, service interaction characteristics and user service cross-enhanced characteristics are aggregated to achieve the second feature cross-over and obtain comprehensive cross-features; finally, based on the comprehensive cross-features, the recommendation value of the target service relative to the target user is calculated. When the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user, thereby enhancing the accuracy of service recommendations and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the detailed description of the preferred embodiment below, the scheme and advantages of the present application will become clear to those skilled in the art. The accompanying drawings are only for the purpose of illustrating the preferred embodiment and are not to be considered as limiting the present invention.

[0029] In the attached picture:

[0030] Figure 1 In the embodiment, a flowchart of the method recommended in this embodiment is shown;

[0031] Figure 2 The figure is a comparison chart of loss rate results of different recommended methods in the embodiment. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.

[0033] This embodiment provides a service recommendation method based on feature intersection. Figure 1 , including the following operations:

[0034] S1. The users and services that have interacted with the target user are regarded as similar users and similar services respectively; the graph structures of the target user and similar users, the graph structures of the target service and similar services, and the graph structures of the target user, similar users, target service and similar services are respectively constructed to obtain the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure; the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure are respectively processed by graph convolution to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service;

[0035] S2. The target user and the target service are embedded to obtain target user features and target service features; among the target user features, target service features and user service interaction features, the features with dimensions exceeding the dimension threshold are subjected to dimensionality reduction processing, and then subjected to feature cross processing to obtain user service cross enhancement features;

[0036] S3. Aggregate the user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; obtain a recommendation value based on the comprehensive cross-features, target user features and target service features; if the recommendation value is greater than the recommendation value threshold, recommend the target service to the target user.

[0037] S1. The users and services that have interacted with the target user are regarded as similar users and similar services respectively; the graph structures of target users and similar users, target services and similar services are constructed respectively, and the graph structures of target users, similar users, target services and similar services are obtained to obtain the user interaction graph structure, service interaction graph structure and user service interaction graph structure; the user interaction graph structure, service interaction graph structure and user service interaction graph structure are processed by graph convolution respectively to obtain user interaction features, service interaction features and user service interaction features.

[0038] Similar users and similar services that can indirectly reflect the personality traits and preference characteristics of the target user are obtained, and combined with the target user and the target service, a user interaction graph structure, a service interaction graph structure, and a user-service interaction graph structure that reflect the interaction relationship between users, between user services, and between services are constructed. Then, they are processed by graph convolution to obtain user interaction features that are convenient for identifying the social relationships and influence between users and for improving the effects of personalized recommendations and social network analysis, and service interaction features that can analyze the relationships between services, reveal the strength of the relationship between the target service and similar users, and are convenient for analyzing the attraction of the target service to the target user, as well as user-service interaction features that are convenient for capturing the complex relationship between users and services and help understand user preferences and service satisfaction, which will help to obtain more accurate recommendation results in the future.

[0039] First, similar users who may have the same interests as the target user are obtained to extract more potential personality information of the target user. Specifically, users who have interacted with the target user are regarded as similar users. Similar users are users who have linked accounts with the target user or / and have commented on the same service as the target user.

[0040] Similarly, in order to obtain the preferences of the target user, the services that the target user has interacted with are regarded as similar services, which are combined with the target service for analysis, and the matching degree between the target service and the target user is indirectly analyzed from the perspective of the strength of the relationship between the target service and the similar users. Similar services are services that the target user has used before.

[0041] Then, in order to facilitate the analysis of the relationship between users, between services, and between users and services, the graph structures of target users and similar users, target services and similar services, and target users, similar users, target services and similar services are constructed respectively, and the user interaction graph structure, service interaction graph structure and user service interaction graph structure are obtained.

[0042] In the user interaction graph structure, user service interaction graph structure, and service interaction graph structure, the nodes are users and services, the edges are the interaction relationships between users, between users and services, and between services, and the edge weights are the social relationship between users, the user's rating of the service, and the social correlation between services.

[0043] Finally, in order to obtain the complex relationships between users, between users and services, and between services as well as high-order connection information, the user interaction graph structure, the user-service interaction graph structure, and the service interaction graph structure are respectively subjected to graph convolution processing to obtain user interaction features, user-service interaction features, and service interaction features.

[0044] The processing of graph convolution can be achieved by the following formula:

[0045] h l+1 =σ(D-1 / 2 AD -1 / 2 h l W l ),

[0046] h l+1 is the output of the l+1th layer, σ is the Sigmoid function, D is the diagonal degree matrix of A, A is the adjacency matrix, h l is the output of the lth layer, h 0 is the initial graph structure, W l is the weight of the lth layer.

[0047] During the above graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users. The adjacency matrix of the user-service interaction graph structure is obtained based on the user's ratings of the services. The adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services.

[0048] In the adjacency matrix of the user interaction graph structure, the value of each position is the social relationship between users, and the social relationship is the weighted sum of the user social intimacy, user behavior similarity, and user location similarity between users. The adjacency matrix constructed in this way can capture richer social interaction information between users.

[0049] The social intimacy of users is based on the mutual attention behavior and social interaction behavior between users. The mutual attention behavior between users is related to whether users pay attention to each other. For example, if user A and user B pay attention to each other, the mutual attention behavior between users can be assigned a value of 1; if user A and user B pay attention to each other unilaterally, the mutual attention behavior between users can be assigned a value of 0.5; if user A and user B do not pay attention to each other, the mutual attention behavior between users can be assigned a value of 0. The social interaction behavior between users is related to the likes, comments, and sharing of experiences between users. If user A often likes the travel guides posted by user B, then the social interaction behavior between user A and user B is more frequent, and the higher the corresponding value, the higher the social intimacy of users.

[0050] The user behavior similarity is based on the historical service query behavior and historical service usage behavior between users. The historical service query behavior between users is related to the keywords used when searching for services between users, or / and the service introductions browsed; if user A and user B often browse the same type of service (tourist attractions) introduction page and search for similar keywords (such as "parent-child amusement park" and "cultural heritage in-depth tour"), then the higher the similarity of the historical service query behavior between user A and user B, the higher the corresponding user behavior similarity. The historical service usage behavior between users is related to the service usage time, method and location between users; for example, the closer the historical service location (travel destination preference), historical service usage time (travel time selection) and historical service usage method (travel method, such as self-driving tour, group tour, etc.) of user A and user B are, the more similar the historical service usage behavior of user A and user B is, and the higher the user behavior similarity between user A and user B is.

[0051] The user location similarity is based on the real-time geographic location and the permanent geographic location of the users. The closer the real-time geographic location and the permanent geographic location of the users are, the higher the user location similarity is.

[0052] At the same time, in the adjacency matrix of the service interaction graph structure, the value of each position is the social relevance between services, and the social relevance is the weighted sum of the collaborative filtering relationship, functional relevance, and content similarity between services. The adjacency matrix constructed in this way can help understand the quality association, functional complementarity, and content connection between services, so that in the recommendation process, services that match each other in quality can be recommended to users.

[0053] The collaborative filtering relationship is based on the frequency of simultaneous use of services and the correlation of user ratings. The frequency of simultaneous use of services is related to the number of times a service is used simultaneously by the same user. For example, when user A uses service C (booking hotel C) and also uses service D (booking tickets for tourist attraction D), the more times they are used simultaneously, the stronger the collaborative relationship between service C and service D. The higher the frequency of simultaneous use, the higher the collaborative filtering relationship. The correlation of user ratings between services is related to the ratings given by the same user within the neighborhood time. For example, within the same day, when user A gives service C (hotel C) a rating greater than the first rating threshold, and gives service D (tourist attraction D) a rating greater than the second rating threshold, this indicates that the correlation of user ratings between service C and service D is strong, and the collaborative filtering relationship is higher.

[0054] Functional relevance is obtained based on the functional complementarity between services and the upstream and downstream relationship between services. The functional complementarity between services is related to whether the functions between services are complementary; for example, the functions of service C (tourism transportation service) and service D (tourism accommodation service) are complementary, and user A needs to use service C before using service D (user A needs to take transportation to the tourism transportation service point), which shows that the functional complementarity between service C and service D is strong, and the functional relevance is higher. The upstream and downstream relationship between services is related to the industrial chain in which the services are located. For example, if service C and service D are in the same industrial chain, service C is an upstream product (service C is a tourism product supplier), and service D is a downstream product (service D is a travel agency), then the upstream and downstream relationship between service C and service D is strong, and the functional relevance is higher.

[0055] Content similarity is based on the theme similarity and service attribute similarity between services. If service C and service D both belong to the same theme such as cultural theme, then service C and service D have stronger theme similarity and higher content similarity. The service attribute similarity between services is related to the target population, price range and quality level of the services; if the target population, price range or quality level of service C is closer to that of service D, then the service attribute similarity between service C and service D is stronger and the content similarity is higher.

[0056] S2. The target user and the target service are embedded to obtain target user features and target service features. Among the target user features, target service features and user service interaction features, features with dimensions exceeding the dimension threshold are subjected to dimensionality reduction processing, and then subjected to feature cross processing to obtain user service cross-enhanced features.

[0057] After dimensionality reduction processing is performed on the target user features, target service features, and user service interaction features, the features whose dimensions exceed the dimensionality threshold and reduce the computational efficiency are then cross-processed to cross-combine information of different dimensions and capture the potential relationship between features, thereby obtaining user service cross-enhanced features that can more accurately identify the target user's preferences.

[0058] First, the target user and target service are embedded and converted into a vector form that is easy to calculate and process, and the target user characteristics and target service characteristics are obtained.

[0059] Then, among the target user features, target service features, and user-service interaction features, the features whose dimensions exceed the dimension threshold are subjected to dimensionality reduction processing, and then subjected to feature cross processing to obtain user-service cross-enhanced features. For example, if the dimension of the target user feature is greater than the dimension threshold, the target user feature is subjected to dimensionality reduction processing.

[0060] The above dimensionality reduction can be achieved by the following formula: O=max(0,Wx I +b I ),x O is the feature after dimensionality reduction, W is the dimensionality reduction weight matrix, x I is the target user feature, or the target service feature, or the user-service interaction feature, b I is the dimensionality reduction compensation.

[0061] The specific operation of feature cross-processing is: cross-aggregate the target user features, target service features and user service interaction features after dimensionality reduction to obtain cross-aggregation features; after the cross-aggregation features are processed by the ReLU activation function several times, they are concatenated with the cross-aggregation features to obtain user service cross-enhanced features.

[0062] The above cross-aggregation operation can be implemented by concatenation or multiplication.

[0063] The above cross-aggregation operation can also be achieved through the following formula:

[0064]

[0065] H z is the cross-aggregation feature, b0 is the global bias term, α is the cross coefficient, X i is the feature of the i-th dimension in the target user feature, X j is the feature of the jth dimension in the target service feature, X k is the feature of the kth dimension in the user-service interaction feature, I, J, K are the total number of dimensions of the target user feature, target service feature, and user-service interaction feature, respectively, and v ij is the latent vector of the features of the i-th dimension in the target user features and the features of the j-th dimension in the target service features, v ik is the latent vector of the feature of the i-th dimension in the target user feature and the feature of the k-th dimension in the user-service interaction feature, v jk is the latent vector of the feature of the jth dimension in the target service feature and the feature of the kth dimension in the user service interaction feature, 〈〉 is the dot product processing of the vector, w1, w2, w3, w4 are the first cross weight, the second cross weight, the third cross weight and the fourth cross weight.

[0066] S3. Aggregate the user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; obtain a recommendation value based on the comprehensive cross-features, target user features and target service features; if the recommendation value is greater than the recommendation value threshold, recommend the target service to the target user.

[0067] The user interaction features, service interaction features and user-service cross-enhancement features are aggregated to achieve the second feature cross-over and obtain comprehensive cross-features, which can identify more complex interaction information between users and services. Then, based on the comprehensive cross-features, the recommendation value of the target service relative to the target user is calculated. When the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user, thereby enhancing the target user's satisfaction.

[0068] Firstly, user interaction features, service interaction features and user-service cross-enhancement features are aggregated to obtain comprehensive cross-features.

[0069] The operation of aggregation processing is realized by the following formula: f =(U·V)⊙H z , H f is a comprehensive cross-feature, U, V, H z They are user interaction features, service interaction features and user-service cross-enhancement features respectively.

[0070] The operation of aggregation processing can also be achieved through splicing processing.

[0071] Then, based on the comprehensive cross-features, target user features, and target service features, the recommendation value is obtained.

[0072] The operation of obtaining the recommended value is achieved through the following formula: y = f (W1X u +W2X s +W3(X u ⊙X s )+W4Z+B), y is the recommended value, Z, X u , X s are comprehensive cross-features, target user features, and target service features, respectively. W1, W2, W3, and W4 are the first recommendation weight, the second recommendation weight, the third recommendation weight, and the fourth recommendation weight, respectively. B is the recommendation bias. f() is the activation function, which can be either a Relu activation function or a Sigmoid activation function.

[0073] Finally, if the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user.

[0074] In order to verify the effect of the method recommended in this embodiment, the following experiment was performed.

[0075] Experimental settings and datasets. The experimental environment is as follows: Python 3.8, deep learning framework Pytorch1.13.1, and GPU is NVIDIA GeForce RTX 3060. The evaluation indicators include accuracy, mean square error, and mean square logarithmic error. The ml-25m of the MoviesLens movie public dataset was selected in the experiment. The dataset contains 25,000,095 ratings and 1,093,360 tags, about 60,000 movies, and 162,541 users. Each user rated at least 20 movies. The dataset acquisition address is: https: / / grouplens.org / datasets / movielens / 25m / .

[0076] Comparison of existing methods. Four personalized recommendation models were selected as comparison methods in the experiment, as follows: NGCF (Neural Graph Collaborative Filtering) method: This method is a collaborative filtering model based on graph neural network. Its core idea is to represent the interaction data of users and services as a graph structure, and capture the high-order relationship between users and services through graph convolution operations, thereby improving the recommendation performance; LightGCN (Light Graph Convolutional Networks) method: This method is a simplified and optimized version of graph convolutional network (GCN) in the recommendation system. It improves the computational efficiency and performance of the model by removing complex nonlinear transformations and feature transformation operations; WDCN method: This method provides a more accurate ROP prediction method by combining width, depth and cross feature learning, especially in complex drilling data environments. It has excellent performance and shows significant advantages in improving the stability and generalization ability of the model; Deep Crossing method: This method effectively captures the complex relationship between features by stacking multiple residual network modules. Compared with traditional feature engineering methods, Deep Crossing method can automatically learn richer feature representations, improving the accuracy and efficiency of click-through rate prediction and recommendation tasks.

[0077] Performance comparison in experimental results. Table 1 summarizes the performance comparison results of various methods, among which the method of this embodiment has the highest accuracy, the lowest mean square error value and the lowest mean square logarithmic error value, and the recommended performance is the best.

[0078] Table 1 Summary of performance comparison results of each method

[0079]

[0080] Convergence speed comparison of each method. In the experiment, the log loss function of each method is compared, and the log loss function is as follows:

[0081]

[0082] loloss is the loss rate, N is the total number of samples, y i is the label of the i-th sample, p i is the recommended value for the i-th sample. The experimental results are as follows: Figure 2 It can be found that the loss rate of the method in this embodiment is the smallest and the convergence speed is the fastest.

[0083] This embodiment further provides a service recommendation system based on feature intersection, which is used to implement the above-mentioned service recommendation method based on feature intersection, including:

[0084] The user interaction feature, service interaction feature and user service interaction feature generation modules are used to respectively regard users and services that have interacted with the target user as similar users and similar services; respectively construct the graph structure of the target user and similar users, the graph structure of the target service and similar services, and the graph structure of the target user, similar users, target service and similar services to obtain the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure; the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure are respectively processed by graph convolution to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service;

[0085] The user service cross-enhanced feature generation module is used to embed the target user and the target service to obtain the target user feature and the target service feature; among the target user feature, the target service feature and the user service interaction feature, the feature with the dimension exceeding the dimension threshold is subjected to dimensionality reduction processing, and then subjected to feature cross-processing to obtain the user service cross-enhanced feature;

[0086] The recommendation module is used to aggregate user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; obtain a recommendation value based on the comprehensive cross-features, target user features and target service features; if the recommendation value is greater than the recommendation value threshold, recommend the target service to the target user.

[0087] This embodiment also provides a service recommendation device based on feature intersection, including a processor and a memory, wherein the processor implements the above-mentioned service recommendation method based on feature intersection when executing a computer program stored in the memory.

[0088] This embodiment further provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the above-mentioned service recommendation method based on feature intersection when executed by a processor.

[0089] The present embodiment provides a method for service recommendation based on feature intersection. First, similar users and similar services that can indirectly reflect the personality characteristics and preference characteristics of the target user are obtained, and in combination with the target user and the target service, a user interaction graph structure, a service interaction graph structure, and a user service interaction graph structure that reflect the interaction relationship between users, between user services, and between services are constructed. Then, the graphs are processed by graph convolution to obtain user interaction features that are convenient for identifying the social relationship and influence between users and for improving the effect of personalized recommendation and social network analysis, and service interaction features that can analyze the relationship between services, reveal the strength of the relationship between the target service and similar users, and are convenient for analyzing the attraction of the target service to the target user, as well as capture the complex relationship between users and services to help understand the user. The method uses a novel method to identify the user preferences and service satisfaction of target users through user service interaction features; then, the features whose dimensions exceed the dimension threshold in the target user features, target service features and user service interaction features are subjected to dimensionality reduction processing, and then feature cross processing is performed to cross-combine information of different dimensions to capture the potential relationship between features and obtain user service cross-enhanced features that can more accurately identify the target user preferences; subsequently, the user interaction features, service interaction features and user service cross-enhanced features are aggregated to achieve the second feature cross-over and obtain comprehensive cross-features; finally, based on the comprehensive cross-features, the recommendation value of the target service relative to the target user is calculated. When the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user, thereby enhancing the accuracy of service recommendations and improving user experience.

Claims

1. A service recommendation method based on feature intersection, characterized in that: The following operations are included: S1. The users and services that have interacted with the target user are regarded as similar users and similar services respectively; the graph structures of the target user and similar users, the graph structure of the target service and similar services, and the graph structure of the target user, similar users, target service and similar services are respectively constructed to obtain the user interaction graph structure, the service interaction graph structure and the user service interaction graph structure; The user interaction graph structure, service interaction graph structure and user service interaction graph structure are processed by graph convolution respectively to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service; S2. The target user and the target service are embedded to obtain target user features and target service features; among the target user features, target service features and user service interaction features, the features with dimensions exceeding the dimension threshold are subjected to dimensionality reduction processing, and then subjected to feature cross processing to obtain user service cross enhancement features; S3, aggregating the user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; and obtaining a recommendation value based on the comprehensive cross-features, target user features and target service features; If the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user.

2. The service recommendation method based on feature intersection according to claim 1, characterized in that: In S1, in the adjacency matrix of the user interaction graph structure, the value of each position is the social relationship degree between users, and the social relationship degree is the weighted sum of user social intimacy, user behavior similarity and user position similarity between users; User social intimacy is based on the mutual attention and social interaction behaviors between users; User behavior similarity is based on historical service query behavior and historical service usage behavior between users; User location similarity is based on the real-time geographic location and permanent geographic location of the users.

3. The service recommendation method based on feature intersection according to claim 1, characterized in that: In S1, in the adjacency matrix of the service interaction graph structure, the value of each position is the social relevance between services, and the social relevance is the weighted sum of the collaborative filtering relationship, functional relevance and content similarity between services; The collaborative filtering relationship is based on the frequency of simultaneous use of services by users and the correlation of user ratings; Functional relevance is obtained based on the functional complementarity between services and the upstream and downstream relationships between services; Content similarity is obtained based on the subject similarity and service attribute similarity between services.

4. The service recommendation method based on feature intersection according to claim 1, characterized in that: The operation of feature cross processing in S2 is specifically as follows: The target user features, target service features and user service interaction features that have undergone dimensionality reduction processing are cross-aggregated to obtain cross-aggregated features; the cross-aggregated features are processed by the ReLU activation function several times and then concatenated with the cross-aggregated features to obtain user service cross-enhanced features.

5. The service recommendation method based on feature intersection according to claim 4, characterized in that: The cross-aggregation operation can be achieved through the following formula: H z is the cross-aggregation feature, b0 is the global bias term, α is the cross coefficient, X i is the feature of the i-th dimension in the target user feature, X j is the feature of the jth dimension in the target service feature, X k is the feature of the kth dimension in the user-service interaction feature, I, J, K are the total number of dimensions of the target user feature, target service feature, and user-service interaction feature, respectively, and v ij is the latent vector of the features of the i-th dimension in the target user features and the features of the j-th dimension in the target service features, v ik is the latent vector of the feature of the i-th dimension in the target user feature and the feature of the k-th dimension in the user-service interaction feature, v jk is the latent vector of the feature of the jth dimension in the target service feature and the feature of the kth dimension in the user service interaction feature, 〈〉 is the dot product processing of the vector, w1, w2, w3, w4 are the first cross weight, the second cross weight, the third cross weight and the fourth cross weight.

6. The service recommendation method based on feature intersection according to claim 1, characterized in that: In S3, the aggregation processing operation is implemented by the following formula: H f =(U·V)⊙H z , H f is a comprehensive cross-feature, U, V, H z They are user interaction features, service interaction features and user-service cross-enhancement features respectively.

7. The service recommendation method based on feature intersection according to claim 1, characterized in that: In S3, the recommended value is obtained by the following formula: y=f(W1X u +W2X s +W3(X u ⊙X s )+W4Z+B), y is the recommended value, Z, X u , X s are comprehensive cross-features, target user features, and target service features, respectively. W1, W2, W3, and W4 are the first recommendation weight, the second recommendation weight, the third recommendation weight, and the fourth recommendation weight, respectively. B is the recommendation bias, and f() is the activation function.

8. A service recommendation system based on feature intersection, used to implement the service recommendation method based on feature intersection according to claim 1, characterized in that: include: A user interaction feature, service interaction feature and user-service interaction feature generation module, used to identify users and services that have interacted with the target user as similar users and similar services, respectively; Build the graph structure of target users and similar users, the graph structure of target services and similar services, and the graph structure of target users, similar users, target services and similar services respectively, and obtain the user interaction graph structure, service interaction graph structure and user service interaction graph structure; The user interaction graph structure, service interaction graph structure and user service interaction graph structure are processed by graph convolution respectively to obtain user interaction features, service interaction features and user service interaction features; during the graph convolution processing, the adjacency matrix of the user interaction graph structure is obtained based on the user social intimacy, user behavior similarity and user location similarity between users, the adjacency matrix of the service interaction graph structure is obtained based on the collaborative filtering relationship, functional relevance and content similarity between services, and the adjacency matrix of the user service interaction graph structure is obtained based on the user's rating of the service; The user service cross-enhanced feature generation module is used to embed the target user and the target service to obtain the target user feature and the target service feature; among the target user feature, the target service feature and the user service interaction feature, the feature with the dimension exceeding the dimension threshold is subjected to dimensionality reduction processing, and then subjected to feature cross-processing to obtain the user service cross-enhanced feature; The recommendation module is used to aggregate the user interaction features, service interaction features and user-service cross-enhancement features to obtain comprehensive cross-features; Based on the comprehensive cross-features, target user features and target service features, the recommended value is obtained; If the recommendation value is greater than the recommendation value threshold, the target service is recommended to the target user.

9. A service recommendation device based on feature cross-talk, characterized in that: The method comprises a processor and a memory, wherein the processor implements the service recommendation method based on feature intersection as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the service recommendation method based on feature intersection as described in any one of claims 1 to 7 is implemented.

Images