WO2025118131A1 - Intelligent recommendation method based on user behavior features - Google Patents

Abstract

An intelligent recommendation method based on user behavior features. The method comprises data collection, data organization, construction of an LR-based CTR model, construction of a CIN-based CTR model, and model selection and recommendation. On the basis of the design idea of a CTR recommendation model, the method takes into account user behavior features such as viewing, purchasing and favoriting, thus making reasonable recommendations on the basis of behaviors of user groups; in addition, massive user data is cleaned and reshaped to filter out valid data, thereby improving the training speed; furthermore, in order to enhance the prediction efficiency and prediction accuracy, a high-order explicit feature interaction terms algorithm is additionally introduced. The method effectively improves the process of conventional recommendation algorithms, thus enhancing the recommendation accuracy.

Description

An intelligent recommendation method based on user behavior characteristics Technical Field

The present invention belongs to the technical field of big data analysis, and in particular relates to an intelligent recommendation method based on user behavior characteristics.

Background Art

With the rapid development of the Internet, cloud computing and artificial intelligence in recent years, intelligent recommendation technology has been widely infiltrated into our daily lives and has huge commercial potential. Therefore, major Internet companies attach great importance to this and have carried out a lot of related research. In such a rapidly developing industry, the existing intelligent recommendation system can easily analyze the massive user data and provide each user with the most suitable suggestions based on their personal character, behavior habits, etc.

Researchers have gone through several stages of improving the intelligent recommendation system, and each stage has certain improvements and developments. In the early days, collaborative filtering models were usually used to build recommendation algorithms. Later, with the rise of machine learning models, attempts were made to apply machine learning to recommendation systems. In the end, due to the good effect of the recommendation model based on the CTR (Click Through Rate) algorithm, it gradually replaced the classic machine learning model and became the current mainstream. The CTR recommendation model collects various feature information of users and recommended content, predicts the user's click-through rate of recommended content, and performs recommendation screening based on the click-through rate, thereby achieving intelligent recommendation.

Summary of the invention

In view of the shortcomings of the prior art, the present invention provides an intelligent recommendation method based on user behavior characteristics, which includes the following main steps:

Step 1: Collect user data. The user data includes the user's basic information, implicit information, and behavior information. This step includes:

Step 1.1, collect basic information of users: when users register, obtain basic descriptive information characteristics of users, including gender, age, education level and other information.

Step 1.2, collect the user's implicit information: the user completes the necessary assessment process, and the user's implicit information is extracted according to the assessment process, including various assessment ability values, personality tendencies and other information.

Step 1.3, collect user behavior information: When the user enters the recommendation page, classify and mark the user's behavior information on different recommended content feedback, including behavior types such as ignore, view, collect, purchase, etc., and record the time of the operation.

Step 2: Reshape the user data. This step includes:

Step 2.1, data cleaning: Use the average value or special marking method to clean invalid data in the user data.

Step 2.2, combination construction: According to the needs of subsequent screening of CTR models, different combinations of the data collected in step 1 are constructed.

Step 2.3, data preprocessing: perform corresponding encoding conversion operations and embedding processing operations on the categorical feature data and continuous feature data in the data collected in step 1, so that they can be used as input of the CTR model.

Step 3: Construct a CTR model based on LR. Based on the logistic regression algorithm, construct a CTR model. This step includes:

Step 3.1, input information features: select the user's basic information features, the user's implicit information features, the user's behavior information features, whether to click on the label, and the product information as model input.

Step 3.2, combine informative features: combine these features using a first-order linear relationship function.

Step 3.3, perform training calculation: according to the actual result of whether the click is made, perform training calculation to obtain the cross entropy of the linear calculation result.

Step 4: Build a CTR model based on CIN. Based on the cross network principle, build a CTR model. This step includes:

Step 4.1, input information features. Select the user's basic information features, the user's implicit information features, the user's behavior information features (whether to click on the label) and the product information as model input.

Step 4.2, construct the first layer vector. Construct the output vector of the first layer of the compressed interaction network CIN. This step includes:

Step 4.2.1, calculate the Hadamard product of the embedded input vector with itself to obtain multiple two-dimensional matrices.

Step 4.2.2, multiply multiple two-dimensional matrices by the corresponding coefficient matrix to obtain a feature map vector.

Step 4.2.3: Repeat step 4.2.2 as needed to obtain multiple feature map vectors to form the first layer of the CIN network.

Step 4.3: construct multi-layer vectors. The CIN network vector of the previous layer is calculated with the input vector as in step 4.2 to continue constructing the next layer of CIN network.

Step 4.4, compress the results. By using a random value pooling method according to a certain coefficient, compress the results of each layer of the CIN network to obtain the output of the CIN network part.

Step 4.5: Joint training: Construct the DNN part and the linear part of the CTR model and perform joint training with the CIN part.

Step 4.6, calculate the cross entropy. Use the sigmoid function to jointly calculate the outputs of the three parts, and perform cross entropy calculation as the output of the entire model.

Step 4.7, regularize the objective function. Regularize the objective function, and add Batch to the deep neural network part. The Normalization layer is used to improve the generalization ability, and Dropout is used for neurons to prevent overfitting in training and L2 regularization is adopted; while the Embedding layer and CIN network part only use L2 regularization.

Step 5: Apply the model to filter the recommendations. The two-layer recommendation model is used to filter the recommendation results. This step includes:

Step 5.1: Preliminary screening: Based on the category selected by the user, the corresponding recommended content is put into the LR-based CTR model for preliminary screening.

Step 5.2: Secondary screening: The results after the initial screening are sent to the CTR model based on CIN for final screening. Finally, the results are sorted according to the output probability, and the top 20 results are obtained as the final output.

The beneficial effect of the present invention is: proposing an intelligent recommendation method based on user behavior characteristics, which can reasonably utilize user basic information characteristics, user implicit information characteristics, and user behavior characteristics, greatly reduce the training cost when training the recommendation model, and improve the accuracy of recommendation.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 shows a flow chart of an intelligent recommendation method based on user behavior characteristics of the present invention;

FIG2 shows the use process of an intelligent recommendation method based on user behavior characteristics of the present invention;

FIG3 shows the specific structure of the core algorithm model of the intelligent recommendation method of the present invention;

FIG4 shows the collection and conversion process of the input data of the model of the present invention;

Figures 5 and 6 show the calculation process of the feature map part of the CIN network part of the present invention.

DETAILED DESCRIPTION

The preferred implementation modes of the present invention are further described below with reference to the accompanying drawings and examples.

The flowchart shown in FIG1 shows the basic process of the implementation of the present invention, and the network structure diagram shown in FIG2 shows the structure of the entire innovative model of the present invention:

Step 1: Collect user data. Collect the user's input feature data in the CTR model. This step includes:

Step 1.1. Collect basic information of users. When users register, obtain basic descriptive information characteristics of users, such as gender, age, and education level.

Step 1.2. Collect the user's implicit information. The user completes the necessary assessment process and uses the assessment form to extract the user's implicit information from the information obtained from the assessment process, including various assessment ability values, personality tendencies and other information.

Step 1.3. Collect user behavior information. When a user enters the recommendation page, classify and mark the user's behavior on different recommended content information, including: ignore, view, collect, purchase and other behavior types, and record the time of the operation, so as to update the user's behavior information in real time.

Step 2: Reshape the user data. Reshape the data obtained in step 1 to make it conform to the requirements of the following steps.

Usage requirements. This step includes:

Step 2.1. Clean the data. Use the average value or special marking method to clean the invalid data collected in step 1.

Step 2.2. Combination construction: According to the needs of subsequent screening of CTR models, different combinations of the data collected in step 1 are constructed.

Step 2.3. Data preprocessing. Perform corresponding encoding conversion and embedding operations on the categorical feature data and continuous feature data collected in step 1, so that they can be used as input for the CTR model. This step includes:

Step 2.3.1. Perform a simple normalization operation on continuous data and use label encoding conversion operation on categorical data.

Step 2.3.2. Based on the LR model, the categorical data that has undergone the label encoding conversion operation in step 2.3.1 is normalized, and the continuous data that has undergone a simple normalization operation in step 2.3.1 is jointly trained with the model.

Step 2.3.3. Based on the CIN model, use one-hot encoding to convert the categorical data that has undergone label encoding conversion in step 2.3.1 into sparse vector data, and then perform embedding operation on it and the continuous data that has undergone simple normalization operation in step 2.3.1 to obtain dense vectors respectively, and use the two dense vectors for model training.

Step 3: Construct a CTR model based on LR. Based on the logistic regression algorithm, construct a CTR model. This step includes:

Step 3.1. Input information features. Select the user's basic information features, the user's implicit information features, the user's behavior information features (whether to click on the label) and the product information as the model input.

Step 3.2. Combine informative features. Combine these features using a first-order linear relationship function.

Step 3.3. Perform training calculations. Perform training calculations to find cross entropy on the linear calculation results based on the actual click results.

Step 4: Build a CTR model based on CIN. Based on the cross network principle, build a CTR model. This step includes:

Step 4.1. Input information features. Select the user's basic information features, the user's implicit information features, and the user's behavior The information features of whether the label is clicked and the product information are used as model inputs.

Step 4.2. Construct the first layer vector. Construct the output vector of the first layer of the compressed interaction network CIN. This step includes:

Step 4.2.1. Calculate the Hadamard product of the embedded input vector with itself to obtain multiple two-dimensional matrices.

Step 4.2.2. Multiply multiple matrices by the corresponding coefficient matrix to obtain a feature map vector.

Step 4.2.3. Repeat step 4.2.2 as required to obtain multiple feature map vectors to form the first layer of CIN network. The calculation process diagram is shown in Figures 5 and 6, and the calculation formula is as follows:

Step 4.3. Construct multi-layer vectors. The CIN network vector of the previous layer is calculated with the input vector as in step 4.2, and the next layer of CIN network is constructed. The calculation formula is as follows:

Step 4.4. Result compression: By using a random value pooling method according to a certain coefficient, the result of each layer of the CIN network is compressed to obtain the output of the CIN network part.

Step 4.5. Joint training: Construct the DNN part and the linear part of the CTR model, and perform joint training with the CIN part.

Step 4.6. Cross entropy calculation. Use the sigmoid function to jointly calculate the outputs of the three parts, and perform cross entropy calculation as the output of the entire model. The calculation formula is as follows:

Step 4.7. Regularize the objective function. Regularize the objective function. In the deep neural network part, add a Batch Normalization layer to improve the generalization ability, use Dropout for neurons to prevent overfitting and use L2 regularization; while only use L2 regularization for the Embedding layer and CIN network part.

Step 5: Apply the model to filter the recommendations. The two-layer recommendation model is used to filter the recommendation results. This step includes:

Step 5.1. Preliminary screening: Based on the category selected by the user, the corresponding recommended content is put into the LR-based CTR model for preliminary screening.

Step 5.2. Secondary screening: The results after the initial screening are sent to the CIN-based CTR model for final screening, and finally sorted according to the output probability, and the top 20 results are obtained as the final output.

Claims (4)

An intelligent recommendation method based on user behavior characteristics, characterized by comprising the following steps: Step 1: Collect user data; the user data includes basic information, implicit information, and behavior information of the user; Step 2, shaping the user data; Step 3: Construct a CTR model based on LR; Based on the logistic regression algorithm, construct a CTR model; Step 4: Build a CTR model based on CIN; Build a CTR model based on the cross network principle; Step 5: Apply the model to filter the recommendations; use the two-layer recommendation model to filter and obtain the recommendation results. An intelligent recommendation method based on user behavior characteristics, characterized in that in step 3, a CTR model based on LR is constructed; based on a logistic regression algorithm, a CTR model is constructed; and step 3 further includes: Step 3.1, input information features: select the user's basic information features, the user's implicit information features, the user's behavior information features, whether to click on the label information and product information as model input; Step 3.2, combine information features: combine these features using a first-order linear relationship function; Step 3.3, perform training calculation: according to the actual result of whether the click is made, perform training calculation to obtain the cross entropy of the linear calculation result. An intelligent recommendation method based on user behavior characteristics, characterized in that in step 4, a CTR model based on CIN is constructed; based on the cross network principle, a CTR model is constructed; and step 4 further includes: Step 4.1, input information features; select the user's basic information features, the user's implicit information features, the user's behavior information features, whether to click on the tag information and the product information as model input; Step 4.2, construct the first layer vector; construct the output vector of the first layer compressed interaction network CIN, this step includes: Step 4.2.1, calculate the Hadamard product of the embedded input vector with itself to obtain multiple two-dimensional matrices; Step 4.2.2, multiply multiple two-dimensional matrices by the corresponding coefficient matrix to obtain a feature map vector; Step 4.2.3, repeat step 4.2.2 as needed to obtain multiple feature map vectors to form the first layer of CIN network; Step 4.3, construct a multi-layer vector; perform the calculation of the CIN network vector of the previous layer and the input vector as in step 4.2, and continue to construct the next layer of CIN network; Step 4.4, compress the result; by using a random value pooling method according to a certain coefficient, compress the result of each layer of the CIN network to obtain the output of the CIN network part; Step 4.5, joint training: construct the DNN part and the linear part of the CTR model, and perform joint training with the CIN part; Step 4.6, calculate cross entropy; use the sigmoid function to jointly calculate the output of the three parts and perform cross entropy calculation As the output of the entire model; Step 4.7, regularize the objective function; regularize the objective function, add a Batch Normalization layer to the deep neural network part to improve the generalization ability, use Dropout on neurons to prevent overfitting in training and use L2 regularization; while only L2 regularization is used in the Embedding layer and CIN network part. An intelligent recommendation method based on user behavior characteristics, characterized in that in step 5, a model is applied to filter the recommendation; a two-layer recommendation model is used to filter and obtain the recommendation result; step 5 further includes: Step 5.1, preliminary screening: according to the category selected by the user, the corresponding recommended content is put into the LR-based CTR model for preliminary screening; Step 5.2, secondary screening: the results after the preliminary screening are sent to the CIN-based CTR model for final screening, and finally sorted according to the output probability, and the top 20 results are obtained as the final output.