Method, apparatus, and electronic device for multi-dimensional reverse mining and content recommendation based on user habit model

Abstract

A method, apparatus, and electronic device based on a user habit model for multi-dimensional reverse exploration and content recommendation are disclosed. The method involves establishing a primary interest vector based on user historical behavior data via a server, and executing a multi-dimensional exploration process to obtain multiple reverse content objects, multiple bridging content objects, and multiple potential interest content objects. These objects are then defined as multiple surprise candidate contents. Next, the surprise candidate contents are dynamically weighted and scored against candidate contents with similar primary interest vectors to generate a recommendation list. The primary interest vectors and dynamic weighted scores are then adjusted based on user feedback data regarding the recommendation list, thereby achieving the technical effect of increasing the diversity of the content recommendation list.

Claims

1. A multi-dimensional reverse exploration and content recommendation method based on a user habit model, executed by a server, the server being connected to a user terminal device and a database, the database storing multiple content objects, characterized in that the method includes: The server acquires a user's historical behavior data from the user terminal device to establish a primary interest vector corresponding to the user; the server executes a multi-dimensional exploration program, which includes: calculating an opposing region in a feature space that is inversely related to the primary interest vector, and retrieving multiple inverse content objects corresponding to the opposing region from the database; extracting multiple interest features with low correlation from the primary interest vector, and connecting the common attributes between each interest feature through a preset knowledge graph, in order to retrieve multiple bridging content objects with cross-domain features from the database; and detecting the user's hesitation behavior data on a specific content object, and increasing the weight of the hesitation behavior data through an amplification algorithm, in order to retrieve multiple potential interest content objects corresponding to the hesitation behavior data from the database. The server defines the reverse content object, the bridging content object, and the potential interest content object as multiple surprise candidate contents, and performs a dynamic weighted score on the surprise candidate contents and multiple similar candidate contents corresponding to the main interest vector to generate a content recommendation list and transmit it to the user terminal device for display; and the server obtains the user's click feedback data on one of the content recommendation lists to correct the parameters of the main interest vector and the dynamic weighted score.

2. The method for multi-dimensional reverse exploration and content recommendation based on a user habit model, as described in request item 1, is characterized in that the step of calculating the opposing regions in the feature space includes: The server converts the primary interest vector into its inverse vector and calculates the cosine similarity between the feature vector of each content object in the database and the inverse vector, so as to select the content object with the cosine similarity greater than a preset threshold as the inverse content object corresponding to the opposing region.

3. The method for multi-dimensional reverse exploration and content recommendation based on a user habit model, as described in request item 1, is characterized in that the step of detecting the hesitation behavior data includes: The server detects the user's dwell time and scrolling frequency on the display page of the specific content object. When the dwell time exceeds a preset time limit and the scrolling frequency is lower than a preset frequency value, the dwell time and the scrolling frequency are used as the hesitation behavior data.

4. The multi-dimensional reverse exploration and content recommendation method based on a user habit model, as described in request item 1, is characterized in that the multi-dimensional exploration procedure further includes: The server calculates the user's interest migration path at different time periods based on the timestamps in the historical behavior data, and predicts the offset trend of the main interest vector at an expected time point based on the interest migration path, so as to retrieve multiple extended content objects corresponding to the offset trend from the database and include them in the surprise candidate content.

5. The multi-dimensional reverse exploration and content recommendation method based on a user habit model, as described in request item 1, is characterized in that the dynamic weighted scoring step includes: The server dynamically adjusts the weighting ratio between the surprise candidate content and the similar candidate content based on the user's current network environment and the type of the user's terminal device, so as to generate a content recommendation list adapted to the user's terminal device.

6. The multi-dimensional reverse exploration and content recommendation method based on a user habit model, as described in request item 1, is characterized in that the step of connecting the common attributes among the interest features through the preset knowledge graph includes: The server defines the multiple interest features as multiple first nodes in the knowledge graph, and retrieves a second node in the knowledge graph that has a common association with the multiple first nodes, wherein the second node is the common attribute, and matches the multiple bridging content objects in the database according to the attribute tags of the second node.

7. The multi-dimensional reverse exploration and content recommendation method based on a user habit model, as described in request item 1, is characterized in that the step of increasing the weight of the hesitation behavior data through the amplification algorithm includes: The server calculates the weighted sum of multiple interactive behaviors of the user on the specific content object. When the interactive behavior includes at least one of increased dwell time, repeated clicks, and screen zooming, a weight coefficient is configured on the hesitation behavior data through the magnification algorithm. When the weight coefficient is greater than the weight of the regular browsing behavior in the historical behavior data, the ranking of the potential interest content object in the surprise candidate content is improved.

8. The multi-dimensional reverse exploration and content recommendation method based on a user habit model, as described in request item 1, is characterized in that the step of modifying the parameters of the main interest vector and the dynamic weighted score includes: The server determines whether the selected feedback data belongs to the surprise candidate content. If so, the server increases the ranking of the surprise candidate content in the content recommendation list.

9. A multi-dimensional reverse exploration and content recommendation device based on a user habit model, characterized in that it comprises: A user profile modeling module is used to acquire historical behavior data of a user from a user terminal device and establish a primary interest vector corresponding to the user. A multi-dimensional exploration module, connected to the user profile modeling module, is used to execute a multi-dimensional exploration program. The multi-dimensional exploration program includes: calculating an opposing region in a feature space that is inversely related to the main interest vector, and retrieving multiple inverse content objects corresponding to the opposing region from a database; extracting multiple interest features with low correlation from the main interest vector, and connecting the common attributes between each interest feature through a preset knowledge graph, to retrieve multiple bridging content objects with cross-domain features from the database; and detecting the user's hesitation behavior data regarding a specific content object, and increasing the weight of the hesitation behavior data through an amplification algorithm, to retrieve multiple potential interest content objects corresponding to the hesitation behavior data from the database. A candidate and scoring module, connected to the multi-dimensional exploration module, is used to define the reverse content object, the bridging content object, and the potential interest content object as multiple surprise candidate contents, and to dynamically weight and score the surprise candidate contents with multiple similar candidate contents corresponding to the main interest vector to generate a content recommendation list and transmit it to the user terminal device for display; and a feedback and adaptive learning module, connected to the candidate and scoring module, is used to obtain user click feedback data on one of the content recommendation lists to correct the parameters of the main interest vector and the dynamic weighted score.

10. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that, when the processor executes the computer program, it implements the multi-dimensional reverse exploration and content recommendation method based on a user habit model as described in claim 1.

Images