Method, device and application for creating multi-dimensional feature map of personal scene

Abstract

The invention provides a method, a device, and an application for sequentially creating a multi-dimensional feature map of a personal scene. The method comprises the following steps: presetting a multi-level scene tag library, and presetting a corresponding scene logic relationship, an association probability calculation rule between scenes, and a sequential relationship and chain serial expression relationship between the scenes; automatically acquiring and / or calculating a multi-level scene label value of the user by using a base station or / and a satellite positioning system used by a mobilephone of the user, correspondingly storing the value in the preset multi-level scene label library, and generating a user personal scene according to the preset scene logic relationship; andThe invention provides a method, a device, and an application for sequentially creating a multi-dimensional feature map of a personal scene. The method comprises the following steps: presetting a multi-level scene tag library, and presetting a corresponding scene logic relationship, an association probability calculation rule between scenes, and a sequential relationship and chain serial expression relationship between the scenes; automatically acquiring and / or calculating a multi-level scene label value of the user by using a base station or / and a satellite positioning system used by a mobile phone ofthe user, correspondingly storing the value in the preset multi-level scene label library, and generating a user personal scene according to the preset scene logic relationship; based on multiple independent user personal scenes, calculating a correlation probability among multiple independent user personal scenes in a preset time period according to the association probability calculation rule between scenes, and generating the user personal scene map according to the sequential relationship and chain serial expression relationship between the preset scenes. According to the method, the device, and the application for sequentially creating the multi-dimensional feature map of the personal scene, the automatic creation of a personal scene map is realized, the personal scene map is appliedto realize user behavior prediction, and personalized recommendation is realized according to a prediction result.based on multiple independent user personal scenes, calculating a correlation probability among multiple independent user personal scenes in a preset time period according to the association probability calculation rule between scenes, and generating the user personal scene map according to the sequential relationship and chain serial expression relationship between the preset scenes. According to the method, the device, and the application for sequentially creating the multi-dimensional feature map of the personal scene, the automatic creation of a personal scene map is realized, the personal scene map is applied to realize user behavior prediction, and personalized recommendation is realized according to a prediction result.

Description

technical field [0001] The present invention relates to the field of Internet technology, in particular, to a method, device and application for sequentially creating a multi-dimensional feature map of a personal scene. Background technique [0002] With the rapid development of big data and artificial intelligence technology in the computer industry, personalized recommendations are becoming more and more popular with users, and have created more and more personalized value for users. Predicting user behavior is an important front-end technology for personalized recommendation, and the current technical solution for predicting user behavior mainly uses recommendation algorithms, specifically: [0003] Build a feature warehouse through user dimension data, content dimension data, time dimension, and address dimension data, and then perform logical calculations based on the feature warehouse data to obtain recommended content for users, including: [0004] 1. Match user cont...

AI Technical Summary

Problems solved by technology

The traditional similarity calculation mainly defines two models as vectors, and uses the cosine similarity method for calculation. However, this method has mandatory requirements for matching the number of elements of the two vectors, which exacerbates the problem of data sparsity

[0007] The above-mentioned recommendation algorithms in the prior art have problems such as cold start, sparsity, accuracy, and diversity; related heterogeneous information is not comprehensive enough, content feature samples are not conducive to user understanding, feature training algorithms are not in line with user logic, results and The actual deviation is relatively large, the recommendation is personalized, targeted and effective, and the accuracy is not high

However, the attributes of the scene map service are rarely screened to meet the individual needs of users. In view of this, the present invention proposes a method for creating a multi-dimensional feature map of a personal scene in time series and its application. By creating a personal scene map, users can be predicted Behavior to achieve accurate, effective and personalized recommendations

Images