Self-adaptive personalized information retrieval system and method
An information retrieval and self-adaptive technology, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as fixation and influence query, and achieve high flexibility, high retrieval accuracy, and flexibility. and the effect of rationality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0074] Specific Embodiments 1. The self-adaptive personalized information retrieval system described in this embodiment includes:
[0075] It is used to form a feature matrix based on the current query information, combined with historical query information and historical click information, and is also used to obtain the data input subsystem of the training parameter prediction model according to the feature matrix;
[0076] A parameter training and prediction subsystem for training and applying a parameter prediction model based on the feature matrix, and obtaining prediction parameters;
[0077] It is used to organize current queries, historical queries and historical clicks with predicted parameters; it is also used to combine user models and query models to form a personalized query model execution retrieval subsystem;
[0078] It is used to find the documents that match the personalized query in the documents to be retrieved as the preliminary retrieval results, and is al...
specific Embodiment approach 2
[0079] Embodiment 2. This embodiment is a further limitation of the data input subsystem in the self-adaptive personalized information retrieval system described in Embodiment 1. The data input subsystem in this embodiment includes:
[0080] a module for generating user behavior features based on current query information, and
[0081] A module for constructing a feature matrix based on all the obtained user behavior features.
specific Embodiment approach 3
[0082] Specific Embodiment 3. This embodiment is a further limitation of the parameter training and prediction subsystem in the self-adaptive personalized information retrieval system described in Embodiment 1. In this embodiment, the parameter training and prediction subsystem includes:
[0083] A data input module for receiving data to be processed;
[0084] A module for calculating historical queries and historical clicks corresponding to each query, and organizing them into the required data format;
[0085] modules used to form feature matrices;
[0086] A module for finding the optimal parameter of the current query in a traversal search mode, the step size of the traversal is 0.1;
[0087] A module for building a mapping of user characteristics and optimal parameters using an SVM regression model.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com