User behavior analysis-based dynamic word bank updating method
A technology of behavior analysis and update method, which is applied in the field of data processing, can solve problems such as low accuracy, inability to adapt to fast and accurate query, poor performance, etc., and achieve high real-time performance, high update efficiency of thesaurus, and accurate query
Active Publication Date: 2020-05-08
苏州视锐信息科技有限公司
View PDF3 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003]
Especially in the application scenario where a large number of professional vocabulary is included in the professional application field, in the existing Chinese word segmentation processing and query application environment, there is no effective extended lexicon and its dynamic update method for professional applications, and more Relying on conventional Chinese word segmentation tools to generate basic thesaurus or general thesaurus for query processing, cannot meet the needs of fast and accurate queries in various professional fields, and is prone to problems such as inaccurate professional vocabulary, low accuracy, and poor performance
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0046] In this example, the user enters the Chinese entry of "fracturing technology" in the field of shale gas for query;
[0047] The system first loads the words in the basic and extended thesaurus of professional vocabulary in the field of shale gas, and uses these professional vocabulary in the field of shale gas as the corpus, and uses a Chinese word segmentation device to perform word segmentation processing on the input "fracturing technology", split The two word segmentations for "fracturing" and "craft" are more in line with the Chinese retrieval habits and semantic norms of the word segmentation text. The word segmentation result set of the above Chinese entry is as follows (here " / " is used to indicate the word segmentation effect):
[0048] Fracturing / Process
[0049] The search engine analyzes the basic thesaurus and the extended thesaurus, generates a document index library, and quickly retrieves documents according to the word segmentation results and index libr...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a user behavior analysis-based dynamic word bank updating method. The method specifically comprises the following steps that: a Chinese entry to be inquired is inputted; a wordsegmentation device performs word segmentation processing; a user behavior analyzer analyzes and dynamically updates an extended word bank. The behavior analysis processor is used for analyzing and processing the behaviors of a user, calculating a current word segmentation retrieval satisfaction score by taking the behaviors of the user as indexes, and then determining an updating strategy of theword bank according to the word segmentation retrieval satisfaction score, so that the initiative of the user can be brought into full play, and the requirements of the user are met; through cyclic iteration, a system continuously adds segmented words higher than the design score into the extended word bank, so that the dynamic updating of the word bank is realized, and real-time performance is high; the system automatically accumulates and increases more professional vocabularies and stores the professional vocabularies in the extended word bank, the number and content of the word bank are continuously updated, and therefore, requirements for rapid query in various professional fields can be met, professional vocabulary query is accurate, and the updating efficiency of the word bank is high.
Description
technical field [0001] The invention relates to a method for updating a dynamic lexicon based on user behavior analysis, and belongs to the technical field of data processing. Background technique [0002] The application of artificial intelligence in scenarios such as computer pattern recognition and information extraction is becoming more and more extensive, and the breadth and depth of applications are also expanding. Natural language processing technology can use computer software to easily simulate and analyze the association of people, objects, events, and rules in the application mode in the real world from the aspects of semantic validity and consistency. Combining artificial intelligence technology and natural language processing technology and applying it to data processing in specific professional fields, such as real-time query service, word segmentation update and collaborative service, real-time analysis and statistics service, etc., will generate specific new ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/31G06F16/33G06F40/289
CPCG06F16/328G06F16/3344Y02D10/00
Inventor 郑坤方发林答海玲易云蕾
Owner 苏州视锐信息科技有限公司