Unlock instant, AI-driven research and patent intelligence for your innovation.
Method, system, electronic device and medium for establishing a target recognition model
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for object recognition and method establishment, applied in the field of object recognition model establishment, which can solve the problems of small scale of high-quality labeled corpus and low recognition accuracy
Active Publication Date: 2021-11-02
SHANGHAI MINGPIN MEDICAL DATA TECH CO LTD
View PDF12 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] The present invention provides a method, system, electronic equipment and medium for establishing a target recognition model to solve the problems of small scale of high-quality labeled corpus and low recognition accuracy in the prior art
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
no. 1 example
[0051] figure 1 It is a schematic flowchart of a method for establishing a target recognition model provided in an embodiment of the present invention.
[0052] Such as figure 1As shown, the method for establishing the target recognition model includes steps S110-S150:
[0053] S110, acquire the text data of sample users, and perform vectorization processing to obtain user data sets, perform clustering processing on the user data sets, obtain several user classification sets, and establish category labels and category label rules, the user The classification set includes user training set and user test set;
[0054] S120, acquire text data in the target domain, and perform vectorization processing to obtain a domain data set, determine the category of data in the domain data set according to the category label rules, and divide the domain data set into several domain classification sets ;
[0055] S130. If the category of the data in the domain dataset cannot be determined...
no. 2 example
[0078] Based on the same inventive concept as the method in the first embodiment, correspondingly, this embodiment also provides a system for establishing a target recognition model.
[0079] Figure 4 It is a schematic flowchart of the target recognition model building system provided by the present invention.
[0080] Such as Figure 4 As shown, the system 4 includes: 41 user data set acquisition module, 42 field data set acquisition module, 43 new category data set acquisition module, 44 training data set acquisition module and 45 target model establishment module.
[0081] Among them, the user data set acquisition module is used to obtain the text data of sample users, and perform vectorization processing to obtain user data sets, perform clustering processing on the user data sets, obtain several user classification sets, and establish category labels and category label rules, the user classification set includes a user training set and a user testing set;
[0082] The...
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 present invention is applicable to the technical field of data processing, and provides a method, system, electronic equipment and medium for establishing a target recognition model, wherein the method includes: acquiring text data of sample users to obtain user data sets; acquiring text data of target fields text data, obtain domain data sets, determine the category of data in the domain data set according to the category label rules, and divide the domain data sets into several domain classification sets; if the category label rules cannot determine the The category of the data in the field data set, then generate a new category data set according to the data in the field data set whose category cannot be determined; determine the similarity between the user classification set and the field classification set to obtain a training data set; use the training The data set trains the initial recognition model to obtain the target recognition model; it solves the problems of small scale of high-quality labeled corpus in the prior art.
Description
technical field [0001] The invention relates to the technical field of data processing, in particular to a method, system, electronic equipment and medium for establishing a target recognition model. Background technique [0002] Natural language processing is to allow computers to understand human language, so as to better realize the interaction between humans and computing (such as voice assistants, automatic message reply, translation software and other applications and human interaction). Natural language processing usually includes word segmentation, part-of-speech tagging, named entity recognition, and grammatical analysis. Named entity recognition is an important part of natural language processing. Named entity recognition refers to the process of identifying the names or symbols of things with specific meanings in the text. Named entities mainly include person names, place names, institution names, dates, proper nouns, etc. However, the current research on named ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More