Model optimization method and device based on scene adaptation
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 model and scene technology, applied in the field of data analysis, can solve problems such as difficult selection, achieve high accuracy, high adaptability, and ensure the effects of various indicators and generalization capabilities
Pending Publication Date: 2019-04-19
BEIJING SHOUGANG AUTOMATION INFORMATION TECH
View PDF6 Cites 8 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
[0006] The embodiment of the present invention provides a model tuning method based on scene adaptation, which solves the technical problem that it is difficult to select a suitable algorithm for the actual scene in the prior art and provides assistance for industrial development
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
Embodiment 1
[0057] figure 1 It is a schematic flowchart of a scene adaptation-based model tuning method in an embodiment of the present invention. Such as figure 1 As shown, the embodiment of the present invention provides a model tuning method based on scene adaptation, the method includes:
[0058] Step 110: Based on the specific scene information provided by the user, determine N algorithm models corresponding to the set scene; wherein, N is a positive integer.
[0059] Specifically, through the model tuning method of the embodiment of the present invention, the user provides specific scene information in the model tuning system, for example, input scenes such as face recognition, defect search, etc., according to the specific scene information and algorithm Matching, according to prior knowledge, there are multiple algorithms for various scenarios, and multiple algorithm models are matched with the adaptation algorithm set for the specific scenario according to the characteristics o...
Embodiment 2
[0077] Based on the same inventive concept as the scene adaptation-based model tuning method in the foregoing embodiments, the present invention provides a scene adaptation-based model tuning device, such as figure 2 As shown, the device includes:
[0078] A first determination unit 11, the first determination unit 11 is configured to determine N algorithm models corresponding to the set scene based on the specific scene information provided by the user; wherein, N is a positive integer;
[0079] A first obtaining unit 12, the first obtaining unit 12 is configured to divide the data set provided by the user to obtain a training set and a test set;
[0080] A second obtaining unit 13, the second obtaining unit 13 is configured to respectively train each algorithm model through the training set, and obtain one or more sub-models corresponding to each algorithm model;
[0081] The second determination unit 14 is configured to respectively test one or more sub-models correspondi...
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 model optimization method and device based on scene adaptation, and the method comprises the steps: determining N algorithm models corresponding to a set scene based on the specific scene information provided by a user; Wherein N is a positive integer; Dividing the data set provided by the user to obtain a training set and a test set; Training each algorithm model throughthe training set to obtain one or more sub-models corresponding to each algorithm model; And testing one or more sub-models corresponding to the algorithm models through the test set, and determiningan optimal model corresponding to the specific scene information. The technical problems that in the prior art, an appropriate algorithm is difficult to select in an actual scene, and assistance is provided for industrial development are solved. The technical effects that all indexes and the generalization capability of the model are guaranteed, the capability of finally confirming the optimal model is achieved, convenience and rapidness are achieved, the accuracy is high, and the optimal model with the high generalization accuracy, performance and adaptability level is obtained are achieved.
Description
technical field [0001] The invention relates to the technical field of data analysis, in particular to a model tuning method based on scenario adaptation. Background technique [0002] When industrial development needs to introduce an algorithm system, there will be a variety of scenarios that need to adapt the corresponding algorithm to solve practical problems. Each scenario has its own characteristics and concerns. For those who are not familiar with the algorithm field, it requires a high learning cost and time investment to implement the algorithm into the industrial scenario. In the entire construction process, the selection of algorithms and the establishment of models are crucial steps. [0003] Through prior knowledge, several possible adaptation algorithms can be preferentially selected for the scene, and several suitable model evaluation methods can be selected according to the data volume and type of the scene. The values of various indicators in the evaluati...
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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N20/00
Inventor 宋扬官泽王旭白璐
Owner BEIJING SHOUGANG AUTOMATION INFORMATION TECH
Login to view more 
Login to view more