Classification method based on neural network and classification device thereof
A neural network and classification method technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problem of low classification performance and achieve the effect of high classification performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0050] Example one
[0051] The first embodiment of the present invention provides a neural network-based classification method, which is suitable for, but not limited to, emotional polarity classification of text data. Refer to figure 1 As shown in the flowchart of the classification method, the method may include the following steps:
[0052] S101: Obtain training samples.
[0053] This embodiment uses sentiment classification as an example to illustrate the method of this application. Specifically, this embodiment proposes a neural network-based sentiment classification scheme.
[0054] Among them, the neural network algorithm (Artificial Neural Networks, ANN): appeared after the 1940s. It is connected by a large number of neurons with adjustable connection weights, and has the characteristics of large-scale parallel processing, distributed information storage, and good self-organization and self-learning capabilities. The BP (Back Propagation) algorithm, also known as the error b...
Example Embodiment
[0103] Example two
[0104] In the second embodiment, reference image 3 As shown in the flowchart of the neural network-based classification method, the method may further include the following steps:
[0105] S104: Verify the classification accuracy of the classifier based on the classification category and the actual category of the sample to be tested.
[0106] This embodiment specifically verifies the accuracy of the classifier trained on the basis of the convolutional neural network classification method in the first embodiment. In the four subject data examples provided in this application, the 4000 entries for each subject after 2012 are specifically The comment text is used as the sample to be tested, and the sample to be tested is classified using a classifier trained based on the convolutional neural network classification method.
[0107] On the basis of classification, compare the category labels obtained by the classification with the actual categories of the 4000 commen...
Example Embodiment
[0112] Example three
[0113] The third embodiment discloses a neural network-based classification device, which corresponds to the neural network-based classification method disclosed in the above embodiments.
[0114] Corresponding to Example 1, refer to Figure 4 The shown schematic diagram of the structure of the neural network-based classification device may include a sample acquisition module 100, a sample processing module 200, and a classifier construction module 300.
[0115] The sample acquisition module 100 is used to acquire training samples.
[0116] The sample acquisition module 100 includes a text grabbing unit for grabbing a predetermined number of text data from a predetermined data source, and using the grabbed text data of the predetermined number as a training sample.
[0117] The sample processing module 200 is used to perform distributed semantic representation processing on training samples to obtain a distributed semantic representation of the training samples.
...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap