Text emotion recognition method, device, server and storage medium
An emotion recognition and text technology, applied in the information field, can solve the problems of inability to obtain emotion classification results, wrong emotion classification results, and inability to update the keyword thesaurus at any time, so as to achieve good comfort, reduce workload, and improve accuracy. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Figure 1a It is a flow chart of the text emotion recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of performing emotion recognition on text input by users, such as user comments, and the method can be executed by a text emotion recognition device , the emotion recognition device can be realized by means of software and / or hardware, and integrated in the server. refer to Figure 1a , the emotion recognition method provided in this embodiment specifically includes:
[0031] S110. Obtain the text to be classified.
[0032] Among them, the text to be classified is a short text with emotional information input by the user. For example, the user's evaluation of a certain product, or the mood diary entered by the user.
[0033] When obtaining the text to be classified, it may be to obtain the text input by all users within the set time interval through the network; it may also be to obtain the text input by...
Embodiment 2
[0071] figure 2 It is a flow chart of the text emotion recognition method provided by Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiments, refer to figure 2 , the emotion recognition method provided in this embodiment specifically includes:
[0072] S210. Obtain an erroneous emotion recognition result obtained by the Bayesian classifier when recognizing historical text to be classified within a preset time period.
[0073] Specifically, the staff of the server can regularly sample and check the emotion recognition results of the historical texts to be classified obtained by the Bayesian classifier to find the wrong emotion recognition results in the emotion recognition results and mark them so that the server can obtain When the result of emotion recognition is incorrect, it is only necessary to find the corresponding mark.
[0074] S220. Analyze the historical text to be classified corresponding to the errone...
Embodiment 3
[0084] image 3 The flow chart of the text emotion recognition method provided by the third embodiment of the present invention, this embodiment is embodied on the basis of the above-mentioned embodiments, refer to image 3 , the emotion recognition method provided in this embodiment specifically includes:
[0085] S310. Obtain an erroneous emotion recognition result obtained by the Bayesian classifier when recognizing historical text to be classified within a preset time period.
[0086] Wherein, the preset time period may be set according to actual conditions, for example, every three days or every week.
[0087] S320. Identify key information in the historical text to be classified corresponding to the erroneous emotion recognition result.
[0088] Specifically, the key information includes: sentence structure, keywords and / or high-frequency error word segmentation, and the grammatical position to which the high-frequency error word segmentation belongs. The high-frequen...
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