Method and device for identifying multi-key input characters
A technology for inputting characters and identifying results, applied in the input/output process of data processing, electrical digital data processing, instruments, etc., to improve input efficiency and avoid re-editing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0165] The user uses a 26-key keyboard to enter Saqima. After typing saqi, he accidentally presses m and n in succession; according to the matching result of the language model, given the above saqi, the language model is queried It is found that the probability of m coming out later is higher than n (prob(m|saqi)>prob(n|saqi)), so the input string is automatically recognized as saqim; among them, prob(A|B) means A under the condition of B Probability of occurrence.
[0166] Reference Figure 4 , Shows an example 1 of this application that recognizes multi-key input characters on a 26 keyboard and displays the corresponding recognition results. In addition to displaying the string saqim containing the recognition results, it also displays the corresponding text candidates of the string saqim.
[0167] The matching result of the language model is considered above. If you also consider the matching result of the error correction model, you can view the user's input history data. When...
example 2
[0170] The user uses a 26-key keyboard and wants to enter a delta. After entering sanjiao, select or display the word "three" on the screen and press the z, s, and x keys at the same time; in this case, the text obtained above includes the selected text Three" and the current input content "jiao".
example 3
[0171] If you do not consider the selected text and the text on the screen, but only consider the current input content as the above, then you can look up the table according to the language model data shown in Table 7 to get prob(s|jiao)=0.0258>prob( x|jiao)=0.147>prob(z|jiao)=0.021, therefore, s can be displayed as the optimal recognition result; refer to Image 6 , Shows an example 3 of this application that recognizes multi-key input characters on a 26 keyboard and displays the corresponding recognition results, which displays the optimal recognition results and corresponding candidates when only considering the current input content as the above.
[0172] Table 7
[0173]
[0174] If you consider the selected text and the on-screen text as the above, then according to the ternary probability of the language model shown in Table 8, look up the table to get prob(x|三jiao)=0.1553>prob(z|三jiao)= 0.0942>prob(s|三jiao)=0.0031, therefore, x can be displayed as the optimal recognition r...
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