Input system for mobile search and method therefor

• US 20080281582A1
• Filed: 10/01/2007
• Published: 11/13/2008
• Est. Priority Date: 05/11/2007
• Status: Abandoned Application

• Current Assignee: Delta Electronics Incorporated
• Original Assignee: Delta Electronics Incorporated
• Inventors: Lu, Yuan-chia, Wang, Ming-hong, Hsu, Tien-ming, Shen, Jia-lin
• Application Number:
  US11/906,498
• Publication Number:
  US 20080281582A1
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An input system for mobile search and a method therefor are provided. The input system includes an input module receiving a code input for a specific term and a voice input corresponding thereto, a database including a glossary and an acoustic model, wherein the glossary includes a plurality of terms and a sequence list, and each of the terms has a search weight based on an order of the sequence list, a process module selecting a first number of candidate terms from the glossary according to the code input by using an input algorithm and obtaining a second number of candidate terms by using a speech recognition algorithm to compare the voice input with the first number of candidate terms via the acoustic model, wherein the second number of candidate terms are listed in a particular order based on their respective search weights, and an output module showing the second number of candidate terms in the particular order for selecting the specific term therefrom.

Claims

1. An input system for mobile search, comprising:

an input module receiving a code input for a specific term and a voice input corresponding to the specific term;

a database including a glossary and an acoustic model, wherein the glossary includes a plurality of terms and a sequence list for the plurality of terms, and each of the plurality of terms has a search weight based on an order of the sequence list;

a process module selecting a first number of candidate terms from the glossary according to the code input by using an input algorithm and obtaining a second number of candidate terms by using a speech recognition algorithm to compare the voice input with the first number of candidate terms via the acoustic model, wherein the second number of candidate terms are listed in a particular order based on their respective search weights; and

an output module showing the second number of candidate terms in the particular order for selecting the specific term therefrom.

2. The input system according to claim 1, wherein the order of the sequence list for the respective terms is provided by a statistic of a usage frequency of the respective terms, and the term having the most usage frequency is given a biggest numeral for the search weight and listed in a top of the sequence list.

3. The input system according to claim 1, wherein the order of the sequence list for the respective term is provided by a network search frequency statistic for the respective terms in a server, and the term having the most network search frequency is given a biggest numeral for the search weight and listed in a top of the sequence list.

4. The input system according to claim 3, further comprising a communication module communicating with an updated database of the server through a linked network to update the respective terms of the glossary and the sequence list therefor.

5. The input system according to claim 4, wherein the updated database gives each of the updated terms a new search weight based on their respective search and usage frequencies in the server during a desire period, so as to update the glossary and the sequence list for the respective terms.

6. The input system according to claim 4, wherein the server further comprises a network glossary having a plurality of terms more than those in the glossary of the database.

7. The input system according to claim 6, wherein the process module is connected to the communication module for selecting corresponding candidate terms from the network glossary according to the code input while no candidate term in the glossary of the database is matched with the code input.

8. The input system according to claim 1, wherein the input algorithm is an associated input characters algorithm.

9. The input system according to claim 8, wherein the term is a keyword of a text and the code input comprises at least one input code for a part of the keyword.

10. The input system according to claim 9, wherein the code input is one selected from the group consisting of a phonetic symbol, a stroke symbol, an alphabetic symbol, a radical symbol, a tone symbol, a cipher and a plurality of common special symbols.

11. The input system according to claim 9, wherein the text is one selected from the group consisting of a Chinese word, a Japan word, a Korean word, an English word, a German word, a French word, a Spanish word, an Arabic word, a Russian word, an Italic word, a Portuguese word, a Netherlands word, a Greek word, a Czech word and a Denmark word.

12. The input system according to claim 1, wherein the particular order is further arranged according to respective similarity weights for the second number of candidate terms obtained by the speech recognition algorithm comparing the first number of candidate terms with the voice.

13. An input method for mobile search to input a specific term, comprising steps of:

(a) providing a database having a glossary, wherein the glossary includes a plurality of terms and a sequence list for the plurality of terms, and each of the plurality of terms has a search weight based on an order of the sequence list;

(b) inputting at least one code of the specific term according to an input method;

(c) selecting a first number of candidate terms from the glossary according to the code;

(d) inputting a voice;

(e) performing a speech recognition for the voice and obtaining a second number of candidate terms by comparing the voice with the first number of candidate terms for generating respective similarity weights for the second number of candidate terms, wherein the second number of candidate terms are listed in a particular order based on their respective search weights and respective similarity weights; and

(f) showing the second number of candidate terms in the particular order for selecting the specific term therefrom.

14. The input method according to claim 13, further comprising a step of (g) providing a network glossary to search more candidate terms via a linked network while no candidate term in the glossary of the database is matched with the code.

15. The input method according to claim 13, further comprising a step of (h) updating the terms of the glossary and the sequence list in the database via a linked network.

16. The input method according to claim 13, wherein the input method is an associated input method.

17. An input system for mobile search to input a specific term, comprising:

an input module a code input for a specific term and a voice input corresponding to the specific term;

a glossary having a plurality of terms and a sequence list for the plurality of terms, and each of the plurality of terms includes a search weight based on an order of the sequence list;

a process module selecting a first number of candidate terms from the glossary according to the code input by using an input algorithm and obtaining a second number of candidate terms by using a speech recognition algorithm to compare the voice with the first number of candidate terms for generating respective similarity weights of the respective second number of candidate terms, wherein the second number of candidate terms are listed in a particular order based on their respective search weights and respective similarity weights; and

an output module showing the second number of candidate terms in the particular order for selecting the specific term therefrom.

18. A process method for mobile search in a mobile communication device to input a specific term, comprising steps of:

receiving a first input, wherein the first input comprises at least one code of the specific term;

determining a first number of candidate terms based on the first input;

receiving a second input including a voice;

determining a second number of candidate terms according to the first input and the second input, wherein each of the second number of candidate terms has at least one weight obtained from one of the first input and the second input; and

selecting the specific term according to their respective weights.

19. The process method according to claim 18 further comprising a step of sorting the second number of candidate terms in a particular order based on their respective weights.

20. The process method according to claim 18, wherein the weight is a search weight and a similarity weight.

21. The process method according to claim 18, wherein the first input is one selected from the group consisting of a touch input, a handwriting recognition input and a keyboard entry.

22. The process method according to claim 18, wherein the second number of candidate terms are determined based on the second input under the first input.

23. The process method according to claim 18, wherein the first number of candidate terms are determined according to a context corresponding to the first input.