JP2005229396A - Portable terminal equipment, information retrieval method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To shorten a time till target telephone number information is retrieved even when registration is performed by associating a plurality of kinds of voice data with one piece of telephone number information. <P>SOLUTION: A memory 16 for telephone numbers and voice data stores the telephone number information and a plurality of kinds of voice data, etc., linked with the telephone number information. A CPU 12 compares input voice data respectively with registration voice data recorded in the memory 16 for the telephone numbers and the voice data, so as to retrieve the telephone number information which is stored linked with registration voice data being coincident with the input voice data. The CPU 12 stores the usage frequency of each kind of voice data registered linked with the telephone number information, changes storage order in the memory 16 for the telephone numbers and the voice data in response to the usage frequency, and performs rearrangement to collate the voice data with the high usage frequency first with the input voice data. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an information search method for searching for target information from a plurality of information registered in advance using a voice recognition function, and more particularly, to a telephone number using a voice recognition function in a mobile terminal such as a mobile phone. The present invention relates to a telephone number information retrieval method for retrieving information.

  In portable terminal devices such as mobile phones, PHS (Personal Handyphone System), PDA (Personal Data Assistance, Personal Digital Assistants), it is possible to search for phone number information using a voice recognition function. Some are provided with a function that can be performed (for example, see Patent Documents 1 and 2). However, there are cases where the data registered by the user is forgotten and not used effectively.

  Conventionally, an operation for calling up specific information such as a telephone number by using a voice recognition function is performed by comparing the voice data input this time with the voice data already linked in one-to-one, and the target telephone number information. I was searching for.

  However, in this method, it is necessary to store all audio data linked one-on-one on the user side. In addition, if there are two or more people with the same surname registered in the same way, it is necessary to memorize the full name, often forgetting the registered voice data, and there is always the possibility that it cannot be used effectively was there.

  In order to solve such a problem, it is possible to register names and abbreviations that are easy to remember by storing a plurality of voice data corresponding to one telephone number information, and a user's memory act There has been proposed a portable terminal device that reduces the burden on the user (see, for example, Patent Document 3). By using such a cellular phone device, even if the first voice data registered in advance corresponding to the telephone number information is forgotten, one voice data such as an abbreviation can be recalled from a plurality of voice data. Then, it becomes possible to call the target telephone number information. For example, even when the full name of the other party who wants to make a call is forgotten, the target telephone number information can be obtained by searching with an abbreviation or nickname. Therefore, telephone number search by voice recognition can be used more effectively.

  However, in such a mobile phone, if the number of voice data to be registered for one telephone number information increases, the number of voice data to be registered jumps as the number of registered telephone number information itself increases. Will increase. Since a certain amount of time is required to compare the input voice data with the previously registered voice data, the conventional mobile phone device takes a long time to search for the target information. There is a problem of end.

For example, when a plurality of audio data is registered for a certain phone number information, the input audio data and the pre-registered audio data are usually compared in the registered order. Therefore, when a search is performed using a recently registered abbreviation, etc., the comparison with the abbreviation registered at the end of the previous voice data will be performed at last. It takes time to be identified.
JP 2002-0333820 A JP 2002-318597 A JP 2002-281144 A

  In the conventional mobile phone described above, when a plurality of voice data is registered corresponding to one phone number information, the search order of the phone number information is fixed, so that the target phone number information can be searched. There was a problem that the time of.

  An object of the present invention is to provide a mobile phone and an information search capable of shortening the time required to search for target telephone number information even when a plurality of audio data are registered corresponding to one telephone number information. Is to provide a method.

In order to achieve the above object, a mobile terminal device of the present invention includes specific information and a memory for audio data in which a plurality of audio data linked to the specific information is stored;
A voice input unit for inputting a voice signal from a user as analog data;
An analog-to-digital conversion unit that performs analog-to-digital conversion processing to convert analog data input by the voice input unit into digital data;
By comparing the input voice data converted by the analog-digital converter with the registered voice data recorded in the specific information and voice data memory, the input voice data is linked to the registered voice data that matches the input voice data. A mobile terminal device comprising: a CPU for searching for specific information stored in
The CPU stores the frequency of use of each voice data registered linked to the specific information, and changes the storage order in the memory for the specific information and the voice data according to the frequency of use. Sorting is performed so that voice data having a high frequency of use is collated with the input voice data first.

  In the present invention, the storage order in the memory for specific information and audio data is changed based on the frequency of use of each audio data, and rearranged so that the audio data with the high frequency of use is collated with the input audio data first. Therefore, the comparison processing between the input voice data and the registered voice data can be reduced, and even when a plurality of voice data is registered corresponding to one telephone number information, the target telephone is recorded. It is possible to shorten the time until the number information can be searched.

  Further, the CPU may delete the audio data having a low usage frequency from the specific information and audio data memory according to the remaining amount of the memory capacity of the specific information and audio data memory.

  According to the present invention, when the memory capacity of the specific information and audio data memory is reduced, the audio data is deleted from the infrequently used audio data. Therefore, the infrequently used audio data is stored in large quantities. It becomes possible to prevent that new specific information cannot be registered.

  Further, the specific information to be searched may be telephone number information. The present invention is applied to a case where telephone number information is searched using a voice recognition function in a mobile phone or the like.

  As described above, according to the present invention, when a plurality of pieces of voice data are registered corresponding to one phone number information, the order of the plurality of pieces of voice data registered for each piece of phone number information is: Since rearrangement is performed based on the frequency of use, it is possible to obtain an effect that it is possible to shorten the time until the target telephone number information can be searched.

  Next, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a block diagram showing a main part of a circuit configuration of a mobile phone according to an embodiment of the present invention.

  As shown in FIG. 1, the mobile phone of this embodiment includes a CPU (Central Processing Unit) 12, a ROM 14, a work memory 15, a telephone number and voice data memory 16, and operation keys (specific keys). 17, timer 18, key input unit 19, display control unit 21, display unit 22, transmission / reception unit 23, analog / digital conversion unit 24, and voice input unit 25. 13 is connected to each block other than the operation key 17, the display unit 22, and the voice input unit 25.

  The ROM 14 is a read-only memory storing fixed data such as a dictionary used for various control programs to be executed by the CPU 12 and character conversion.

  The work memory 15 is constituted by a RAM (Random Access Memory), and stores data temporarily required for the CPU 12 to execute the program. The voice data input from the user is also stored in a predetermined area of the work memory 15.

  The telephone number and voice data memory 16 is a memory for storing telephone number information, voice data linked to the telephone number information, and the number of voice data linked to individual telephone number information, and is composed of a nonvolatile memory. ing. An example of data stored in the telephone number and voice data memory 16 is shown in FIG.

  The key input unit 19 is an input circuit that receives a key input for calling a specific information search function using a voice recognition function and an end key for ending various processes. The display control unit 21 is a control circuit that controls display on the display unit 22. The display unit 22 is disposed on the front surface of a device main body (not shown), and is a display device such as a monochrome or color liquid crystal panel or organic EL (electrofluorescence). The transmission / reception unit 23 is a circuit that transmits and receives data wirelessly.

  The voice input unit 25 inputs a voice signal from the user as analog data. The analog-digital conversion unit 24 performs analog-digital conversion processing for converting analog data input by the voice input unit 25 into digital data.

  The telephone number search function using the voice recognition function is made to correspond to the specific key 17, and the CPU 12 measures the time by the timer 18 and monitors whether or not the specific key is continuously pressed for a predetermined time or more.

  Further, the CPU 12 compares the input voice data converted by the analog-digital conversion unit 24 with the registered voice data recorded in the telephone number and the voice data memory 16 to thereby match the registered voice data with the input voice data. Retrieve phone number information stored linked to the data. Then, the CPU 12 displays the telephone number information on the display unit 22 via the display control unit 21. Then, the CPU 12 in this embodiment stores the frequency of use of each voice data registered linked to the phone number information, and changes the storage order in the phone number and the voice data memory 16 according to this usage frequency. As a result of the change, rearrangement is performed so that voice data having a high frequency of use is collated with input voice data first.

  Next, the operation of the mobile phone according to the present embodiment will be described in detail with reference to the drawings.

  First, with reference to FIG. 3, the telephone number information search process used in this embodiment will be described.

  When the user of the cellular phone uses the telephone number information search function by voice, a predetermined key (in this example) assigned as a key for calling the telephone number information search function in the standby state (step S41) The “Book” key) is continuously pressed for a predetermined time or more (step S42: Y). Based on the detection result of the key input unit 19, the CPU 12 determines whether or not any key is continuously pressed for a predetermined time or longer in the timer unit 18. When it is detected that the “Book” key in this example is continuously pressed for the predetermined time or longer (step S42: Y), the CPU 12 displays a voice input request screen as shown in FIG. 22 (step S43) and waits until a voice is input (step S44).

  When the CPU 12 detects that a voice is input to the voice input unit 25 (step S44), the analog-digital conversion unit 24 performs analog-digital conversion (step S45). The CPU 12 compares the input voice data digitized by the search engine unit (S50) with the voice data linked to the telephone number and the telephone number stored in the voice data memory 16, and is registered as the inputted voice data. When the voice data matches the voice data (step S50: Y), the matched telephone number is incorporated into the corresponding part of the telephone call screen and displayed on the display unit 22 in an editable state as shown in FIG. S47). When the input voice data does not match the registered voice data in the comparison process in step S50 (step S50: N), a new link confirmation screen as shown in FIG. (Step 48), and when registering a new phone number No. (Step S49: Y), the voice data is added to the registered voice data VD [m] [n] of the telephone number and the corresponding telephone number in the voice data memory 16 shown in FIG. 2 (step S4A). If not newly registered, pressing of the “END key”, which is a specific key of the operation key 17, is detected and the process returns to the standby state (step S49: N).

  FIG. 7 shows the internal processing of the search engine unit (step S50) of FIG.

  The CPU 12 substitutes the converted voice data for the variable VOICE (step S51), and substitutes the telephone number and the number of registered telephone numbers stored in the voice data memory 16 for the variable M (step S52). A variable m representing the telephone number currently being searched is initialized with “0”. Next, m is incremented by 1 to obtain telephone number information sequentially (step S54). The number of voice data linked to the telephone number is substituted into the variable N (step S55). voice data No. linked to the telephone number of m. Is initialized with “0” (step S56). Next, in order to acquire voice data sequentially linked to the telephone number, n is incremented by 1 (step S57), and the variable VOICE is compared with the voice data VD [m] [n] acquired by the variables m and n. If there is a match, the return value of the search engine unit (step S50) returns the result of the conditional expression as Y, and the searched telephone number information is returned as the return value of the search result (step S5C). If there is no match, a match with all the registered audio data VD [] [] is confirmed (step S59, step S5A). If there is no match (step S59: Y, step S5A: Y), a search is performed. The return value of the engine unit (step S50) is returned as N (step S5B).

  In the mobile phone of the present embodiment, the CPU 12 stores the telephone number and the usage frequency selected by the user for each registered voice data VD [m] [n] in the voice data memory 16. A learning function is provided for rearranging the order of a plurality of voice data registered for each telephone number information based on the frequency of use. In other words, by arranging the most frequently used one at the head, it is possible to shorten the search time and speed up the search engine.

(Second Embodiment)
Next, a mobile phone according to a second embodiment of the present invention will be described.

  In the mobile phone according to the first embodiment, the search engine unit (step S50) shown in FIG. 3 is described as having one search result between the input voice data and the registered voice data. However, in the second embodiment of the present invention, a case where two or more search results correspond will be described.

  FIG. 8, which is an improvement after the search engine section (step S50) in FIG. 3, shows an example in which two or more search results in the first voice data (here, the surname is used as an example) correspond (step S81). : Y), the user may be further prompted to input the second voice data (named here as an example) (step S82), and the search engine may be extended. Regarding the extension, the search for the second voice data (named here as an example) is narrowed down to target the voice data of the corresponding number searched in the first voice data (step) S85). If the search engine stores voice data such as first name, last name, abbreviation, etc., if there is a concern that the number of voice data to be registered increases and consumes a large amount of memory, You can use the VD [m] [n] usage frequency learning function to delete from the least frequently used VD [m] [n] voice data linked to the phone number. good. As a result, when the memory amount of the telephone number and voice data memory 16 is reduced, the voice data is deleted from the less frequently used voice data, and thus a large amount of less frequently used voice data is stored. Thus, it becomes possible to prevent the registration of new telephone number information.

  In the mobile phone according to the first and second embodiments described above, a case has been described where specific phone number information is searched from phone number information registered by the user. Is also applicable. As an example, various functions are called by pressing a specific key. However, if a function for calling each function using a voice recognition function is provided, voice data that the user is likely to guess about this function, or a user May be linked to audio data that is easy to memorize.

  In the above description, the case where voice information is searched in a mobile phone has been described. However, the present invention is not limited to a mobile phone, but a PHS (Personal Handyphone System), PDA (Personal Data Assistance, Personal Digital). The present invention can be applied in the same way when searching for telephone number information in a portable terminal device such as Assistants (personal portable information communication device) and a device such as a fixed telephone. Further, the present invention can be similarly applied to any device that searches not only phone number information but also target information from a plurality of information registered in advance using a voice recognition function. It can be done.

  Although not shown in the figure, the mobile phone according to the present embodiment includes a recording medium on which a program for executing the information search method described above is recorded. This recording medium may be a magnetic disk, a semiconductor memory, or another recording medium. This program is read from the recording medium to the CPU 12 and controls the operation of the CPU 12. The above processing is realized by instructing the hardware resource in the mobile phone to perform a specific processing by controlling the program read by the CPU 12.

It is a block diagram which shows the structure of the mobile telephone of the 1st Embodiment of this invention. It is a figure which shows the data structure stored in the memory for telephone number and audio | voice data 16. FIG. It is the flowchart which showed the search processing of telephone number information in the portable telephone of one execution form of this invention. It is a figure which shows an example of the audio | voice input request | requirement screen for prompting a user to input audio | voice. 6 is a diagram illustrating an example of a screen displayed on the display unit 22. FIG. 12 is a diagram illustrating another example of a screen displayed on the display unit 22. FIG. It is the flowchart which showed the internal process of the search process of step S50 shown in FIG. It is a flowchart which shows the process in the mobile telephone of the 2nd Embodiment of this invention.

Explanation of symbols

12 CPU (Central Processing Unit)
13 Bus line 14 ROM
15 Work memory 16 Telephone number and voice data memory 17 Operation keys (specific keys)
18 timer 19 key input unit 21 display control unit 22 display unit 23 transmission / reception unit 24 analog-digital conversion unit 25 voice input unit

Claims (7)

Memory for specific information and audio data in which a plurality of audio data linked to the specific information and the specific information are stored;
A voice input unit for inputting a voice signal from a user as analog data;
An analog-to-digital conversion unit that performs analog-to-digital conversion processing to convert analog data input by the voice input unit into digital data;
By comparing the input voice data converted by the analog-digital converter with the registered voice data recorded in the specific information and voice data memory, the input voice data is linked to the registered voice data that matches the input voice data. A mobile terminal device comprising: a CPU for searching for specific information stored in
The CPU stores the frequency of use of each voice data registered linked to the specific information, and changes the storage order in the memory for the specific information and the voice data according to the frequency of use. A mobile terminal device that performs sorting so that voice data having a high frequency of use is collated with the input voice data first.   The portable terminal device according to claim 1, wherein the CPU deletes audio data with low usage frequency from the specific information and audio data memory according to a remaining amount of memory capacity of the specific information and audio data memory.   The mobile terminal device according to claim 1, wherein the specific information to be searched is telephone number information. Inputting an audio signal from a user as analog data and performing an analog-digital conversion process for converting the analog data into digital data;
Input audio data converted by the analog-digital conversion unit, specific information in which a plurality of audio data linked to the specific information and the specific information are stored, and registered audio data recorded in the audio data memory And searching for specific information stored by linking to the registered voice data that matches the input voice data by comparing with each of the input voice data,
By storing the usage frequency of each voice data registered linked to the specific information, and changing the storage order in the memory for the specific information and the voice data according to the usage frequency, the high usage frequency The information search method further comprising the step of rearranging the voice data so as to be collated with the input voice data first.   5. The information search method according to claim 4, further comprising the step of deleting audio data having a low usage frequency from the specific information and audio data memory in accordance with a remaining amount of memory capacity of the specific information and audio data memory.   6. The information search method according to claim 4, wherein the specific information to be searched is telephone number information. The program for making a computer perform the information search method of any one of Claim 4 to 6.

Images