JP2008250708A - Input character string prediction apparatus and input character string prediction program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an input character string prediction apparatus which can delete by simple operation, erroneously selected prediction candidates from input-defined character strings, when the selection error is made for the prediction candidate, and further can delete it from a learning history. <P>SOLUTION: The input character string prediction apparatus comprises: a means which, when a prediction candidate is selected from a displayed estimation candidate list, adds a selected prediction candidate to an input-defined character string, and stores the selected prediction candidate in a learning history storage memory as history data; an input means for allowing a user to input a candidate selection cancellation instruction for canceling the selected prediction candidate; and a means which, when the candidate selection cancellation instruction is input after the prediction candidate has been selected, deletes the character string of the prediction candidate selected just before from the input-defined character string, and deletes, from a learning history storage memory, a prediction candidate stored last in the learning history storage memory. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an input character string prediction device and an input character string for generating and displaying a prediction candidate list by predicting a character string to be input by a user based on a character or a character string input by the user. Concerning prediction program.

  With the spread of information devices such as computers, it has become common to store sentences as digitized text, and the burden of inputting character strings using a keyboard or the like has increased. Similarly, in the medical field, with the popularization of electronic medical records and the like, medical chart input from handwritten keyboards is being performed.

  In the field where quick input is required, there is a desire to reduce the load of character string input. There is an input character string predicting device as means for reducing the load of character string input. The input character string prediction apparatus predicts a word starting with the character or character string by inputting the character or character string at the head of the word to be input, and displays the predicted word as a prediction candidate. Then, when the user selects a desired one from the displayed prediction candidates, the word selected by the user is automatically input.

  Note that a display priority is set for the prediction candidates, and normally, a predetermined number of prediction candidates having a high display priority are displayed in the order of high display priority. This display priority is set based on a word appearance probability (word occurrence probability) determined by the language model, a history of character strings (learning history) input by the user in the past, and the like.

  In the input character string predicting device, it is possible to input a word from a part thereof without inputting all the character strings of the word to be input, so that the input load can be reduced. It is also possible to predict and display candidate character strings following the selected character string based on the learning history. The prediction in this case is called connection prediction. A character string for which input such as a prediction candidate selected by the user is confirmed is stored as a learning history in time series. The prediction accuracy is improved by referring to the stored learning history during the next and subsequent predictions. By outputting the learning history stored in the input character string prediction device to an external file (learning dictionary), the learning history can be used in another input character string prediction device.

By the way, since a character string input operation or selection operation is performed by a human, an input error or a selection error may occur. Japanese Patent Application Laid-Open No. 11-212705 discloses an input character stored in an input buffer when the user deletes the last character in the input character string when an input error occurs in the input character prediction device. A technology that deletes the deleted character from the sequence, searches the word dictionary for the character string that has the input character string after the deletion at the beginning, and then (after) does not have the deleted character, and displays it as a prediction candidate Is disclosed.
Japanese Patent Laid-Open No. 11-212705

  In the above prior art, at the timing when the input character string is corrected, a prediction candidate predicted from the input character string after correction is excluded from the prediction candidate predicted from the input character string before correction. Thus, a selection error such that an unnecessary prediction candidate is selected is unlikely to occur. The above prior art is a technique related to how to search for a prediction candidate when the last character in the input character string is deleted in an indeterminate state before selecting the prediction candidate. It is not a technique for when there is a selection error after.

  If there is a selection error after selecting the prediction candidate, the user deletes the character string whose input has been confirmed by the wrong selection operation, and again inputs the character or the character string to select the prediction candidate again. Then, an operation is performed such that the correct candidate is selected again from the displayed prediction candidates.

  Such an operation is troublesome, and more characters may be deleted when deleting a character string whose input has been confirmed by an erroneous selection operation. In addition, in the input character string predicting device that learns the input history, when there is such a selection error, the input is confirmed even if the character string whose input is confirmed by an erroneous selection operation is deleted. There is a problem that the character string remains in the learning history. This will be described with reference to FIG.

  The upper diagram in FIG. 4 shows that the prediction candidate list is generated based on “a” by inputting the character “a” into the input unit, and the generated prediction candidate list is displayed on the prediction candidate display unit. Indicates the state. It is assumed that the user mistakenly selects “atopic dermatitis” in the prediction candidate where “allergic conjunctivitis” should be selected.

  Then, as shown in the middle diagram of FIG. 4, the selected “atopic dermatitis” is displayed in the input unit, and is generated based on the “atopic dermatitis” selected in the prediction candidate display unit. The predicted candidate list is displayed. That is, the selected “atopic dermatitis” is added to the character string whose input has been confirmed. The selected “atopic dermatitis” is stored as history data in a memory for storing learning history. The user deletes the eight characters “atopic dermatitis” displayed on the input unit with the BS key (backspace key), and then inputs the character “A” again. As a result, “atopic dermatitis” is deleted from the input confirmed character string.

  Then, as shown in the lower diagram of FIG. 4, “A” is displayed in the input unit, a prediction candidate list is generated based on “A”, and the generated prediction candidate list is displayed in the prediction candidate display unit. Is displayed. Since the prediction candidate “atopic dermatitis” selected by the previous selection error remains in the learning history, “atopic dermatitis” is displayed at the top of the prediction candidate list.

  The present invention provides an input character string prediction device capable of deleting a prediction candidate selected by a selection error by a simple operation from a character string whose input has been confirmed and also deleting it from a learning history when there is a prediction candidate selection error, and An object is to provide an input character string prediction program.

  Further, according to the present invention, when there is a selection error in the prediction candidate, the prediction candidate selected by the selection error can be deleted from the input confirmed character string by a simple operation and can be deleted from the learning history, and the selection error An object of the present invention is to provide an input character string predicting device and an input character string predicting program that can automatically display a prediction candidate list that was displayed when the error occurred.

  Further, according to the present invention, when there is a selection error in the prediction candidate, the prediction candidate selected by the selection error can be deleted from the input confirmed character string by a simple operation and can be deleted from the learning history, and the selection error It is an object to provide an input character string prediction device and an input character string prediction program capable of automatically displaying a prediction candidate list displayed when an error occurs, except for a prediction candidate with a selection error. And

  Further, according to the present invention, when there is a selection error of a prediction candidate, the prediction candidate selected by the selection error can be deleted from the input confirmed character string with a simple operation and displayed when a selection error occurs. It is an object of the present invention to provide an input character string prediction device and an input character string prediction program that can automatically display a prediction candidate list excluding a prediction candidate having a selection error.

  The invention according to claim 1 predicts an input character string for generating and displaying a prediction candidate list by predicting a character string that the user intends to input based on a character or character string input by the user. In the input character string prediction device that uses the history of the character string input in the past for prediction of the input character string, the prediction selected when the prediction candidate is selected from the displayed prediction candidate list Means for adding the candidate to the input-confirmed character string, storing the selected prediction candidate in the learning history storage memory as history data, and allowing the user to input a candidate selection cancellation command for canceling the selected prediction candidate When a candidate selection cancellation command is input after the input means and the prediction candidate is selected, the character string of the prediction candidate selected immediately before the input confirmed character string is With dividing, characterized in that it comprises means for deleting the predicted candidates saved from the learning history storage memory to the last learning history storage memory.

  According to a second aspect of the present invention, in the input character string prediction device according to the first aspect, when a candidate selection cancellation command is input after a prediction candidate is selected, a prediction candidate list at the time of selection of the prediction candidate is displayed. It is characterized by having a means for redisplaying.

  According to a third aspect of the present invention, in the input character string predicting device according to the first aspect, when a candidate selection cancellation command is input after a prediction candidate is selected, the prediction candidate list at the time of selection of the prediction candidate is used. Means is provided for re-displaying the one excluding the prediction candidate.

  The invention according to claim 4 predicts an input character string for generating and displaying a prediction candidate list by predicting a character string to be input by the user based on a character or a character string input by the user. In an input character string prediction program that uses a history of previously input character strings to predict an input character string, the computer is selected when a prediction candidate is selected from the displayed prediction candidate list. The selected prediction candidate is added to the input-confirmed character string, the selected prediction candidate is stored as history data in the learning history storage memory, and the candidate selection cancellation command for canceling the selected prediction candidate is input to the user When the candidate selection cancel command is input after the prediction candidate is selected and the input means for causing the input to be Deletes the character string-option prediction candidates, characterized in that the learning history storage memory in the learning history storage memory is intended to function as means for deleting the predicted candidates was last saved.

  The invention according to claim 5 predicts an input character string for generating and displaying a prediction candidate list by predicting a character string to be input by the user based on a character or a character string input by the user. In the apparatus, when a prediction candidate is selected from the displayed prediction candidate list, a means for adding the selected prediction candidate to the input-confirmed character string, and a candidate selection cancellation command for canceling the selected prediction candidate When a candidate selection cancellation command is input after the prediction candidate is selected and the input candidate is selected, the character string of the prediction candidate selected immediately before is deleted from the input confirmed character string, and the prediction Means is provided for redisplaying a list obtained by removing the prediction candidate from the prediction candidate list at the time of selection of the candidate.

  The invention according to claim 6 predicts an input character string for generating and displaying a prediction candidate list by predicting a character string to be input by the user based on a character or a character string input by the user. When a prediction candidate is selected from the displayed prediction candidate list, the program is a means for adding the selected prediction candidate to the input confirmed character string, and a candidate for canceling the selected prediction candidate Input means for allowing the user to input a selection cancellation command, and when a candidate selection cancellation command is input after a prediction candidate is selected, the character string of the prediction candidate selected immediately before is deleted from the input confirmed character string And functioning as a means for re-displaying the prediction candidate list excluding the prediction candidate when the prediction candidate is selected. That.

  According to the first or fourth aspect of the present invention, when there is a prediction candidate selection error, the prediction candidate selected by the selection error can be deleted from the input-confirmed character string by a simple operation and learning is performed. It can be deleted from the history.

  According to the second aspect of the present invention, when there is a prediction candidate selection error, the prediction candidate selected by the selection error can be deleted from the input confirmed character string with a simple operation and also deleted from the learning history. In addition, the prediction candidate list that was displayed when a selection error occurred can be automatically displayed.

  According to the third aspect of the present invention, when there is a prediction candidate selection error, the prediction candidate selected by the selection error can be deleted from the input confirmed character string with a simple operation and also deleted from the learning history. In addition, it is possible to automatically display a prediction candidate list that is displayed when a selection error occurs and excludes a prediction candidate having a selection error.

  According to the invention of claim 5 or claim 6, when there is a selection error of the prediction candidate, the prediction candidate selected by the selection error can be deleted from the input confirmed character string by a simple operation, It is possible to automatically display a prediction candidate list that is displayed when a selection error occurs, excluding a prediction candidate having a selection error.

  Embodiments of the present invention will be described below with reference to the drawings.

[1] Configuration of input string prediction device

  FIG. 1 shows the configuration of the input character string prediction apparatus.

  The input character string prediction device includes an input unit 1, an input character string prediction unit 2, a prediction candidate display unit 3, a learning history storage unit 4, a candidate selection cancellation unit 5, a prediction dictionary (word dictionary) 11, and a learning history storage memory 12 And a learning dictionary 13.

  The prediction dictionary (word dictionary) 11 stores words to be predicted. Each word in the prediction dictionary 11 is added with a score representing the degree of correctness of the prediction candidate (degree of correctness). This score is determined based on, for example, a word appearance probability (word occurrence probability) determined by the language model.

  In the learning dictionary 13, a character string whose input is confirmed, such as a prediction candidate selected by the user from the prediction candidate list, is stored as a learning history. When the input character string prediction device is powered on, the learning history stored in the learning dictionary 13 is read into the learning history storage memory 12. Of the learning histories read into the learning history storage memory 12, learning histories for which a predetermined period (for example, six months) has elapsed since registration are deleted.

  After the power is turned on, every time the input is confirmed, the notation and reading of the character string whose input is confirmed are stored in the learning history storage memory 12 in time series. The number of character strings that can be stored in the learning history storage memory 12 is limited. When the number of character strings to be stored exceeds a predetermined number, the old character string is deleted and a new character string is stored. As will be described later, the contents of the learning history storage memory 12 are output to the learning dictionary 13 at a predetermined timing, and the contents of the learning dictionary 13 are updated.

[2] Input unit 1

  The input unit 1 receives a reading or notation of a character string (input character string) input by the user and sends it to the input character string prediction unit 2. When the character input method is keyboard input, a character string reading is input to the input unit 1, and when the character input method is a handwritten character input method, a character string notation is input to the input unit 1. . For example, the reading of “sugar” in “diabetes” is “to”, and the notation when entered in kanji is “sugar”.

[3] Input character string prediction unit 2

  Each time a character is input to the input unit 1, the input character string prediction unit 2 searches the prediction dictionary 11 and the learning history in the learning history storage memory 12 for a word starting with the character string input to the input unit 1. Then, based on the score added to the searched word and the appearance frequency of the word in the learning history, the priority of each searched word is determined, and the prediction candidate list is generated in descending order of priority.

  Further, when a prediction candidate is selected from the prediction candidate list, the input character string prediction unit 2 performs connection prediction and generates a prediction candidate list. That is, the same character string as the selected prediction candidate is searched from the learning history in the learning history storage memory 12. Then, the character string registered next (next in chronological order) after the searched character string is searched as a prediction candidate. Then, a priority order is determined for each obtained prediction candidate based on the frequency searched this time, and a prediction candidate list is generated in descending order of priority.

[4] Prediction candidate display section 3

  The prediction candidate display unit 3 displays a part or all of the prediction candidate list generated by the input character string prediction unit 2 on a display (not shown). Normally, the prediction candidate display unit 3 causes the display to display a predetermined number (N) of prediction candidates with high priority among the prediction candidate lists generated by the input character string prediction unit 2. The prediction candidate display unit 3 notifies the learning history storage unit 4 of the selection result when a prediction candidate is selected.

[5] Learning history storage unit 4

  The learning history storage unit 4 stores (additionally saves) the notation and reading of the character string for which the input of the selected prediction candidate or the like is confirmed in the learning history storage memory 12 as a learning history. In addition, the learning history storage unit 4 stores the contents of the entire learning history in the learning history storage memory 12 at the timing of character input delimitation such as line feed and window focus switching or when the power is turned off (when finished). Save to. Thereby, the contents of the learning dictionary 13 are updated.

[6] Candidate selection cancellation unit 5

  The input unit 1 outputs a candidate selection cancellation command to the candidate selection cancellation unit 5 when there is a predetermined candidate selection cancellation key input after a prediction candidate is selected from the prediction candidate list. In this embodiment, the candidate selection cancel key input is generated by simultaneously pressing the Shift key and the BS key.

  When there is a candidate selection cancellation command from the input unit 1, the candidate selection / cancellation unit 5 automatically deletes characters corresponding to the number of characters of the prediction candidate selected immediately before from the last character of the character string whose input has been confirmed. . In addition, when there is a candidate selection cancellation command from the input unit 1, the candidate selection cancellation unit 5 outputs an erroneous selection candidate deletion command to the learning history storage unit 4 and based on the erroneous selection candidate deletion to the prediction candidate display unit 3. A prediction candidate redisplay command (hereinafter simply referred to as a prediction candidate redisplay command) is output.

  When the learning history storage unit 4 receives an erroneous selection candidate deletion command from the candidate selection cancellation unit 5, the learning history storage unit 4 deletes the prediction candidate stored last in the learning history storage memory 12 and deletes the prediction candidate (selected by mistake). Prediction candidate) is given to the prediction candidate display unit 3.

  When the prediction candidate display unit 3 receives the prediction candidate redisplay command from the candidate selection cancellation unit 5, the prediction candidate display unit 3 performs a prediction candidate redisplay process based on the erroneous selection candidate deletion. In the prediction candidate redisplay process based on deletion of erroneous selection candidates, a prediction candidate list generated one time before by the input character string prediction unit 2 (a prediction candidate list generated one time before the currently displayed prediction candidate list) ) To generate a prediction candidate list excluding the prediction candidate selected immediately before (prediction candidate selected in error). Then, a predetermined number of prediction candidates having a high display priority among the obtained prediction candidate lists are displayed on the display. Note that the prediction candidate selected immediately before is given from the learning history storage unit 4.

  For example, as shown in the upper part of FIG. 2, a predetermined number N (in this example) having a high display priority in the prediction candidate list generated by the input character string prediction unit 2 when the character “a” is input to the input unit. Let us assume that N = 6) prediction candidates are displayed on the prediction candidate display section. It is assumed that the user mistakenly selects “atopic dermatitis” at the place where “allergic conjunctivitis” should be selected from among the prediction candidates in the prediction candidate list.

  Then, as shown in the middle diagram of FIG. 2, “atopic dermatitis” selected and confirmed is displayed in the input unit, and the display priority order in the prediction candidate list generated by the input character string prediction unit 2 is displayed. High N prediction candidates are displayed on the prediction candidate display unit. Therefore, it is assumed that the candidate selection cancel key input is generated when the user simultaneously presses the Shift key and the BS key.

  Then, as shown in the lower diagram of FIG. 2, when the character string of “atopic dermatitis” input to the input unit is deleted and an erroneous selection is made on the prediction candidate display unit Of the prediction list excluding “atopic dermatitis” that has been erroneously selected from the prediction candidate list that was partially displayed, N prediction candidates with high display priority are displayed on the prediction candidate display unit. .

[7] Operation of input character string prediction device

  FIG. 3 shows the operation of the input character string prediction apparatus.

  When there is a key input (step S1), it is determined whether or not the key input is a character key input (step S2). If it is not a character key input, the process returns to step S1. If it is determined in step S2 that the input is a character key, a prediction candidate list is generated based on the input character string (step S3), and the generated prediction candidate list is used as the first candidate list. A is stored in the buffer (step S4). Then, the generated prediction candidate list is displayed (step S5).

  When the prediction candidate list is displayed, whether or not an operation for confirming an input such as selecting a prediction candidate from the displayed prediction candidate list has been performed by the user (step S6), or whether or not a key input other than the input confirmation operation has been performed ( Step S7) is monitored. If there is a key input other than the input confirmation operation, the process returns to step S2. If there is an input confirmation operation, the process proceeds to step S8.

  In step S8, the character string S whose input is confirmed (or the selected prediction candidate when the input is confirmed by the prediction candidate selection operation) is additionally stored in the learning history storage memory 12. Further, based on the character string S whose input is confirmed, a prediction process (connection prediction process) is performed to generate a prediction candidate list (step S9), and the generated prediction candidate list is stored in the buffer as the second candidate list B. (Step S10). Then, the generated prediction candidate list is displayed (step S11).

  When the prediction candidate list is displayed, whether or not an operation for confirming an input such as selecting a prediction candidate from the displayed prediction candidate list has been performed by the user (step S12), or whether or not a key input other than the input confirmation operation has been performed ( Step S13) is monitored. If there is a key input other than the input confirmation operation, it is determined whether or not the key input is a candidate selection cancel key input (SHIFT + BS) (step S15). If it is not a candidate selection cancel key input, the process returns to step S2.

  If there is an input confirmation operation after displaying the prediction candidate list in step S11 (YES in step S12), the contents of the first candidate list A are updated to the contents of the second candidate list B (step S14). Returning to step S8, the processes in steps S8 to S11 are executed again. In other words, the character string S whose input has been confirmed (or the selected prediction candidate when the input is confirmed by the prediction candidate selection operation) is additionally stored in the learning history storage memory 12, and based on the character string S whose input has been confirmed. Thus, a prediction candidate list is generated, and the generated prediction candidate list is buffered and stored as the second candidate list B.

  If the candidate selection cancel key input operation is performed without performing any key input operation other than the candidate selection cancel key input operation after the prediction candidate list is displayed in step S11, YES is obtained in step S15. Control goes to step S16.

  In step S16, by sending out BS key inputs corresponding to the number of characters of the character string S whose input has been confirmed last (character string S last stored in the learning history storage memory 12), the end of the character string whose input has been confirmed. Characters corresponding to the number of characters in the character string S whose input has been finalized are deleted from the last character. Further, the first candidate list A is updated by deleting the character string S whose input has been finalized from the first candidate list A (step S17). Further, the character string S whose input has been finalized is deleted from the learning history storage memory 12 (step S18). Then, the first candidate list A is displayed again as a prediction candidate list (step S19). Thereafter, the process returns to step S6.

  Note that the processing in step S17 may be omitted. In this case, when the first candidate list A is redisplayed in step S19, the selection candidate S that has been erroneously selected is also displayed again.

It is a block diagram which shows the structure of an input character string prediction apparatus. It is a schematic diagram for demonstrating operation | movement when there exists predetermined candidate selection cancellation key input immediately after a prediction candidate is selected from a prediction candidate list | wrist. It is a flowchart which shows operation | movement of an input character string prediction apparatus. It is a schematic diagram for demonstrating the conventional coping method when there exists a selection error after selecting and confirming a prediction candidate.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Input part 2 Input character string prediction part 3 Prediction candidate display part 4 Learning history preservation | save part 5 Candidate selection cancellation part 11 Prediction dictionary (word dictionary)
12 Learning history storage memory 13 Learning dictionary

Claims (6)

An input character string prediction device for generating and displaying a prediction candidate list by predicting a character string to be input by a user based on a character or character string input by the user, the input character string predicting device being input in the past In the input character string prediction device that uses the history of the character string to predict the input character string,
When a prediction candidate is selected from the displayed prediction candidate list, the selected prediction candidate is added to the input confirmed character string, and the selected prediction candidate is stored in the learning history storage memory as history data ,
Input means for allowing the user to input a candidate selection cancellation command for canceling the selected prediction candidate, and when a candidate selection cancellation command is input after the prediction candidate has been selected, it is selected immediately before the input confirmed character string. Means for deleting the prediction candidate last saved in the learning history storage memory from the learning history storage memory, as well as deleting the predicted prediction character string
An input character string predicting device comprising: 2. The input character string according to claim 1, further comprising means for redisplaying a prediction candidate list at the time of selection of the prediction candidate when a candidate selection cancellation command is input after the prediction candidate is selected. Prediction device. When a candidate selection cancellation command is input after a prediction candidate has been selected, there is provided means for redisplaying the prediction candidate list excluding the prediction candidate when the prediction candidate is selected. Item 4. The input character string prediction device according to Item 1. An input character string prediction program for generating and displaying a prediction candidate list by predicting a character string to be input by a user based on a character or a character string input by the user, which is input in the past In the input string prediction program that uses the history of the character string to predict the input string,
Computer
When a prediction candidate is selected from the displayed prediction candidate list, the selected prediction candidate is added to the input confirmed character string, and the selected prediction candidate is stored in the learning history storage memory as history data ,
Input means for allowing the user to input a candidate selection cancellation command for canceling the selected prediction candidate, and when a candidate selection cancellation command is input after the prediction candidate is selected, the input selection is made immediately before the character string that has been confirmed. Means for deleting the prediction candidate last saved in the learning history storage memory from the learning history storage memory, as well as deleting the predicted prediction character string
Input string prediction program to function as In an input character string prediction device for generating and displaying a prediction candidate list by predicting a character string that the user intends to input based on a character or character string input by the user,
Means for adding the selected prediction candidate to the input confirmed character string when the prediction candidate is selected from the displayed prediction candidate list;
Input means for allowing the user to input a candidate selection cancellation command for canceling the selected prediction candidate, and when a candidate selection cancellation command is input after the prediction candidate has been selected, it is selected immediately before the input confirmed character string. Means for deleting the prediction candidate character string and redisplaying the prediction candidate list excluding the prediction candidate when the prediction candidate is selected,
An input character string predicting device comprising: An input character string prediction program for generating and displaying a prediction candidate list by predicting a character string that a user intends to input based on a character or character string input by the user,
Computer
Means for adding the selected prediction candidate to the input confirmed character string when the prediction candidate is selected from the displayed prediction candidate list;
Input means for allowing the user to input a candidate selection cancellation command for canceling the selected prediction candidate, and when a candidate selection cancellation command is input after the prediction candidate has been selected, it is selected immediately before the input confirmed character string. Means for deleting the prediction candidate character string and redisplaying the prediction candidate list excluding the prediction candidate when the prediction candidate is selected,
Input string prediction program to function as

Images