Input support program, input support method, and input support apparatus

Abstract

To improve the accuracy of estimating the reading of an input character string.SOLUTION: An input support apparatus 100 includes a storage unit 110. The storage unit 110 stores words that appeared together in a document created in the past by a user, in association with each other. The input support apparatus 100 applies, when incorrect input is detected from a character string 102 input on the basis of user operation, predetermined repair processing to the incorrect input, to create one or more reading candidates 103 for the input character string 102. The input support apparatus 100 refers to the storage unit 110, and identifies a reading candidate 103 which is associated with a word that appears in the same document 101 as the input character string 102, from among the created one or more reading candidates 103. The input support apparatus 100 determines the reading 104 of the input character string 102 on the basis of the identified reading candidate 103.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an input support program, an input support method, and an input support device for assisting character input performed based on a user's operation.

Background Art

[0002] Conventionally, in a Japanese input system, there is a technique for automatically correcting input errors made by a user. For example, when an input error such as the omission of a vowel is detected from the input string, the correct vowel is supplemented at the position where the vowel is missing to estimate the correct reading, and the result of converting the estimated reading into kanji or the like is output as a conversion candidate.

[0003] As a prior art for assisting character input, there is one that searches for a word for which input has been received in the creation of a publication from dictionary information in which words and comments are associated, and displays the searched comment following the word for which input has been received (see, for example, Patent Document 1 below).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the prior art, there is a problem that input errors made by a user cannot be correctly corrected, the estimation accuracy of the reading for the input string decreases, and conversion candidates that the user does not want may be output.

[0006] In one aspect, an object of the present invention is to provide an input support program, an input support method, and an input support device that improve the estimation accuracy of the reading of an input string.

Means for Solving the Problems

[0007] In order to solve the above-described problems and achieve the object, when an input error is detected from a character string input based on a user operation, the input support program according to the present invention creates one or more reading candidates for the character string by performing a predetermined repair process on the input error, and refers to a storage unit that stores, in association with each other, words that have co-occurred in documents created by the user in the past, and identifies, from among the one or more created reading candidates, a reading candidate associated with a word that appears in the same document as the character string, and causes a computer to execute a process of determining the reading of the character string based on the identified reading candidate.

[0008] Further, the input support program according to the present invention causes the computer to execute a process of outputting a conversion candidate corresponding to the character string based on the determined reading in the above invention.

[0009] Further, in the input support program according to the present invention, in the above invention, when the determined reading candidate is one, the determined process determines the identified reading candidate as the reading of the character string.

[0010] Further, in the input support program according to the present invention, in the above invention, when the determined reading candidate is two or more, based on the words that appear in the same document as the character string, likelihoods of the respective identified reading candidates are set, and based on the set likelihoods, any one of the identified reading candidates is determined as the reading of the character string.

[0011] In addition, in the input support program according to the present invention, in the above invention, the storage unit stores, in association with each of a plurality of homophonic words, other words that appeared together with the word in a document created by the user in the past, and the determination process refers to the storage unit to identify a reading candidate associated with a word that appears in the same document as the created one or more reading candidates from among the created one or more reading candidates, and determines the word corresponding to the identified reading candidate. This is the gist of the invention.

[0012] In addition, in the input support program according to the present invention, in the above invention, based on information that enables evaluation of the plausibility of transitions between adjacent characters in a character string, the computer is caused to execute a process of detecting an input error from the character string input based on the user's operation. This is the gist of the invention.

[0013] In addition, in the input support method according to the present invention, when an input error is detected from a character string input based on the user's operation, one or more reading candidates for the character string are created by performing a predetermined repair process on the input error, and a storage unit that stores in association words that appeared together in a document created by the user in the past is referred to, and a reading candidate associated with a word that appears in the same document as the character string is identified from among the created one or more reading candidates, and based on the identified reading candidate, the computer executes a process of determining the reading of the character string. This is the gist of the invention.

[0014] In addition, the input support device according to the present invention has a control unit that, when an input error is detected from a character string input based on the user's operation, creates one or more reading candidates for the character string by performing a predetermined repair process on the input error, refers to a storage unit that stores in association words that appeared together in a document created by the user in the past, identifies a reading candidate associated with a word that appears in the same document as the character string from among the created one or more reading candidates, and based on the identified reading candidate, determines the reading of the character string. This is the gist of the invention.

Advantages of the Invention

[0015] According to the input support program, input support method, and input support device according to the present invention, it is possible to achieve the effect of improving the estimation accuracy of the reading of the input character string.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0017] Hereinafter, with reference to the drawings, embodiments of an input support device, an input support method, and an input support program according to the present invention will be described in detail.

[0018] (An Example of an Input Support Method According to an Embodiment) FIG. 1 is an explanatory diagram showing an example of an input support method according to an embodiment. In FIG. 1, the input support device 100 is a computer that supports character input performed based on a user's operation. The input support device 100 is, for example, a PC (Personal Computer), a tablet PC, or a smartphone.

[0019] The user's operation is performed using an input device such as a keyboard or a touch panel. In the case of Japanese input, there are input modes such as Roman character input or kana input. In Roman character input, when inputting Japanese, Roman characters that combine the consonants and vowels of the characters are input. Kana input is performed using kana characters written on a keyboard or the like.

[0020] In character input performed based on the user's operation, input errors may occur. Examples of input errors include omission of characters such as vowels, misstyping a character such as a vowel with another character, input of extra characters, and incorrect input order of characters. If an input error occurs by the user, it would be convenient to be able to automatically correct the input error, saving the trouble of the user having to re-enter.

[0021] As a method for correcting input errors, for example, when a vowel is omitted, it is conceivable to supplement the vowel at the missing position. Also, based on a technique such as machine learning like deep learning, learn the natural order of Roman characters as Japanese, and for input errors, it is conceivable to supplement characters, delete extra characters, or swap the order of characters.

[0022] However, in the prior art, there are cases where input errors by the user cannot be correctly corrected. If the input error cannot be correctly corrected, the correct reading of the character string with the input error cannot be obtained, and a conversion result that the user does not want is output.

[0023] For example, when a character string "buyouin" is input based on the user's operation, the vowel "u" after "b" is an error of "i", and it is considered that the character string "biyouin" is correct and the reading "びよういん" is correct. For example, when a character string "buyouin" is input, the vowel "u" after "b" is extra, and it is considered that the character string "byouin" is correct and the reading "びょういん" is correct.

[0024] In the prior art, it is difficult to determine which of the reading candidates "byouin" and "byouin" for the "buyouin" input based on the user's operation is the correct reading. Also, in the prior art, it is difficult to determine whether it is correct to repair the input error from "buyouin" to "biyouin" or "byouin" based on the user's operation.

[0025] For example, it is conceivable to determine the correct reading from multiple reading candidates in consideration of the natural order of the learned Roman characters as Japanese. However, in the above example, both the reading candidate "byouin" and the reading candidate "byouin" exist as actual words, and it is difficult to determine the correct reading from the order of the Roman characters.

[0026] For example, among the vowels (a, i, u, e, o), assume that the probability of transitioning from "b" is highest for "i", and it is determined that "biyouin" is the most natural order of Roman characters. However, if the user has described "hospital" together with words such as "examination" and "diagnosis" in a document created in the past, and also describes words such as "examination" and "diagnosis" in the document to be created this time, then "byouin (byouin)" is the correct reading, and "biyouin (biyouin)" is considered an incorrect reading unintended by the user.

[0027] Also, for example, whether it is correct to repair the input error from "buyouin" to "biyouin" depends on whether the user has described words such as "hair" and "perm" in the document to be created this time. Therefore, if the user has not described words such as "hair" and "perm" in the document to be created this time, it is considered an error to repair the input error from "buyouin" to "biyouin".

[0028] Therefore, in the present embodiment, when estimating the reading of a string in which an input error has occurred, by considering words that appear in the same document as the string input based on the user's operation, and documents created by the user in the past, an input support method for improving the estimation accuracy of the correct reading will be described. Here, a processing example of the input support device 100 will be described. The processing example of the input support device 100 is executed, for example, in a conversion process of estimating the reading of the input string and converting it to kana, kanji, etc.

[0029] In FIG. 1, the input support device 100 includes a storage unit 110. The storage unit 110 stores, in association with each other, words that have appeared together in documents created by the user in the past. In the example of FIG. 1, specifically, the storage unit 110 stores, in association with each other, the word "beauty salon (びよういん)" and words such as "hair", "perm", and "salon" that have appeared together in documents created by the user in the past. In the example of FIG. 1, specifically, the storage unit 110 stores, in association with each other, the word "hospital (びょういん)" and words such as "examination", "medical examination", and "checkup" that have appeared together in documents created by the user in the past.

[0030] (1) When an input error is detected from the input string 102 input based on the user's operation, the input support device 100 creates one or more reading candidates 103 for the input string 102 by performing a predetermined repair process on the input error. The input string 102 is a string before confirmation. For example, in the case of Japanese input in Roman character input mode, the input string 102 corresponds to the input Roman character spelling or the result of converting the Roman character spelling to kana. Also, in the case of Japanese input in kana input mode, the input string 102 corresponds to the input kana spelling (keystrokes). The reading candidate 103 corresponds to, for example, repairing the user's input keystrokes and converting the repaired input keystrokes to kana.

[0031] Input errors include, for example, omission of characters such as vowels, misspelling of characters such as vowels with other characters, input of extra characters, and incorrect input order. The predetermined repair process is a process of supplementing characters such as vowels, changing characters such as vowels, deleting extra characters, and swapping the order of characters for input errors. The reading candidate 103 is, for example, the result of converting the input string 102 into kana after repairing it.

[0032] In the example of FIG. 1, it is assumed that Japanese is input in Roman character input mode, and the input string 102 is "buyouin". "Buyouin" is the Roman character spelling of the input. In the input string 102, it is assumed that the vowel after b is an incorrect input. The input support device 100 detects the incorrect input of the vowel after b from the input string 102 as an input error. In this case, the input support device 100 performs a repair process on the input error, for example, and creates a reading candidate 103 for the input string 102.

[0033] One of the reading candidates 103 is, for example, "びよういん (biyouin)" obtained by changing the vowel after b in the input string 102 to "i" and converting it into kana. One of the reading candidates 103 is, for example, "びょういん (byouin)" obtained by deleting the vowel after b in the input string 102 and converting it into kana. Specifically, the input support device 100 creates "びよういん (biyouin)" and "びょういん (byouin)" as the reading candidates 103.

[0034] (2) The input support device 100 refers to the storage unit 110 and identifies a reading candidate 103 associated with a word that appears in the same document 101 as the input character string 102 from among one or more created reading candidates 103. The same document 101 as the input character string 102 is the destination of the input character string 102. The same document 101 as the input character string 102 is, for example, a document being created that determines the input character string 102 and describes a conversion result obtained by converting the reading 104 of the input character string 102 into kana, kanji, or the like. The reading 104 is, for example, any one of the reading candidates 103. The reading 104 corresponds to, for example, the result of repairing the user's input keystrokes and converting the repaired input keystrokes into kana in the case of Roman character input.

[0035] The input support device 100 refers to the storage unit 110, for example, and identifies a word associated with each of one or more created reading candidates 103. In the example of FIG. 1, specifically, the input support device 100 identifies words such as "hair", "perm", and "salon" associated with the word "beauty salon" obtained by converting the reading candidate 103 "biyouin". Specifically, the input support device 100 identifies words such as "examination", "medical examination", and "checkup" associated with the word "hospital" obtained by converting the reading candidate 103 "byouin".

[0036] The input support device 100 determines, for example, whether a identified word appears in the same document 101 as the input character string 102, and identifies a reading candidate 103 associated with a word that appears in the same document 101 as the input character string 102. In the example of FIG. 1, specifically, it is assumed that the input support device 100 determines that the word "hair" appears in the same document 101 as the input character string 102 and identifies the reading candidate 103 "biyouin". Thereby, the input support device 100 can evaluate the plausibility of the reading candidate 103. In the example of FIG. 1, specifically, since the word "hair" appears, the input support device 100 can evaluate that the plausibility of the reading candidate 103 "biyouin" is high.

[0037] (3) The input support device 100 determines the reading 104 of the input string 102 based on the identified reading candidate 103. For example, if there is only one identified reading candidate 103, the input support device 100 determines the identified reading candidate 103 as the reading 104 of the input string 102. In the example of FIG. 1, specifically, the input support device 100 determines the reading candidate 103 "byouin" as the reading 104 of the input string 102.

[0038] For example, when there are multiple identified reading candidates 103, the input support device 100 may determine the reading 104 of the input string 102 based on, for example, the number of words associated with each of the identified reading candidates 103 that appear in the same document 101 as the input string 102. Specifically, the input support device 100 may determine any one of the identified reading candidates 103 for which the number of words associated with the identified reading candidate 103 that appears in the same document 101 as the input string 102 is the largest as the reading 104 of the input string 102.

[0039] Thereby, the input support device 100 can correctly correct input errors by the user and obtain the correct reading 104. For this reason, the input support device 100 can make it easier for the conversion result desired by the user to be output. For example, when a string 102 "buyouin" is input based on a user operation, the input support device 100 can appropriately determine whether it is preferable to correct it to either "biyouin" or "byouin".

[0040] Specifically, it is conceivable that the user has described "hospital" together with words such as "examination" and "diagnosis" in a document created in the past, and the current document 101 to be created also describes words such as "examination" and "diagnosis". In this case, the input support device 100 can determine that "byouin" is the correct reading 104 and "biyouin" is an incorrect reading 104 not intended by the user.

[0041] Specifically, it is conceivable that the user has described "beauty salon" together with words such as "hair" and "perm" in a document created in the past, and the words such as "hair" and "perm" are also described in the document 101 to be created this time. In this case, the input support device 100 can determine that "biyouin" is the correct reading 104, and "byouin" is an incorrect reading 104 unintended by the user.

[0042] In addition, the input support device 100 can appropriately determine whether it is correct to repair the input error from "buyouin" to "biyouin" according to the words described in the document 101 to be created by the user. Also, the input support device 100 can appropriately determine whether it is correct to repair the input error from "buyouin" to "byouin" according to the words described in the document 101 to be created by the user. In this way, the input support device 100 can improve the estimation accuracy of the reading 104 of the character string 102 in which the input error has occurred.

[0043] Here, the input support device 100 may output a conversion candidate corresponding to the input character string 102 based on the determined reading 104. In the example of FIG. 1, specifically, the input support device 100 repairs the input character string 102 "buyouin" to "biyouin" based on the determined reading 104 "biyouin", and outputs a conversion candidate "beauty salon" obtained by converting the determined reading 104. Thereby, the input support device 100 can present the conversion result desired by the user to the user.

[0044] Here, the case where the function as the input support device 100 is realized by a single computer has been described, but it is not limited to this. For example, the function as the input support device 100 may be realized by the cooperation of a plurality of computers. Specifically, the function as the input support device 100 may be realized on the cloud.

[0045] (Hardware configuration example of input support device 100) Next, with reference to FIG. 2, a hardware configuration example of the input support device 100 will be described. Here, the case where the input support device 100 is applied to a computer such as a PC or a tablet PC will be described as an example. However, the input support device 100 may be applied to a server connectable from a PC or the like used by the user.

[0046] FIG. 2 is a block diagram showing a hardware configuration example of the input support device 100 according to the embodiment. In FIG. 2, the input support device 100 includes a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, and a RAM (Random Access Memory) 203.

[0047] The input support device 100 also includes an HDD (Hard Disc Drive) 204, an HD 205, a CD (Compact Disc)-RW (ReWritable) drive 206, and a CD-RW 207. The input support device 100 also includes a display 208, a keyboard 209, a mouse 210, and a network I / F (Interface) 211. Each component is connected by a bus 200.

[0048] Here, the CPU 201 controls the entire input support device 100. The CPU 201 may have a plurality of cores. The ROM 202 and the HD 205 store various programs. The programs stored in the ROM 202 and the HD 205 are, for example, the present input support program. The present input support program is applied to, for example, kana-kanji conversion software. The program stored in the ROM 202 is loaded into the CPU 201 to cause the CPU 201 to execute the coded processing. The RAM 203 is used as a work area for the CPU 201.

[0049] The HDD 204 controls the reading or writing of data to / from the HD 205 according to the control of the CPU 201. The HD 205 stores the data written according to the control of the HDD 204. The CD-RW drive 206 controls the reading or writing of data to / from the CD-RW 207 according to the control of the CPU 201. The CD-RW 207 stores the data written according to the control of the CD-RW drive 206. The CD-RW 207 may be detachable from, for example, the input support device 100.

[0050] The display 208 displays various data such as a cursor, an icon, a menu, a window, a toolbox, characters, an image, or function information. The display 208 is, for example, a liquid crystal display, an organic EL (Electroluminescence) display, or the like.

[0051] The keyboard 209 has keys for inputting characters, numerical values, various instructions, etc., and performs data input. The mouse 210 performs selection or execution of various instructions, selection of a processing target, or movement of the mouse pointer. Also, the display 208 may be a touch panel and may have functions corresponding to the keyboard 209 and the mouse 210. In this case, the input support device 100 may not have the keyboard 209 and the mouse 210.

[0052] The network I / F 211 is connected to the network NW through a communication line and is connected to other computers via the network NW. The network NW is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, or the like. The network I / F 211 manages the interface between the network NW and the inside of the input support device 100 and controls the input / output of data from / to other computers. The network I / F 211 is, for example, a modem, a LAN adapter, or the like.

[0053] In addition to the components described above, the input support device 100 may have, for example, a DVD (Digital Versatile Disc) drive, or an SSD (Solid State Drive). Further, in addition to the components described above, the input support device 100 may have, for example, a USB (Universal Serial Bus) port. Further, in addition to the components described above, the input support device 100 may have, for example, a printer, a scanner, a microphone, or a speaker. Further, the input support device 100 may not have, for example, an HDD 204, an HD 205, a CD-RW drive 206, a CD-RW 207, etc. among the components described above.

[0054] (Stored content of the co-occurrence information management table 300) Next, with reference to FIG. 3, an example of the stored content of the co-occurrence information management table 300 used by the input support device 100 will be described. The co-occurrence information management table 300 is realized by, for example, a storage device such as the RAM 203 or the HD 205 of the input support device 100 shown in FIG. 2. The co-occurrence information management table 300 is preferably prepared for each user, for example.

[0055] FIG. 3 is an explanatory diagram showing an example of the stored content of the co-occurrence information management table 300. As shown in FIG. 3, the co-occurrence information management table 300 has fields for readings, conversion results, and co-occurring words. The co-occurrence information management table 300 stores co-occurrence information (for example, co-occurrence information 300-1 to 300-6) as records by setting information in each field for each reading.

[0056] The reading field is set with the reading of the character string. The reading is, for example, "byoin" or "byoin". The conversion result field is set with the word that is the conversion result of the reading. The conversion result is, for example, "beauty salon" converted from "byoin" or "byoin" converted from "byoin". The co-occurring word field is set with other words that appeared together with the word that is the conversion result of the reading in a document created by the user in the past. Other words that appeared together with "beauty salon" are, for example, "hair", "perm", and "salon". Other words that appeared together with "byoin" are, for example, "examination", "examination", and "check-up".

[0057] The co-occurrence information management table 300 may be created automatically by analyzing Japanese document data, or may be created manually. The contents stored in the co-occurrence information management table 300 may be updated as needed. For example, combinations of words that appear together in the same document may be registered or updated according to the number of occurrences or frequency of semantically related word combinations in Japanese document data.

[0058] (Example of Functional Configuration of Input Support Device 100) Next, an example of a functional configuration of the input support device 100 will be described with reference to FIG.

[0059] 4 is a block diagram showing an example of a functional configuration of the input support device 100. The input support device 100 includes a storage unit 410, a reception unit 401, an input error detection unit 402, a candidate creation unit 403, a candidate specification unit 404, a correct reading determination unit 405, a conversion unit 406, and an output unit 407.

[0060] The storage unit 410 is realized by a storage device such as the RAM 203 or the HD 205 shown in FIG. 2, for example. Hereinafter, the case where the storage unit 410 is included in the input support device 100 will be described, but it is not limited thereto. For example, the storage unit 410 may be included in a device different from the input support device 100, and the stored content of the storage unit 410 may be referable from the input support device 100.

[0061] The reception units 401 to the output unit 407 function as an example of a control unit. Specifically, the reception units 401 to the output unit 407 realize their functions by causing the CPU 201 to execute a program stored in a storage device such as the ROM 202, the RAM 203, or the HD 205 shown in FIG. 2, for example, or by the network I / F 211. The processing results of each functional unit are stored in a storage device such as the RAM 203 or the HD 205 shown in FIG. 2, for example.

[0062] The storage unit 410 stores various types of information that are referred to or updated in the processing of each functional unit. The storage unit 410 stores, for example, words that co-occurred in a document created by the user in the past in association with each other. The word is a character string representing a reading, or a converted form such as kana or kanji of the reading. The storage unit 410 stores, for example, a character string representing a reading in association with a word such as kana or kanji that co-occurred with the converted form such as kana or kanji of the reading in a document created by the user in the past.

[0063] The storage unit 410 may store, for example, each of a plurality of homonymous words in which the same reading is converted into different kana or kanji, etc., in association with other words that co-occurred with the word in a document created by the user in the past. The storage unit 410 preferably stores, for example, for each user, words that co-occurred in a document created by the user in the past in association with each other. The storage unit 410 may, for example, store in association with two or more users, words that co-occurred in a document created by any of the two or more users in the past in association with each other. Specifically, the storage unit 410 stores the co-occurrence information management table 300.

[0064] The storage unit 410 may store evaluation information that enables evaluation of the plausibility of transitions between adjacent characters in a character string. The evaluation information is, for example, a model. The model is generated, for example, by a method based on machine learning such as deep learning based on character strings appearing in documents created by the user in the past. The model has a function of outputting an evaluation value representing the plausibility of transitions between adjacent characters in the character string when receiving the character string. The model may be, for example, a neural network or the like.

[0065] The evaluation information may include, for example, a transition probability indicating the plausibility of transitioning from one character to another in a character string. The evaluation information may be, for example, a graph or the like. Specifically, the evaluation information may include a transition probability indicating the plausibility of transitioning from the consonant b to the vowel u, a transition probability indicating the plausibility of transitioning from the consonant b to the vowel i, or a transition probability indicating the plausibility of transitioning from the consonant b to the consonant y in the character string. The evaluation information may be information that enables evaluation of the plausibility of transitions of three or more consecutive characters in a character string.

[0066] The storage unit 410 may store detection information that enables detection of input errors in a character string. The detection information represents, for example, features of Japanese. The features of Japanese are, for example, the natural arrangement of Roman characters as Japanese. The detection information is generated, for example, by a method based on machine learning such as deep learning based on documents created in the past. The detection information is learned about the features of Japanese from information on character strings input in the past during Japanese input. The detection information is, for example, a model. The model has a function of outputting a result of determining whether there is an input error in the character string when receiving the character string. The model may have a function of identifying the character with the input error among the character string. The model may be, for example, a neural network or the like.

[0067] The storage unit 410 stores repair information that can, for example, repair input errors in a character string and create one or more reading candidates for the character string. The repair information is generated, for example, by a method based on machine learning such as deep learning based on documents created in the past. The repair information is, for example, a model. The model has a function that, when receiving a character string, repairs the character string, creates one or more reading candidates for the character string, and outputs them. The model adds characters such as vowels, changes characters such as vowels, deletes unnecessary characters, or rearranges the order of characters for input errors in the character string. The model may be, for example, a neural network or the like.

[0068] As a method for repairing input errors, for example, when a vowel is missing, it is conceivable to supplement the missing position with a vowel. As a method for repairing input errors, it is conceivable to learn the natural order of Roman letters as Japanese by a method based on machine learning such as deep learning, and to supplement characters, delete unnecessary characters, or rearrange the order of characters for input errors.

[0069] The reception unit 401 acquires various information used for the processing of each functional unit. The reception unit 401 stores the acquired various information in the storage unit 410 or outputs it to each functional unit. Further, the reception unit 401 may output the various information stored in the storage unit 410 to each functional unit. The reception unit 401 acquires various information, for example, based on a user's operation. The reception unit 401 may receive various information from a device different from the input support device 100, for example.

[0070] The reception unit 401 receives an input of a character string based on a user operation. The input character string is a character string before confirmation. For example, in the case of Japanese input in Roman character input mode, the input character string corresponds to the input Roman character spelling or the result of converting the Roman character spelling into kana. Specifically, the reception unit 401 receives an input of the character string "buyouin". The reception unit 401 receives the reception of the input of the character string as a start trigger for starting the processing of the input error detection unit 402 to the output unit 407.

[0071] The input error detection unit 402 detects an input error from the character string input based on a user operation. Input errors include, for example, omission of characters such as vowels, misstyping of characters such as vowels with other characters, input of extra characters, and input order mistakes. The input error detection unit 402, for example, refers to evaluation information, obtains an evaluation value of the plausibility of the transition between adjacent characters in the input character string, and detects, as an input error, a location in the input character string where the obtained evaluation value is below a threshold.

[0072] The input error detection unit 402 may detect an input error from the input character string by referring to detection information, for example. The input error detection unit 402 detects, as an input error, a location in the input character string that deviates from the natural order of Roman characters as Japanese, for example. Specifically, in the input character string "buyouin", it is assumed that the vowel after b is a misinput. Specifically, the input error detection unit 402 detects the misinput of the vowel after b as an input error from the input character string "buyouin".

[0073] More specifically, for example, input errors include insertion errors, deletion errors, substitution errors, and transposition errors. An insertion error is a mistake where an arbitrary keyed character is entered additionally (e.g., nyuuryoku (にゅうりょく) → nyuuuryoku (にゅううりょく)). A deletion error is a mistake where an arbitrary keyed character is missing (e.g., nyuuryoku (にゅうりょく) → nyuuyoku (にゅうよく)). A substitution error is a mistake where an arbitrary keyed character is mistaken for another character (such as a character of an adjacent key) (e.g., nyuuryoku (にゅうりょく) → nuuuryoku (ぬううりょく)). A transposition error is a mistake where the keying order of an arbitrary keyed character is reversed (e.g., nyuuryoku (にゅうりょく) → nyuuyroku (にゅうyろく)). Note that any existing technology may be used as the technology for detecting input errors.

[0074] When an input error is detected from the character string input based on the user's operation, the candidate generation unit 403 creates one or more reading candidates of the input character string by performing a predetermined repair process on the input error. The predetermined repair process is a process of supplementing characters such as vowels, changing characters such as vowels, deleting extra characters, or swapping the order of characters for the input error. The reading candidate is, for example, the input character string converted into kana. The candidate generation unit 403 creates, for example, one or more repair candidates of the input character string and one or more reading candidates of the input character string by referring to repair information.

[0075] Specifically, the candidate generation unit 403 changes the vowel after b in the input character string "buyouin" to "i" and creates "びよういん (biyouin)" which is converted into kana. Specifically, the candidate generation unit 403 deletes the vowel after b in the input character string "buyouin" and creates "びょういん (byouin)" which is converted into kana.

[0076] The candidate identification unit 404 refers to the storage unit 410 and identifies, from among the one or more created reading candidates, the reading candidates associated with words that appear in the same document as the input character string. The same document as the input character string is the destination of the input character string. The same document as the input character string is, for example, a document that determines the input character string and describes the conversion result of converting the reading of the input character string into kana, kanji, or the like.

[0077] The candidate identification unit 404 refers to the storage unit 410, for example, and identifies the words associated with each of the one or more created reading candidates. Specifically, the candidate identification unit 404 identifies words such as "hair", "permanent wave", and "salon" associated with the word "beauty salon" obtained by converting the reading candidate "biyouin". Specifically, the candidate identification unit 404 identifies words such as "examination", "medical examination", and "checkup" associated with the word "hospital" obtained by converting the reading candidate "byouin".

[0078] The candidate identification unit 404 determines, for example, whether the identified word appears in the same document as the input character string, and identifies the reading candidates associated with the words that appear in the same document as the input character string. Specifically, assuming that the candidate identification unit 404 determines that the word "hair" appears in the same document as the input character string and identifies the reading candidate "biyouin". Thereby, the candidate identification unit 404 can evaluate the plausibility of the reading candidate. The candidate identification unit 404 can evaluate the plausibility of the reading candidate and identify an appropriate reading candidate.

[0079] The candidate identification unit 404 may identify, from among the one or more created reading candidates, the reading candidates associated with the words that appear in a predetermined range in the same document as the input character string. The predetermined range is, for example, before the location in the document where the conversion result of converting the reading of the input character string into kana, kanji, or the like is described. The predetermined range may be, for example, a predetermined number of lines existing before and after the location in the document where the conversion result of converting the reading of the input character string into kana, kanji, or the like is described.

[0080] Based on the identified reading candidates, the correct reading determination unit 405 determines the reading of the character string. When there is one identified reading candidate, the correct reading determination unit 405 determines the identified reading candidate as the reading of the character string. Specifically, the correct reading determination unit 405 determines the reading candidate "biyouin" as the reading of the input character string.

[0081] When there are two or more identified reading candidates, the correct reading determination unit 405 sets the likelihood of each of the identified reading candidates based on the words that appear in the same document as the input character string, and based on the set likelihoods, determines any one of the identified reading candidates as the reading of the input character string. The likelihood is, for example, the number of words associated with the reading candidate that appear in the same document as the input character string. The correct reading determination unit 405 may set the likelihood such that the likelihood of the reading candidate increases each time a word associated with the reading candidate appears in the same document as the input character string.

[0082] For example, the correct reading determination unit 405 determines the reading candidate with the highest set likelihood as the reading of the input character string. For example, the correct reading determination unit 405 may determine the reading candidates with a set likelihood of a certain level or higher as the reading of the input character string. Thereby, the correct reading determination unit 405 can determine the correct reading of the input character string.

[0083] Based on the determined reading, the conversion unit 406 identifies conversion candidates corresponding to the input character string. For example, based on the determined reading "biyouin", the conversion unit 406 repairs the input character string "buyouin" to "biyouin" and identifies the conversion candidate "beauty salon" obtained by converting the determined reading "biyouin". When there are multiple determined readings, the conversion unit 406 may identify conversion candidates corresponding to the input character string based on each of the determined readings.

[0084] The conversion unit 406 may specify, with reference to the storage unit 410, a word corresponding to the specified reading candidate as a conversion candidate. For example, when there are a plurality of homonymous words that can be converted from the specified reading candidate, the conversion unit 406 determines which of the plurality of words is preferable as a conversion result of the specified reading candidate, and specifies the conversion candidate. Specifically, the conversion unit 406 determines that, among the plurality of words, a word associated with a word that appears in the same document as the input character string is preferable as a conversion candidate for the specified reading candidate, and specifies it.

[0085] The output unit 407 outputs the processing result of at least one of the functional units. The output format is, for example, display on a display, print output to a printer, transmission to an external device via the network I / F 211, or storage in a storage device such as the RAM 203 or the HD 205. Thereby, the output unit 407 can notify the user of the processing result of at least one of the functional units, and can improve the convenience of the input support device 100.

[0086] The output unit 407 outputs a conversion candidate corresponding to the input character string. For example, the output unit 407 outputs the conversion result obtained by converting the determined reading as a conversion candidate corresponding to the input character string. Specifically, the output unit 407 outputs the conversion candidate "beauty salon" obtained by converting the determined reading "biyouin". For example, when there are a plurality of conversion candidates, the output unit 407 may output a list in which each of the conversion candidates is arranged. At this time, the output unit 407 may output a list in which the conversion candidates corresponding to the readings with a higher set likelihood are arranged preferentially. Thereby, the input support device 100 can present the conversion result desired by the user to the user.

[0087] (Example of determination of the reading of a character string in which an input error has occurred) Next, with reference to FIGS. 5 and 6, an example of determining the reading of a character string in which an input error has occurred by the input support device 100 will be described. The processing described with reference to FIGS. 5 and 6 is executed, for example, in kana-kanji conversion processing.

[0088] FIG. 5 and FIG. 6 are explanatory diagrams showing examples of determination of the reading of a character string in which an input error has occurred. In FIG. 5, document 500 is text data created by user A in the past. Document 500 includes, for example, a conversion result obtained by converting the reading of a character string input based on the key input of user A. Specifically, it includes sentence 501 "I had a perm at a neighborhood beauty salon instead of a salon in the city."

[0089] (5-1) Based on document 500, input support device 100 updates co-occurrence information management table 300. For example, since words such as "perm" and "salon" appear together with the word "beauty salon" in document 500, input support device 100 adds a record associating the reading "biyouin" with the word "beauty salon" and words such as "perm" and "salon" to co-occurrence information management table 300. The records to be added are, for example, records 300-1, 300-2, 300-3 shown in FIG. 3.

[0090] Thereafter, input support device 100 is creating document 510 based on the key input of user A and is displaying document 510. Document 510 is displayed, for example, on display 208 shown in FIG. 2. Document 510 includes, for example, a conversion result obtained by converting the reading of a character string input based on the key input of user A. Specifically, it includes sentence 511 "The reputation of a hair perm was better than that of a salon."

[0091] Suppose the user tries to input the word "beauty salon" to document 510 and keys in the character string "buyouin". Therefore, the vowel "u" after "b" is an incorrect input of the vowel "i". Input support device 100 accepts the character string "buyouin" input based on the key input of user A for document 510 and displays the reading 512 "buyouin" of the input character string "buyouin" on the currently displayed document 510. The character string "buyouin" is before being finalized.

[0092] (5-2) The input support device 100 receives a keystroke of a conversion key for the character string "buyouin". The conversion key may be, for example, the space key. The input support device 100 identifies conversion candidates corresponding to the character string "buyouin" in response to the keystroke of the conversion key.

[0093] The input error detection unit 402 detects an input error from the input character string. For example, the input error detection unit 402 determines that the vowel "u" after "b" in the input character string "buyouin" is an incorrect input, and detects the incorrect input of the vowel after "b" as an input error.

[0094] When an input error is detected from the input character string, the candidate creation unit 403 creates one or more reading candidates for the input character string by performing a predetermined repair process on the input error. The predetermined repair process is a process of supplementing characters such as vowels, changing characters such as vowels, deleting unnecessary characters, or swapping the order of characters for the input error. For example, the candidate creation unit 403 performs a repair process of changing the vowel after "b" to "i" in the input character string "buyouin", and creates "びよういん (biyouin)" converted to kana as a reading candidate. For example, the candidate creation unit 403 performs a repair process of deleting the vowel after "b" in the input character string "buyouin", and creates "びょういん (byouin)" converted to kana as a reading candidate.

[0095] The candidate specifying unit 404 refers to the storage unit 410 and specifies, from among the one or more created reading candidates, the reading candidates associated with the words that appear in the same document 510 as the input character string "buyouin". For example, the candidate specifying unit 404 refers to the co-occurrence information management table 300 and specifies the words associated with each of the one or more created reading candidates. Specifically, the candidate specifying unit 404 specifies words such as "hair", "perm", and "salon" that are associated with the word "beauty salon" obtained by converting the reading candidate "byouin". Specifically, the candidate specifying unit 404 specifies words such as "examination", "medical examination", and "checkup" that are associated with the word "hospital" obtained by converting the reading candidate "byouin".

[0096] For example, the candidate specifying unit 404 determines whether the specified word appears in the same document 510 as the input character string "buyouin", and specifies the reading candidates associated with the words that appear in the same document 510 as the input character string "buyouin". Specifically, since the candidate specifying unit 404 determines that the words "salon, hair, perm" appear in the same document as the input character string, it specifies the reading candidate "byouin". Thereby, the candidate specifying unit 404 can evaluate the plausibility of the reading candidates. The candidate specifying unit 404 can evaluate the plausibility of the reading candidates and specify appropriate reading candidates.

[0097] The correct reading determination unit 405 determines the reading of the character string based on the specified reading candidates. Since there is one specified reading candidate, the correct reading determination unit 405 determines the determined reading candidate "byouin" as the reading of the input character string. The conversion unit 406 specifies a conversion candidate corresponding to the input character string based on the determined reading. For example, based on the determined reading "byouin", the conversion unit 406 repairs the input character string "buyouin" to "biyouin" and specifies the conversion candidate "beauty salon" obtained by converting the determined reading "byouin".

[0098] As a result, the correct reading determination unit 405 can correctly repair input errors made by the user and obtain the correct reading. For this reason, the correct reading determination unit 405 can make it easier for the conversion result desired by the user to be output. For example, when a character string "buyouin" is input based on the user's operation, the correct reading determination unit 405 can appropriately determine which of "biyouin" and "byouin" is preferable for repair.

[0099] (5-3) The output unit 407 may output a conversion candidate 513 corresponding to the input character string. For example, based on the determined reading "biyouin", the output unit 407 repairs the input character string "buyouin" to "biyouin" and outputs the conversion candidate 513 "beauty salon" obtained by converting the determined reading "biyouin".

[0100] Specifically, the output unit 407 displays the conversion candidate 513 "beauty salon" on the document 510 in a selectable manner. Specifically, the output unit 407 may display a message 514 in association with the conversion candidate 513 "beauty salon". The message 514 is a message indicating that the input error included in the input character string "buyouin" has been repaired.

[0101] As a result, even when the user makes an input error during Japanese input, the output unit 407 can enable the user to obtain the desired conversion candidate 513 without re-entering the character string. In addition, the output unit 407 can enable the user to recognize that the input error has been automatically repaired by referring to the message 514. Note that after displaying the conversion candidate 513, when a confirmation instruction (selection operation) is performed by the user's operation, for example, the input support device 100 selects the conversion candidate 513 and determines the input.

[0102] In this way, even when multiple reading candidates are assumed for a string in which an input error has occurred, the input support device 100 can estimate the correct reading by referring to the same document as the input string. As a result, the input support device 100 can improve the estimation accuracy of the reading of the string in which the input error has occurred, and can easily output the conversion candidate desired by the user.

[0103] Here, the case where the output unit 407 displays only the conversion candidate "beauty salon" has been described, but it is not limited to this. For example, the output unit 407 may display, in addition to the conversion candidate "beauty salon", a conversion candidate "hospital". In this case, it is preferable that the output unit 407 preferentially displays the conversion candidate "beauty salon" obtained by converting the determined reading "biyouin" over the other conversion candidate "hospital". The output unit 407 may display, for example, a list in which a plurality of conversion candidates are arranged so that the conversion candidate "beauty salon" is arranged above the other conversion candidate "hospital".

[0104] Also, for example, the output unit 407 may display, in addition to the conversion candidate "beauty salon", a conversion candidate obtained by converting the reading "buyouin" of the string before repair. In this case, it is preferable that the output unit 407 preferentially displays the conversion candidate "beauty salon" obtained by converting the determined reading "biyouin" over the conversion candidate obtained by converting the reading "buyouin". The output unit 407 may display, for example, a list in which a plurality of conversion candidates are arranged so that the conversion candidate "hospital" is arranged above the conversion candidate obtained by converting the reading "buyouin". Next, the description will proceed to FIG. 6.

[0105] In FIG. 6, the document 600 is text data created by user A in the past. The document 600 includes, for example, a conversion result obtained by converting the reading of a string input based on the keystrokes of user A, and specifically includes the sentence 601 "When I had a medical check-up, I was advised to have a medical examination at a hospital."

[0106] (6-1) The input support device 100 updates the co-occurrence information management table 300 based on the document 600. For example, in the document 600, since words such as "examination", "inspection", and "medical examination" appear together with the word "hospital", the input support device 100 adds a record to the co-occurrence information management table 300 that associates the reading "byouin" with the word "hospital" and words such as "examination", "inspection", and "medical examination". The records to be added are, for example, the records 300-4, 300-5, 300-6 shown in FIG. 3.

[0107] After that, the input support device 100 is creating the document 610 based on the keystrokes of user A and is displaying the document 610. The document 610 is displayed, for example, on the display 208 shown in FIG. 2. The document 610 includes, for example, the conversion result of converting the reading of the character string input based on the keystrokes of user A, and specifically includes the sentence 611 "In the medical examination, the inspection results from the physical examination are necessary."

[0108] Suppose the user tries to input the word "hospital" into the document 610 and types the character string "buyouin". Therefore, the vowel "u" after "b" is an extra character. The input support device 100 accepts the character string "buyouin" input based on the keystrokes of user A for the document 610 and displays the reading 612 "buyouin" of the input character string "buyouin" in the currently displayed document 610. The character string "buyouin" is before confirmation.

[0109] (6-2) The input support device 100 accepts the keystroke of the conversion key for the character string "buyouin". The conversion key may be, for example, the space key. The input support device 100 identifies the conversion candidates corresponding to the character string "buyouin" as shown below in response to the keystroke of the conversion key.

[0110] The input error detection unit 402 detects input errors from the input character string. For example, in the input character string "buyouin", the input error detection unit 402 determines that the vowel "u" after "b" is an incorrect input, and detects the incorrect input of the vowel after "b" as an input error.

[0111] When an input error is detected from the input character string, the candidate creation unit 403 creates one or more reading candidates for the input character string by performing a predetermined repair process on the input error. The predetermined repair process is a process of supplementing characters such as vowels, changing characters such as vowels, deleting unnecessary characters, or swapping the order of characters for the input error. For example, in the input character string "buyouin", the candidate creation unit 403 performs a repair process of changing the vowel after "b" to "i", and creates "びよういん (biyouin)", which is converted into kana, as a reading candidate. For example, in the input character string "buyouin", the candidate creation unit 403 performs a repair process of deleting the vowel after "b", and creates "びょういん (byouin)", which is converted into kana, as a reading candidate.

[0112] The candidate identification unit 404 refers to the storage unit 410 and identifies, from among the one or more created reading candidates, the reading candidates associated with the words that appear in the same document 610 as the input character string "buyouin". For example, the candidate identification unit 404 refers to the co-occurrence information management table 300 and identifies the words associated with each of the one or more created reading candidates. Specifically, the candidate identification unit 404 identifies words such as "hair", "permanent wave", and "salon" associated with the word "beauty salon" obtained by converting the reading candidate "びよういん". Specifically, the candidate identification unit 404 identifies words such as "examination", "medical examination", and "checkup" associated with the word "hospital" obtained by converting the reading candidate "びょういん".

[0113] The candidate identification unit 404 determines, for example, whether the identified word appears in the same document 610 as the input character string "buyouin", and identifies the reading candidates associated with the words that appear in the same document 610 as the input character string "buyouin". Specifically, since the candidate identification unit 404 determines that the words "examination, check-up, inspection" appear in the same document as the input character string, it identifies the reading candidate "byouin". Thereby, the candidate identification unit 404 can evaluate the plausibility of the reading candidates. The candidate identification unit 404 can evaluate the plausibility of the reading candidates and identify appropriate reading candidates.

[0114] Based on the identified reading candidates, the correct reading determination unit 405 determines the reading of the character string. Since there is one identified reading candidate, the correct reading determination unit 405 determines the determined reading candidate "byouin" as the reading of the input character string. Based on the determined reading, the conversion unit 406 identifies the conversion candidates corresponding to the input character string. For example, based on the determined reading "byouin", the conversion unit 406 repairs the input character string "buyouin" to "byouin" and identifies the conversion candidate "hospital" obtained by converting the determined reading "byouin".

[0115] Thereby, the correct reading determination unit 405 can correctly repair the input error made by the user and obtain the correct reading. Therefore, the correct reading determination unit 405 can facilitate the output of the conversion result desired by the user. For example, based on the user's operation, when the character string "buyouin" is input, the correct reading determination unit 405 can appropriately determine which of "byouin" and "byouin" is preferable for repair.

[0116] (6-3) The output unit 407 may output the conversion candidate 613 corresponding to the input character string. For example, based on the determined reading "byouin", the output unit 407 repairs the input character string "buyouin" to "byouin" and outputs the conversion candidate 613 "hospital" obtained by converting the determined reading "byouin".

[0117] Specifically, the output unit 407 displays the conversion candidate 613 "hospital" on the document 610 in a selectable manner. Specifically, the output unit 407 may display the message 614 in association with the conversion candidate 613 "hospital". The message 614 is a message indicating that the input error included in the input character string "buyouin" has been corrected.

[0118] Thereby, even when the user makes an input error during Japanese input, the output unit 407 can enable the user to obtain the desired conversion candidate 613 without re-entering the character string. Further, the output unit 407 can enable the user to recognize that the input error has been automatically corrected by referring to the message 614. Note that after the conversion candidate 613 is displayed, when a confirmation instruction (selection operation) is performed by the user's operation, for example, the input support device 100 selects the conversion candidate 613 and determines the input.

[0119] In this way, even when multiple reading candidates are assumed for the character string in which an input error has occurred, the input support device 100 can refer to the same document as the input character string and estimate the correct reading. Thereby, the input support device 100 can improve the estimation accuracy of the reading of the character string in which an input error has occurred, and can easily output the conversion candidate desired by the user.

[0120] Here, the case where the output unit 407 displays only the conversion candidate "hospital" has been described, but it is not limited to this. For example, the output unit 407 may display other conversion candidates "hospital" in addition to the conversion candidate "hospital". In this case, it is preferable that the output unit 407 preferentially displays the conversion candidate "hospital" obtained by converting the determined reading "byouin" over other conversion candidates "hospital". The output unit 407 may display a list in which a plurality of conversion candidates are arranged so that, for example, the conversion candidate "hospital" is arranged above other conversion candidates "hospital".

[0121] Further, for example, even when the output unit 407 displays conversion candidates such as a conversion candidate obtained by converting the reading "buyouin" of the pre-repair character string "buyouin" in addition to the conversion candidate "hospital", the output unit 407 preferably displays the conversion candidate "hospital" obtained by converting the determined reading "byouin" with priority over conversion candidates such as the conversion candidate obtained by converting the reading "buyouin". For example, the output unit 407 may display a list in which a plurality of conversion candidates are arranged such that the conversion candidate "hospital" is arranged above conversion candidates such as the conversion candidate obtained by converting the reading "buyouin".

[0122] (Overall processing procedure) Next, with reference to FIG. 7, an example of the overall processing procedure executed by the input support device 100 will be described. The overall processing is realized, for example, by the CPU 201 shown in FIG. 2, storage devices such as the RAM 203 and the HD 205, and the network I / F 211.

[0123] FIG. 7 is a flowchart showing an example of the overall processing procedure. In the flowchart of FIG. 7, first, the input support device 100 receives a series of key presses by the user's operation (step S701). Next, the input support device 100 receives an input of a character string corresponding to the series of key presses received until the conversion key is pressed by the user's operation (step S702). Then, the input support device 100 executes a detection process on the input character string (step S703).

[0124] Next, the input support device 100 determines whether an input error has been detected from the input character string (step S704). Here, when no input error is detected (step S704: No), the input support device 100 proceeds to the process of step S705. On the other hand, when an input error is detected (step S704: Yes), the input support device 100 proceeds to the process of step S706.

[0125] In step S705, the input support device 100 determines the reading of the input character string (step S705). Then, the input support device 100 proceeds to the process of step S709.

[0126] In step S706, the input support device 100 creates one or more reading candidates for the input string by executing a repair process for input errors (step S706). The input support device 100 refers to the co-occurrence information management table 300 by executing the specific process described later with reference to FIG. 8, and identifies a reading candidate associated with a word that appears in the same document as the input string from among the one or more created reading candidates (step S707). The input support device 100 determines the reading of the input string based on the identified reading candidate (step S708). Then, the input support device 100 proceeds to the process of step S709.

[0127] In step S709, the input support device 100 creates a conversion candidate corresponding to the input string based on the reading of the input string (step S709). Next, the input support device 100 outputs the created conversion candidate (step S710). Then, the input support device 100 ends the overall process.

[0128] (Specific processing procedure) Next, an example of the specific processing procedure executed by the input support device 100 will be described with reference to FIG. 8. The specific process is realized by, for example, the CPU 201 shown in FIG. 2, storage devices such as the RAM 203 and the HD 205, and the network I / F 211.

[0129] FIG. 8 is a flowchart showing an example of the specific processing procedure. In the flowchart of FIG. 8, first, the input support device 100 refers to the co-occurrence information management table 300 to identify the word associated with the identified reading candidate (step S801). Next, the input support device 100 searches for a word that appears in the same document as the input string among the identified words (step S802). Then, the input support device 100 identifies the reading candidate associated with the searched word (step S803). After that, the input support device 100 ends the specific process.

[0130] As described above, according to the input support device 100 according to the embodiment, when an input error is detected from a character string input based on a user operation, one or more reading candidates of the input character string can be created by performing a predetermined repair process on the input error. According to the input support device 100, referring to the storage unit 410 that stores words that co-occur in documents created by the user in association with each other, among the one or more created reading candidates, a reading candidate associated with a word that appears in the same document as the input character string can be specified. According to the input support device 100, based on the specified reading candidate, the reading of the input character string can be determined. Thereby, the input support device 100 can improve the estimation accuracy of the correct reading of the character string in which an input error has occurred.

[0131] Also, according to the input support device 100, based on the determined reading, a conversion candidate corresponding to the input character string can be output. Thereby, the input support device 100 can make the conversion candidate for the correct reading of the character string in which an input error has occurred referable to the user. The input support device 100 can make it easier for the user to refer to the conversion candidate desired by the user.

[0132] Also, according to the input support device 100, when there is one specified reading candidate, the specified reading candidate can be determined as the reading of the input character string. Thereby, when there is one specified reading candidate, the input support device 100 can appropriately determine the reading of the input character string.

[0133] Also, according to the input support device 100, when there are two or more specified reading candidates, based on the words that appear in the same document as the input character string, the likelihood of each of the specified reading candidates can be set. According to the input support device 100, based on the set likelihood, any one of the specified reading candidates can be determined as the reading of the input character string. Thereby, when there are two or more specified reading candidates, the input support device 100 can appropriately determine the reading of the input character string.

[0134] According to the input support device 100, in the storage unit 410, each of a plurality of homophonic words can be associated with and stored with other words that appeared together with the word in a document created by the user in the past. According to the input support device 100, by referring to the storage unit 410, among one or more created reading candidates, a reading candidate associated with a word that appears in a document identical to the character string can be specified, and a word corresponding to the specified reading candidate can be determined. Thereby, when there are a plurality of homophonic words corresponding to the reading candidate, the input support device 100 can determine which word has the correct reading.

[0135] According to the input support device 100, based on information that enables evaluation of the plausibility of transitions between adjacent characters in a character string, an input error can be detected from a character string input based on a user operation. Thereby, the input support device 100 can accurately detect an input error and improve the estimation accuracy of the correct reading of the character string in which the input error occurred.

[0136] Note that the input support method described in this embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. This input support program is recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, a DVD, or a USB memory, and is executed by being read from the recording medium by a computer. Also, this input support program may be distributed via a network such as the Internet.

Industrial Applicability

[0137] The input support program, input support method, and input support device according to this invention are useful for a computer system that supports character input performed based on a user operation, and in particular, are suitable for a computer system that inputs Japanese based on a user operation.

Explanation of Signs

[0138] 100 Input Support Device 101, 500, 510, 600, 610 Documents 102 Character String 103 Candidate 110, 410 Memory Unit 200 Bus 201 CPU 202 ROM 203 RAM 204 HDD 205 HD 206 RW Drive 207 RW 208 Display 209 Keyboard 210 Mouse 211 Network I / F 300 Co-occurrence Information Management Table 401 Reception Unit 402 Input Error Detection Unit 403 Candidate Creation Unit 404 Candidate Identification Unit 405 Correct Reading Judgment Unit 406 Conversion Unit 407 Output Unit 501, 511, 601, 611 Sentences 513, 613 Conversion Candidates 514, 614 Messages

Claims

1. When an input error is detected from a character string input based on a user operation, one or more reading candidates for the character string are created by performing a predetermined repair process on the input error, referring to a storage unit that stores, in association with each other, words that have co-occurred in documents created by the user in the past, and identifying, from among the one or more created reading candidates, a reading candidate associated with a word that appears in the same document as the character string, determining the reading of the character string based on the identified reading candidate, An input support program characterized by causing a computer to execute the process.

2. Outputting a conversion candidate corresponding to the character string based on the determined reading, The input support program according to claim 1, characterized in that the computer is caused to execute the process.

3. The process of determining is When there is one identified reading candidate, determining the identified reading candidate as the reading of the character string, The input support program according to claim 1 or 2, characterized by this.

4. The process of determining is When there are two or more identified reading candidates, based on the words that appear in the same document as the character string, setting the likelihood of each of the identified reading candidates, and based on the set likelihood, determining any one of the identified reading candidates as the reading of the character string, The input support program according to claim 1 or 2, characterized by this.

5. The storage unit further stores, in association with each other, each of a plurality of homophonous words obtained by converting the same reading into different kana kanji, and other words that have co-occurred with the word in documents created by the user in the past, The process of determining is Referring to the storage unit, identifying a reading candidate associated with a word that appears in the same document as the character string from among the one or more created reading candidates, and determining the word corresponding to the identified reading candidate, The input support program according to claim 1 or 2, characterized by this.

6. Detecting an input error from a character string input based on a user operation based on information that enables evaluation of the plausibility of transitions between adjacent characters in the character string, The input support program according to claim 1 or 2, characterized in that the computer is caused to execute the process.

7. When an input error is detected from a character string input based on a user operation, one or more reading candidates for the character string are created by performing a predetermined repair process on the input error, referring to a storage unit that stores in association words that have co-occurred in documents created by the user in the past, and identifying, from among the one or more created reading candidates, a reading candidate associated with a word that appears in the same document as the character string, determining the reading of the character string based on the identified reading candidate, An input support method characterized in that a computer executes the process.

8. When an input error is detected from a character string input based on a user operation, one or more reading candidates for the character string are created by performing a predetermined repair process on the input error, referring to a storage unit that stores in association words that have co-occurred in documents created by the user in the past, and identifying, from among the one or more created reading candidates, a reading candidate associated with a word that appears in the same document as the character string, determining the reading of the character string based on the identified reading candidate, An input support device characterized by having a control unit.

Images