JP7739706B2 - Input support device, input support system and program - Google Patents

Description

The present invention relates to an input support device, an input support system, and a program.

Patent Document 1 describes a program that causes a computer to input a first original language in a first language system and a second original language in a second language system that is a bilingual translation of the first original language, and to output second co-occurring words in the second language system that are appropriate for use with the first original language. The program includes a first co-occurring word extraction means that uses a corpus dictionary of the first language system to extract multiple first co-occurring words that co-occur with the first original language, and a bilingual dictionary of the first language system that extracts pairs of the first co-occurring words. This disclosure discloses a program that causes a computer to function as a first bilingual co-occurrence word extraction means that extracts second bilingual co-occurrence words that serve as translations, a first occurrence frequency search means that uses a corpus dictionary of a second language system to search for the occurrence frequency for each word string that combines a second original language and a second bilingual co-occurrence word, and a co-occurrence word determination means that determines the second bilingual co-occurrence word in the word string with the highest occurrence frequency as a second co-occurrence word that is appropriate for use with the first original language.

Patent document 2 discloses an electronic dictionary comprising: an input means for inputting phonetic notations; dictionary body data consisting of headwords and their corresponding translations; pronunciation rule data indicating the correspondence between characters input by the input means and characters in the language of the headwords; phonetic notation-to-character conversion means for converting the phonetic notation input by the input means into characters in the language of the headwords using the pronunciation rule data; extraction means for extracting from the dictionary body data headwords that contain characters that match the characters converted by the phonetic notation-to-character conversion means; and display means for displaying the headwords extracted by the extraction means.

Japanese Patent Application Laid-Open No. 2015-143907 Japanese Patent Application Laid-Open No. 2007-317163

The present invention aims to provide an input support device, input support system, and program that can provide input candidate support when a user whose native language is a first language inputs characters in a second language different from the first language, even when the second language is deemed invalid.

Incorrect entry refers to entering a string of characters that is not used in the second language or entering it incorrectly by the user.

The present invention according to claim 1 is an input support system comprising: a related word storage unit that stores related words in a second language that correspond to character strings in a first language in association with each other; a user information storage unit that stores user information including information about the user's native language; and a processor, wherein the processor identifies the user's native language based on the user information acquired from the user information storage unit; and, if a character string input by a user whose native language is the first language is determined to be invalid in light of the structure of a second language different from the first language, acquires related words in the second language that are linked to the character string in the first language that are stored in the related word storage unit, and outputs candidate character strings that are predicted using the acquired related words; and, if there is a possibility that the character string input by the user whose native language is the first language is either invalid or not invalid in light of the structure of the second language different from the first language, also outputs candidate character strings that are predicted from the input character string in the first language .
The present invention according to claim 2 is an input support system comprising: a related word storage unit that stores related words in a second language that correspond to character strings in a first language in association with each other; a user information storage unit that stores user information including information about the user's native language; and a processor, wherein the processor identifies the user's native language based on the user information acquired from the user information storage unit; and, if a character string input by a user whose native language is the first language is determined to be invalid in light of the structure of a second language different from the first language, acquires related words in the second language that are associated with the character string in the first language that are stored in the related word storage unit, and outputs candidate character strings that are predicted using the acquired related words; and, if there is both a possibility that the character string input by the user whose native language is the first language is invalid and a possibility that it is not invalid in light of the structure of the second language different from the first language, the processor preferentially outputs candidate character strings that are predicted using the acquired related words or candidate character strings that are predicted using the character string in the input first language .

Note that here, a string may contain only one character.

The present invention according to claim 3 is the input support system according to claim 1 or 2, wherein the processor determines that a character string input using the pronunciation in the first language is invalid in light of the structure of the second language .

The present invention according to claim 4 is the input support system according to claim 3, wherein the processor analyzes an input character string in a first language to determine whether the character string is invalid in light of the structure of the second language .

The present invention according to claim 5 is an input support system according to any one of claims 1 to 4, wherein the processor determines that a character string input by an input device having a character arrangement corresponding to a first language is invalid in a second language .

A sixth aspect of the present invention is the input support system according to the fifth aspect, wherein the processor acquires type information of the input device used by the user .

The present invention according to claim 7 is as follows.

The present invention according to claim 8 is:

According to the present invention as set forth in claim 1 or 7 , when a user whose native language is a first language inputs characters in a second language different from the first language, input candidate assistance can be provided even when the second language is determined to be incorrect. Furthermore, related words can be obtained whether the input is incorrect or correct.
According to the present invention as set forth in claim 2 or 8 , when a user whose native language is a first language inputs characters in a second language different from the first language, input candidate support can be provided even when the second language is determined to be invalid. Furthermore, related words can be acquired by prioritizing either the incorrect answer or the correct answer.

According to the present invention as set forth in claim 3 , in addition to the effect of the present invention as set forth in claim 1 or 2 , it is possible to determine fraud when a user inputs using the pronunciation in the first language.

According to the fourth aspect of the present invention, in addition to the effect of the third aspect of the present invention, it is possible to determine whether or not an input character string is fraudulent.

According to the fifth aspect of the present invention, in addition to the effect of any one of the first to fourth aspects of the present invention, it is possible to determine whether or not an illegal act has occurred based on the state of the character string input by the input device.

According to the sixth aspect of the present invention, in addition to the effect of the fifth aspect of the present invention, the arrangement state of the character strings can be acquired.

1 is a block diagram illustrating a document management system according to an embodiment of the present invention. 1 is a diagram showing a data structure of a user information database used in an embodiment of the present invention. 1 is a diagram showing a data structure of a language correspondence database used in an embodiment of the present invention. 1 is a diagram showing a data structure of a search keyword database used in an embodiment of the present invention. 1 is a block diagram showing hardware of an input support device according to an embodiment of the present invention. 1 is a flowchart showing an operation flow in the first embodiment of the present invention. FIG. 1 is a configuration diagram showing a first example according to a first embodiment of the present invention. FIG. 10 is a configuration diagram showing a second example according to the first embodiment of the present invention. FIG. 10 is a configuration diagram showing a third example according to the first embodiment of the present invention. FIG. 10 is a configuration diagram showing a fourth example according to the first embodiment of the present invention. FIG. 10 is a configuration diagram showing a fifth example according to the first embodiment of the present invention. 1A is a plan view showing a QWERTY keyboard (Japanese) and FIG. 1B is a plan view showing an AZERTY keyboard (French) for comparison. 10 is a flowchart showing an operation flow according to a second embodiment of the present invention.

Next, an embodiment of the present invention will be described in detail with reference to the drawings.

Figure 1 shows an entire input support system 10 according to an embodiment of the present invention. The input support system 10 has an input support device 12, which is constituted, for example, by a server. This input support device 12 is connected to a user information database 14, a language support database 16, a search keyword base 18, and a search target database 20. The input support device 12 supports input made by a user via a terminal device 22 based on data registered in these databases 14, 16, 18, and 20, and provides input support when searching in a second language different from the first language, which is the user's native language.

A terminal device 22 is connected to the input support device 12 via a network such as a LAN (Local Area Network) or the Internet. The terminal device 22 is, for example, a personal computer, and has a display device 24 and an input device 26, for example, a keyboard.

Note that the input device 26 includes not only a keyboard but also a voice input device for voice input.

The user information database 14 constitutes the user information storage unit and stores user information. As shown in Figure 2, the user information includes a user ID for identifying the user, a password, information about the user's native language (first language), and information about the type of keyboard used by the user.

The language correspondence database 16 constitutes the related word storage unit, and as shown in FIG. 3, is a database in which character strings in a second language are linked to and registered with character strings in a first language. For example, if the first language is Chinese and the keyboard layout is a Pinyin keyboard, "shi" in the second language, Japanese, is linked and registered to correspond to "Xi" and "Si." If the first language is Korean and the keyboard layout is Roman alphabetb, "Che" is linked to "Choi" and "Kin" is linked to "Gim." If the first language is French and the keyboard layout is AZERTY, "Sa" is linked to "Sq" and "Ka" is linked to "Kq."

As shown in Figure 4, the search keyword database 18 is a database in which predicted keywords are registered using the input or converted related words as headings. For example, if the heading is "shi", then "product", "new product", "new product", etc. are registered. The search target database 20 is a database in the second language that is the target of the search, and may be the same as the search keyword database.

Figure 5 shows a block diagram of the hardware of the input support device 12.

The input support device 12 has a processor (CPU 28), memory 30, storage device 32, input/output interface 34, and communication interface 36, which are connected via a bus 38.

The CPU 28 executes predetermined processes based on control programs stored in the memory 30. The storage device 32, which is composed of, for example, a hard disk, stores the necessary software and data. The communication interface 34 is connected to the aforementioned network and inputs and outputs data via the network.

Figure 3 shows a flowchart for the first embodiment.

In step S10, when the user logs in, the CPU 28 executes login processing. In the next step S12, the CPU 28 acquires user information. As described above, the user information includes information about the user's first language. In the next step S14, when the user inputs a string of characters, the CPU 28 accepts the input string information.

In the next step S16, the CPU 28 determines whether the character string received in step S14 is invalid in the second language. The aforementioned memory 32 stores structural information for the second language, and the CPU 28 analyzes the structure of the input character string and determines whether the analyzed character string is invalid in light of the structure of the second language. For example, in Japanese, "xi" can be input as "ィ", but "ィ" is never used as the first character, so it is determined to be invalid. Furthermore, the character string "kexi" does not exist in Japanese, so it is determined to be invalid.

If it is determined in step S16 that the received character string is invalid in the second language, the process proceeds to step S18. In step S18, it is determined whether or not there is a related word corresponding to the received character string in the language correspondence database 16. As shown in Figure 3, "xi" is linked to the related word "shi", so it is determined that there is a related word. If it is determined in step S18 that there is a related word, the process proceeds to step S20, where the character is converted into the linked second language.

On the other hand, if it is determined in step S16 that the received character string is not invalid in the second language, i.e., is correct, or if it is determined in step S18 that there are no related words in the language correspondence database 16 that correspond to the received character string, the process proceeds to step S22. In step S22, keyword candidates corresponding to the input character string are obtained from the search keyword database 18. In the next step S24, the keyword candidates obtained in step S22 are presented to the user, for example, by displaying them on the display device 24 of the terminal device 22.

In the next step S26, it is determined whether additional characters have been input. If it is determined that additional characters have been input, the process returns to step S16. If it is determined that additional characters have not been input, the process proceeds to step S28, where a search is performed using the input string or the selected candidate, and the process ends.

Figure 7 shows a first example of the first embodiment.

A user's native language is Chinese and they use a Pinin keyboard. Suppose this user types "xi." In step S16 described above, "xi" is determined to be invalid in Japanese, the user's second language. However, since the Japanese character "shi" is associated with "Xi" in the language correspondence database 16, it is determined in step S18 that there is a related word, and it is converted to the Japanese character "shi" in step S20. The search keyword database 18 is searched for products, new products, and new arrivals for the heading "shi," and these are presented to the user. Next, the search target database 20 is searched for "shi," but this search target database 20 may be the same as the search keyword database 18.

In addition, if a Chinese pronunciation similar to "xi" is entered using a voice input device, it will be converted to the Japanese "shi" on the keyboard, just like "xi."

Figure 8 shows a second example of the first embodiment.

A user's native language is Japanese and they use a QWERTY (English) keyboard. Suppose this user types "play." When a user whose native language is Japanese hears a second language, they have difficulty distinguishing between "l" and "r," and are also prone to confusing "e" and "a." For this reason, the language correspondence database 16 associates "Play," "play," and "prey" with "play." Therefore, the search keyword database 18 is searched using the headings "Play," "play," and "prey," and the search results are presented to the user. Next, the search target database 20 is searched for "Play," "play," and "prey," but this search target database 20 may be the same as the search keyword database 18.

Figure 9 shows a third example of the first embodiment.

The user's native language is Japanese and they use a QWERTY (English) keyboard. Let's say the user types "zyou." In the language correspondence database 16, "zhou" is associated with "zyou." Therefore, the search keyword database 18 is searched using the heading "zhou," and the search results presented to the user are "Zhou," "Zhou," and "Broom." The search target database 20 is searched for "Zhou," "Zhou," and "Broom," but this search target database 20 may be the same as the search keyword database 18.

Figure 10 shows a fourth example of the first embodiment.

The user's native language is Korean, and the keyboard layout is Korean romanization. Let's say the user types "choi." In Japanese, "choi" is pronounced "choi," but in Korean it is pronounced "che." Therefore, it is thought that the user intended to type "che" but mistakenly typed "choi." In the language correspondence database 16, "che" is associated with "choi." Therefore, the search keyword database 18 is searched using the heading "che," and the search results presented to the user are "check out," "check in," and "chain store."

However, the user's intention may be "Choi" rather than "Che." Therefore, instead of using only "Che" as a headline, a search keyword database may be performed using "Choi" as a headline. In other words, if a character string entered by a user whose native language is a first language is either incorrect or correct depending on the second language different from the first language, both may be presented. Furthermore, rather than presenting both the incorrect and correct answers, only one may be presented at the user's choice. Furthermore, the answers may be presented at different times, such as presenting one first and the other later.

Figure 11 shows a fifth example related to the first embodiment.

The user's native language is French, and they use an AZERTY keyboard. As shown in Figure 12, when compared to a QWERTY keyboard (Japanese), the AZERTY keyboard (French) has a "q" key instead of the "a" key on a QWERTY keyboard. Suppose this user types "sq." Although "sq" is not used in Japanese, it is likely that the user intended to type "sa" but mistakenly typed "sq." In the language correspondence database 16, "sa" is associated with "sq." Therefore, the search keyword database 18 is searched using the heading "sa," and the search results presented to the user are "restart," "check in," and "chain store."

Figure 13 shows a flowchart for the second embodiment.

This second embodiment differs from the first embodiment in that it determines a language as invalid if it cannot be used as a second language.

That is, in the first embodiment, if it is determined in step S16 that the input string is not invalid in the second language, processing is performed in step S22 to obtain keyword candidates corresponding to the input string, but there may be cases where there are no keyword candidates. Taking this into consideration, the next step S30 determines whether there are any keyword candidates. If it is determined in step S30 that there are no keyword candidates, the process returns to step S18, and it is determined whether there are any corresponding related words in the language correspondence database.

The subsequent processing is the same as in the first embodiment, so the same step numbers are used and the explanation is omitted.

For example, if a user's native language is Chinese and their second language is Japanese, and they enter "uxiga," even if "uiga" is not determined to be invalid in step S16, it is unfamiliar in Japanese, so there are no keyword candidates in step S30 and the process returns to step S18. Since "xi" is linked to "shi" in the language correspondence database 16, it is determined in step S18 that there is a corresponding related word, and in the next step S20, "uxiga" is converted to "ushiga." Then, in the next step S22, using "ushiga" as the heading, keyword candidates such as "ushiga," "ushigaeru," and "ushikaeru" are detected and presented to the user.

In the above embodiment, the term "processor" refers to a processor in a broad sense, including general-purpose processors (e.g., CPU: Central Processing Unit, etc.) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

Furthermore, the processor operations in each of the above embodiments may not only be performed by a single processor, but may also be performed by multiple processors located in physically separate locations working together. Furthermore, the order of the processor operations is not limited to the order described in each of the above embodiments, and may be changed as necessary.

REFERENCE SIGNS LIST 10 Input support system 12 Input support device 14 User information database 16 Language correspondence database 18 Search keyword database 20 Search target database 22 Terminal device 24 Display device 26 Input device 28 CPU
30 Memory 32 Storage device 34 Input/output interface 36 Communication interface 38 Bus

Claims (8)

a related word storage unit that stores related words in a second language corresponding to character strings in a first language in association with each other ;
a user information storage unit that stores user information including information on the user's native language;
an input support device having a processor,
The processor:
Identifying the user's native language based on the user information acquired from the user information storage unit;
When a character string entered by a user whose native language is a first language is determined to be invalid in light of the structure of a second language different from the first language, a related word in the second language associated with the character string in the first language stored in the related word storage unit is acquired;
Outputs candidate strings predicted based on the related words obtained,
If a character string entered by a user whose native language is a first language is either invalid or not in light of the structure of a second language different from the first language, candidate character strings predicted from the character string in the entered first language are also output.
Input support system. a related word storage unit that stores related words in a second language corresponding to character strings in a first language in association with each other ;
a user information storage unit that stores user information including information on the user's native language;
an input support device having a processor,
The processor:
Identifying the user's native language based on the user information acquired from the user information storage unit;
When a character string entered by a user whose native language is a first language is determined to be invalid in light of the structure of a second language different from the first language, a related word in the second language associated with the character string in the first language stored in the related word storage unit is acquired;
Outputs candidate strings predicted based on the related words obtained,
When a character string entered by a user whose native language is a first language may or may not be invalid in light of the structure of a second language different from the first language, the system preferentially outputs either a character string candidate predicted by the acquired related words or a character string candidate predicted by the character string in the entered first language.
Input support system. 3. The input support system according to claim 1, wherein the processor determines that a character string input using the pronunciation in the first language is invalid in light of the structure of the second language. 4. The input support system according to claim 3 , wherein the processor analyzes an input character string in the first language to determine whether the character string is invalid in light of the structure of the second language. 5. The input support system according to claim 1, wherein the processor determines that a character string input by an input device having a character arrangement corresponding to a first language is invalid in the second language. 6. The input support system according to claim 5 , wherein the processor acquires type information of the input device used by the user. A program for controlling the operation of an input support system having an associated word storage unit that stores associated words in a second language corresponding to a character string in a first language, a user information storage unit that stores user information including information on the user's native language, and an input support device,
Identifying the native language of the user based on the user information acquired from the user information storage unit;
a step of acquiring related words in the second language associated with the character string in the first language stored in the related word storage unit when the character string entered by the user whose native language is the first language is determined to be invalid in light of the structure of a second language different from the first language;
a step of outputting character string candidates predicted by the acquired related words;
a step of outputting, when a character string input by a user whose native language is a first language is either invalid or not in light of the structure of a second language different from the first language, also candidates for a character string predicted from the character string in the input first language;
A program that causes a computer to execute the following. A program for controlling the operation of an input support system having an associated word storage unit that stores associated words in a second language corresponding to a character string in a first language, a user information storage unit that stores user information including information on the user's native language, and an input support device,
Identifying the native language of the user based on the user information acquired from the user information storage unit;
a step of acquiring related words in the second language associated with the character string in the first language stored in the related word storage unit when the character string entered by the user whose native language is the first language is determined to be invalid in light of the structure of a second language different from the first language;
a step of outputting character string candidates predicted by the acquired related words;
a step of preferentially outputting, when there is a possibility that a character string input by a user whose native language is a first language may or may not be invalid in light of the structure of a second language different from the first language, a character string candidate predicted by the acquired related words or a character string candidate predicted by the character string in the input first language;
A program that causes a computer to execute the following.