JP2024030779A - Character input devices, character input methods, and character input programs - Google Patents

Abstract

The present invention provides a character input device, a character input method, and a character input program that can appropriately judge and evaluate a user's knowledge, ability, etc. in a written test conducted at CBT. In a network system in which a plurality of user terminals are connected to a server device via a network for data communication, a server device 1 includes a character recognition section 11a and an output section 11b in a control unit 11 as a character input device. Be prepared. The character recognition unit 11a compares the first shape of the handwritten input character with the second shape of the registered character registered in the dictionary, and recognizes this input character. The output unit 11b outputs characters recognized by the character recognition unit for input characters. Commonly used characters and non-standard characters are registered in the dictionary as registered characters. [Selection diagram] Figure 2

Description

The present invention relates to technology for determining and evaluating a user's academic ability, ability, etc. using a computer.

BACKGROUND ART CBT (Computer Based Testing), which uses a computer to conduct tests to judge and evaluate the knowledge, abilities, etc. of users (test takers), has been widely used. In CBT, problems are displayed on a terminal (computer) display. The user operates an input device such as a mouse and a keyboard provided on the terminal to answer the questions displayed on the display.

Further, Patent Document 1 describes a system for conducting a CBT written test using a tablet terminal that can perform handwritten input.

Japanese Patent Application Publication No. 2011-81024

When performing a written test using handwritten characters in CBT, a handwriting input device is provided for the user to input characters by hand.

When recognizing characters handwritten by a user (hereinafter referred to as handwritten characters), the characters may be replaced with a character string with the highest degree of similarity. Specifically, a feature amount of a handwritten character is extracted, and a similar converted character string estimated from this feature amount is obtained from a dictionary database. That is, even if the user inputs handwritten characters that do not exist in the dictionary database, a converted character string that is the correct answer will be obtained. Therefore, there is a possibility that the user's knowledge, ability, etc. cannot be judged or evaluated appropriately.

An object of the present invention is to provide a technology that can appropriately judge and evaluate the knowledge, ability, etc. of a user who is a test taker when conducting a written test in CBT.

First, the external characters in the present invention will be defined. External characters are character strings that are not registered in character input software such as dictionaries, and include character strings independently registered by the user, character strings containing typographical errors, and created character strings. These external characters are registered in advance by the user who provides the written test at CBT.

In order to achieve the above object, the character input device of the present invention is configured as shown below.

The character input device includes a character recognition section and an output section. The character recognition unit recognizes the input character by comparing the first shape of the handwritten input character with the second shape of the registered character registered in the dictionary. The output unit outputs characters recognized by the character recognition unit for input characters. Commonly used characters and non-standard characters are registered in the dictionary as registered characters.

In this configuration, the first shape of a handwritten character input by a user who is a CBT (Computer Based Testing) examinee by operating a handwriting input device is compared with the second shape of a registered character registered in a dictionary. . This allows handwritten characters to be recognized. By outputting the character string recognized in this way, it is possible to determine whether the answer is correct or incorrect without replacing the character string handwritten by the user with another character string.

For example, an example in which the user inputs the character string "specialty" will be explained. At this time, the user inputs "sen (a character with an apostrophe added that does not exist in the dictionary)" (hereinafter referred to as the external character "sen") and the character string "mon". The character input device inputs the first shape of the private character "Sen" + character string "Mon" (hereinafter referred to as the first character string), and the first shape of the private character "Sen" + character string "Mon" (hereinafter referred to as the second character string) registered in the dictionary. column) with the second shape. The character input device determines that the first shape of the first character string and the second shape of the second character string are the same, and outputs the second character string as an answer.

As a result, if the user remembers handwritten characters incorrectly, the second character string registered as a non-standard character is output as the answer. Therefore, when conducting a written test using CBT, it is possible to appropriately judge and evaluate the knowledge, ability, etc. of the user who is the examinee.

Further, for example, the character recognition unit may recognize the input character as a common character or a custom character that has the highest degree of similarity between the input character and the first shape or the highest degree of similarity between the input character and the second shape. Thereby, it is possible to appropriately determine whether a character is a commonly used character or a non-standard character according to the degree of similarity between the first shape and the second shape.

Also, for example, the character recognition unit recognizes a common character whose first shape has the highest degree of similarity to the input character among common characters, and a common character whose second shape has the highest degree of similarity to the input character among the custom characters. Extract external characters as candidates. The character input device recognizes the selected candidate among the extracted candidates as an input character. Thereby, the first shape of the first character string and the second shape of the second character string can be compared, and the external character with the highest degree of similarity can be extracted as a conversion candidate. That is, even if the character recognition unit makes a misrecognition, it is possible to suppress scoring mistakes.

Further, for example, the character recognition unit extracts the top n characters having a high degree of similarity in the first shape with the input character from among the registered characters as candidates, and inputs the selected candidate from among the extracted candidates. Recognize it as a character. Thereby, it is possible to appropriately determine the input character intended by the user. Furthermore, the user on the scoring side can appropriately score the character string input by the user.

Further, for example, an adjustment unit is provided that adjusts the arrangement of the candidates extracted by the character recognition unit and displays them on the screen of the display device. As a result, the position of the correct answer in the output conversion candidates can be changed for each question, and the user's knowledge, ability, etc. can be judged and evaluated more appropriately.

Further, for example, a scoring section is provided that scores input characters recognized by the character recognition section as answers. Thereby, the user who provides the questions using CBT can easily score the questions.

According to this invention, when conducting a written test using CBT (Computer Based Testing), it is possible to appropriately judge and evaluate the knowledge, ability, etc. of a user who is a test taker.

FIG. 1 is a schematic diagram showing a network system that implements CBT (Computer Based Testing) in a written test. FIG. 2 is a block diagram showing the configuration of the main parts of the server device. FIG. 3 is a block diagram showing the configuration of the main parts of the user terminal. FIG. 4 is an image diagram of a character string displayed on a user terminal. FIG. 5 is a flowchart showing the operation of the server device. FIG. 6 is a flowchart showing the operation of the user terminal. FIG. 7 is an image diagram of a character string displayed on a user terminal in Modification 1. FIG. 8 is a flowchart showing the operation of the server device in the first modification. FIG. 9 is a flowchart showing the operation of the user terminal in Modification 1. FIG. 10 is a block diagram showing the configuration of the main parts of the server device in Modification 2. FIG. 11 is an image diagram of a character string displayed on a user terminal in Modification 2.

Embodiments of this invention will be described below.

<1. Application example＞
FIG. 1 is a schematic diagram showing a network system for conducting a written test using CBT (Computer Based Testing). As shown in FIG. 1, the network system of this example has a configuration in which a plurality of user terminals 2 are connected to a server device 1 via a network 5 for data communication.

Each user terminal 2 is a personal computer or a tablet terminal operated by a user who is a CBT examinee. The server device 1 distributes questions related to a written test conducted in CBT to the user terminal 2, and scores the answers sent from the user terminal 2.

In this example, the character input device according to the present invention is applied to a server device 1.

The server device 1 distributes to the user terminal 2 questions related to a handwritten written test conducted in CBT. The user terminal 2 is equipped with an input device for performing handwritten input. This input device may be one that is traced with a finger on a track pad or the like, or one that inputs information using a mouse on an input pad displayed on the display of the user terminal 2.

The user terminal 2 displays the questions distributed from the server device 1 on the screen of the display device. The user operates an input device (eg, a trackpad) to input an answer to this problem. Here, the user inputs the answer in kanji.

For example, the server device 1 is
Correct the word (senmon) in "(senmon) goes to school" into kanji.
The problem is distributed to the user terminal 2.

A user, who is a test taker, uses the input device of the user terminal 2 to input handwritten characters corresponding to "Senmon". The user terminal 2 outputs the input handwritten characters to the server device 1.

The user inputs the external character "sen" (a character with an apostrophe added that does not exist in the dictionary) and the character "mon". The user terminal 2 transmits the input external character "sen" + character "mon" (hereinafter referred to as the first character string) to the server device 1.

The server device 1 acquires the first character string (the received external character "sen" + character string "mon"). The server device 1 compares the first shape of the first character string and the second shape of the second character string acquired from the dictionary included in the server device 1. The server device 1 acquires a second character string having a second shape similar to the first shape. The server device 1 recognizes the second character string as an answer.

The server device 1 scores each user terminal 2 (that is, each user) to determine whether the user's answer to the question is correct or incorrect.

In this way, in this network system, a second character string similar in shape to the first character string input by the user can be used as an answer, and this answer can be scored. In other words, the character string input by the user can be scored as an answer without replacing the first character string with another character. Therefore, when conducting a written test using CBT, it is possible to appropriately judge and evaluate the knowledge, ability, etc. of the user who is the examinee.

<2. Configuration example>
FIG. 2 is a block diagram showing the configuration of the main parts of the server device in this example. The server device 1 includes a control unit 11, a similar character database 12 (similar character DB12), a dictionary database 13 (dictionary DB13), and a communication section 14.

The control unit 11 controls each part of the server device 1 main body. The control unit 11 also includes a character recognition section 11a, an output section 11b, and a scoring section 11c. The character recognition section 11a, output section 11b, and scoring section 11c included in the control unit 11 will be described later.

The similar character DB 12 is a database in which characters having similar shapes are grouped and stored. The similar character DB 12 includes the above-mentioned external characters.

The similar character DB 12 stores, for example, a group of characters extracted as candidates (a group of characters having similar shape features) for a certain recognized character in character recognition using a well-known OCR (Optical Character Reader). This is a database that is digitized and stored. The dictionary DB 13 is a database in which readings (kana notation), parts of speech, converted character strings (kanji notation), etc. are registered in correspondence. The communication unit 14 performs data communication with the user terminal 2 connected via the network 5.

The similar character DB 12 and the dictionary DB 13 may be, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or another storage medium. Further, the similar character DB 12 and the dictionary DB 13 may be configured by dividing the storage area of a single storage medium, or may be configured by different storage media.

In this similar character DB 12, character strings that do not exist in the dictionary DB 13 (for example, the external character "sen" + character "mon" shown in FIG. 4) are registered. As described above, it is preferable to pre-register in the similar character DB 12 character strings with statistically frequent errors, character strings that are assumed to be written incorrectly by the user, such as the position of a dot, the number of lines, etc., as external characters.

Next, the character recognition section 11a, output section 11b, and scoring section 11c included in the control unit 11 will be explained.

The character recognition unit 11a acquires the first shape of the handwritten character (first character string) received from the user terminal 2. When a character string (second character string) having a shape similar to the first shape does not exist in the dictionary DB 13, the character recognition unit 11a acquires the second shape from the similar character DB 12.

The output unit 11b outputs the second character string to the scoring unit 11c.

The scoring unit 11c scores the second character string acquired from the similar character DB 12 and determines whether the answer is correct or incorrect.

The control unit 11 of the server device 1 is configured by a hardware CPU, memory, and other electronic circuits. When the hardware CPU executes the character input program according to the present invention, it operates as a character recognition section 11a, an output section 11b, and a scoring section 11c. The memory also has an area for developing the character input program according to the present invention and an area for temporarily storing data generated during execution of the character input program. The control unit 11 may be an LSI integrated with a hardware CPU, memory, and the like. Further, the hardware CPU is a computer that executes the character input method according to the present invention.

FIG. 3 is a block diagram showing the configuration of the main parts of the user terminal in this example. The user terminal 2 includes a control section 21, a display 22, an operation section 23, and a communication section 24. The user terminal 2 is a general personal computer or a tablet terminal. FIG. 4 is an image diagram showing conversion candidates displayed on the display 22 in the user terminal of this example. The display 22 includes a handwriting input section 221.

The control unit 21 controls the operation of each part of the user terminal 2 main body.

A screen corresponding to the state of the user terminal 2 is displayed on the display 22. The operation unit 23 includes input devices such as a mouse, a keyboard, and a touch panel. The operation unit 23 receives a user's input operation on the user terminal 2 body. The communication unit 24 performs data communication with the server device 1 connected via the network 5.

The control unit 21 of the user terminal 2 is composed of a hardware CPU, memory, and other electronic circuits. Furthermore, the control unit 21 may be an LSI that integrates a hardware CPU, memory, and the like.

As shown in FIG. 4, the user inputs the external character "sen" + the character "mon" (first character string) into the handwriting input section 221. The user terminal 2 transmits the first character string via the communication unit 24. The character recognition unit 11a of the server device 1 acquires the first shape of the first character string.

Next, the character recognition unit 11a determines whether a character string similar to the first shape exists in the similar character DB 12 and the dictionary DB 13. More specifically, first, the character recognition unit 11a determines whether a character string of a second shape similar to the first shape exists in the dictionary DB13.

If a character string with a second shape similar to the first shape does not exist in the dictionary DB 13, the character recognition unit 11a determines whether a character string with a second shape similar to the first shape exists in the similar character DB 12. . When a character string of a second shape (second character string) similar to the first shape exists in the similar character DB 12, the character recognition unit 11a outputs the second character string to the output unit 11b.

Here, a more specific flow for the character recognition unit 11a to acquire the second character string will be described. The character recognition unit 11a acquires the first shape of the first character string as an image. At this time, the character recognition unit 11a acquires the feature amount of the first shape.

The character recognition unit 11a decomposes the first shape of the first character string input through the operation unit 23 of the user terminal 2 into lines, points, curves, etc., and extracts feature amounts. Specifically, the contour of the first character string is extracted, and the line segments connecting the contours are quantized to be vertical, upward to the right, horizontal, downward to the left, etc., and a direction pattern is created. Note that the feature amount may be extracted based on a change in direction.

Next, the character recognition unit 11a searches for a second character string having a second shape similar to the feature amount of the first shape. First, the character recognition unit 11a searches the dictionary DB 13 for a second character string having the second shape. At this time, the feature amount of the first shape and the feature amount of the second shape are compared.

Furthermore, the character recognition unit 11a searches the similar character DB 12 for a second character string having the second shape. At this time, similarly to when searching the dictionary DB 13, the feature amount of the first shape and the feature amount of the second shape are compared.

Among the feature quantities extracted from the similar character DB 12 and the dictionary DB 13 in this way, the character recognition unit 11a determines that the one with the value closest to the feature quantity of the first shape as the second character string with the highest degree of similarity. judge.

The output unit 11b outputs the second character string to the scoring unit 11c. The scoring unit 11c determines whether the second character string is a correct answer or an incorrect answer. That is, the scoring unit 11c determines that the second character string is an incorrect answer.

The communication unit 14 of the server device 1 transmits to the communication unit 24 of the user terminal 2 that the first character string (external character “sen” + character “mon”) input by the user into the handwriting input unit 221 is an incorrect answer. .

The communication unit 24 outputs the result to the control unit 21. The control unit 21 causes the display 22 to display that the first character string is an incorrect answer.

<3. Operation example>
The operations of the server device 1 and the user terminal 2 when conducting a written test in CBT will be described below. FIG. 5 is a flowchart showing the operation of the server device, and FIG. 6 is a flowchart showing the operation of the user terminal.

The server device 1 uses the communication unit 14 to distribute the written test questions input by hand to the user terminal 2 (S101). The questions distributed by the server device 1 are received by the communication unit 24 of the user terminal 2 via the network 5. For example, the server device 1 is
Correct the word (senmon) in "(senmon) goes to school" into kanji.
The problem is distributed to the user terminal 2.

The user terminal 2 receives, in the communication unit 24, the question distributed from the server device 1 (S201: Yes). The user terminal 2 displays the received question on the display 22 (S202). Note that if the question cannot be received (S201: No), step S201 is executed again.

The user operates an input device such as a touch pad provided on the operation unit 23 to input the answer to the question displayed on the display 22 in handwritten characters (S203). The user inputs, for example, the external character "sen" + the character "mon" (first character string) (see FIG. 4).

The user terminal 2 transmits the first character string to the server device 1 in the communication unit 24 (S204). The user terminal 2 waits to receive the scoring results from the server device 1 (S205).

After distributing the question to the user terminal 2 in step S101, the server device 1 waits to receive an answer from the user terminal 2 (S102). The server device 1 receives, in the communication unit 14, the answer that the user terminal 2 sent in step S204 (S102: Yes).

The character recognition unit 11a of the server device 1 acquires the first shape of the first character string (S103).

Next, the character recognition unit 11a of the server device 1 acquires the feature amount of the first shape of the first character string, and searches whether a character string similar to the first character string exists in the dictionary DB 13 (S104). .

When the character recognition unit 11a of the server device 1 determines that the second character string of the second shape similar to the first shape does not exist (S105: No), it searches the similar character DB 12.

The character recognition unit 11a of the server device 1 searches the similar character DB 12 for the second character string of the second shape (S106), and acquires the second character string having the highest degree of similarity to the first shape. The character recognition unit 11a outputs the second character string to the output unit 11b.

The output unit 11b outputs the second character string to the scoring unit 11c. The scoring unit scores the second character string (S107).

The scoring unit 11c transmits the scoring results to the communication unit 24 of the user terminal 2 via the communication unit 14 (S108).

The communication unit 24 receives the scoring results (S205). The communication unit 24 outputs the scoring results to the control unit 21. The control unit 21 causes the display 22 to display the scoring results.

The server device 1 performs scoring in step S108 and determines whether the answer is correct or incorrect. If the server device 1 determines that the answer is incorrect, it may output the answer to the user terminal 2 so as to explicitly display the incorrect part. This allows the user to easily recognize the incorrect location.

Therefore, in this network system, the user can score the handwritten characters input by the user at the user terminal 2 without replacing them with other characters (character strings). Therefore, when conducting a written test using CBT, it is possible to appropriately judge and evaluate the knowledge, ability, etc. of the user who is the examinee.

In the above description, the flow of searching the dictionary DB 13 in step S104 and then searching the similar character DB 12 in step S106 was explained. However, the configuration may be such that the dictionary DB 13 is searched after the similar character DB 12 is searched.

Furthermore, in the above description, the character string having the highest degree of similarity to the first shape was described as the second character string. However, a configuration may also be adopted in which a threshold value is set in advance, and when the degree of similarity is less than this threshold value, a message to the effect that the character string cannot be recognized is transmitted to the user terminal 2. At this time, the threshold value is preferably determined according to the type of character string (kanji, hiragana, katakana, numbers, alphabetic characters).

In addition, in the above explanation, the case where the server device 1 distributes the questions one by one to the user terminal 2 is used as an example, but the server device 1 distributes a plurality of questions at once to the user terminal 2, and Alternatively, a configuration may be adopted in which a process for receiving answers from the user terminal 2 is performed.

In addition, in the above-mentioned structure, the example which acquired the 1st shape of a 1st character string as an image was shown. However, it is not limited to acquiring as an image. For example, stroke data obtained from the movement direction and speed of a touch pen or finger when performing handwriting input may be acquired. In other words, the character recognition unit 11a may acquire the first shape by extracting the vector amount of the first character.

<4. Modification example 1>
Next, a character input device according to Modification 1 will be described with reference to the drawings. In configuration example 1, a handwritten first character string is transmitted, whereas in modification example 1, the result of recognizing the first character string is displayed as a conversion candidate. The rest of the configuration is the same as the character input device in configuration example 1, and a description of the similar parts will be omitted.

FIG. 7 is an image diagram of a character string displayed on a user terminal in Modification 1. FIG. 8 is a flowchart showing the operation of the server device in Modification 1. FIG. 9 is a flowchart showing the operation of the user terminal in Modification 1.

The specific process flow will be explained. As shown in FIG. 7, the display 22 of the user terminal 2 includes a handwriting input section 221 and a candidate display section 222. The user inputs the external character "sen" + the character "mon" (first character string) into the handwriting input section 221. The user terminal 2 transmits the first character string via the communication unit 24. The character recognition unit 11a of the server device 1 acquires the first shape of the first character string.

As described above, the character recognition unit 11a obtains a second character string similar to the first character string. The user terminal 2 acquires the second character string with the highest degree of similarity via the communication unit 24 . As a result, the control unit 21 causes the candidate display unit 222 to display the second character string.

The user confirms the second character string displayed on the candidate display section 222. Next, the user selects the second character string and transmits the answer to the server device 1.

Next, a specific process flow will be explained using FIGS. 8 and 9. Note that the steps up to step S103 in FIG. 8 and up to step S204 in FIG. 9 are the same as the configuration of the above-described configuration example.

The server device 1 uses the communication unit 14 to distribute the written test questions input by hand to the user terminal 2 (S101). The questions distributed by the server device 1 are received by the communication unit 24 of the user terminal 2 via the network 5. For example, the server device 1 is
Correct the word (senmon) in "(senmon) goes to school" into kanji.
The problem is distributed to the user terminal 2.

The user terminal 2 receives, in the communication unit 24, the question distributed from the server device 1 (S201: Yes). The user terminal 2 displays the received question on the display 22 (S202). Note that if the question cannot be received (S201: No), step S201 is executed again.

The user operates an input device such as a touch pad provided on the operation unit 23 to input the answer to the question displayed on the display 22 in handwritten characters (S203). The user inputs, for example, the external character "sen" + the character "mon" (first character string) (see FIG. 7).

The user terminal 2 transmits the first character string to the server device 1 through the communication unit 24 (S204). The user terminal 2 waits to receive conversion candidates from the server device 1 (S211).

After distributing the question to the user terminal 2 in step S101, the server device 1 waits to receive the first character string from the user terminal 2 (S102). The server device 1 receives, in the communication unit 14, the first character string that the user terminal 2 transmitted in step S204 (S102: Yes).

The character recognition unit 11a of the server device 1 acquires the first shape of the first character string (S103).

Next, the character recognition unit 11a of the server device 1 searches the dictionary DB 13 for a character string similar to the first shape of the first character string (S104).

When the character recognition unit 11a of the server device 1 determines that the second character string of the second shape similar to the first shape does not exist (S105: No), it searches the similar character DB 12. If the character recognition unit 11a determines that the second character string exists, it outputs the second character string to the output unit 11b. Next, step S111 shown below is executed.

The character recognition unit 11a of the server device 1 searches the similar character DB 12 for the second character string of the second shape (S106), and acquires the second character string. The character recognition unit 11a outputs the second character string to the output unit 11b.

The output unit 11b transmits the conversion candidates to the user terminal 2 via the communication unit 14 (S111).

The communication unit 24 of the user terminal 2 receives the second character string as a conversion candidate (S211: Yes). If the communication unit 24 cannot receive a conversion candidate (S211: No), it waits until it receives a conversion candidate.

The control unit 21 displays the received conversion candidate (second character string) on the candidate display unit 222 (see FIG. 7) of the display 22 (S212).

The control unit 21 determines whether the conversion candidate displayed on the candidate display unit 222 has been selected (S213). The control unit 21 detects that the user has selected a conversion candidate in the candidate display unit 222 (S213: Yes), and transmits the selected candidate as an answer to the server device 1 via the communication unit 24 (S214). ). Note that the control unit 21 waits until a conversion candidate is selected (S213: No).

The communication unit 14 of the server device 1 receives the answer (S112: Yes). The communication unit 14 outputs the answer to the scoring unit 11c. Note that the communication unit 14 waits until receiving the answer (S112: No).

The scoring unit 11c performs scoring (S113). The scoring unit 11c transmits the scoring results to the user terminal 2 via the communication unit 14 (S114).

The communication unit 24 receives the scoring results (S215). The communication unit 24 outputs the scoring results to the control unit 21. The control unit 21 causes the display 22 to display the scoring results.

Even with such a configuration, the user can select the intended first character string. Furthermore, on the server device 1 side as well, it becomes possible to appropriately score the first character string selected by the user.

<5. Modification example 2>
Next, a character input device according to modification 2 will be described with reference to the drawings. Modification 2 differs in that a plurality of (top n, n is an integer value) conversion candidates are obtained in order of similarity. The rest of the configuration is the same as the character input device in Modification 1, and a description of the similar parts will be omitted.

FIG. 10 is a block diagram showing the configuration of the main parts of the server device in Modification 2. FIG. 11 is an image diagram of a character string displayed on a user terminal in Modification 2.

As shown in FIG. 10, the server device 1 includes an adjustment section 11d. The character recognition unit 11a acquires a plurality of second character strings that are recognized to be similar to the first character string. At this time, the character recognition unit 11a acquires a plurality of (top n) second character strings in descending order of similarity to the first character string. More specifically, in step S111 of the flowchart of FIG. 8 (modification 1), a plurality of conversion candidates (top n) may be transmitted in descending order of similarity.

The character recognition unit 11a outputs the plurality of second character strings to the adjustment unit 11d. The adjustment unit 11d rearranges the plurality of second character strings in descending order of similarity, and transmits the second character strings to the user terminal 2 via the communication unit 14.

The specific process flow will be explained. As shown in FIG. 11, the display 22 of the user terminal 2 includes a handwriting input section 221 and a candidate display section 222. The user inputs the external character "sen" + the character "mon" (first character string) into the handwriting input section 221. The user terminal 2 transmits the external character "sen" + the character "mon" (first character string) via the communication unit 24. The character recognition unit 11a of the server device 1 acquires the first shape of the first character string.

As described above, the character recognition unit 11a acquires a plurality of second character strings similar to the first character string (for example, character strings "special question", "specialty", etc.). The user terminal 2 acquires the plurality of second character strings via the communication unit 24. Accordingly, the control unit 21 causes the candidate display unit 222 to display the plurality of second character strings. At this time, the plurality of second character strings may be displayed in descending order of similarity.

The user selects an answer from the plurality of second character string candidates displayed on the candidate display section 222 and transmits the answer to the server device 1 .

With this configuration, the first character string that the user intends can be selected. Furthermore, on the server device 1 side as well, it becomes possible to appropriately score the first character string selected by the user.

In the above example, the adjustment unit 11d displays a plurality of second character strings in descending order of similarity. However, when the adjustment unit 11d determines that the display order of the correct answer is high, the adjustment unit 11d may be configured to display the correct answer with a low priority.

<6. Modification example 3>
The configuration of the character recognition unit 11a, output unit 11b, scoring unit 11c, and adjustment unit 11d included in the control unit 11 of the server device 1, shown in the above configuration, may be provided in the control unit 21 of the user terminal 2. . With this configuration, the user terminal can also be used as a learning terminal for the user to prepare and review.

Further, in the above example, the character recognition unit 11a is configured to extract characters with similar shapes from among the characters in the similar character DB 12 and the dictionary DB 13. Characters generated by replacing biases, adding or deleting points to the character structure, or adding or deleting horizontal bars or vertical bars (characters that do not exist may be used) are similar in shape. It may be configured to extract as characters.

Furthermore, the present invention is not limited to specific types of certification exams or subjects, and can be used to conduct written exams in CBT.

It should be noted that the present invention is not limited to the above-described embodiments as they are, but can be implemented by modifying the constituent elements within the scope of the invention at the implementation stage. Moreover, various inventions can be formed by appropriately combining the plurality of components disclosed in the above embodiments. For example, some components may be deleted from all the components shown in the embodiments. Furthermore, components from different embodiments may be combined as appropriate.

Furthermore, the correspondence between the configuration according to the present invention and the configuration according to the above-described embodiments can be described as in the following supplementary notes.
<Additional notes>
a character recognition unit (11a) that recognizes the input character by comparing a first shape of the handwritten input character with a second shape of the registered character registered in a dictionary;
an output unit (11b) that outputs characters recognized by the character recognition unit (11a) for the input characters;
In the dictionary, commonly used characters and non-standard characters are registered as the registered characters.
Character input device (1).

1... Server device 2... User terminal 5... Network 11... Control unit 11a... Character recognition section 11b... Output section 11c... Scoring section 11d... Adjustment section 12... Similar character database (similar character DB)
13...Dictionary database (dictionary DB)
14...Communication unit 21...Control unit 22...Display unit 23...Operation unit 24...Communication unit 221...Handwriting input unit 222...Candidate display unit

Claims (8)

a character recognition unit that recognizes the input character by comparing a first shape of the handwritten input character with a second shape of the registered character registered in a dictionary;
an output unit that outputs characters recognized by the character recognition unit for the input characters,
In the dictionary, commonly used characters and non-standard characters are registered as the registered characters.
Character input device. The character recognition unit recognizes that the input character is the common character or the external character with the highest degree of similarity between the input character and the first shape or the highest degree of similarity between the input character and the second shape.
The character input device according to claim 1. The character recognition unit is
Among the common characters, the common character having the highest degree of similarity in a first shape with the input character, and among the foreign characters, the foreign character having the highest degree of similarity in a second shape with the input character. Extract as,
Recognizing a selected candidate among the extracted candidates as the input character;
The character input device according to claim 1. The character recognition unit is
Extracting the top n characters having a high degree of similarity in first shape with the input character from among the registered characters as candidates;
recognizing a selected candidate among the extracted candidates as the input character;
The character input device according to claim 1. 5. The character input device according to claim 3, further comprising an adjustment section that adjusts the arrangement of candidates extracted by the character recognition section and displays them on a screen of a display device. 5. The character input device according to claim 3, further comprising a scoring section that scores the input characters recognized by the character recognition section as answers. a character recognition step of comparing a first shape of an input character entered by handwriting with a second shape of a registered character registered in a dictionary, and recognizing the input character;
For the input character, the computer executes an output step of outputting the character recognized in the character recognition step,
In the dictionary, commonly used characters and non-standard characters are registered as the registered characters.
Character input method. a character recognition step of comparing a first shape of an input character entered by handwriting with a second shape of a registered character registered in a dictionary, and recognizing the input character;
causing the computer to perform an output step of outputting the characters recognized in the character recognition step for the input characters;
In the dictionary, commonly used characters and non-standard characters are registered as the registered characters.
Character input program.

Images