JP7698866B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Technologies for acquiring the difficulty level of text have existed for some time. The difficulty level estimation device described in Patent Document 1 performs morphological analysis on the text of a picture book for which the difficulty level is to be acquired, and calculates the occurrence frequency of each of the words that make up the text. The difficulty level estimation device also stores, for each difficulty class of the text, the occurrence probability of each of the words included in the text to which that difficulty class has been assigned. The difficulty level estimation device estimates the likelihood that the text of the picture book belongs to a difficulty class based on the calculated occurrence frequency of each word and the stored occurrence probability. The difficulty level estimation device then estimates the difficulty class with the highest likelihood among the estimated likelihoods as the text of the picture book.

JP 2016-152033 A

The difficulty level estimation device described above estimates the difficulty class of a picture book text based on a morphological analysis of the text. However, morphological analysis may not be able to perform an accurate analysis when there is a relatively large number of hiragana characters in the text. In other words, when the picture book text to be estimated for difficulty contains a relatively large number of hiragana characters, the difficulty level estimation device described above may not be able to accurately estimate the difficulty class of the text.

The difficulty of a text is also related to the readability of the text. As an example, as a user (e.g., an elementary school student) learns kanji in elementary school, etc., they will be able to read a relatively difficult text even if the text contains a relatively large number of kanji (according to their grade). For this reason, it is necessary to estimate the difficulty of the text, i.e., the readability of the text, so that the user can read the text according to their learning situation (level of comprehension).

The present invention aims to provide an information processing device, an information processing method, and an information processing program that can obtain the readability of text.

An information processing device of one embodiment includes a first acquisition unit that acquires text information in which text is recorded, a second acquisition unit that acquires a proportion of hiragana characters used in the text based on the text information acquired by the first acquisition unit, a calculation unit that calculates the readability of the text recorded in the text information based on the proportion of hiragana characters acquired by the second acquisition unit, and an output control unit that controls the readability of the text calculated by the calculation unit to be output.

In one aspect of the information processing method, a computer executes a first acquisition step of acquiring text information in which text is recorded, a second acquisition step of acquiring a proportion of hiragana characters used in the text based on the text information acquired by the first acquisition step, a calculation step of calculating the readability of the text recorded in the text information based on the proportion of hiragana characters acquired by the second acquisition step, and an output control step of controlling the readability of the text calculated by the calculation step to be output.

An information processing program according to one embodiment causes a computer to realize a first acquisition function that acquires text information in which text is recorded, a second acquisition function that acquires the proportion of hiragana characters used in the text based on the text information acquired by the first acquisition function, a calculation function that calculates the readability of the text recorded in the text information based on the proportion of hiragana characters acquired by the second acquisition function, and an output control function that controls the output of the readability of the text calculated by the calculation function.

An information processing device of one embodiment acquires text information in which text is recorded, acquires the proportion of hiragana used in the text based on the text information, calculates the readability of the text recorded in the text information based on the proportion of hiragana, and controls the output of the calculated readability of the text, thereby obtaining the readability of the text.
The information processing method and the information processing program according to one aspect can achieve the same effects as the information processing device according to the above aspect.

FIG. 1 is a diagram illustrating an information processing device according to an embodiment. FIG. 1 is a block diagram illustrating an information processing device according to an embodiment. 1 is a first flowchart illustrating an information processing method according to an embodiment. 11 is a second flowchart illustrating an information processing method according to an embodiment.

One embodiment of the present invention is described below.

[Overview of information processing device 1]
First, an overview of an information processing device 1 according to an embodiment will be described.
FIG. 1 is a diagram illustrating an information processing device 1 according to an embodiment.

The information processing device 1 may be a computer such as a server, desktop, laptop, or tablet. The information processing device 1 acquires the readability of the text recorded in the text information 100 based on the text information 100 generated from various contents. The text information 100 may be information in which characters such as kanji, hiragana, and katakana are recorded. The readability of the text may be considered, for example, as the difficulty level of the text. In this case, the information processing device 1 may acquire the readability of the text based on the ratio of the ratio of hiragana written in the text. The ratio of hiragana may be, for example, the ratio of hiragana to all or a part (a specified range) of characters (kanji and hiragana, etc.) in the text. Or, the ratio of hiragana may be, for example, the ratio of kanji and hiragana to all or a part (a specified range) of characters in the text.

[Details of information processing device 1]
Next, details of the information processing device 1 according to an embodiment will be described.
FIG. 2 is a block diagram for explaining the information processing device 1 according to an embodiment.

The information processing device 1 includes a communication unit 21, a memory unit 22, a display unit 23, and a control unit 10. The communication unit 21, the memory unit 22, and the display unit 23 may be an embodiment of an "output unit". The control unit 10 may be configured, for example, by an arithmetic processing device of the information processing device 1. The control unit 10 may function, for example, as a first acquisition unit 11, a second acquisition unit 12, a third acquisition unit 13, a fourth acquisition unit 14, a calculation unit 15, a rewriting unit 16, a first identification unit 17, a second identification unit 18, and an output control unit 19.

The communication unit 21 is capable of transmitting and receiving information to and from, for example, a device (external device) (not shown) outside the information processing device 1. The communication unit 21 is capable of communicating with, for example, external devices such as a server, a terminal (for example, a desktop, a laptop, a tablet, a smartphone, etc.), an OCR (Optical Character Recognition) device, and a voice acquisition device.
The server and the terminal, for example, generate files (text information) in which text generated on the own device is described, and store files (text information) in which text generated on the own device and other devices is described.
When an image is generated based on a medium containing text, such as a book, picture book, or magazine, an OCR device recognizes characters recorded in the image and generates text information.
The voice capture device captures voice using, for example, a microphone, performs voice recognition based on the captured voice, and generates text information.

The storage unit 22 stores, for example, various types of information and programs.
The storage unit 22 may store, for example, text information. In this case, the storage unit 22 may store, for example, text information generated by the information processing device 1, or text information acquired from outside the information processing device 1.
The storage unit 22 may store various information generated by the information processing device 1, including information on the readability of text calculated by the calculation unit 15, based on the control of the output control unit 19 described later. The storage unit 22 may store information acquired from outside the information processing device 1, for example.

The display unit 23 displays, for example, various characters, symbols, images, etc. The display unit 23 may display characters, symbols, images, etc. based on various information generated by the information processing device 1, including the readability of text calculated by the calculation unit 15, based on the control of the output control unit 19 described below. The display unit 23 may display characters, symbols, images, etc. based on information acquired from outside the information processing device 1, for example.

The first acquisition unit 11 acquires text information in which text is recorded. The first acquisition unit 11 may acquire text information stored in the storage unit 22, for example. Or, the first acquisition unit 11 may acquire text information via the communication unit 21, for example. The text information may be generated based on a medium in which text is written, such as a book, a picture book, or a magazine, or may be generated based on text in a daily report, monthly report, report, or other such report. The text information may also be generated based on a voice uttered by a user. That is, the text information may be, for example, information in which various texts are recorded.

The second acquisition unit 12 acquires the ratio of hiragana used in the text based on the text information acquired by the first acquisition unit 11. The second acquisition unit 12 acquires, for example, the ratio of hiragana in the entire text or a part (predetermined range) of the text recorded in the text information. The predetermined range of the text may be, for example, any range in the entire text, that is, a text of a predetermined number of characters at any point in the entire text. That is, the ratio of hiragana in the predetermined range of the text may be, for example, the ratio of hiragana to a text (characters) of a predetermined number of characters at any point in the entire text. As an example, the predetermined number of characters may be about 500 to 3000 characters, and a larger number of characters makes it possible to more accurately calculate the readability of the text by the calculation unit 15 described later. The ratio of hiragana may be, for example, the number of hiragana characters to the characters (total number of characters or number of characters in a predetermined range) of the entire text or a part (predetermined range).

The second acquisition unit 12 may also acquire the ratio of kanji and hiragana from, for example, a portion of the text recorded in the text information. That is, the ratio of hiragana used in the above-mentioned text may be the ratio of kanji and hiragana used in the text. The portion of the text may be, for example, the above-mentioned specified range of text. The ratio of kanji and hiragana may be, for example, the ratio of the number of kanji characters and the number of hiragana characters to the characters (total number of characters or number of characters in a specified range) of the entire text or a portion (specified range) of the text.

The third acquisition unit 13 may acquire the average length of one sentence of the text based on the text information acquired by the first acquisition unit 11. In this case, when the proportion of hiragana (proportion of kanji and hiragana) is acquired from a part of the text (a specified range of text) by the above-mentioned second acquisition unit 12, the third acquisition unit 13 may acquire the average length of one sentence of the part of the text (a specified range of text). The average length of the text may be, for example, the arithmetic mean length of the sentences constituting the entire text or the part (specified range). The average length of the text may also be, for example, the average number of characters in one sentence.
Furthermore, when acquiring the length of one sentence, the third acquisition unit 13 may acquire the length (number of characters in one sentence) without including symbols (delimiters) such as parentheses ("(", ")", "" and """), question marks and exclamation marks ("?", "!" and "!?"), and periods ("."). Therefore, the third acquisition unit 13 may acquire the average length (number of characters) of one sentence from multiple sentences based on the length (number of characters) of one sentence excluding symbols such as delimiters.

The fourth acquisition unit 14 may perform morphological analysis based on the text information acquired by the first acquisition unit 11, and acquire at least one of the rate of Chinese words, the rate of Japanese words, the rate of verbs, and the rate of particles in the text based on the results of the analysis.
That is, the fourth acquisition unit 14 performs morpheme analysis on the text based on the text information. In this case, for example, when the fourth acquisition unit 14 has acquired the ratio of hiragana (the ratio of kanji and hiragana) from a part of the text (a predetermined range of text) by the above-mentioned second acquisition unit 12, the fourth acquisition unit 14 may perform morpheme analysis on the part of the text (a predetermined range of text).
The fourth acquiring unit 14 may acquire at least one of the proportion of Chinese words in the text, the proportion of Japanese words in the text, the proportion of verbs in the text, and the proportion of particles in the text based on the result of the morphological analysis, for example. In this case, the fourth acquiring unit 14 may acquire the number of Chinese words in the text as the proportion of Chinese words, the number of Japanese words in the text as the proportion of Japanese words, the number of verbs in the text as the proportion of verbs, and the number of particles in the text as the proportion of particles.
As a specific example, the fourth identification unit uses various publicly known morphological analysis engines (e.g., MeCab, etc.) to perform word segmentation on text based on text information and obtain at least one of the Chinese word rate, the Japanese word rate, the verb rate, and the particle rate.

The calculation unit 15 acquires the readability of the text recorded in the text information (the difficulty of the text) based on the proportion of hiragana acquired by the second acquisition unit 12. The readability of the text is, for example, information that quantitatively indicates the degree of readability of the text. The calculation unit 15 may estimate that the text is easier to read, for example, when the proportion of hiragana acquired by the second acquisition unit 12 is relatively large (there are more hiragana). In other words, the calculation unit 15 may estimate that the text is more difficult to read, for example, when the proportion of hiragana acquired by the second acquisition unit 12 is relatively small (there are fewer hiragana).

In this case, the calculation unit 15 may acquire the readability of the text according to age (e.g., grade of school such as elementary school, junior high school, and high school). When a threshold value for the proportion of hiragana characters for estimating the readability of the text according to age is set, the calculation unit 15 may estimate that the text is easy to read if the proportion of hiragana characters acquired by the second acquisition unit 12 is equal to or greater than the threshold value (if the number of hiragana characters is greater than the threshold value). In other words, the calculation unit 15 may estimate that the text is difficult to read if the proportion of hiragana characters acquired by the second acquisition unit 12 is less than the threshold value (if the number of hiragana characters is less than the threshold value).

Note that multiple thresholds may be set as described above. As an example, when two thresholds (first threshold > second threshold) are set, the calculation unit 15 may estimate that the text is easier to read if the proportion of hiragana acquired by the second acquisition unit 12 is equal to or greater than the first threshold. As another example, the calculation unit 15 may estimate that the text is easier to read if the proportion of hiragana acquired by the second acquisition unit 12 is less than the first threshold and equal to or greater than the second threshold. As another example, the calculation unit 15 may estimate that the text is difficult to read if the proportion of hiragana acquired by the second acquisition unit 12 is less than the second threshold.

The calculation unit 15 calculates the readability of the text recorded in the text information based on the ratio of hiragana characters acquired by the second acquisition unit 12. The calculation unit 15 may also calculate the readability of the text based on, for example, the ratio of kanji characters and hiragana characters acquired by the second acquisition unit 12. The calculation unit 15 may calculate the readability of the text by substituting the ratio of hiragana characters (the ratio of kanji characters and hiragana characters) acquired by the second acquisition unit 12 into a predetermined arithmetic expression. The calculation unit 15 can use various arithmetic expressions as the arithmetic expression, and may, for example, calculate the readability of the text using equation (1) described later.
Here, the calculation unit 15 may calculate the readability of the text, for example, by acquiring the readability of the text as described above, that is, estimating the readability by using a threshold value or the like.

The calculation unit 15 may calculate the readability of the text according to the age based on the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12. The calculation unit 15 may, for example, estimate the readability of the text according to the age by classifying a value (a value indicating the readability of the text) obtained by substituting the ratio of hiragana (the ratio of kanji to hiragana) into an arithmetic formula (for example, formula (1) described later, etc.). The calculation unit 15 may perform the classification by using, for example, a preset threshold value.
As an example, when the age is 8 years old (grade 3 of elementary school), the text may be set to be easy to read if it is equal to or greater than the third threshold and less than the fourth threshold, when the age is 9 years old (grade 4 of elementary school), the text may be set to be easy to read if it is equal to or greater than the fourth threshold and less than the fifth threshold, and when the age is 10 years old (grade 5 of elementary school), the text may be set to be easy to read if it is equal to or greater than the fifth threshold and less than the sixth threshold (sixth threshold>fifth threshold>fourth threshold>third threshold). In such an example, when the value obtained by substituting into the arithmetic expression (e.g., expression (1), etc.) is equal to or greater than the fourth threshold and less than the fifth threshold, the calculation unit 15 may estimate that the text is easy to read (appropriate) for a child aged 9 years old (grade 4 of elementary school), that the text is difficult to read (difficult) for a child aged 8 years old (grade 3 of elementary school), and that the text is easy to read (easy) for a child aged 10 years old (grade 5 of elementary school).

Note that, in addition to or in addition to calculating the readability of the text according to age as described above, the calculation unit 15 may calculate the readability of the text according to age by using at least one of difficulty information regarding the difficulty of the vocabulary used in the text and the content of the kanji to be learned according to the school grade (learned kanji information). The difficulty information may be, for example, information that associates the vocabulary with the difficulty of the vocabulary. The learned kanji information may be, for example, information that associates the school grade, such as elementary school, junior high school, and high school, with the kanji to be learned in each grade. In this case, the calculation unit 15 may calculate the readability of the text according to age (school grade), for example, based on the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12 and at least one of the difficulty information and the learned kanji information.

The calculation unit 15 may also calculate the readability of the text based on the ratio acquired by the second acquisition unit 12 and the average length of one sentence acquired by the third acquisition unit 13. That is, the calculation unit 15 may calculate the readability of the text by using, for example, the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12 and the average length of one sentence acquired by the third acquisition unit 13. The calculation unit 15 may calculate the readability of the text by substituting, for example, the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12 and the average length of one sentence acquired by the third acquisition unit 13 into a predetermined arithmetic expression. The calculation unit 15 may use, for example, various arithmetic expressions as the arithmetic expression, and may calculate the readability of the text by using, for example, equation (1) described later.

The calculation unit 15 may calculate the readability of the text based on the ratio acquired by the second acquisition unit 12, the average length of one sentence acquired by the third acquisition unit 13, and at least one of the Chinese word ratio, the Japanese word ratio, the verb ratio, and the particle ratio acquired by the fourth acquisition unit 14. That is, the calculation unit 15 may calculate the readability of the text using, for example, the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12 and the average length of one sentence acquired by the third acquisition unit 13, as well as at least one of the Chinese word ratio, the Japanese word ratio, the verb ratio, and the particle ratio acquired by the fourth acquisition unit 14. The calculation unit 15 may, for example, calculate the readability of the text by substituting the ratio of hiragana (the ratio of kanji to hiragana) acquired by the second acquisition unit 12, the average length of one sentence acquired by the third acquisition unit 13, and at least one of the ratio of Chinese words, the ratio of Japanese words, the ratio of verbs, and the ratio of particles acquired by the fourth acquisition unit 14 into a preset arithmetic formula. The calculation unit 15 may use, for example, various arithmetic formulas as the arithmetic formula, and may, for example, calculate the readability of the text using formula (1) described below.

The calculation unit 15 may calculate the readability YL of the text using the following formula (1), where a is the ratio (the ratio of hiragana (the ratio of kanji to hiragana)) acquired by the second acquisition unit 12, b is the average length of one sentence acquired by the third acquisition unit 13, c is the Chinese word ratio, d is the Japanese word ratio, e is the verb ratio, and f is the particle ratio acquired by the fourth acquisition unit 14.
YL=60*a+0.24*b+126*c+42*d+145*e+44*f...(1)

Each term in the above-mentioned formula (1) may be increased or decreased according to the value obtained by the above-mentioned second to fourth acquisition units 12, 13, and 14. That is, as an example, when calculating the readability of text using only the ratio a obtained by the second acquisition unit 12, the calculation unit 15 may calculate the readability YL of text by the following formula (2) based on formula (1).
YL=10*a...(2)

Similarly, as an example, when calculating the readability of a text using the ratio a acquired by the second acquisition unit 12 and the average length of one sentence b acquired by the third acquisition unit 13, the calculation unit 15 may calculate the readability YL of the text using the following formula (3) based on formula (1).
YL=60*a+0.24*b...(3)

Similarly, as an example, when the calculation unit 15 calculates the readability of a text using the ratio a acquired by the second acquisition unit 12, the average length of one sentence b acquired by the third acquisition unit 13, and the Chinese word rate c acquired by the fourth acquisition unit 14, the calculation unit 15 may calculate the readability YL of the text using the following formula (4) based on formula (1).
YL=60*a+0.24*b+126*c...(4)

The coefficients in the above formulas (1) to (4) are not limited to the above example, and may be values that are set appropriately.

The calculation unit 15 may improve the accuracy of the readability YL by setting coefficients such as those in the above-mentioned formula (1) and introducing new terms using, for example, machine learning and deep learning. In this case, the calculation unit 15 may use, for example, information obtained from various services to build a learning model tailored to the user's education (for example, children's reading education, etc.).
Furthermore, the calculation unit 15 is not limited to the example of calculating the readability YL of the text using the arithmetic formula as described above, and may calculate the readability YL using, for example, machine learning, deep learning, etc. As an example, the calculation unit 15 may calculate the readability YL based on a learning model generated by learning the text and the readability of the text in association with each other, and information acquired by the second to fourth acquisition units 12, 13, and 14.
Furthermore, the calculation unit 15 may determine the level of difficulty by taking into account the complexity of the flow of the entire sentence, for example, by using natural language processing technology or the like.
The calculation unit 15 may also evaluate an index such as psychological readability by reflecting the ups and downs of the entire sentence. In this case, the calculation unit 15 may perform a positive/negative judgment for each word or the like, and read the ups and downs of the story in chronological order.

The information processing device 1 can use the obtained text readability YL as described above for various purposes.
The control unit 10 may, for example, rewrite the text to suit the reading ability of the user (for example, a child) (in a plurality of patterns for each readability level). As an example, the control unit 10 may be used for reference books, textbooks, articles, and the like.
The control unit 10 may, for example, publish media such as books for each readability level YL so that the user's reading ability gradually improves.
The control unit 10 may support the writing activities of a user (e.g., a writer, author, etc.) by obtaining the readability YL (difficulty) of a sentence (text) created by the user in real time. In this case, the control unit 10 may apply the readability YL to various general sentences, not just writing, and develop various services for children and elderly people. In addition, the control unit 10 may obtain the user's speaking habits and vocabulary by converting the user's voice into text and analyzing it, and provide advice (to brush up the presentation) so that the user can make a presentation that is easy for other users to understand.
The control unit 10 can also improve the user's writing ability by using, for example, the readability YL. In this case, the control unit 10 can, for example, determine the level of complex logical structures and vocabulary used in the text, and encourage the user to further improve their level. The control unit 10 can also, for example, determine elements such as sentence structure in the text, and encourage the user to improve their level.
The control unit 10 may provide the user with reading guidance using, for example, the readability level YL. In this case, the control unit 10 may create questions (tests) that can measure the complex elements that make up the user's reading ability by isolating them. In addition, the control unit 10 may measure the user's ability by ability level, rather than just the score of the questions (tests), and thus lead to an approach that can resolve the user's weak points in the shortest possible time.
A specific example of the control unit 10 when the above-mentioned text readability YL is used for various purposes will be described below.

The rewriting unit 16 may rewrite the text recorded in the text information acquired by the first acquisition unit 11 so as to have a different readability level from the readability level calculated by the calculation unit 15 based on the first correspondence information that associates the text with the readability level corresponding to the text. That is, the rewriting unit 16 may rewrite the text based on the first correspondence information so as to raise (or lower) the readability level calculated by the calculation unit 15. As a specific example, if there is a textbook used by a fourth-grade elementary school student and the student finds the textbook difficult, the rewriting unit 16 may rewrite the text based on the textbook to a level that a third-grade elementary school student can read based on the first correspondence information. Similarly, as a specific example, if there is a textbook used by a fourth-grade elementary school student and the student finds the textbook easy, the rewriting unit 16 may rewrite the text based on the textbook to a level that a fifth-grade elementary school student can read based on the first correspondence information.

The first correspondence information may record, for example, kanji, phrases, expressions, and learning contents (e.g., vocabulary words, etc.) to be learned according to age (school grade).
For example, as in the example described above, when rewriting a textbook used by a fourth-grade elementary school student to a level that can be read by a third-grade elementary school student, the rewriting unit 16 may rewrite the textbook (text) used by the fourth-grade elementary school student to a third-grade elementary school level based on the first correspondence information so as to rewrite the kanji learned in the fourth grade of elementary school into hiragana and maintain the kanji learned in the first to third grades of elementary school.
Similarly, when rewriting a textbook used by a fourth-grade elementary school student to a fifth-grade elementary school level, as in the example described above, the rewriting unit 16 may rewrite the textbook (text) used by a fourth-grade elementary school student to a fifth-grade elementary school level based on the first correspondence information, so as to rewrite hiragana into kanji for kanji learned in the fifth grade of elementary school, and to maintain the kanji learned in the first to fourth grades of elementary school.

The first identification unit 17 may identify advice to the user to raise the readability level calculated by the calculation unit 15 based on second correspondence information that associates text, a readability level corresponding to the text, and advice to the user corresponding to the readability level. As a specific example, if a fourth-grade elementary school student writes a text and the calculation unit 15 calculates the readability of the written text to be at the third-grade elementary school level, the first identification unit 17 may identify advice to raise the level of the child's writing to the fourth-grade elementary school level based on the second correspondence information.

The second correspondence information may, for example, record kanji, phrases, expressions, and learning contents (e.g., words, etc.) to be learned according to age (grade at school), and advice to raise the level according to age (grade at school). In this case, the advice may, for example, be to raise the readability level for a third grade elementary school student to a fourth grade elementary school student, and if the kanji learned by a fourth grade elementary school student is written in hiragana in the text, the advice may be to teach the hiragana kanji. The advice may, for example, be in the form of displaying a sentence on the display unit 23 of the terminal used by the user, or in the form of outputting audio from the speaker of the terminal used by the user, etc.

In other words, for example, if the readability level of a piece of text written by a fourth-grade elementary school student is the third-grade elementary school level and the text contains kanji at the fourth-grade elementary school level written in hiragana, the first identification unit 17 may identify advice encouraging the student to rewrite the hiragana into kanji based on the second correspondence information.

The first identification unit 17 is not limited to the example of providing advice on composition (writing of text) as described above, but may provide various advice based on the results (text) of recognizing the voice spoken by the user. In this case, the first identification unit 17 may provide advice on the user's presentation, for example.

The second identification unit 18 may identify questions corresponding to the readability level calculated by the calculation unit 15 based on third correspondence information that associates readability levels with questions corresponding to the readability levels. As a specific example, when questions (tests) are given to fourth-grade elementary school students, the second identification unit 18 may identify questions based on the third correspondence information so that questions (tests) suitable for fourth-grade elementary school students can be given.

The third correspondence information may, for example, record kanji, phrases, and expressions to be learned according to age (school grade), and questions written in kanji, phrases, and expressions according to age (school grade). That is, for example, when the readability level of a text for a fourth-grade elementary school student is at the third-grade elementary school level, the second identification unit 18 identifies questions based on the third correspondence information that are questions on content learned in the fourth grade of elementary school but written in kanji etc. learned in the third grade of elementary school.

The output control unit 19 controls the output unit to output the readability of the text calculated by the calculation unit 15. The output unit may be, for example, a communication unit 21, a storage unit 22, a display unit 23, and the like.
That is, the output control unit 19 may control the communication unit 21 to transmit information regarding the readability of the text calculated by the calculation unit 15 to an external device (for example, a server, a terminal, etc.).
The output control unit 19 may, for example, control the storage unit 22 to store information regarding the readability of the text calculated by the calculation unit 15 .
The output control unit 19 may, for example, control the display unit 23 to display the readability of the text calculated by the calculation unit 15 .

The output control unit 19 may control the output unit to output the text rewritten by the rewriting unit 16. That is, the output control unit 19 may control the communication unit 21, the storage unit 22, and the display unit 23 (output unit) to output the text rewritten by the rewriting unit 16, similar to the output related to the "readability of text" described above.

The output control unit 19 may control the output unit to output the advice identified by the first identification unit 17. That is, the output control unit 19 may control the communication unit 21, the memory unit 22, and the display unit 23 (output unit) to output the advice identified by the first identification unit 17, similar to the case described above.

The output control unit 19 may control the output unit to output the question identified by the second identification unit 18. That is, the output control unit 19 may control the communication unit 21, the memory unit 22, and the display unit 23 (output unit) to output the question identified by the second identification unit 18, similar to the case described above.

Here, as a specific example, the control unit 10 (e.g., the first acquisition unit 11, the second acquisition unit 12, the third acquisition unit 13, the fourth acquisition unit 14, the calculation unit 15, the rewriting unit 16, the first identification unit 17, the second identification unit 18, and the output control unit 19) may utilize an API (Application Programming Interface) to be able to output the readability of text, etc., based on text information.
That is, the control unit 10 performs morphological analysis and analysis of the text based on text information (text information written in Japanese) of a predetermined number of characters or more, or audio (audio information) or image (image information) that can be converted into text information, and outputs various data regarding the difficulty of the sentence including the readability YL of the text, that is, as an example, the readability YL, details of the various parameters used to calculate the readability YL, and vocabulary difficulty, etc.
In addition, the control unit 10 may also output data on the structure and characteristics of a sentence that do not fall within the category of simple text difficulty. The control unit 10 may output, for example, a representation of the flow of a sentence as numerical time-series data, various tendencies such as the "rigidity" of a sentence, and the genre of the sentence (for example, a broad classification such as story and non-fiction, and a detailed genre such as "romance,""adventure," and "school-related").

[Information processing method]
Next, an information processing method according to an embodiment will be described.

First, a process of acquiring the readability of text will be described as an information processing method according to an embodiment.
FIG. 3 is a first flowchart illustrating an information processing method according to an embodiment.

In step ST101, the first acquisition unit 11 acquires text information in which text is recorded.

In step ST102, the second acquisition unit 12 acquires the proportion of hiragana used in the text based on the text information acquired in step ST101. In this case, the second acquisition unit 12 may acquire the proportion of kanji and hiragana used in the text. Here, the second acquisition unit 12 may acquire the proportion of hiragana (the proportion of kanji and hiragana) based on all or part of the text based on the text information, for example.

In step ST103, the third acquisition unit 13 acquires the average length of one sentence of the text based on the text information acquired in step ST101. In this case, the third acquisition unit 13 may acquire the average length of one sentence from within the range of the text for which the hiragana ratio (the ratio of kanji to hiragana) is acquired in step ST102, for example.

In step ST104, the fourth acquisition unit 14 performs a morphological analysis based on the text information acquired in step ST101, and acquires at least one of the Chinese word rate, the Japanese word rate, the verb rate, and the particle rate in the text based on the results of the analysis. In this case, the fourth acquisition unit 14 may acquire at least one of the Chinese word rate, the Japanese word rate, the verb rate, and the particle rate, for example, from within the range of the text from which the hiragana rate (the ratio of kanji to hiragana) is acquired in step ST102, or from within the range of the text from which the average length of one sentence is acquired in step ST103.

In step ST105, the calculation unit 15 calculates the readability of the text recorded in the text information acquired in step ST101 based on the ratio (the ratio of hiragana or the ratio of kanji and hiragana) acquired in step ST102. In this case, the calculation unit 15 may calculate the readability of the text according to age based on the ratio acquired in step ST102.
Furthermore, the calculation unit 15 may calculate the readability of the text based on the ratio acquired in step ST102 and the average length of one sentence acquired in step ST103.
In addition, the calculation unit 15 may calculate the readability of the text based on the ratio obtained in step ST102, the average length of one sentence obtained in step ST103, and at least one of the Chinese word rate, the Japanese word rate, the verb rate, and the particle rate obtained in step ST104.
The calculation unit 15 may calculate the readability YL of the text using the following formula (5), where a is the ratio obtained in step ST102, b is the average length of one sentence obtained in step ST103, c is the Chinese word ratio, d is the Japanese word ratio, e is the verb ratio, and f is the particle ratio obtained in step ST104.
YL=60*a+0.24*b+126*c+42*d+145*e+44*f...(5)

In step ST106, the output control unit 19 controls the output unit to output the readability of the text calculated in step ST105. The output unit may be, for example, the communication unit 21, the memory unit 22, the display unit 23, etc.

Next, a process of outputting various pieces of information by utilizing the readability of text will be described as an information processing method according to an embodiment.
FIG. 4 is a second flowchart illustrating the information processing method according to an embodiment.

The information processing device 1 uses the text readability YL calculated in step ST104 of FIG. 3 to perform the processes in steps ST201 to ST203 below to generate various information, which can then be output in step ST204. A detailed explanation is given below.

In step ST201, the rewriting unit 16 rewrites the text recorded in the text information acquired in step ST101 of FIG. 3 based on the first correspondence information so that the readability level YL is different from the readability level calculated in step ST104. Here, the first correspondence information is, for example, information that associates text with a readability level corresponding to the text.

In step ST202, the first identification unit 17 identifies advice to the user to raise the level of readability YL calculated in step ST104 based on the second correspondence information. Here, the second correspondence information is, for example, information that associates text, a readability level corresponding to the text, and advice to the user corresponding to the readability level.

In step ST203, the second identification unit 18 identifies a question (test) corresponding to the level of readability YL calculated in step ST104 based on the third correspondence information. Here, the third correspondence information is, for example, information that associates a readability level with a question corresponding to the readability level.

Note that the above-mentioned processing of steps ST201 to ST203 is not limited to being performed in this order, and for example, all or part of the processing of steps ST201 to ST203 may be performed in any order.

In step ST204, the output control unit 19 controls the output unit to output the results of the processing in step ST201, the processing in step ST202, and the processing in step ST203. That is, the output control unit 19 may control the output unit to output the text rewritten in step ST201, for example. The output control unit 19 may control the output unit to output the advice identified in step ST202, for example. The output control unit 19 may control the output unit to output the problem identified in step ST203, for example. The output unit may be, for example, the communication unit 21, the memory unit 22, the display unit 23, etc.

In this specification, the term "information" is used, but the term "information" can be replaced with "data" and the term "data" can be replaced with "information."

Each unit of the information processing device described above may be realized as a function of a computer's arithmetic processing device, etc. That is, the first acquisition unit, the second acquisition unit, the third acquisition unit, the fourth acquisition unit, the calculation unit, the rewriting unit, the first identification unit, the second identification unit, and the output control unit (control unit) of the information processing device may be realized as a first acquisition function, a second acquisition function, a third acquisition function, a fourth acquisition function, a calculation function, a rewriting function, a first identification function, a second identification function, and an output control function (control function) by the computer's arithmetic processing device, etc.
The information processing program can cause a computer to realize each of the above-mentioned functions. The information processing program may be recorded in a non-transitory computer-readable recording medium, such as an external memory or an optical disk.
Also, as described above, each part of the information processing device may be realized by a processing device of a computer or the like. The processing device or the like is, for example, configured by an integrated circuit or the like. Therefore, each part of the information processing device may be realized as a circuit constituting the processing device or the like. That is, the first acquisition unit, the second acquisition unit, the third acquisition unit, the fourth acquisition unit, the calculation unit, the rewriting unit, the first identification unit, the second identification unit, and the output control unit (control unit) of the information processing device may be realized as a first acquisition circuit, a second acquisition circuit, a third acquisition circuit, a fourth acquisition circuit, a calculation circuit, a rewriting circuit, a first identification circuit, a second identification circuit, and an output control circuit (control circuit) constituting the processing device of a computer or the like.
The communication unit, storage unit, and display unit (output unit) of the information processing device may be realized as a communication function, a storage function, and a display function (output function) including the functions of an arithmetic processing device, etc. The communication unit, storage unit, and display unit (output unit) of the information processing device may be realized as a communication circuit, a storage circuit, and a display circuit (output circuit) by being configured, for example, by an integrated circuit, etc. The communication unit, storage unit, and display unit (output unit) of the information processing device may be realized as a communication device, a storage device, and a display device (output device) by being configured, for example, by a plurality of devices.

[Aspects and Effects of the Present Embodiment]
Next, one aspect of the present embodiment and the effects of each aspect will be described. Note that the effects described below are merely examples, and the effects of each aspect are not limited to those described below.

(Aspect 1)
An information processing device of one embodiment includes a first acquisition unit that acquires text information in which text is recorded, a second acquisition unit that acquires a proportion of hiragana used in the text based on the text information acquired by the first acquisition unit, a calculation unit that calculates the readability of text recorded in the text information based on the proportion of hiragana acquired by the second acquisition unit, and an output control unit that controls the readability of the text calculated by the calculation unit to be output.
This allows the information processing device to obtain the readability of the text.

(Aspect 2)
In one embodiment of the information processing device, the second acquisition unit may acquire the ratio of kanji and hiragana from a portion of the text recorded in the text information, and the calculation unit may calculate the readability of the text according to age based on the ratio of kanji and hiragana acquired by the second acquisition unit.
It is considered that the kanji to be learned varies depending on age. In other words, it is considered that the number of kanji to be learned increases as the age increases. Therefore, the information processing device can obtain the readability of the text according to the age by considering the ratio of kanji to hiragana in the text.

(Aspect 3)
In one embodiment of the information processing device, a third acquisition unit is provided that acquires the average length of one sentence of the text based on the text information acquired by the first acquisition unit, and the calculation unit may calculate the readability of the text based on the ratio acquired by the second acquisition unit and the average length of one sentence acquired by the third acquisition unit.
In general, a user may feel that a text is difficult to read if the length of a sentence is long. In particular, children such as elementary school students are more likely to feel that a text is difficult to read if the length of a sentence is long. The information processing device can obtain the readability of the text by considering the average length of a sentence in addition to the ratio of hiragana in the text (the ratio of kanji to hiragana).

(Aspect 4)
An information processing device of one embodiment includes a fourth acquisition unit that performs morphological analysis based on text information acquired by the first acquisition unit, and acquires at least one of the rate of Chinese words, the rate of Japanese words, the rate of verbs, and the rate of particles in the text based on the results of the analysis, and the calculation unit calculates the readability of the text based on the rate acquired by the second acquisition unit, the average length of a sentence acquired by the third acquisition unit, and at least one of the rate of Chinese words, the rate of Japanese words, the rate of verbs, and the rate of particles acquired by the fourth acquisition unit.
In general, it is considered that the readability of a text varies depending on the ratio of Chinese characters, the ratio of Japanese characters, the ratio of verbs, and the ratio of particles in the text. The information processing device can obtain the readability of a text by considering at least one of the ratio of Chinese characters, the ratio of Japanese characters, the ratio of verbs, and the ratio of particles in the text, in addition to the ratio of hiragana characters (the ratio of kanji characters to hiragana characters) in the text and the average length of one sentence.

(Aspect 5)
In one embodiment of the information processing device, the calculation unit may calculate the readability YL of the text using the following formula (6): a is the proportion acquired by the second acquisition unit, b is the average length of one sentence acquired by the third acquisition unit, c is the rate of Chinese words acquired by the fourth acquisition unit, d is the rate of Japanese words, e is the rate of verbs, and f is the rate of particles.
YL=60*a+0.24*b+126*c+42*d+145*e+44*f...(6)
The information processing device can calculate the readability of text using various calculation formulas, and can obtain the readability of text based on, for example, the above-mentioned formula (6).

(Aspect 6)
An information processing device of one embodiment may include a rewriting unit that rewrites text recorded in text information acquired by a first acquisition unit so that the readability level is different from the readability level calculated by the calculation unit based on first correspondence information that corresponds the text to a readability level corresponding to the text, and the output control unit may control the output of the text rewritten by the rewriting unit.
Generally, when the readability of a text is calculated as described above, there is a possibility that a user may wish to change the readability level of the text depending on the user. For example, in a school, there are cases where the learning levels of children are different even in the same grade. That is, for example, there are cases where a child A in the same class can read and understand a textbook, but another child B finds the textbook difficult to read and understand.
The information processing device includes a rewriting unit, which allows the information processing device to change the readability level of a text to another readability level (raise or lower the readability level), i.e., output text of one or different readability levels from one text.
Therefore, as an example, the information processing device can output text appropriate to the level of a child from a single textbook, thereby assisting the child in his/her learning.

(Aspect 7)
An information processing device of one embodiment includes a first identification unit that identifies advice to a user to increase the readability level calculated by the calculation unit based on second correspondence information that associates text, a readability level corresponding to the text, and advice to the user corresponding to the readability level, and an output control unit that may be controlled to output the advice identified by the first identification unit.
For example, when a child at school writes an essay, if he or she is not good at writing, he or she may not know how to write the essay, and the kanji and phrases used in the essay may be at a lower level than the grade level the child belongs to.
The information processing device can, for example, obtain a readability level based on a sentence created by a user, and output advice for improving the level of the sentence according to the level.
Therefore, as an example, the information processing device can output advice according to the child's level, and can assist the child in learning.

(Aspect 8)
An information processing device of one embodiment may include a second identification unit that identifies questions corresponding to the readability level calculated by the calculation unit based on third correspondence information that associates readability levels with questions corresponding to the readability levels, and an output control unit may control the output of the questions identified by the second identification unit.
Generally, in schools, etc., there are cases where the learning levels of children are different even in the same grade. In such a case, if question (test) C is given to children A and B in the same class, child A may be able to understand question C, but child B may find it difficult to read and answer question C.
The information processing device, for example, prepares third correspondence information regarding questions corresponding to multiple readability levels for a single task content, and when it obtains the readability level of a text created by a user as described above, it can output questions appropriate to the user based on the obtained readability level and the third correspondence information.
Therefore, as an example, the information processing device can output questions appropriate to the level of the child from one textbook, thereby assisting the child in his/her learning.

(Aspect 9)
In one aspect of the information processing method, a computer executes a first acquisition step of acquiring text information in which text is recorded, a second acquisition step of acquiring a percentage of hiragana used in the text based on the text information acquired by the first acquisition step, a calculation step of calculating the readability of the text recorded in the text information based on the percentage of hiragana acquired by the second acquisition step, and an output control step of controlling the readability of the text calculated by the calculation step to be output.
The information processing method can achieve the same effects as the information processing device according to the above-described embodiment.

(Aspect 10)
An information processing program of one embodiment causes a computer to realize a first acquisition function that acquires text information in which text is recorded, a second acquisition function that acquires the proportion of hiragana used in the text based on the text information acquired by the first acquisition function, a calculation function that calculates the readability of text recorded in the text information based on the proportion of hiragana acquired by the second acquisition function, and an output control function that controls the output of the readability of the text calculated by the calculation function.
The information processing program can achieve the same effects as the information processing device according to the above aspect.

REFERENCE SIGNS LIST 1 Information processing device 10 Control unit 11 First acquisition unit 12 Second acquisition unit 13 Third acquisition unit 14 Fourth acquisition unit 15 Calculation unit 16 Rewriting unit 17 First identification unit 18 Second identification unit 19 Output control unit 21 Communication unit 22 Storage unit 23 Display unit

Claims (10)

A first acquisition unit that acquires text information in which text is recorded;
a second acquisition unit that acquires a ratio of hiragana and kanji used in a text based on the text information acquired by the first acquisition unit;
a calculation unit that calculates the readability of the text recorded in the text information based on at least one of the ratio of hiragana and kanji acquired by the second acquisition unit, difficulty level information that associates vocabulary used in the text with the difficulty of the vocabulary, and learned kanji information that associates grades in elementary school, junior high school, and high school with kanji learned in each grade ; and
an output control unit that controls the readability of the text calculated by the calculation unit to be output;
An information processing device comprising: The information processing apparatus according to claim 1 , wherein the calculation unit calculates the readability of the text according to age based on the ratio of kanji and hiragana acquired by the second acquisition unit. a third acquisition unit that acquires an average length of one sentence of a text based on the text information acquired by the first acquisition unit;
The information processing device according to claim 1 , wherein the calculation unit calculates the readability of the text based on the ratio acquired by the second acquisition unit and an average length of one sentence acquired by the third acquisition unit. a fourth acquisition unit that performs a morphological analysis based on the text information acquired by the first acquisition unit, and acquires at least one of a rate of Chinese words, a rate of Japanese words, a rate of verbs, and a rate of particles in the text based on a result of the analysis;
4. The information processing device according to claim 3, wherein the calculation unit calculates readability of a text based on the ratio acquired by the second acquisition unit, the average length of one sentence acquired by the third acquisition unit, and at least one of the Chinese word rate, the Japanese word rate, the verb rate, and the particle rate acquired by the fourth acquisition unit. The calculation unit calculates the readability YL of the text by the following formula, where a is the ratio acquired by the second acquisition unit, b is the average length of one sentence acquired by the third acquisition unit, c is the ratio of Chinese words acquired by the fourth acquisition unit, d is the ratio of Japanese words, e is the ratio of verbs, and f is the ratio of particles acquired by the fourth acquisition unit: YL=60*a+0.24*b+126*c+42*d+145*e+44*f
The information processing device according to claim 4. a rewriting unit that rewrites text recorded in the text information acquired by the first acquisition unit so that the text has a readability level different from the readability level calculated by the calculation unit, based on first correspondence information that associates text with a readability level corresponding to the text;
6. The information processing device according to claim 1, wherein the output control unit controls so as to output the text rewritten by the rewriting unit. a first specifying unit that specifies advice to a user for increasing the readability level calculated by the calculation unit, based on second correspondence information that associates a text, a readability level corresponding to the text, and advice to a user corresponding to the readability level;
The information processing device according to claim 1 , wherein the output control unit performs control so as to output the advice identified by the first identification unit. a second identification unit that identifies questions corresponding to the readability level calculated by the calculation unit, based on third correspondence information that associates the readability level with questions corresponding to the readability level;
The information processing device according to claim 1 , wherein the output control unit controls so as to output the question identified by the second identification unit. The computer
a first acquisition step of acquiring text information in which text is recorded;
a second acquisition step of acquiring a ratio of hiragana and kanji used in the text based on the text information acquired by the first acquisition step;
a calculation step of calculating readability of the text recorded in the text information based on at least one of the ratio of hiragana and kanji acquired by the second acquisition step , difficulty level information associating vocabulary used in the text with the difficulty of the vocabulary, and learned kanji information associating grades in elementary, junior high, and high schools with kanji learned in each grade ;
an output control step of controlling the readability of the text calculated by the calculation step to be output;
An information processing method for performing the above. On the computer,
a first acquisition function for acquiring text information in which the text is recorded;
A second acquisition function that acquires a ratio of hiragana and kanji used in a text based on the text information acquired by the first acquisition function;
a calculation function that calculates the readability of the text recorded in the text information based on at least one of the ratio of hiragana and kanji acquired by the second acquisition function, difficulty level information that associates the vocabulary used in the text with the difficulty of the vocabulary, and learned kanji information that associates the grades of elementary school, junior high school, and high school with the kanji learned in each grade ; and
an output control function that controls the readability of the text calculated by the calculation function to be output;
An information processing program that realizes this.

Images