Information processing device, information processing method, and information processing program

Abstract

To provide an information processor capable of easily generating a selection problem from any document file, an information processing method, and an information processing program.SOLUTION: An information processor includes: an acquisition unit that acquires a document file including text data; a preprocessing unit that performs morphological analysis of the text data and adds a tag to each morpheme; and a generation unit that generates a question and an answer to a selection problem, which is the format to select an answer to the question from multiple choices, from the text data and generates an option of combination with the answer based on a tag attached to the answer and the degree of similarity with the tag attached to the morpheme; and a delivery unit that delivers the selection problem, in which the question generated by the generation unit, the answers, and choices are combined, to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program that generate multiple-choice questions from text data. [Background technology]

[0002] In order to measure the understanding of people who receive public information documents in companies or schools, technology is being used to automatically generate questions related to the documents.

[0003] For example, a technology is known that determines the content of questions based on the results of analyzing the layout of a document in a process of automatically generating questions (for example, Patent Document 1). Also, a technology is known that generates fill-in-the-blank questions based on a database prepared in advance (for example, Patent Document 2). Also, a technology is known that automatically generates multiple-choice questions to test comprehension in conjunction with dictionary data (for example, Patent Document 3). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2020-160158 [Patent Document 2] Japanese Patent Application Laid-Open No. 2012-234106 [Patent Document 3] Japanese Patent Application Laid-Open No. 2010-181651 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional technologies require adjusting the layout of document files, preparing a dedicated database, and preparing electronic dictionary data to link with questions. Therefore, even if there is a desire to conduct a simple test when distributing an internal document, advance preparation is required to automatically generate questions from the document, which places a burden on the person in charge.

[0006] Furthermore, while fill-in-the-blank questions can be generated using simple methods such as creating a few blank spaces in a document, multiple-choice questions consisting of a question and a set of options are preferable for measuring document comprehension. However, as mentioned above, automatic generation of multiple-choice questions requires preliminary preparation and is not easy.

[0007] Therefore, the present disclosure proposes an information processing device, an information processing method, and an information processing program that can easily generate multiple-choice questions from any document file. [Means for solving the problem]

[0008] In order to solve the above problems, the information processing device according to the present disclosure includes an acquisition unit that acquires a document file containing text data, a preprocessing unit that performs morphological analysis on the text data and assigns tags to each morpheme, a generation unit that generates, from the text data, questions and answers for multiple-choice questions in which an answer to a question is selected from a plurality of options, and generates options to be combined with the answers based on the similarity between the tags assigned to the answers and the tags assigned to the morphemes, and a distribution unit that distributes to a user multiple-choice questions that combine the questions, answers, and options generated by the generation unit. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an overview of information processing according to an embodiment. [Figure 2] FIG. 2 is a block diagram schematically illustrating the flow of information processing according to the embodiment. [Figure 3] FIG. 1 is a diagram illustrating an example of the configuration of an information processing device according to an embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of a text data storage unit according to the embodiment. [Figure 5] FIG. 4 is a diagram illustrating an example of a generation result storage unit according to the embodiment. [Figure 6] FIG. 10 is a diagram for explaining a generation process according to the embodiment. [Figure 7] 10 is a flowchart illustrating a procedure of information processing according to the embodiment. [Figure 8] FIG. 1 is a diagram (1) showing an application example of information processing according to an embodiment. [Figure 9] FIG. 2 is a diagram (2) showing an application example of information processing according to the embodiment. [Figure 10] FIG. 3 is a diagram showing an application example of information processing according to the embodiment. [Figure 11] FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the following embodiments, the same components are designated by the same reference numerals, and redundant description will be omitted.

[0011] (1. Embodiment) [1-1. Example of information processing according to the embodiment] Fig. 1 is a diagram schematically illustrating a flow of information processing according to an embodiment. The information processing according to the embodiment is executed by an information processing system 1 shown in Fig. 1. The information processing system 1 includes an information processing device 100, which is an example of an information processing device according to the present disclosure, and a user terminal 200. The devices included in the information processing system 1 are capable of transmitting and receiving data to and from each other via wireless communication or the like.

[0012] The information processing device 100 is an information processing device that acquires any document file and generates multiple-choice questions related to the content of the acquired document file. For example, the information processing device 100 receives a document file related to an internal alert and generates multiple-choice questions to measure employees' understanding based on the content of the document file. Note that a multiple-choice question is a question that has a format that combines a question in the form of a sentence, its answer, and incorrect answer choices. The information processing device 100 is, for example, a cloud server.

[0013] The user terminal 200 is a terminal device used by the user 10. For example, the user terminal 200 is a smartphone, a tablet terminal, or the like. The user 10 is, for example, an employee of the system department or the management department who creates a document file to alert employees in the company and distributes it within the company.

[0014] When distributing a document file to raise awareness or making some kind of announcement on the web, the person in charge may want to measure whether the content is properly understood by users. One example of an action to measure comprehension is to generate questions based on the content of the document file and present them to users. However, it is a heavy burden for the person who created the document file to create the questions every time. Furthermore, even when using automatic question generation technology, it is necessary to create a document file that conforms to a specified format, or it may only be possible to generate simple fill-in-the-blank questions.

[0015] In other words, there is a need for those in charge of issuing warnings to be able to use document files in any format, rather than in a specified format, and to be able to generate multiple-choice questions that are highly effective in measuring comprehension.

[0016] Therefore, the information processing device 100 according to the present disclosure solves the above problem by the information processing described below. Specifically, when the information processing device 100 according to the present disclosure acquires a document file containing text data, it performs morphological analysis on the text data and assigns tags to each morpheme. The information processing device 100 also generates questions and answers for multiple-choice questions from the text data, generates options to be combined with the answers based on the similarity between the tags assigned to the answers and the tags assigned to the morphemes, and delivers the generated multiple-choice questions to the user. This allows the information processing device 100 to easily generate multiple-choice questions from any document file. Below, an overview of information processing by the information processing system 1 will be described using FIG. 1.

[0017] In the example of Fig. 1, user 10 is an example of a user requesting the generation of questions related to a document file. User 10 transmits, via user terminal 200, document file 20 for which the user requests the generation of questions to information processing device 100 (step S1). As shown in Fig. 1, document file 20 is a document created for the purpose of alerting employees about the prevention of infectious diseases and informing them of countermeasures.

[0018] When the information processing device 100 acquires the document file 20, it analyzes the text data contained in the document file 20 and generates multiple-choice questions related to the content contained in the text data (step S2).

[0019] For example, the information processing device 100 generates two multiple-choice questions as shown in the generation result 21. Note that the information processing device 100 may generate any number of multiple-choice questions according to settings made by the user 10. The user 10 may also specify the number of options or generate different questions for each distribution target person.

[0020] Then, the information processing device 100 returns the generated result 21 to the user 10 (step S3). This allows the user 10 to obtain the multiple-choice questions related to the document file 20. The user 10 can also specify conditions such as a distribution date and time, and have the multiple-choice questions generated by the information processing device 100 distributed to employees, etc.

[0021] Next, an overview of the flow of information processing executed by the information processing device 100 will be described with reference to Fig. 2. Fig. 2 is a block diagram schematically showing the flow of information processing according to the embodiment.

[0022] First, the information processing device 100 acquires an arbitrary document file 30 (step S11). The document file 30 may be in any file format as long as it is a document containing text data. Alternatively, the document file 30 may be in any format as long as it contains a certain amount of text data, such as the text of an email to be distributed, regardless of the file format.

[0023] Next, if the acquired document file 30 contains a large amount of text data, the information processing device 100 performs document summarization to reduce the total amount of text data (step S12). For example, the information processing device 100 may perform summarization using an API (Application Programming Interface) provided by an arbitrary summarization service. Note that the information processing device 100 may not need to perform summarization depending on the amount of text data.

[0024] Next, the information processing device 100 performs a morphological analysis of the text data included in the acquired document file 30, and performs preprocessing to assign tags to each word (step S13). For example, the information processing device 100 assigns linguistic information (part of speech, meaning, pronunciation, lexeme, etc.) to be tagged to each word based on any dictionary data. Note that the information processing device 100 may use a user-specific dictionary in which linguistic information is described at this time. Through this process, the information processing device 100 assigns tags to each word in the text data. In other words, the information processing device 100 assigns features to each word in the text data.

[0025] The information processing device 100 also generates question and answer combinations (QA) for multiple-choice questions from the text data (step S14). For example, the information processing device 100 generates questions and answers using a trained natural language processing model that has undergone a predetermined learning process. As an example, the information processing device 100 uses a model for generating question sentences for each sentence or word included in the document file 30, assuming that each sentence or word is an answer. The information processing device 100 then determines the question and answer combinations based on the output answers and a score that evaluates whether the corresponding questions are appropriate (for example, whether the questions are written as natural question sentences). This process allows the information processing device 100 to output questions and answers that are close to the training data (learning data in which questions and answers each consist of a sentence) used during learning, thereby enabling the information processing device 100 to generate multiple-choice questions with combinations of question sentences and answers that appear appropriate (natural) to humans.

[0026] The above process is an example, and the information processing device 100 may generate combinations of questions and answers from the document file 30 using any known technology.

[0027] After generating combinations of questions and answers, the information processing device 100 extracts predetermined words based on the similarity between the tags attached to the answers and the tags attached to other morphemes, and adds the extracted words as options (step S15). For example, the information processing device 100 may add words that are similar to the answers in various elements, such as parts of speech, meanings, number of characters, and spelling, as options. The information processing device 100 may also generate word vectors from the feature amounts of each word in the document file 30, and extract words to be options based on the vector similarity.

[0028] For example, in the generation result 21 shown in FIG. 1, the information processing device 100 extracts "as attached" as the answer and generates a question that is appropriate for the question, "What should be the guidelines for dealing with a new infectious disease?" Then, the information processing device 100 extracts "infection prevention," "prevention of spread," and "ensure implementation" as phrases similar to "as attached," and adds them as options. Furthermore, the information processing device 100 extracts "dinner parties" as the answer and generates a question that is appropriate for the question, "What should you avoid, including lunch?" Then, the information processing device 100 extracts "hand washing," "conversation," and "preventive actions" as phrases similar to "dinner parties," and adds them as options.

[0029] As in the above example, the information processing device 100 does not necessarily extract only one word as an answer or an option, but may extract two or more consecutive words. Furthermore, the information processing device 100 may express the answer not as a single word, but as a natural sentence generated from the extracted words.

[0030] As described above with reference to FIGS. 1 and 2, when the information processing device 100 according to the embodiment acquires a document file 20 containing text data, it performs morphological analysis on the text data and assigns tags to each morpheme. The information processing device 100 then generates, from the text data, a question and an answer for a multiple-choice question in which the answer to the question is selected from multiple options, and generates options to be combined with the answer based on the similarity between the tag assigned to the answer and the tag assigned to the morpheme. Furthermore, the information processing device 100 distributes to the user 10 a multiple-choice question that combines the generated question, answer, and options.

[0031] In this way, the information processing device 100 can generate multiple-choice questions from a document file 20 of any format, making it possible to measure the level of understanding of users to whom the document file 20 is to be distributed and to reduce the effort required to create questions.

[0032] [1-2. Configuration of the information processing device according to the embodiment] Next, a description will be given of the configuration of the information processing device 100 that executes information processing according to the embodiment. Fig. 3 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment.

[0033] 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also include an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator who manages the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0034] The communication unit 110 is realized by, for example, a network interface controller or the like. The communication unit 110 is connected to a network N (for example, the Internet) by wire or wirelessly, and transmits and receives information to and from the user terminal 200 or the like via the network N. For example, the communication unit 110 may transmit and receive information using a communication standard or communication technology such as Wi-Fi (registered trademark), SIM (Subscriber Identity Module), or LPWA (Low Power Wide Area).

[0035] The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has a text data storage unit 121 and a generation result storage unit 122.

[0036] The text data storage unit 121 stores document files that are used to generate multiple-choice questions, and text data included in the document files. FIG. 4 illustrates an example of information stored in the text data storage unit 121. FIG. 4 is a diagram illustrating an example of the text data storage unit 121 according to the embodiment. In the example shown in FIG. 4, the text data storage unit 121 has items such as "data ID" and "text data."

[0037] "Data ID" indicates identification information for identifying data such as a document file received by the information processing device 100. "Text data" indicates the content of the text data contained in the document file, etc. Note that, for example, if the information processing device 100 receives a file containing audio, the text data may include a recognition result in which the audio data has been converted into text. Also, in Figures 4 and 5, the information stored in the storage unit 120 may be conceptually described as "B01," but in reality, the storage unit 120 stores specific information such as text data and data for generated multiple-choice questions.

[0038] The generation result storage unit 122 stores information related to multiple-choice questions generated by the information processing device 100. FIG. 5 illustrates an example of information stored in the generation result storage unit 122. FIG. 5 is a diagram illustrating an example of the generation result storage unit 122 according to the embodiment. In the example shown in FIG. 5, the generation result storage unit 122 has items such as "generation ID," "original data," "specified conditions," "distribution conditions," and "generation data."

[0039] "Generation ID" indicates identification information for identifying the generated multiple-choice questions. "Original data" indicates identification information for the data that is the source of the multiple-choice questions. "Specified conditions" indicate conditions specified by user 10 when generating multiple-choice questions. For example, the specified conditions may be the number of questions to be generated or a topic specified by user 10. For example, when a topic is specified by user 10, information processing device 100 makes adjustments to highly evaluate the score related to that topic, making it easier to generate multiple-choice questions related to that topic.

[0040] "Distribution conditions" indicate the conditions for distributing the generated multiple-choice questions. "Generated data" indicates the data of the generated multiple-choice questions (combinations of questions, answers, and options).

[0041] In the example shown in Figure 5, for example, the multiple-choice question identified by generation ID "E01" is a document file whose original data is identified by data ID "A01", the specified condition is "generate two multiple-choice questions", no particular distribution is specified, and the data for the generated multiple-choice question is "F01".

[0042] In another example shown in Figure 5, for example, a multiple-choice question identified by generation ID "E03" has original data as a document file identified by data ID "A01," and the specified condition is "to generate a multiple-choice question so that the question word includes 'infectious disease,'" and the question is set to be distributed at a specified date and time, and the data for the generated multiple-choice question is "F03."

[0043] Returning to Fig. 3, the explanation will be continued. The control unit 130 is realized by, for example, a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), or the like executing a program stored inside the information processing device 100 using a random access memory (RAM) or the like as a working area. The control unit 130 is also a controller, and is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0044] As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a preprocessing unit 132, a generation unit 133, and a distribution unit 134.

[0045] The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires a document file including text data from the user 10 or the like.

[0046] The acquisition unit 131 may accept files of various formats as document files. For example, the acquisition unit 131 may acquire a file scheduled for distribution that is scheduled to be distributed to employees as an email. In this case, the file scheduled for distribution may be a text file containing only text data. The acquisition unit 131 may also acquire a file containing audio. In this case, the acquisition unit 131 converts the audio into text using voice recognition and acquires the text data.

[0047] The preprocessing unit 132 performs morphological analysis on the text data acquired by the acquiring unit 131 and assigns a tag to each morpheme.

[0048] For example, the preprocessing unit 132 inputs text data into a trained natural language processing model and divides the text data into morphemes. Then, the preprocessing unit 132 refers to dictionary data or the like and assigns tags consisting of linguistic information to each word. The preprocessing unit 132 may also input the text data into a trained natural language processing model that analyzes the meaning and importance of each word in consideration of the context, and calculate a word vector for each word.

[0049] The generation unit 133 generates questions and answers for multiple-choice questions from the text data acquired by the acquisition unit 131, and also generates options to be combined with the answers based on the similarity between the tags attached to the answers and the tags attached to the morphemes.

[0050] At this time, the generating unit 133 may receive from the user 10 a setting as to how many multiple-choice questions to generate from the document file, and generate the set number of combinations of questions, answers, and options.

[0051] Furthermore, the generation unit 133 may receive from the user 10 a specification of a topic for which multiple-choice questions should be generated from the document file, and generate a combination of questions, answers, and options for the specified topic. For example, the generation unit 133 may receive from the user 10 a topic in the form of specifying a word, or may receive from the user 10 a topic in the form of including a word in a question.

[0052] The above generation processing will be described with reference to Fig. 6. Fig. 6 is a diagram for explaining the generation processing according to the embodiment.

[0053] FIG. 6 shows an example in which the information processing device 100 generates multiple-choice questions based on a document file 40.

[0054] At this time, the information processing device 100 receives question setting parameters 41 from the user 10. For example, the question setting parameters 41 include a question method, question words, distribution timing, etc. The question method is a specification of whether to select the correct answer or the incorrect answer, the number of options to be generated, and the question format, such as whether the answer is in sentence form or word form. The question words are words that the user desires to include in the question text. The distribution timing is the date and time at which the generated multiple-choice question is distributed, etc.

[0055] In the example of Fig. 6, it is assumed that the user 10 specifies the question method as "select the correct answer," the question word as "preventive measures," and the distribution timing as "one hour later" as question setting parameters 41. In this case, the information processing device 100 generates a multiple-choice question containing "preventive measures" in a format in which the user selects the correct answer, as shown in the generation result 42. Furthermore, the information processing device 100 distributes the multiple-choice question displayed in the generation result 42 to the distribution target one hour after generation.

[0056] In this way, the information processing device 100 can generate a variety of different multiple-choice questions based on arbitrary settings of the user 10 who requests question generation.

[0057] Furthermore, the generation unit 133 may generate a combination of questions, answers, and options based on conditions set in advance for each attribute of a user to whom delivery is scheduled.

[0058] Specifically, the generation unit 133 may generate different combinations of questions, answers, and options for each user attribute based on at least one of the content of the questions to be generated, the number of questions to be generated, and the timing of distribution as conditions preset for each user attribute.

[0059] For example, the generation unit 133 may further accept settings for the attributes of users to be distributed (for example, whether they are managers or department employees, or whether they belong to the systems department or not), question words that differ for each attribute, and distribution timing in the question setting parameters 41 shown in Fig. 6. This allows the generation unit 133 to generate multiple-choice questions in various modes, such as not distributing the generated multiple-choice questions to the company's systems department but only to other department employees, or generating questions other than system-related questions for the systems department and generating system-related questions for other department employees.

[0060] The generation unit 133 may also identify text data intended to be a request or a demand from the text data and generate a question from the identified portion. For example, in the example of FIG. 6, the document file 40 includes text intended to be a request or a demand, such as "Please perform virus scans regularly." The generation unit 133 extracts a portion intended to be a request or a demand using a known intention analysis process or the like, and sets words included in the extracted portion as question words. For example, the generation unit 133 adjusts the input to the model, such as by setting a high score for words included in the extracted portion, thereby making it easier to generate multiple-choice questions related to the question words. Generally, text intended to be a request or a demand often contains content that calls attention to the recipient. Therefore, by generating questions related to such portions, the information processing device 100 can more strongly call the user's attention and promote the user's understanding.

[0061] The generation unit 133 may also generate questions, answers, and options from text data included in a file to be distributed, such as an email. In this case, the subsequent distribution unit 134 distributes the multiple-choice questions generated from the text data included in the file to be distributed, along with the content of the file to be distributed. This allows the generation unit 133 to allow the user to view the document and the multiple-choice questions simultaneously, thereby enabling effective email distribution. Note that the distribution unit 134 may distribute links to web pages containing multiple-choice questions, rather than the multiple-choice questions themselves, as will be described later with reference to FIG. 10.

[0062] The distribution unit 134 distributes to users multiple-choice questions that combine the questions, answers, and options generated by the generation unit 133. In this case, the user includes not only the user 10 who requested the generation of the questions, but also other users (e.g., employees) who are the distribution targets.

[0063] The distribution unit 134 can also distribute multiple-choice questions at a date and time specified by the user 10. This allows the distribution unit 134 to distribute questions to employees, etc., to determine whether or not they have checked a document file, for example, several hours after the user 10 makes the document file public. The distribution unit 134 may also change the distribution destination based on attributes, such as not distributing multiple-choice questions to managers but only to section staff.

[0064] [1-3. Information Processing Procedure According to the Embodiment] Next, the procedure of processing according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the procedure of information processing according to the embodiment.

[0065] 7, the information processing device 100 determines whether or not a document file has been received (step S21). If the document file has not been received (step S21; No), the information processing device 100 waits until a document file is received.

[0066] On the other hand, when a document file is received (step S21; Yes), the information processing device 100 determines whether or not the document file needs to be summarized (step S22). If summarization is necessary (step S22; Yes), the information processing device 100 summarizes the text included in the document file (step S23).

[0067] After summarizing, or if summarizing is not necessary (step S22; No), the information processing device 100 performs preprocessing such as analyzing the text and attaching tags (step S24). In addition, the information processing device 100 accepts setting parameters related to question generation (step S25).

[0068] Then, the information processing device 100 generates questions and answers for the multiple choice questions (step S26). Subsequently, the information processing device 100 generates incorrect options (step S27).

[0069] Thereafter, the information processing device 100 determines whether or not the timing for distributing the generated multiple-choice questions has arrived (step S28). If it is not the timing for distribution (step S28; No), the information processing device 100 waits until the timing for distribution arrives.

[0070] On the other hand, if the distribution timing has arrived (step S28; Yes), the information processing device 100 distributes the multiple-choice question to the distribution target (step S29).

[0071] (2. Application Examples of the Embodiments) [2-1. Distribution of multiple choice questions] In the above embodiment, an example has been shown in which information processing is performed between the information processing device 100 according to the present disclosure and the user terminal 200. Here, the information processing according to the embodiment may be performed including the user terminal 250 that acquires the distributed questions. This point will be described with reference to FIG. 8. FIG. 8 is a diagram showing an application example (1) of the information processing according to the embodiment. The user terminal 250 shown in FIG. 8 is used by a user 60 who is the distribution target.

[0072] First, the user 10 who has created the document file 50 related to the warning accesses a multiple-choice question generation module via a network or the like to generate multiple-choice questions for the document file 50 (step S41). Note that the multiple-choice question generation module is synonymous with the information processing device 100.

[0073] The user 10 stores the document file 50 in the storage unit 120. The control unit 130 associated with the information processing device 100 acquires the document file 50 uploaded by the user 10 (step S42), and generates multiple-choice questions (step S43).

[0074] Then, the information processing device 100 distributes the generated result 51 to the user terminal 250 used by the user 60 at the date and time designated by the user 10 (step S44).

[0075] By this process, the user 10 can easily distribute to the user 60 multiple-choice questions created from the document file 50 in any format.

[0076] [2-2. Examples of application on web pages, etc.] Another application example when the information processing according to the embodiment is actually used will be described with reference to Fig. 9. Fig. 9 is a diagram showing an application example (2) of the information processing according to the embodiment.

[0077] 9, the user 10 uploads a document file to the response module 300 via the user terminal 200 (step S51). The response module 300 is a system that has a function of generating a web page or the like that lists the generated multiple-choice questions when a request for question generation is received.

[0078] The uploaded document file is received by the multiple-choice question generation module 410. The multiple-choice question generation module 410 corresponds to the multiple-choice question generation module shown in FIG.

[0079] The multiple-choice question generation module 410 sends the generated multiple-choice questions to the system 320, which converts the questions into multiple-choice question web pages (step S52). The system 320 generates a web page including the received multiple-choice questions (step S53).

[0080] The system 320 sends a link of the generated web page to the multiple-choice question generation module 410 (step S54). Furthermore, the multiple-choice question generation module 410 sends the link to the user 10 (step S55). This allows the user 10 to generate a web page including multiple-choice questions.

[0081] 9, the user 10 uploads educational materials used for educational purposes as document files to the response module 300. After that, the user 10 distributes the link to the webpage to the students, allowing them to answer multiple-choice questions and gauge their understanding.

[0082] [2-3. Examples of application in email distribution, etc.] Another application example when the information processing according to the embodiment is actually used will be described with reference to Fig. 10. Fig. 9 is a diagram showing an application example (3) of the information processing according to the embodiment.

[0083] 10, the user 10 uploads a document file to the distribution module 400 via the user terminal 200 (step S61). The distribution module 400 includes the response module shown in FIG. 9 and an email transmission module 330 that transmits emails.

[0084] The uploaded document file is received by the email transmission module 330. In Fig. 10, the document file may be the body of an email to be delivered to the user 60. The user 60 may also upload information such as a destination address and an attached file together with the document file.

[0085] The mail sending module 330 sends each piece of data received from the user 10 to the response module 300 (step S62). The response module 300 generates a web page including multiple choice questions, similar to the example shown in FIG.

[0086] System 320 sends the link of the generated web page to email sending module 330 (step S64). Email sending module 330 distributes the link of the web page to user 60 along with the body of the email (step S65). This allows user 10 to distribute an email to user 60 with, for example, an added comprehension check test link, making it easy to confirm whether user 60 has viewed the email or whether user 60 has understood the content of the email.

[0087] [2-4. Modifications] The information processing according to the embodiment may be modified in various ways. For example, although the information processing according to the embodiment is performed by the information processing device 100 connected to the user terminal 200 via a network N in the example shown, the user terminal 200 may perform the processing independently. In this case, the user terminal 200 has the same configuration as the information processing device 100 shown in FIG. 3.

[0088] (3. Other embodiments) The processing according to the above-described embodiment may be implemented in various different forms other than the above embodiment.

[0089] For example, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. Furthermore, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0090] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0091] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0092] Furthermore, the effects described in this specification are merely examples and are not limiting, and other effects may also be present.

[0093] (4. Effects of the information processing device according to the present disclosure) As described above, the information processing device according to the present disclosure (information processing device 100 in the embodiment) includes an acquisition unit (acquisition unit 131 in the embodiment), a preprocessing unit (preprocessing unit 132 in the embodiment), a generation unit (generation unit 133 in the embodiment), and a distribution unit (distribution unit 134 in the embodiment). The acquisition unit acquires a document file including text data. The preprocessing unit performs morphological analysis on the text data and assigns a tag to each morpheme. The generation unit generates, from the text data, questions and answers for multiple-choice questions in which an answer to a question is selected from multiple options, and generates options to be combined with the answers based on the similarity between the tags assigned to the answers and the tags assigned to the morphemes. The distribution unit distributes to the user the multiple-choice questions that combine the questions, answers, and options generated by the generation unit.

[0094] In this way, the information processing device according to the present disclosure can generate multiple-choice questions from document files of any format, thereby making it possible to measure the level of understanding of users to whom the document files are to be distributed and to reduce the effort required to create questions.

[0095] The generator also receives a setting for how many multiple-choice questions to generate from the document file, and generates the set number of combinations of questions, answers, and options.

[0096] In this way, the information processing device according to the present disclosure can generate the number of multiple-choice questions that meets the user's needs by accepting settings.

[0097] The generator also receives a specification of a topic from the document file for which multiple-choice questions should be generated, and generates a combination of questions, answers, and options related to the specified topic.

[0098] In this way, the information processing device according to the present disclosure can adjust the tendency of automatically generated multiple-choice questions to suit the user's needs by accepting the designation of a topic.

[0099] The generation unit also generates combinations of questions, answers, and options based on conditions set in advance for each attribute of a user to whom delivery is planned.

[0100] In this way, the information processing device according to the present disclosure can generate questions that correspond to a variety of situations, such as generating multiple-choice questions for each department within a company.

[0101] In addition, the generation unit generates different combinations of questions, answers, and options for each user attribute based on at least one of the content of the questions to be generated, the number of questions to be generated, and the timing of distribution as conditions preset for each user attribute.

[0102] In this way, by accepting conditions for each attribute, the information processing device according to the present disclosure can respond flexibly when distributing multiple-choice questions to a relatively large number of people, such as within a company, by distributing multiple-choice questions with content appropriate for each target.

[0103] The generation unit also identifies text data intended to be a request or a demand from the text data, and generates a question from the identified portion.

[0104] In this way, the information processing device according to the present disclosure can generate questions that are more effective in attracting attention and promoting understanding by generating questions that are in line with the intent of the original document.

[0105] The acquisition unit acquires a distribution-scheduled file as a document file that is scheduled to be distributed to the user. The generation unit generates questions, answers, and options from text data included in the distribution-scheduled file. The distribution unit distributes to the user multiple-choice questions that combine the questions, answers, and options generated from the text data included in the distribution-scheduled file, along with the content of the distribution-scheduled file.

[0106] In this way, the information processing device according to the present disclosure can measure whether the content of the email has been properly understood by including multiple-choice questions in emails or the like and delivering them.

[0107] (5. Hardware Configuration) Information devices such as the information processing device 100 and user terminal 200 according to the above-described embodiments are realized by a computer 1000 having a configuration as shown in FIG. 11, for example. The information processing device 100 according to the embodiment will be described below as an example. FIG. 11 is a hardware configuration diagram showing an example of the computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input / output interface 1600. The components of the computer 1000 are connected by a bus 1050.

[0108] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. For example, the CPU 1100 loads the programs stored in the ROM 1300 or the HDD 1400 into the RAM 1200 and executes processing corresponding to the various programs.

[0109] The ROM 1300 stores boot programs such as a Basic Input Output System (BIOS) executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000 .

[0110] HDD 1400 is a computer-readable recording medium that non-temporarily records programs executed by CPU 1100 and data used by such programs. Specifically, HDD 1400 is a recording medium that records a program that executes information processing according to the present disclosure, which is an example of program data 1450.

[0111] The communication interface 1500 is an interface for connecting the computer 1000 to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from other devices and transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

[0112] The input / output interface 1600 is an interface for connecting the input / output device 1650 and the computer 1000. For example, the CPU 1100 receives data from an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 also transmits data to an output device such as a display, a speaker, or a printer via the input / output interface 1600. The input / output interface 1600 may also function as a media interface for reading programs and the like recorded on a predetermined recording medium. Examples of media include optical recording media such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disk), magneto-optical recording media such as an MO (Magneto-Optical disk), tape media, magnetic recording media, and semiconductor memories.

[0113] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes an information processing program loaded onto the RAM 1200, thereby realizing functions of the control unit 130 and the like. The HDD 1400 stores programs for executing information processing according to the present disclosure and data in the storage unit 120. The CPU 1100 reads and executes program data 1450 from the HDD 1400, but as another example, the CPU 1100 may obtain these programs from another device via an external network 1550.

[0114] The embodiments of the present application have been described in detail above with reference to the drawings, but these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art. [Explanation of symbols]

[0115] 1. Information Processing Systems 100 Information processing device 110 Communications Department 120 Storage section 121 Text data storage unit 122 Generation result storage unit 130 control section 131 Acquisition Department 132 Preprocessing section 133 Generation part 134 Distribution Department 200 user terminals

Claims

1. an acquisition unit that acquires a document file including text data; a preprocessing unit that performs morphological analysis on the text data and assigns, for each morpheme, a tag indicating linguistic information corresponding to the morpheme; a generation unit that generates, from the text data, multiple-choice questions and answers in a format in which an answer to the question is selected from a plurality of options, and generates options to be combined with the answers from the text data based on the similarity between the tag attached to the morpheme corresponding to the answer by the preprocessing unit and the tags attached to other morphemes; a distribution unit that distributes multiple-choice questions that combine the questions, answers, and options generated by the generation unit to users; An information processing device comprising:

2. The generation unit Accepting a setting for the number of multiple-choice questions to be generated from the document file, and generating the set number of combinations of questions, answers, and options; 2. The information processing apparatus according to claim 1, wherein:

3. The generation unit Accepting a designation of a topic for which multiple-choice questions should be generated from the document file, and generating a combination of questions, answers, and options for the designated topic; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The generation unit generating a combination of the question, answer, and option based on a condition set in advance for each attribute of the user to whom the delivery is scheduled; 4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. The generation unit generating different combinations of questions, answers, and options for each attribute of the user based on at least one of the content of the questions to be generated, the number of questions to be generated, and the timing of distribution as conditions preset for each attribute of the user; 5. The information processing apparatus according to claim 4,

6. The generation unit Identifying text data intended as a request or a demand from the text data, and generating the question from the identified portion.

6. The information processing device according to claim 1, wherein the information processing device is a computer.

7. The acquisition unit A file scheduled for distribution to the user is acquired as the document file; The generation unit generating the questions, answers, and options from text data included in the file to be distributed; The distribution unit a multiple-choice question that combines the question, answer, and option combination generated from the text data included in the file to be distributed together with the content of the file to be distributed to the user; 7. The information processing device according to claim 1, wherein:

8. The computer Obtain a document file containing text data; performing a preprocessing step of morphologically analyzing the text data and assigning, for each morpheme, a tag indicating linguistic information corresponding to the morpheme; Generate, from the text data, a question and an answer for a multiple-choice question in a format in which an answer to the question is selected from a plurality of options, and generate options to be combined with the answer from the text data based on the similarity between the tag attached to the morpheme corresponding to the answer by the preprocessing and the tags attached to other morphemes; delivering a multiple-choice question that combines the generated questions, answers, and options to a user; An information processing method comprising:

9. Computer, an acquisition unit that acquires a document file including text data; a preprocessing unit that performs morphological analysis on the text data and assigns, for each morpheme, a tag indicating linguistic information corresponding to the morpheme; a generation unit that generates, from the text data, multiple-choice questions and answers in a format in which an answer to the question is selected from a plurality of options, and generates options to be combined with the answers from the text data based on the similarity between the tag attached to the morpheme corresponding to the answer by the preprocessing unit and the tags attached to other morphemes; a distribution unit that distributes multiple-choice questions that combine the questions, answers, and options generated by the generation unit to users; An information processing program characterized by causing the program to function as:

Images