Program, information processor, and method for processing information

Abstract

To provide a program, an information processor, and a method for processing information which can evaluate the difficulty according to the contents of a content more precisely.SOLUTION: The program according to an embodiment causes a computer to function as an input unit, an acquisition unit, and a determination unit. The input unit receives an input of a content. The acquisition unit acquires text information showing the contents of the content from the content. The determination unit determines the difficulty of the content on the basis of the text information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to a program, an information processing apparatus, and an information processing method.

Background Art

[0002] Conventionally, there has been known a technique for assisting a user in selecting educational content when the user selects educational content such as e-learning. For example, there are techniques for converting content into feature amounts, measuring the similarity between contents based on the feature amounts, and grouping similar contents.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, with the conventional technology, it has been difficult to more accurately evaluate the difficulty level according to the content of the content.

Means for Solving the Problems

[0005] The program according to the embodiment causes a computer to function as an input unit, an acquisition unit, and a determination unit. The input unit receives an input of content. The acquisition unit acquires text information indicating the content of the content from the content. The determination unit determines the difficulty level of the content based on the text information.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0007] Embodiments of a program, an information processing apparatus, and an information processing method will be described in detail below with reference to the accompanying drawings.

[0008] In the following embodiments, teaching materials for lessons provided in services that implement education such as schools, lifelong learning, or workplace education are used as examples of content.

[0009] In recent years, not only face-to-face classes but also online classes are conducted, and the class content is recorded and can be viewed on demand. Also, in e-learning, there are cases where teaching materials are displayed on the screen and lessons are conducted while implementing tests related to the class content. Based on such a background, in the following embodiments, the teaching materials are not limited to documents such as textbooks, but also include the voices and images of educational videos.

[0010] (First Embodiment) First, an example of the functional configuration of the information processing apparatus according to the first embodiment will be described.

[0011] [Example of Functional Configuration] FIG. 1 is a diagram showing an example of the functional configuration of the information processing apparatus 1 according to the first embodiment. The information processing apparatus 1 according to the first embodiment includes an input unit 101, an acquisition unit 102, a determination unit 103, a ranking unit 104, and a display control unit 105.

[0012] The input unit 101 receives the input of content. For example, the content is a document, voice, etc.

[0013] The acquisition unit 102 acquires text information indicating the content of the content from the content. For example, from content that is originally represented by text information such as a textbook, the text information is acquired. Also, for example, from voice content, text information is acquired by voice recognition and transcription, etc. Also, for example, from image content, text information is acquired using OCR (Optical Character Recognition), etc.

[0014] Note that the content may be provided with a title, description, etc., and the information provided in such content is also acquired as text information.

[0015] The determination unit 103 determines the difficulty level of the content based on the text information. Details of the method for determining the difficulty level will be described later.

[0016] The ranking unit 104 ranks a plurality of contents based on the difficulty levels of the plurality of contents.

[0017] The display control unit 105 displays display information including the content and the difficulty level of the content on a display device. Specifically, the display information includes a plurality of ranked contents. Note that the display device may be provided in a device separate from the information processing device 1, or may be provided as a display unit in the information processing device 1.

[0018] [Example of information processing method] FIG. 2 is a flowchart showing an example of the information processing method according to the first embodiment. First, the input unit 101 receives an input of content (step S1).

[0019] Next, the acquisition unit 102 extracts text information from the content (step S2).

[0020] Next, the determination unit 103 determines the difficulty level of the content from the text information (step S3). Several methods for determining the difficulty level are conceivable. For example, it is a method of determining the difficulty level based on a keyword list prepared in advance.

[0021] FIG. 3 is a diagram showing an example of the keyword list according to the first embodiment. In the keyword list of FIG. 3, keywords corresponding to each difficulty level are set. When the text information of the content includes the keywords set in the keyword list, the determination unit 103 determines the difficulty level of the content as the difficulty level corresponding to the keyword.

[0022] For example, when the text information obtained from the title of the content or the like includes "basic course for managers", the difficulty level of the content is determined to be elementary. Also, for example, when the text information obtained from the title of the content or the like includes "critical thinking application", the difficulty level of the content is determined to be advanced.

[0023] Also, for example, there is a method of determining the difficulty level using the length of the content. Specifically, the determination unit 103 determines a higher difficulty level as the content such as a textbook is thicker (the larger the number of pages). Also, the determination unit 103 determines a lower difficulty level as the content such as a textbook is thinner (the smaller the number of pages). That is, in the case of this determination method, the determination unit 103 determines a higher difficulty level of the content as the number of characters included as text information is larger.

[0024] Also, for example, there is a method of determining the difficulty level using the generality of words in the text information. It is considered that the content that uses many rare words that are not commonly used has a high difficulty level, and the content with many common words has a low difficulty level. For example, the determination unit 103 counts the number of documents containing each word using a large number of documents prepared in advance, and calculates the IDF (Inverse Document Frequency) using the following formula. IDF = (total number of documents) / (number of documents containing the word)

[0025] The smaller the IDF, the more common the word is included in various articles. The determination unit 103 calculates the IDF for each word included in the text information of the content. Then, the determination unit 103 sets the maximum value and average value of the calculated IDF as the IDF of the content. The determination unit 103 determines a higher difficulty level of the content as the IDF is higher.

[0026] Another method for determining difficulty level is to use the co-occurrence between words in text information. Co-occurrence is the rate at which words are used in the same document. Words related to similar topics have a high co-occurrence rate. For example, (calculus, linear algebra) has a high co-occurrence rate, but (calculus, curry rice) has a low co-occurrence rate. Content that deals with a wide range of topics has a low co-occurrence rate between words, while content that deals with a narrow range of topics has a high co-occurrence rate. Furthermore, the more specialized a word is, the higher the co-occurrence rate between words will be, as it is only used in specific topics. The determination unit 103 calculates the co-occurrence rate using the following formula. Co-occurrence rate = (number of documents containing word A and word B) / max(number of documents containing word A, number of documents containing word B)

[0027] Here, max(A,B) is a function that compares the value of A with the value of B and outputs the larger value.

[0028] For example, when the content is a document, the co-occurrence rate of "talk" and "tapioca" is calculated as follows. Number of documents containing "talk" and "tapioca": 50 Number of documents containing "talk": 1000 Number of documents containing "tapioca": 80 Co-occurrence rate = 50 / 1000 = 0.05

[0029] The word "talk" has a high frequency and therefore co-occurs with various words, but the co-occurrence with each word is not high. In order to correctly evaluate the co-occurrence rate with a frequently occurring word such as "talk", when calculating the co-occurrence rate, division is performed by the more frequent word. A large number of documents are used in advance to calculate the co-occurrence rates between words in the documents, and the calculation results are stored. The determination unit 103 obtains the co-occurrence rate using the stored values ​​for each word pair included in the text information of the content. The determination unit 103 then determines the maximum and average co-occurrence rates as the co-occurrence of the document. The determination unit 103 determines the difficulty level of the content to be higher the higher the co-occurrence.

[0030] The determination unit 103 determines the difficulty level numerically in each of the above-described determination methods. Note that the determination unit 103 may determine the difficulty level by any one of the above-described determination methods, or may determine the difficulty level based on the average of a plurality of difficulty levels output by each determination method.

[0031] Next, the ranking unit 104 ranks a plurality of contents based on the difficulty level determined in step S4, and rearranges the plurality of contents based on the ranking (step S4). Note that the ranking process in step S4 may be omitted.

[0032] Finally, the display control unit 105 displays display information in which the content name and the difficulty level are jointly noted on the display device (step S5).

[0033] As described above, in the information processing apparatus 1 according to the first embodiment, the input unit 101 receives the input of the content. The acquisition unit 102 acquires text information indicating the content of the content from the content. Then, the determination unit 103 determines the difficulty level of the content based on the text information.

[0034] Accordingly, according to the first embodiment, it is possible to more accurately evaluate the difficulty level according to the content of the content. (Second Embodiment) Next, the second embodiment will be described. In the description of the second embodiment, the same description as that of the first embodiment will be omitted, and the parts different from the first embodiment will be described.

[0035] [Example of Functional Configuration] FIG. 4 is a diagram showing an example of the functional configuration of the information processing apparatus 1-2 according to the second embodiment. The information processing apparatus 1-2 according to the second embodiment includes an input unit 101, an acquisition unit 102, a determination unit 103, a ranking unit 104, a display control unit 105, a conversion unit 106, a grouping unit 107, a dimensional compression unit 108, a mapping unit 109, and an imparting unit 110.

[0036] The input unit 101, the acquisition unit 102, the determination unit 103, and the display control unit 105 are the same as those in the first embodiment, and thus the description thereof is omitted.

[0037] The conversion unit 106 converts the content into feature amounts based on the text information. The feature amounts are represented, for example, by a multi-dimensional numerical vector indicating the features of the content.

[0038] The grouping unit 107 classifies a plurality of contents into one or more groups based on the feature amounts. The ranking unit 104 in the second embodiment ranks the plurality of contents within the group based on the difficulty levels of the plurality of contents.

[0039] The dimensionality reduction unit 108 compresses the dimensionality of the feature amounts to two dimensions. For example, methods such as principal component analysis (PCA), singular value decomposition, and t-distributed stochastic neighbor embedding (t-SNE) are used for the dimensionality reduction.

[0040] The mapping unit 109 maps a plurality of contents into a two-dimensional space based on the two-dimensional feature amounts.

[0041] The assigning unit 110 assigns a group name to the group based on the contents within the group. For example, the assigning unit 110 identifies words that are frequently used (for example, words whose usage frequency is greater than a threshold value) from the text information of the contents within the group, and assigns a name to each group based on the words that are frequently used. Also, for example, the assigning unit 110 generates the name of the group from the text information of the contents within the group using a text generation model.

[0042] [Example of information processing method] FIG. 5 is a flowchart showing an example of the information processing method according to the second embodiment. Steps S11 and S12 are the same as steps S1 and S2 (see FIG. 2) in the first embodiment, and thus the description thereof is omitted.

[0043] After the text information is acquired in step S12, the conversion unit 106 converts the text information into feature amounts represented by multi-dimensional numerical vectors (step S13). Several conversion methods for step S13 are conceivable. For example, there is a conversion method called Bag of Words. In Bag of Words, a large number of documents are prepared in advance, and a word list is created from those documents. For the text information of each content, a vector with the dimension of the number of words in the word list is prepared, and the number of occurrences of each word in the text information is set as the value of each element of the vector. Alternatively, the value obtained by multiplying the number of occurrences of each word by its IDF may be set as the value of each element of the vector.

[0044] Also, as the conversion method for step S13, a pre-trained machine learning model such as a Transformer may be used.

[0045] Next, the grouping unit 107 groups similar contents into one group based on the feature amounts obtained in step S13 (step S14). As the grouping method, for example, an unsupervised clustering method such as k-means is used. k-means is a method that does not require labels of clusters etc., and when the number of clusters is specified, it divides the contents into that number of clusters. In the process of step S14, a pre-trained clustering model may be used. Also, when there is a large amount of content, the clustering model used in step S14 may be trained with the feature amounts of the content.

[0046] Next, the determination unit 103 determines the difficulty level of the content (step S15).

[0047] Next, the ranking unit 104 determines the ranking of the contents within the group (step S16). Note that in the second embodiment, the ranking between the contents of different groups is not considered.

[0048] When the feature amount calculated in step S13 is high-dimensional, it is difficult to visualize. Therefore, the dimensionality reduction unit 108 converts the feature amount calculated in step S13 into a two-dimensional vector by performing dimensionality reduction on the feature amount (step S17).

[0049] Next, the mapping unit 109 maps each content converted into a two-dimensional vector into a two-dimensional space (step S18). Next, the assigning unit 110 assigns a name to each group (step S19).

[0050] Next, the display control unit 105 displays display information including the content grouped into groups and the difficulty level of the content within the group on the display device (step S20). The display information of the second embodiment shows the relationship between a plurality of contents based on the distance between the plurality of contents in the two-dimensional space based on the two-dimensional space in which each content is mapped in step S18.

[0051] [Example of display information] FIG. 6 is a diagram showing an example of the display information of the second embodiment. The example of FIG. 6 is a display example when each content is mapped into a two-dimensional space. In the example of FIG. 6, the similarity between contents and the similarity between groups are visualized in the two-dimensional space, so it becomes possible to know which groups are similar to each other. Also, in the example of FIG. 6, the difficulty level of each content within the group is displayed by numbers.

[0052] When there are a wide variety of skills to be learned and difficulty level settings, it is not possible to compare the difficulty levels of the contents within the group just by grouping as in the conventional case, so it is not known which content within the group should be selected.

[0053] According to the display information of the second embodiment shown in FIG. 6, since the difficulty level based on the content (text information) of the content can be presented, the user can more easily grasp the content to be selected.

[0054] (Third Embodiment) Next, the third embodiment will be described. In the description of the third embodiment, the same explanations as those in the second embodiment will be omitted, and the differences from the second embodiment will be described.

[0055] [Example of functional configuration] FIG. 7 is a diagram showing an example of the functional configuration of the information processing apparatus 1-3 according to the third embodiment. The information processing apparatus 1-3 according to the third embodiment includes an input unit 101, an acquisition unit 102, a determination unit 103, a ranking unit 104, a display control unit 105, a conversion unit 106, a grouping unit 107, a dimensional compression unit 108, a mapping unit 109, an imparting unit 110, and a division unit 111.

[0056] The input unit 101, the acquisition unit 102, the determination unit 103, the ranking unit 104, the display control unit 105, the conversion unit 106, the grouping unit 107, the dimensional compression unit 108, the mapping unit 109, and the imparting unit 110 are the same as those in the second embodiment, so the description thereof will be omitted.

[0057] The division unit 111 divides the content into one or more segments based on the text information. In the second embodiment, the same processing as that in the second embodiment is performed in units of segments instead of content units.

[0058] [Example of information processing method] FIG. 8 is a flowchart showing an example of the information processing method according to the third embodiment. Steps S31 and S32 are the same as steps S1 and S2 (see FIG. 2) in the first embodiment, so the description thereof will be omitted.

[0059] The division unit 111 divides the content into one or more segments based on the text information acquired in step S32 (step S33). In the processing from step S34 onward, the same processing as that in the second embodiment is performed in units of segments instead of content units. Note that when there is one segment included in the content, the content and the segment are the same.

[0060] Several methods for segmenting segments can be considered. For example, in the case of text information with chapter headings such as textbooks, the segmentation unit 111 performs segment segmentation based on the units defined within the text information, such as by chapter or by paragraph.

[0061] Also, for example, when the content is represented by text, the segmentation unit 111 uses a text segmentation method to segment the text. Specifically, text information such as the speech recognition result obtained from the audio content does not have a chapter structure like a textbook, so a chapter structure is assigned by text segmentation. In text segmentation, a machine learning model that has been learned in advance is used to assign a chapter structure to the text, and segment segmentation is performed based on the units for each chapter structure.

[0062] Also, for example, the segmentation unit 111 segments the text using a topic model method such as LDA (Latent Dirichlet Allocation). The topic model is a method of assigning a topic suitable for the text from among a predefined number of topics. The topic model is learned from a large number of documents with a predefined number of topics.

[0063] When a new document is input to the topic model, it is estimated which topic the document belongs to. For example, the segmentation unit 111 segments the long text information obtained from the content into a fixed number of sentences, and estimates the topic for each segmented part. Then, the segmentation unit 111 performs segment segmentation where the topic changes. By doing so, segments are segmented at the topic transition.

[0064] Also, for example, in the case of audio content, etc., the segmentation unit 111 may perform segment segmentation using not only text information but also timings with long silent periods and sound effects, or timings with large changes in the video screen.

[0065] [Example of display information] FIG. 9 is a diagram showing Example 1 of display information according to the third embodiment. In the example of FIG. 9, each content is divided into four groups ("corporate ethics", "mental health", "critical thinking", and "logical thinking"), and the rankings within the groups are displayed. By displaying each content as in the example of FIG. 9, the user can easily select the content.

[0066] For example, from the content name "Introduction to Management" alone, it is not specifically clear what kind of content it includes. As shown in the example of FIG. 9, if it is displayed that "Introduction to Management" is in the same group as the contents "Basic Corporate Ethics", "Personal Information Protection", and "Internal Control", the user can understand that they can learn about corporate ethics and other related contents from "Introduction to Management". In this way, even content with an abstract title can have its content inferred from other contents by being grouped according to its content (text information). Also, since there are rankings for each group, the user can also know which content to take.

[0067] Here, in the example of FIG. 9, the content "Thinking Methods" is classified into two groups ("Critical Thinking" and "Logical Thinking"). This is because "Thinking Methods" is divided into two segments by the dividing unit 111, one segment is classified as "Critical Thinking", and the other segment is classified as "Logical Thinking". In the example of FIG. 9, "Thinking Methods" is displayed in two groups ("Critical Thinking" and "Logical Thinking") in a form where the two segments are combined.

[0068] As in the example of "Introduction to Thinking Methods", one content may include multiple contents. In such a case, since it cannot be appropriately processed by performing feature quantification and grouping at the content unit level, the segment division by the above-mentioned dividing unit 111 is performed.

[0069] FIG. 10 is a diagram showing Example 2 of display information according to the third embodiment. The example of FIG. 10 is a display example when each content is mapped to a two-dimensional space. In the example of FIG. 10, "thinking methods" are classified into two groups ("critical thinking" and "logical thinking").

[0070] FIG. 11 is a diagram showing Example 3 of display information according to the third embodiment. The example of FIG. 11 shows the case where each content is classified into five groups. Also, in the example of FIG. 11, "introduction to thinking methods" is classified into three segments, and "introduction to thinking methods" is classified into three groups. Also, in the example of FIG. 11, the order of taking courses is displayed by arrows in ascending order of the difficulty level of the content. Also, in the example of FIG. 11, the completed content and the uncompleted content are displayed in a distinguishable manner. Note that, as in the example of FIG. 11, the group names may not be displayed.

[0071] As described above, in the information processing apparatus 1-3 according to the third embodiment, the splitting unit 111 splits the content into one or more segments based on the text information. The conversion unit 106 converts the segment into a feature amount based on the text information included in the segment. The grouping unit 107 classifies a plurality of segments into one or more groups based on the feature amount, and for the content split into a plurality of segments, each segment is classified into a different group. The ranking unit 104 ranks a plurality of segments in the group based on the difficulty level of the plurality of segments. Also, the display information according to the third embodiment includes, for example, as shown in FIGS. 9 to 11, a plurality of segments grouped and ranked for each group.

[0072] (Fourth Embodiment) Next, the fourth embodiment will be described. In the description of the fourth embodiment, an embodiment will be described in which the content ranked by the information processing apparatus 1 (1-2, 1-3) according to the first to third embodiments is recommended to the user. [Example of Functional Configuration] FIG. 12 is a diagram showing an example of the functional configuration of the information processing apparatus 1-4 according to the fourth embodiment. The information processing apparatus 1-4 according to the fourth embodiment includes a user level input unit 112, a specifying unit 113, a display control unit 114, a target level input unit 115, a query input unit 116, a storage unit 117, and a storage control unit 118.

[0073] The user level input unit 112 receives the user level of the user. For example, the user level indicates the degree of understanding of the user measured for each group. Specifically, there is a method of using the learning history for measuring the user level. For example, if there is content that the user has completed learning within the group, the user level of that user may be regarded as having reached the difficulty level of that content. Also, for example, an understanding test may be created from each piece of content, and the user level may be measured based on the scores of the understanding test.

[0074] The specifying unit 113 specifies content with a difficulty level corresponding to the user level.

[0075] The display control unit 114 displays display information including the specified content and the difficulty level of the specified content on a display device. Note that the display device may be provided in a device separate from the information processing apparatus 1-4, or may be provided as a display unit in the information processing apparatus 1-4.

[0076] The target level input unit 115 receives a target level indicating the level that the user aims for. For example, the target level indicates the level that the user should reach and is set for each group. When a target level is input to the target level input unit 115, the specifying unit 113 further specifies content with a higher level than the target level. Then, the display control unit 114 displays on the display device the display information in which the content with a difficulty level corresponding to the user level and the content with a higher level than the target level are identified.

[0077] The query input unit 116 receives a query used for searching for content. When a query is input to the query input unit 116, for example, the specifying unit 113 specifies content with a difficulty level corresponding to the user level in the group and content with a difficulty level higher than the target level in the group, and then further specifies content that matches the query. Then, the display control unit 114 displays display information including the content that matches the query on the display device.

[0078] The storage unit 117 is a database that stores the content ranked by the information processing apparatus 1 (1-2, 1-3) of the first to third embodiments. Specifically, the storage unit 117 is a storage device that stores content and the difficulty level determined based on the text information obtained from the content. Further, the storage unit 117 may further store identification information for identifying the group to which the content belongs.

[0079] The storage control unit 118 performs storage control such as reading, adding, deleting, or updating the data stored in the storage unit 117.

[0080] [Example 1 of Information Processing Method] FIG. 13 is a flowchart showing Example 1 of the information processing method of the fourth embodiment. First, the user level input unit 112 receives an input of the user level (step S51). Next, the target level input unit 115 receives an input of the target level (step S52). Note that the input of the target level in step S52 may be omitted.

[0081] The specifying unit 113 specifies the content recommended to the user based on the user level input in step S51, the target level input in step S52, and the difficulty level of the content (step S53).

[0082] Next, the display control unit 114 displays display information including the content specified in step S53 on the display device (step S54).

[0083] [Example of Display Information] FIG. 14 is a diagram showing Example 1 of display information according to the fourth embodiment. The display information in FIG. 14 includes content below the user level (for example, acquired (attended) content) and recommended content. The recommended content is, for example, unacquired (unattended) content with a higher difficulty level than the user level.

[0084] Note that it is desirable that the content within a group be attended in ascending order of difficulty. For example, in the example of FIG. 10, the content is attended in the order of difficulty level (1) (thinking method, mental health, manager introduction), difficulty level (2) (introduction to critical thinking, anger management, basic corporate ethics), difficulty level (3) (application of critical thinking, intermediate logical thinking, mentoring, personal information protection), and difficulty level (4) (practice of critical thinking, advanced logical thinking, internal control). Also, the specific part 123 may specify the order of attendance including a plurality of contents in different groups, and the order of attendance may be recommended by the display control unit 114. For example, in the example of FIG. 10 described above, the distance between groups indicates the similarity between the groups, but it is conceivable to recommend the content in order from the group with a higher similarity so that it is easier for the user to attend.

[0085] Specifically, in the example of FIG. 10, when the content is attended in the order of group similarity, the order is critical thinking → logical thinking → mental health → corporate ethics, or the reverse order.

[0086] In addition, the specific part 113 may calculate the average difficulty level of the recommended content within the group, identify the recommended content of the group with a lower difficulty level, and recommend taking courses from the recommended content of the group with an even lower difficulty level. In the example of FIG. 14, the average difficulty level of the recommended content included in business ethics is 2.5, the average difficulty level of the recommended content included in mental health is 3, the average difficulty level of the recommended content included in critical thinking is 4, and the average difficulty level of the recommended content included in logical thinking is 3. Therefore, when taking courses in the order of difficulty level of the recommended content, the order is business ethics → mental health → logical thinking → critical thinking.

[0087] FIG. 15 is a diagram showing Example 2 of the display information of the fourth embodiment. The example of FIG. 15 shows the display information output when, for example, the target level of a mid-level employee is input. The display information in FIG. 15 includes content below the user level (for example, content that has been acquired (taken)), recommended content, and content higher than the target level.

[0088] FIG. 16 is a diagram showing Example 3 of the display information of the fourth embodiment. The example of FIG. 16 shows the display information output when, for example, the target level of the manager layer is input. Since the target level of the manager layer is higher than that of the mid-level employee, in the example of FIG. 16, more courses are recommended than in the case of the example of FIG. 15.

[0089] In addition, in the fourth embodiment, the recommended content may be specified based on further query input from the user. [Example 2 of Information Processing Method] FIG. 17 is a flowchart showing Example 2 of the information processing method of the fourth embodiment. First, the query input unit 116 receives a query input (step S61).

[0090] The query may be a word such as "logical thinking" or "accounting processing", or a sentence such as "for managers", "ways not to get irritated", or "how to train juniors".

[0091] Search using a query can be performed by searching the content text with the words in the query, or by converting the query in the conversion unit 106 and outputting, as search results, content with a high degree of similarity between the query feature amount and the content feature amount.

[0092] Steps S62 and S63 are the same as steps S51 and S52 described above, so the description thereof is omitted.

[0093] Next, the specifying unit 113 specifies the content recommended for the user based on the query input in step S61, the user level input in step S62, the target level input in step S63, and the difficulty level of the content (step S64). Specifically, the specifying unit 113 searches the text information obtained from the content with the query, and specifies the recommended content from among the content corresponding to the query.

[0094] When a plurality of contents are searched, the specifying unit 113 may further specify the order recommended for the user based on the target level input in step S63 and the difficulty level of the content.

[0095] Next, the display control unit 114 displays, on the display device, display information including the content specified in step S64 (step S65). The display control unit 114 outputs not only the search results by the query simply, but also display information for recommending content according to the user level and the target level.

[0096] Note that the search target by the query may be not only at the content unit but also at the group unit. In the case of the group unit, a group including the corresponding content is output.

[0097] As described above, according to the information processing apparatus 1-4 of the fourth embodiment, the user can more easily grasp the content to be selected.

[0098] Finally, an example of the hardware configuration of the information processing apparatus 1 (1-2, 1-3, 1-4) according to the first to fourth embodiments will be described.

[0099] [Example of Hardware Configuration] FIG. 18 is a diagram showing an example of the apparatus configuration of the information processing apparatus 1 (1-2, 1-3, 1-4) according to the first to fourth embodiments. The information processing apparatus 1 (1-2, 1-3, 1-4) according to the first to fourth embodiments includes a processor 201, a main storage device 202, an auxiliary storage device 203, a display device 204, an input device 205, and a communication device 206. The processor 201, the main storage device 202, the auxiliary storage device 203, the display device 204, the input device 205, and the communication device 206 are connected via a bus 210.

[0100] Note that the information processing apparatus 1 (1-2, 1-3, 1-4) may not include some of the above configurations. For example, when the information processing apparatus 1 (1-2, 1-3, 1-4) can utilize the input function and display function of an external device, the information processing apparatus 1 (1-2, 1-3, 1-4) may not be provided with the display device 204 and the input device 205.

[0101] The processor 201 executes a program read from the auxiliary storage device 203 into the main storage device 202. The main storage device 202 is a memory such as a ROM and a RAM. The auxiliary storage device 203 is an HDD (Hard Disk Drive), a memory card, or the like.

[0102] The display device 204 is, for example, a liquid crystal display or the like. The input device 205 is an interface for operating the information processing apparatus 1 (1-2, 1-3, 1-4). Note that the display device 204 and the input device 205 may be realized by a touch panel or the like having a display function and an input function. The communication device 206 is an interface for communicating with other devices.

[0103] For example, the program executed by the information processing apparatus 1 (1-2, 1-3, 1-4) is a file in an installable format or an executable format, and is recorded on a computer-readable storage medium such as a memory card, hard disk, CD-RW, CD-ROM, CD-R, DVD-RAM, and DVD-R, and is provided as a computer program product.

[0104] Also, for example, the program executed by the information processing apparatus 1 (1-2, 1-3, 1-4) may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.

[0105] Also, for example, the program executed by the information processing apparatus 1 (1-2, 1-3, 1-4) may be configured to be provided via a network such as the Internet without being downloaded. Specifically, it may be configured to execute information processing by a so-called ASP (Application Service Provider) type service that realizes a processing function only by an execution instruction and result acquisition from a server computer without transferring the program.

[0106] Also, for example, the program of the information processing apparatus 1 (1-2, 1-3, 1-4) may be configured to be provided by being pre-embedded in a ROM or the like.

[0107] The program executed by the information processing apparatus 1 (1-2, 1-3, 1-4) has a module configuration including functions that can also be realized by the program among the above-described functional configurations. Each of these functions, as actual hardware, is such that when the processor 201 reads and executes the program from the storage medium, each of the above functional blocks is loaded onto the main storage device 202. That is, each of the above functional blocks is generated on the main storage device 202.

[0108] Note that a part or all of each of the functions described above may be realized by hardware such as an IC (Integrated Circuit) instead of by software.

[0109] Alternatively, each function may be realized by using a plurality of processors 201. In that case, each processor 201 may realize one of the functions or two or more of the functions.

[0110] Although some embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention and are included in the invention described in the claims and the equivalent scope thereof.

Description of Reference Numerals

[0111] 1 Information processing apparatus 101 Input unit 102 Acquisition unit 103 Decision unit 104 Ranking unit 105 Display control unit 106 Conversion unit 107 Grouping unit 108 Dimension compression unit 109 Mapping unit 110 Assignment unit 111 Division unit 112 User level input unit 113 Identification unit 114 Display control unit 115 Target level input unit 116 Query input unit 117 Storage unit 118 Storage control unit 201 Processor 202 Main memory device 203 Auxiliary storage device 204 Display device 205 Input device 206 Communication device 210 Bus

Claims

1. A program for causing a computer to function as an input unit that receives an input of content, an acquisition unit that acquires text information indicating the content of the content from the content, and a determination unit that determines the difficulty level of the content based on the text information.

2. The program according to claim 1, further causing the computer to function as a display control unit that displays display information including the content and the difficulty level of the content on a display device.

3. The program according to claim 2, further causing the computer to function as a ranking unit that ranks a plurality of the contents based on the difficulty levels of the plurality of contents, wherein the display information includes the plurality of ranked contents.

4. The program according to claim 3, further causing the computer to function as a conversion unit that converts the content into feature amounts based on the text information, and a grouping unit that classifies the plurality of contents into one or more groups based on the feature amounts, wherein the ranking unit ranks the plurality of contents within a group based on the difficulty levels of the plurality of contents, and the display information includes the plurality of contents grouped by group and ranked by group.

5. The program according to claim 4, wherein the feature amount is a multi-dimensional numerical vector indicating the features of the content.

6. The program according to claim 4 or 5, further causing the computer to function as a dimensional compression unit that compresses the dimension of the feature amount into two dimensions, and a mapping unit that maps the plurality of contents into a two-dimensional space based on the two-dimensional feature amount, wherein the display information indicates the relationship between the plurality of contents based on the distance between the plurality of contents in the two-dimensional space.

7. The program according to claim 4 or 5, further causing the computer to function as an assignment unit that assigns a group name to the group based on the contents within the group, wherein the display information further includes the group name of the group.

8. The program according to claim 4 or 5, further causing the computer to function as a division unit that divides the content into one or more segments based on the text information, and a conversion unit that converts the segment into feature amounts based on the text information included in the segment. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ Based on the feature amount, classifying a plurality of the segments into one or more groups, and for the content segmented into a plurality of segments, a grouping unit that classifies each segment into a different group, and further functions as, the ranking unit ranks a plurality of the segments within a group based on the difficulty levels of the plurality of segments, the display information includes the plurality of ranked segments grouped for each group, The program according to claim 3.

9. An input unit that receives an input of content, an acquisition unit that acquires text information indicating the content of the content from the content, a determination unit that determines the difficulty level of the content based on the text information, An information processing apparatus comprising the above.

10. A step in which an information processing apparatus receives an input of content, a step in which the information processing apparatus acquires text information indicating the content of the content from the content, a step in which the information processing apparatus determines the difficulty level of the content based on the text information, An information processing method including the above.

Images