JP2012189624A - Learning support device, learning support method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To report the learning situation of a more appropriate rival to a learner to be supported.SOLUTION: A learning support device includes a similar learner detection unit which detects, on the basis of learner information including a learning goal, a learning level, and a learning style, a similar learner having similar characteristics of the learner information and a similar learner information providing unit which provides a learner to be supported with the learner information of a learner similar to the learner to be supported, detected by the similar learner detection unit.

Description

  The present technology relates to a learning support device, a learning support method, and a program.

  The existence of rivals is valuable for effective learning. For example, learning efficiency increases by competing with rivals or sharing information with rivals. But finding rivals is difficult. You may be able to find a rival by chance in an environment where you have a group life such as school or work. However, in a personal learning environment, it may be difficult to find rivals that are doing the same kind of learning.

  In view of these circumstances, a system for automatically selecting rivals has been developed. For example, Patent Document 1 below discloses a method for selecting rivals using information such as test scores, age, and sex. Further, regarding a method for increasing motivation of learning, Patent Document 2 below proposes a system that provides each learner's position in a learner set. Furthermore, regarding a method for grasping the learning situation, Patent Document 3 below proposes a method for measuring the learner's proficiency level based on changes in brain activity.

JP 2004-192523 A JP 2010-204883 A JP 2004-170958 A

  Although various techniques as described above have been developed, there is no technique for automatically selecting a suitable rival according to the learning goal or learning style of the learner. However, the learning efficiency improvement effect obtained by knowing rival information during the course of learning is difficult to discard. Therefore, the present technology has been devised in view of the circumstances as described above, and the intent of the present technology is to inform the support target learner of a more suitable rival learning situation. A new and improved learning support apparatus, learning support method, and program are provided.

  In order to solve the above problem, according to one aspect of the present technology, based on learner information including a learning goal, a proficiency level, and a learning style, a similar learner that detects similar learners whose features of the learner information are similar A learner detection unit, and a similar learner information providing unit for providing learner information of a similar learner similar to the learner of the support target detected by the similar learner detection unit to the learner of the support target A learning support device is provided.

  The learning support apparatus includes a clustering unit that clusters learning content, a class cluster extraction unit that extracts an attribution cluster of learning content that a learner has taken, and an attribution cluster extracted by the class cluster extraction unit. A feature amount acquisition unit that acquires a feature amount for each learning target from an attribution cluster having the maximum degree of attribution, and a learning target corresponding to the maximum value among the feature amounts for each learning target acquired by the feature amount acquisition unit And a learning target determining unit that determines the selected learning target as the learning target of the learner.

  The learning support apparatus includes a clustering unit that clusters learning content, a class cluster extraction unit that extracts an attribution cluster of learning content that a learner has taken, and an attribution cluster extracted by the class cluster extraction unit. A feature quantity acquisition unit that acquires a feature quantity for each learning style from the attribution cluster having the maximum degree of attribution, and the learning style of the learner based on the feature quantity for each learning style acquired by the feature quantity acquisition unit. And a learning style determination unit for determining.

  Further, the feature amount acquisition unit may be configured to further acquire a feature amount for each learning style from the belonging cluster having the maximum degree of belonging among the belonging clusters extracted by the course cluster extracting unit. . Furthermore, the learning support apparatus may further include a learning style determination unit that determines the learning style of the learner based on the feature amount for each learning style acquired by the feature amount acquisition unit.

  In addition, the learning support device described above has a condition that allows the same learner to belong to a plurality of clusters based on the feature amount for each learning target and the feature amount for each learning style acquired by the feature amount acquisition unit. A learner clustering unit for clustering learners below may be further provided.

  In addition, the learning style determination unit is configured to determine the learning style of the learner based on time information indicating a learner's attendance status and information entropy calculated from a feature value for each learning style. May be.

  The similar learner detection unit is similar to the support learner by performing vector matching using a vector that combines the feature quantity for each learning target and the feature quantity for each learning style. May be configured to detect.

  In addition, the learning support apparatus includes a feature vector calculation unit that calculates a vector that combines a feature amount for each learning target and a feature amount for each learning style for all learning contents to be recommended, and the feature vector calculation A predetermined number in the order from the vector calculated by the unit to the vector that combines the feature amount for each learning target and the feature amount for each learning style corresponding to the learner to be supported acquired by the feature amount acquisition unit. And a learning content recommendation unit that recommends learning content corresponding to the vector extracted by the feature vector extraction unit to the support target learner.

  Further, the learning support device includes a learning target feature value calculation unit that calculates a learning target feature value obtained by summing the feature values for each learning target for each learner having the same learning target as the support target learner. A proficiency level evaluation unit that evaluates the proficiency level of the support target learner by comparing the maximum value of the target learning feature value with the target learning feature value calculated for the support target learner. Furthermore, you may provide.

  The learning support apparatus includes a relationship extraction unit that extracts a relationship between a learning target determination term for determining a predetermined learning target and the predetermined learning target by machine learning, and a learner describes on a social network. A discriminant term extracting unit for extracting the learning target discriminating term from the text obtained, and learning indicating the strength of the relationship extracted by the relation extracting unit for each learning target discriminating term extracted by the discriminant term extracting unit A learning target weight value calculation unit for calculating a target weight value, and a learning target related to a learning target determination term having a maximum total value by summing the learning target weight values calculated for each learning target determination term And a learning target determination unit that determines the learning target of the learner as a learning target.

  In addition, the learning support device includes a relationship extraction unit that extracts a relationship between a learning style determination term for determining a predetermined learning style and the predetermined learning style by machine learning, and a learner describes on a social network A discriminant term extracting unit for extracting the learning style discriminant term from the determined text, and learning indicating the strength of the relationship extracted by the relationship extracting unit for each learning style discriminant term extracted by the discriminant term extracting unit A learning style weight value calculation unit for calculating a weight value for each style, and a learning style related to the learning style determination term having the maximum total value by summing the weight values for each learning style calculated for each learning style determination term. And a learning style determination unit that determines the learning style of the learner.

  The learning support apparatus may further include a subjective expression extracting unit that extracts positive subjective expressions and negative subjective expressions from text described by the learner on the social network. In this case, the similar learner information providing unit compares the amount of positive subjective expression extracted by the subjective expression extracting unit with the amount of negative subjective expression for the similar learner, and compares the comparison result with the similar learning. To the learner as the support target as learner information indicating the motivation of the learner.

  The learning support apparatus may further include a proficiency level change observation unit that observes the proficiency level change and a progress level evaluation unit that evaluates the progress level according to the increase in the proficiency level. Good.

  In order to solve the above problem, according to another aspect of the present technology, based on learner information including a learning target, a proficiency level, and a learning style, similar learners with similar features of the learner information are obtained. Similar learner information providing a similar learner detection step to detect and learner information of a similar learner similar to the learner of the support target detected in the similar learner detection step to the support target learner A learning support method including a providing step.

  In order to solve the above problem, according to another aspect of the present technology, based on learner information including a learning target, a proficiency level, and a learning style, similar learners with similar features of the learner information are obtained. Similar learner information providing a similar learner detection function to detect and learner information of a similar learner similar to the support target learner detected by the similar learner detection function to the support target learner A program for causing a computer to provide the provided function is provided.

  In order to solve the above problem, according to another aspect of the present technology, a computer-readable recording medium on which the above-described program is recorded is provided.

  As described above, according to the present technology, it is possible to inform a support target learner of a more suitable rival learning situation.

It is explanatory drawing which showed the function structure of the learning assistance apparatus which concerns on one Embodiment of this technique. It is explanatory drawing which showed the function structure of the reaction analysis module which concerns on the same embodiment. It is explanatory drawing which showed the function structure of the environment analysis module which concerns on the same embodiment. It is explanatory drawing which showed the function structure of the learning experience module which concerns on the embodiment. It is explanatory drawing which showed the function structure of the information sharing module between learners which concerns on the embodiment. It is explanatory drawing which showed the function structure of the learner group analysis module which concerns on the embodiment. It is explanatory drawing which showed the function structure of the rival search and recommendation module which concerns on the embodiment. It is explanatory drawing which showed the function structure of the learning content search and recommendation module which concerns on the embodiment. It is explanatory drawing which showed the function structure of the learning arrival stage analysis module which concerns on the same embodiment. It is explanatory drawing which showed the function structure of the learning content management module which concerns on the embodiment. It is explanatory drawing which showed the function structure of the information integration module which concerns on the embodiment. It is explanatory drawing for demonstrating the reaction analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the reaction analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the reaction analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the environment analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the environment analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the environment analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the information sharing process between learners concerning the embodiment. It is explanatory drawing for demonstrating the information sharing process between learners concerning the embodiment. It is explanatory drawing for demonstrating the information sharing process between learners concerning the embodiment. It is explanatory drawing for demonstrating the information sharing process between learners concerning the embodiment. It is explanatory drawing for demonstrating the learner group analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning target which concerns on the same embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the automatic measurement process of the learning style which concerns on the embodiment. It is explanatory drawing for demonstrating the learner group analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the rival search and recommendation process which concerns on the embodiment. It is explanatory drawing for demonstrating the rival search and recommendation process which concerns on the embodiment. It is explanatory drawing for demonstrating the rival search and recommendation process which concerns on the embodiment. It is explanatory drawing for demonstrating the learning content search and recommendation process which concerns on the same embodiment. It is explanatory drawing for demonstrating the learning content search and recommendation process which concerns on the same embodiment. It is explanatory drawing for demonstrating the learning content search and recommendation process which concerns on the same embodiment. It is explanatory drawing for demonstrating the learning arrival stage analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the learning arrival stage analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the learning arrival stage analysis process which concerns on the same embodiment. It is explanatory drawing for demonstrating the information integration process which concerns on the same embodiment. It is explanatory drawing for demonstrating the information integration process which concerns on the same embodiment. It is explanatory drawing for demonstrating the information integration process which concerns on the same embodiment. It is explanatory drawing for demonstrating the information integration process which concerns on the same embodiment. It is explanatory drawing for demonstrating the whole flow of the learning experience process which concerns on the embodiment. It is explanatory drawing for demonstrating the whole flow of the learning experience process which concerns on the embodiment. It is explanatory drawing for demonstrating the whole flow of the learning experience process which concerns on the embodiment. It is explanatory drawing for demonstrating the calculation process of the motivation which concerns on the same embodiment. It is explanatory drawing for demonstrating the calculation process of the progress which concerns on the embodiment. It is explanatory drawing which showed the hardware structural example of the information processing apparatus which can implement | achieve the function of the learning assistance apparatus which concerns on the embodiment.

  Hereinafter, preferred embodiments according to the present technology will be described in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

[About the flow of explanation]
Here, the flow of explanation described below will be briefly described.

  First, the functional configuration of the learning support apparatus 100 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the reaction analysis module 101 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the environment analysis module 102 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the learning experience module 103 according to the present embodiment will be described with reference to FIG. Next, a functional configuration of the inter-learner information sharing module 104 according to the present embodiment will be described with reference to FIG.

  Next, the functional configuration of the learner group analysis module 105 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the rival search / recommendation module 106 according to the present embodiment will be described with reference to FIG. Next, a functional configuration of the learning content search / recommendation module 107 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the learning arrival stage analysis module 108 according to the present embodiment will be described with reference to FIG. Next, the functional configuration of the learning content management module 109 according to the present embodiment will be described with reference to FIG. Next, a functional configuration of the information integration module 110 according to the present embodiment will be described with reference to FIG.

  Next, the reaction analysis process according to the present embodiment will be described with reference to FIGS. Next, the environment analysis process according to the present embodiment will be described with reference to FIGS. Next, the inter-learner information sharing process will be described with reference to FIGS. Next, a learner group analysis process according to the present embodiment will be described with reference to FIGS. In this section, an automatic measurement method for learning objectives and learning styles will be described. Next, rival search / recommendation processing according to the present embodiment will be described with reference to FIGS. 43 to 45. Next, the learning content search / recommendation process according to the present embodiment will be described with reference to FIGS. 46 to 48.

  Next, the learning arrival stage analysis processing according to the present embodiment will be described with reference to FIGS. 49 to 51. Next, the information integration process according to the present embodiment will be described with reference to FIGS. 52 to 55. Next, an overall flow of the learning experience process according to the present embodiment will be described with reference to FIGS. 56 to 58. Next, motivation calculation processing according to the present embodiment will be described with reference to FIG. Next, a progress degree calculation process according to the present embodiment will be described with reference to FIG. Next, a hardware configuration example of an information processing apparatus capable of realizing the function of the learning support apparatus according to the present embodiment will be described with reference to FIG.

(Description item)
1: Configuration of Learning Support Device 100 1-1: Overall Module Configuration 1-2: Functional Configuration of Reaction Analysis Module 101 1-3: Functional Configuration of Environment Analysis Module 102 1-4: Functional Configuration of Learning Experience Module 103 1-5: Functional configuration of inter-learner information sharing module 104 1-6: Functional configuration of learner group analysis module 105 1-7: Functional configuration of rival search / recommendation module 106 1-8: Learning content search / recommendation module 1-9: Functional configuration of learning arrival stage analysis module 108 1-10: Functional configuration of learning content management module 109 1-11: Functional configuration of information integration module 110 2: Operation of learning support apparatus 100 2- 1: Reaction analysis process 2-2: Environmental analysis process 2-3: Information sharing process between learners With and 2-4: For learner group analysis processing
2-4-1: Overall processing
2-4-2: Automatic measurement of learning target # 1 (distribution information base)
2-4-3: Automatic measurement of learning style # 1 (distribution information base)
2-4-4: Automatic measurement of learning target # 2 (SNS base)
2-4-5: Automatic measurement of learning style # 2 (SNS base)
2-5: Rival search / recommendation process 2-6: Learning content search / recommendation process 2-7: Learning arrival stage analysis process 2-8: Information integration process 2-9: Overall learning experience process About flow 2-10: About calculation processing of motivation 2-11: About calculation processing of progress 2-12: Effect 3: Example of hardware configuration

<1: Configuration of the learning support apparatus 100>
Hereinafter, the configuration of the learning support apparatus 100 according to the present embodiment will be described.

[1-1: Overall module configuration]
First, the module configuration of the learning support apparatus 100 will be described with reference to FIG.

  Note that the learning support apparatus 100 may be configured by one information processing apparatus or an information processing system configured by a plurality of information processing apparatuses. For example, some of the modules constituting the learning support apparatus 100 may be a network distributed information processing system configured on a network such as a cloud system. Some of the modules constituting the learning support apparatus 100 include a mobile phone, an information terminal, a personal computer, an information appliance, a television receiver, a recording / playback apparatus, a portable music player, and a car navigation system held by the learner. It may be.

  As illustrated in FIG. 1, the learning support apparatus 100 includes a reaction analysis module 101, an environment analysis module 102, a learning experience module 103, an inter-learner information sharing module 104, and a learner group analysis module 105. The learning support apparatus 100 further includes a rival search / recommendation module 106, a learning content search / recommendation module 107, a learning arrival stage analysis module 108, a learning content management module 109, and an information integration module 110. Hereinafter, the functional configuration of each module will be described with reference to FIGS.

[1-2: Functional configuration of reaction analysis module 101]
As shown in FIG. 2, the reaction analysis module 101 includes a reaction analysis module detection unit 1011, a reaction analysis module input unit 1012, a reaction analysis module storage unit 1013, and a reaction analysis module calculation unit 1014. The reaction analysis module 101 may be connected to an input device, a voice recognition device, an image recognition device, a biological information sensor, or the like.

  Examples of the input device include a mouse, a keyboard, a remote controller (hereinafter referred to as a remote controller), and a touch sensor. The speech recognition device has a function of recognizing speech uttered by a learner (hereinafter referred to as a user). In addition, the image recognition apparatus has a function of recognizing user characteristics (for example, a face and a posture). The biological information sensor has a function of detecting biological data such as data on cortisol (a hormone substance secreted in response to stress).

  The reaction analysis module detection unit 1011 acquires information (hereinafter referred to as reaction information) such as voice, image, and biological reaction in real time during the learning experience of the user. Then, the reaction analysis module detection unit 1011 stores the acquired reaction information in the reaction analysis module storage unit 1013 in time series. In addition, the timing which acquires reaction information is controlled by the reaction analysis module calculating part 1014.

  The reaction analysis module input unit 1012 acquires data (hereinafter, learner input data) input by the user using an input device such as a pointing device during the user's learning experience. Then, the reaction analysis module input unit 1012 stores the acquired learner input data in the reaction analysis module storage unit 1013 in time series.

  The reaction analysis module storage unit 1013 stores the reaction information acquired by the reaction analysis module detection unit 1011 and the learner input data acquired by the reaction analysis module input unit 1012. For example, the reaction analysis module storage unit 1013 stores position information pointed by the input device, voice data, image data, biological reaction data, and the like.

  The reaction analysis module calculation unit 1014 analyzes learner input data and reaction information stored in the reaction analysis module storage unit 1013. The analysis process by the reaction analysis module calculation unit 1014 may be performed online or offline. The analysis result by the reaction analysis module calculation unit 1014 is stored in the reaction analysis module storage unit 1013. Further, the analysis result by the reaction analysis module calculation unit 1014 is transmitted to the information integration module 110.

  The functional configuration of the reaction analysis module 101 has been described above. Note that the function of the reaction analysis module calculation unit 1014 may be transferred to the learning experience module 103 as necessary. The reaction analysis module calculation unit 1014 reads out the reaction information and learner input data stored in the reaction analysis module storage unit 1013 when another module requests reaction information and learner input data. Send to.

[1-3: Functional configuration of environment analysis module 102]
As shown in FIG. 3, the environment analysis module 102 includes an environment analysis module detection unit 1021, an environment analysis module storage unit 1022, and an environment analysis module calculation unit 1023. The environment analysis module 102 may be connected to a radio clock, a GPS receiver, a voice recognition device, an image recognition device, a biological information sensor, or the like.

  The radio timepiece is used, for example, to acquire time information during a user learning experience. The GPS receiver is used, for example, to acquire location information during the user's learning experience. In addition, the voice recognition device, the image recognition device, and the biological information sensor are used to detect information on the situation at the time of the user's learning experience and the user's mood, for example.

  The environment analysis module detection unit 1021 acquires information (hereinafter, environment information) related to the time, place, user's situation, user's mood, and the like during the user's learning experience in real time. Then, the environment analysis module detection unit 1021 stores the acquired environment information in the environment analysis module storage unit 1022 in time series. Note that the timing for acquiring environment information is controlled by the environment analysis module calculation unit 1023.

  The environment analysis module storage unit 1022 stores the environment information detected by the environment analysis module detection unit 1021. The environment analysis module calculation unit 1023 analyzes the environment information stored in the environment analysis module storage unit 1022. Note that the analysis processing by the environment analysis module calculation unit 1023 may be performed online or offline. The analysis result by the environment analysis module calculation unit 1023 is stored in the environment analysis module storage unit 1022. Further, the analysis result by the environment analysis module calculation unit 1023 is transmitted to the information integration module 110.

  The functional configuration of the environment analysis module 102 has been described above. Note that the function of the environment analysis module calculation unit 1023 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests environment information, the environment analysis module calculation unit 1023 reads the environment information stored in the environment analysis module storage unit 1022 and transmits it to the other module.

[1-4: Functional configuration of learning experience module 103]
As illustrated in FIG. 4, the learning experience module 103 includes a learning experience module input unit 1031, a learning experience module display unit 1032, a learning experience module storage unit 1033, and a learning experience module calculation unit 1034. The function of the learning experience module 103 is realized by a mobile phone, an information terminal, a personal computer, an information home appliance, a television receiver, a recording / playback device, a portable music player, a car navigation system, etc. that can be used by the user for learning. .

  The learning experience module input unit 1031 is an input device such as a keyboard, a mouse, a remote controller, or a touch panel. Information (learner input data) input by the learning experience module input unit 1031 is input to the learning experience module calculation unit 1034.

  The learning experience module calculation unit 1034 transmits learner input data (user operation content (for example, input of proficiency, goal, learning style, etc.)) input from the learning experience module input unit 1031 to the information integration module 110. . Further, the learning experience module calculation unit 1034 receives information such as the results of search and recommendation regarding rivals, the results of search and recommendation regarding learning contents, and the learning status of rivals transmitted from the information integration module 110 to store the learning experience module. The data is stored in the unit 1033.

  The learning experience module calculation unit 1034 controls the screen display of the learning experience module display unit 1032. For example, the learning experience module calculation unit 1034 displays information on rivals or learning content stored in the learning experience module storage unit 1033 on the learning experience module display unit 1032 (see FIG. 21). The learning experience module calculation unit 1034 controls the layout of the GUI displayed on the learning experience module display unit 1032.

  The learning experience module storage unit 1033 stores learner input data used by the learning experience module calculation unit 1034. The learning experience module storage unit 1033 stores search results and recommendation results related to rivals or learning content transmitted from the information integration module 110. The learning experience module display unit 1032 displays search results and recommendation results related to rivals or learning content in accordance with control by the learning experience module calculation unit 1034.

  In addition, the learning experience module display unit 1032 displays a GUI screen for displaying rival related information (for example, profile and learning status) and learning content related information (for example, metadata and reason for recommendation). . Furthermore, the learning experience module display unit 1032 can also display the learning content itself. For example, the function of the learning experience module display unit 1032 is realized by an output device such as a monitor, a speaker, or a printer.

  As information displayed on the learning experience module display unit 1032, in addition to information stored in the learning experience module storage unit 1033, a GUI screen for prompting the user to operate, a user selects a rival or learning content There is related information displayed in case.

  The functional configuration of the learning experience module 103 has been described above. The learning experience module calculation unit 1034 is requested when other modules request information stored in the learning experience module storage unit 1033, such as learner input data, rivals, and learning content search results and recommendation results. Information sent to other modules. For example, the learning experience module calculation unit 1034 transmits the information stored in the learning experience module storage unit 1033 to the rival search / recommendation module 106 and the learning content search / recommendation module 107 via the information integration module 110.

[1-5: Functional configuration of inter-learner information sharing module 104]
As shown in FIG. 5, the inter-learner information sharing module 104 includes an inter-learner information sharing module storage unit 1041 and an inter-learner information sharing module calculation unit 1042. The inter-learner information sharing module 104 is a software module and network module for sharing learning status and information between users and communicating between users. A social network is constructed by the inter-learner information sharing module 104.

  The inter-learner information sharing module storage unit 1041 stores information related to the learning status such as the learning group, the user's proficiency level, the user's goal, and the user's learning style transmitted from the information integration module 110. Further, the inter-learner information sharing module storage unit 1041 stores interactive text between users and shared content (for example, text, moving images, still images, audio, etc.) between users. Further, the inter-learner information sharing module storage unit 1041 stores the calculation result by the inter-learner information sharing module calculation unit 1042.

  The inter-learner information sharing module calculation unit 1042 performs an operation related to information sharing between users for information related to the learning status stored in the inter-learner information sharing module storage unit 1041, conversation text between users, and shared content between users. Execute. For example, the inter-learner information sharing module calculation unit 1042 associates information to be shared between users according to rival relationships between users (for example, “no relationship”, “cooperation relationship”, “competitive relationship”, etc.). Do.

  Further, the inter-learner information sharing module calculation unit 1042 stores the association result in the inter-learner information sharing module storage unit 1041. Further, the inter-learner information sharing module calculation unit 1042 transmits the association result to the information integration module 110.

  The functional configuration of the inter-learner information sharing module 104 has been described above. Note that the function of the inter-learner information sharing module calculation unit 1042 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests information stored in the inter-learner information sharing module storage unit 1041, the inter-learner information sharing module calculation unit 1042 reads out the information and transmits it to the other module.

[1-6: Functional configuration of learner group analysis module 105]
As shown in FIG. 6, the learner group analysis module 105 includes a learner group analysis module analysis unit 1051 and a learner group analysis module storage unit 1052. The learner group analysis module 105 performs an analysis on a similar learner group according to the user's proficiency level, the user's goal, and the user's learning style. For example, the function of the learner group analysis module 105 is realized using an information processing device such as a server device or a client device, or a software module that controls these information processing devices.

  The learner group analysis module storage unit 1052 stores the user's proficiency level transmitted from the information integration module 110, the user's goal, the input content regarding the user's learning style, and the analysis result regarding the user's learning achievement stage. Further, the learner group analysis module storage unit 1052 stores the calculation result by the learner group analysis module analysis unit 1051.

  The learner group analysis module analysis unit 1051 displays the analysis results regarding the user's proficiency level, the user's goal, the user's learning style input content, and the user's learning achievement stage stored in the learner group analysis module storage unit 1052. Used to analyze similar learners. Then, the learner group analysis module analysis unit 1051 stores the analysis result of the similar learner group in the learner group analysis module storage unit 1052. The learner group analysis module analysis unit 1051 transmits the analysis result of the similar learner group to the information integration module 110.

  The functional configuration of the learner group analysis module 105 has been described above. Note that the function of the learner group analysis module analysis unit 1051 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests information stored in the learner group analysis module storage unit 1052, the learner group analysis module analysis unit 1051 reads out the information and transmits it to the other module.

[1-7: Functional Configuration of Rival Search / Recommendation Module 106]
As illustrated in FIG. 7, the rival search / recommendation module 106 includes a rival search / recommendation module calculation unit 1061 and a rival search / recommendation module storage unit 1062. The rival search / recommendation module 106 is a module that realizes rival search and rival recommendation. For example, the function of the rival search / recommendation module 106 is realized by using an information processing apparatus such as a server apparatus or a client apparatus, or a software module that controls these information processing apparatuses.

  The rival search / recommendation module storage unit 1062 receives user response information, environment information, operation information, preference information, input content related to proficiency / goal / learning style, and analysis results related to the learning achievement stage transmitted from the information integration module 110. Remember. The rival search / recommendation module storage unit 1062 stores the user preference information extracted by the rival search / recommendation module calculation unit 1061. Further, the rival search / recommendation module storage unit 1062 stores the calculation result by the rival search / recommendation module calculation unit 1061.

  The rival search / recommendation module calculation unit 1061 stores user reaction information, environment information, operation information, preference information, input content related to proficiency / goal / learning style, and learning stored in the rival search / recommendation module storage unit 1062 Search for rivals and recommend rivals using the analysis results regarding the stage of arrival. The rival search / recommendation module calculation unit 1061 stores the rival search result and the rival recommendation result in the rival search / recommendation module storage unit 1062. Further, the rival search / recommendation module calculation unit 1061 transmits a rival search result and a rival recommendation result to the information integration module 110.

  In addition, the rival search / recommendation module calculation unit 1061 updates the user preference information using information stored in the rival search / recommendation module storage unit 1062. Then, the rival search / recommendation module calculation unit 1061 stores the updated preference information in the rival search / recommendation module storage unit 1062.

  The functional configuration of the rival search / recommendation module 106 has been described above. Note that the function of the rival search / recommendation module calculation unit 1061 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests information stored in the rival search / recommendation module storage unit 1062, the rival search / recommendation module calculation unit 1061 reads out the information and transmits it to the other module.

[1-8: Functional Configuration of Learning Content Search / Recommendation Module 107]
As shown in FIG. 8, the learning content search / recommendation module 107 includes a learning content search / recommendation module calculation unit 1071 and a learning content search / recommendation module storage unit 1072. The learning content search / recommendation module 107 is a module for realizing learning content search and learning content recommendation. For example, the function of the learning content search / recommendation module 107 is realized by using an information processing apparatus such as a server apparatus or a client apparatus, or a software module that controls these information processing apparatuses.

  The learning content search / recommendation module storage unit 1072 includes metadata of learning content transmitted from the information integration module 110, user reaction information, environment information, operation information, preference information, input content related to proficiency / target / learning style, And the analysis result regarding the learning achievement stage is stored. The learning content search / recommendation module storage unit 1072 stores user preference information extracted by the learning content search / recommendation module calculation unit 1071. Further, the learning content search / recommendation module storage unit 1072 stores the calculation result by the learning content search / recommendation module calculation unit 1071.

  The learning content search / recommendation module calculation unit 1071 includes metadata of learning content stored in the learning content search / recommendation module storage unit 1072, user reaction information, environment information, operation information, preference information, proficiency level / target / Search of learning content and recommendation of learning content are performed using the input content related to the learning style and the analysis result related to the learning achievement stage. The learning content search / recommendation module calculation unit 1071 stores the learning content search result and the learning content recommendation result in the learning content search / recommendation module storage unit 1072. Further, the learning content search / recommendation module calculation unit 1071 transmits the search result of learning content and the recommendation result of learning content to the information integration module 110.

  The functional configuration of the learning content search / recommendation module 107 has been described above. Note that the function of the learning content search / recommendation module calculation unit 1071 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests information stored in the learning content search / recommendation module storage unit 1072, the learning content search / recommendation module calculation unit 1071 reads out the information and transmits it to the other module.

[1-9: Functional configuration of learning arrival stage analysis module 108]
As illustrated in FIG. 9, the learning arrival stage analysis module 108 includes a learning arrival stage analysis module analysis unit 1081 and a learning arrival stage analysis module storage unit 1082. The learning achievement stage analysis module 108 performs an analysis on the learning achievement level of the user. For example, the function of the learning arrival stage analysis module 108 is realized by using an information processing apparatus such as a server apparatus or a client apparatus, or a software module that controls these information processing apparatuses.

  The learning attainment stage analysis module storage unit 1082 stores the input content related to the user's proficiency / goal / learning style transmitted from the information integration module 110, user reaction information, environment information, operation information, and the like. Further, the learning arrival stage analysis module storage unit 1082 stores a calculation result related to the learning arrival stage by the learning arrival stage analysis module analysis unit 1081.

  The learning attainment stage analysis module analysis unit 1081 uses input contents relating to the user's proficiency / goal / learning style, user reaction information, environment information, operation information, and the like stored in the learning attainment stage analysis module storage unit 1082. Analyze the learning achievement stage. Then, the learning arrival stage analysis module analysis unit 1081 stores the analysis result of the learning arrival stage analysis in the learning arrival stage analysis module storage unit 1082. Further, the learning arrival stage analysis module analysis unit 1081 transmits the analysis result of the learning arrival stage analysis to the information integration module 110.

  The functional configuration of the learning arrival stage analysis module 108 has been described above. Note that the function of the learning arrival stage analysis module analysis unit 1081 may be transferred to the learning experience module 103 as necessary. In addition, when another module requests information stored in the learning arrival stage analysis module storage unit 1082, the learning arrival stage analysis module analysis unit 1081 reads out the information and transmits it to the other module.

[1-10: Functional Configuration of Learning Content Management Module 109]
As illustrated in FIG. 10, the learning content management module 109 includes a learning content management module calculation unit 1091 and a learning content management module storage unit 1092. The learning content management module 109 is a module for managing learning content and distributing learning content. For example, the function of the learning content management module 109 is realized using a broadcast device, an information processing device such as a server device or a client device, or a software module that controls these devices or devices.

  The learning content management module storage unit 1092 stores metadata of learning content. Further, the metadata stored in the learning content management module storage unit 1092 is updated in a timely manner according to the operating rules of the distribution source that distributes the learning content.

  The learning content management module calculation unit 1091 manages learning content data such as moving images, still images, sounds, texts, web pages, and language information resources. The learning content management module calculation unit 1091 transmits learning content data and language information resources to the information integration module 110. For example, the function of the learning content management module calculation unit 1091 corresponds to the function of a distribution server of a television broadcasting system, the function of a Web server or a streaming content server on the Internet, and the like.

  The functional configuration of the learning content management module 109 has been described above. In addition, when another module requests information stored in the learning content management module storage unit 1092, the learning content management module calculation unit 1091 reads out the information and transmits it to the other module as necessary.

[1-11: Functional Configuration of Information Integration Module 110]
As illustrated in FIG. 11, the information integration module 110 includes an information integration module management unit 1101 and an information integration module storage unit 1102. The information integration module 110 is a module responsible for integration and relay of information between modules. For example, the function of the information integration module 110 is realized by using an information processing device such as a server device or a client device, or a software module that controls these devices or devices.

  The information integration module storage unit 1102 stores information transmitted and received by the information integration module management unit 1101 in time series. Also, the information integration module management unit 1101 manages various information received from other modules and transmits it to a desired module in response to a request. In addition, the information integration module 110 controls transmission / reception timing and priority based on a calculation load and operation rules in a part or the whole of the learning support apparatus 100. The information integration module management unit 1101 stores information to be transmitted and received in the information integration module storage unit 1102 as necessary.

  The functional configuration of the information integration module 110 has been described above.

(Modification)
The module configuration of the learning support apparatus 100 according to the present embodiment has been described above. However, the module configuration described here is an example and can be changed as appropriate. For example, information can be directly exchanged between the modules, and the information integration module 110 can be omitted. In addition, the processing may be performed based on the user operation content that can be acquired by the learning experience module 103 without using the reaction analysis module 101 or the environment analysis module 102. 1 shows a form in which all modules are connected via the information integration module 110, but each module may be connected via a network such as the Internet or an intranet. In this case, the network may be wired or wireless. As described above, the module configuration can be variously modified.

<2: Operation of Learning Support Device 100>
Next, the operation of the learning support apparatus 100 according to the present embodiment will be described with reference to FIGS. Hereinafter, various processes performed by the learning support apparatus 100 will be described.

[2-1: Reaction analysis process]
First, the reaction analysis process will be described with reference to FIGS. The reaction analysis process described here is mainly executed by the reaction analysis module 101.

  As shown in FIG. 12, first, the reaction analysis module 101 determines whether or not to detect reaction information (S101). When detecting reaction information, the reaction analysis module 101 advances the process to step S102. On the other hand, when the reaction information is not detected, the reaction analysis module 101 advances the process to step S103. When the process proceeds to step S102, the reaction analysis module 101 detects the reaction information and stores the detected reaction information (S102). For example, the reaction analysis module 101 detects reaction information such as voice data, image data, and biological data as shown in FIG.

  When the process proceeds to step S103, the reaction analysis module 101 determines whether or not to analyze the reaction information (S103). When analyzing the reaction information, the reaction analysis module 101 advances the process to step S104. On the other hand, when the reaction information is not analyzed, the reaction analysis module 101 advances the process to step S105. When the process proceeds to step S104, the reaction analysis module 101 analyzes the reaction information and stores the analysis result (S104). For example, as shown in FIG. 14, the reaction analysis module 101 extracts subjective utterances from audio data, extracts a user's smile level and concentration level from image data, and extracts a stress level from biometric data. Or

  When the process proceeds to step S105, the reaction analysis module 101 determines whether to transmit the analysis result to the information integration module 110 (S105). When transmitting an analysis result to the information integration module 110, the reaction analysis module 101 advances the process to step S106. On the other hand, when the analysis result is not transmitted to the information integration module 110, the reaction analysis module 101 ends a series of processes related to the reaction analysis. When the process proceeds to step S106, the reaction analysis module 101 transmits the analysis result to the information integration module 110 (S106).

  The reaction analysis process has been described above.

[2-2: Environmental analysis processing]
Next, the environment analysis process will be described with reference to FIGS. The environment analysis process described here is mainly executed by the environment analysis module 102.

  As shown in FIG. 15, first, the environment analysis module 102 determines whether or not to detect environment information (S111). When detecting environment information, the environment analysis module 102 advances the process to step S112. On the other hand, when the environment information is not detected, the environment analysis module 102 advances the process to step S113. When the process proceeds to step S112, the environment analysis module 102 detects the environment information and stores the detected environment information (S112). For example, the environment analysis module 102 detects environmental information such as date / time data, location data, and situation data as shown in FIG.

  When the process proceeds to step S113, the environment analysis module 102 determines whether to analyze the environment information (S113). When analyzing environment information, the environment analysis module 102 advances the process to step S114. On the other hand, when the environment information is not analyzed, the environment analysis module 102 advances the process to step S115. When the process proceeds to step S114, the environment analysis module 102 analyzes the environment information and stores the analysis result (S114). For example, as shown in FIG. 17, the environment analysis module 102 converts date and time data into expressions such as “Monday” and “daytime”, converts place data into expressions such as “home”, and experiences from situation data. Or extracting a sharer.

  When the process proceeds to step S115, the environment analysis module 102 determines whether or not to transmit the analysis result to the information integration module 110 (S115). When transmitting the analysis result to the information integration module 110, the environment analysis module 102 advances the process to step S116. On the other hand, when the analysis result is not transmitted to the information integration module 110, the environment analysis module 102 ends a series of processes related to the environment analysis. When the process proceeds to step S116, the environment analysis module 102 transmits the analysis result to the information integration module 110 (S116).

  The environmental analysis process has been described above.

[2-3: Information sharing process between learners]
Next, the inter-learner information sharing process will be described with reference to FIGS. The inter-learner information sharing process described here is mainly executed by the inter-learner information sharing module 104.

  As shown in FIG. 18, first, the inter-learner information sharing module 104 determines whether or not to acquire learner shared information (S121). When acquiring learner shared information, the inter-learner information sharing module 104 advances the process to step S122. On the other hand, if the learner shared information is not acquired, the inter-learner information sharing module 104 advances the process to step S123. When the process proceeds to step S122, the inter-learner information sharing module 104 acquires the learner shared information and stores the acquired learner shared information (S122). For example, the inter-learner information sharing module 104 acquires learner shared information as shown in FIG. The learner shared information is presented to the user as shown in FIG.

  When the process proceeds to step S123, the inter-learner information sharing module 104 determines whether to analyze the learner shared information (S123). When the learner shared information is analyzed, the inter-learner information sharing module 104 advances the process to step S124. On the other hand, if the learner shared information is not analyzed, the inter-learner information sharing module 104 advances the process to step S125. When the process proceeds to step S124, the inter-learner information sharing module 104 analyzes the learner shared information and stores the analysis result (S124). For example, the inter-learner information sharing module 104 updates the learner shared information as shown in FIG.

  When the process proceeds to step S125, the inter-learner information sharing module 104 determines whether to transmit the analysis result to the information integration module 110 (S125). When transmitting the analysis result to the information integration module 110, the inter-learner information sharing module 104 advances the process to step S126. On the other hand, when the analysis result is not transmitted to the information integration module 110, the inter-learner information sharing module 104 ends a series of processes related to inter-learner information sharing. When the process proceeds to step S126, the inter-learner information sharing module 104 transmits the analysis result to the information integration module 110 (S126).

  The information sharing process between learners has been described above.

[2-4: About learner group analysis processing]
Next, the learner group analysis process will be described with reference to FIGS. The learner group analysis process described here is mainly executed by the learner group analysis module 105. In the following description, a method for automatically measuring a user's goal and learning style is also described.

(2-4-1: Overall processing content)
As shown in FIG. 22, first, the learner group analysis module 105 determines whether or not to acquire learner input data and history learning content (S131). When acquiring learner input data and history learning content, the learner group analysis module 105 advances the process to step S132. On the other hand, when the learner input data and the history learning content are not acquired, the learner group analysis module 105 advances the process to step S133. When the process proceeds to step S132, the learner group analysis module 105 acquires learner input data and history learning content (S132).

  When the process proceeds to step S133, the learner group analysis module 105 determines whether to analyze the learner group (S133). When analyzing a learner group, the learner group analysis module 105 advances the process to step S134. On the other hand, when the learner group is not analyzed, the learner group analysis module 105 advances the process to step S135. When the process proceeds to step S134, the learner group analysis module 105 analyzes the learner group and stores the analysis result (S134).

  When the process proceeds to step S135, the learner group analysis module 105 determines whether to transmit the analysis result to the information integration module 110 (S135). When transmitting the analysis result to the information integration module 110, the learner group analysis module 105 advances the process to step S136. On the other hand, when the analysis result is not transmitted to the information integration module 110, the learner group analysis module 105 ends a series of processes related to the learner group analysis. When the process proceeds to step S136, the learner group analysis module 105 transmits the analysis result to the information integration module 110 (S136).

  The overall processing contents of the learner group analysis processing have been described above. However, details of the analysis contents of the learner group executed in step S134 are omitted here. Hereinafter, the details of the analysis contents of the learner group omitted in the above description will be described. In particular, the learning target and learning style automatic measurement processing included in the learner group analysis processing executed in step S134 will be described in detail.

(2-4-2: Automatic measurement of learning target # 1 (distribution information base))
First, the learning target automatic measurement processing based on the distribution information of the learning learning content will be described with reference to FIGS. This process is executed by the learner group analysis module 105, for example. However, this process may be modified so that other modules execute it.

  As shown in FIG. 23, the learner group analysis module 105 determines whether or not to cluster learning content (S201). When performing clustering of learning content, the learner group analysis module 105 advances the process to step S202. On the other hand, when the learning content is not clustered, the learner group analysis module 105 advances the process to step S203.

  When the process proceeds to step S202, the learner group analysis module 105 extracts feature amounts related to the target and the learning style for all learning contents, and the learning content is extracted based on the extracted feature amounts as shown in FIG. Clustering is performed (S202). Further, as shown in FIG. 24, the learner group analysis module 105 calculates the degree of membership of each learning content with respect to each cluster.

  When the process has proceeded to step S203, the learner group analysis module 105 extracts the attribution cluster of the learning content that the user has taken as shown in FIG. 25 (S203). Next, as shown in FIG. 26, the learner group analysis module 105 extracts a feature amount from the belonging cluster having the largest degree of belonging with respect to the learning content that the user has taken (S204). Next, as shown in FIG. 26, the learner group analysis module 105 determines a user (learner) target based on the extracted feature amount (S205), and ends the series of processes.

  In the above, the automatic measurement processing of the learning target based on the distribution information of the learning learning content has been described.

(2-4-3: Automatic measurement of learning style # 1 (distribution information base))
Next, the learning style automatic measurement processing based on the distribution information of the learning learning content will be described with reference to FIGS. This process is executed by the learner group analysis module 105, for example. However, this process may be modified so that other modules execute it.

  As shown in FIG. 28, the learner group analysis module 105 determines whether or not to cluster learning content (S211). When performing clustering of learning content, the learner group analysis module 105 advances the process to step S212. On the other hand, when the learning content is not clustered, the learner group analysis module 105 advances the process to step S213.

  When the process proceeds to step S212, the learner group analysis module 105 extracts feature amounts related to the target and the learning style for all the learning contents, and clusters the learning contents based on the extracted feature values (S212). Further, as shown in FIG. 29, the learner group analysis module 105 calculates the degree of membership of each learning content with respect to each cluster.

  When the process proceeds to step S213, the learner group analysis module 105 extracts the belonging cluster of the learning content that the user has taken as shown in FIG. 30 (S213). Next, as shown in FIG. 31, the learner group analysis module 105 extracts a feature amount from the belonging cluster having the largest degree of belonging with respect to the learning content taken by the user (S214). Next, as shown in FIG. 32, the learner group analysis module 105 extracts time information and calculates information entropy based on the extracted feature amount (S215). Next, as shown in FIG. 33, the learner group analysis module 105 determines the learning style of the user (learner) (S216) and ends the series of processes.

  In the above, the automatic measurement processing of the learning style based on the distribution information of the learning learning content has been described.

(2-4-4: Automatic measurement of learning target # 2 (SNS base))
Next, the learning target automatic measurement processing based on the description text on the social network will be described with reference to FIGS. This process is executed by the learner group analysis module 105, for example. However, this process may be modified so that other modules execute it.

  As shown in FIG. 34, first, the learner group analysis module 105 determines whether or not to perform text analysis learning (S221). When learning text analysis, the learner group analysis module 105 advances the process to step S222. On the other hand, when learning of text analysis is not performed, the learner group analysis module 105 advances the process to step S223. When the process proceeds to step S222, as shown in FIG. 35, the learner group analysis module 105 determines the relationship between the target discrimination term used for target discrimination and the target by machine learning using the description text and the correct answer data. A target-specific weight value indicating the strength of the relationship is extracted (S222).

  When the process proceeds to step S223, as shown in FIG. 36, the learner group analysis module 105 extracts the target discriminant term from the description text of the user, and acquires the target-specific weight value corresponding to the target discriminant term. (S223). Next, as shown in FIG. 37, the learner group analysis module 105 sums the target-specific weight values for each of the target discrimination terms included in the user's description text, and sets the target with the maximum total value as the user's target. The determination is made (S224), and the series of processing ends.

  In the above, the automatic measurement processing of the learning target based on the description text on the social network has been described. Note that it is possible to arbitrarily determine whether to use the automatic measurement processing of the learning target based on the distribution information of the registered learning content or to use the automatic measurement processing of the learning target based on the description text on the social network.

(2-4-5: Automatic measurement of learning style # 2 (SNS base))
Next, the automatic measurement processing of the learning style based on the description text on the social network will be described with reference to FIGS. This process is executed by the learner group analysis module 105, for example. However, this process may be modified so that other modules execute it.

  As shown in FIG. 38, first, the learner group analysis module 105 determines whether or not to perform text analysis learning (S231). When learning text analysis, the learner group analysis module 105 advances the process to step S232. On the other hand, when learning of text analysis is not performed, the learner group analysis module 105 advances the process to step S233. When the process proceeds to step S232, the learner group analysis module 105, as shown in FIG. 39, uses the learning style discriminating term and the learning style to discriminate the learning style by machine learning using the descriptive text and the correct answer data. And the learning style weight value indicating the strength of the relationship is calculated (S232).

  When the process proceeds to step S233, as shown in FIG. 40, the learner group analysis module 105 extracts a learning style discriminant term from the description text of the user, and the weight value for each learning style corresponding to the learning style discriminant term. Is acquired (S233). Next, as shown in FIG. 41, the learner group analysis module 105 sums the weight values for each learning style for each of the learning style discrimination terms included in the user's descriptive text, and determines the learning style that maximizes the total value. The learning style is determined (S234), and the series of processing ends.

  In the above, the automatic measurement processing of the learning style based on the description text on the social network has been described. Note that it is possible to arbitrarily determine whether to use the automatic measurement processing of the learning style based on the distribution information of the registered learning content or to use the automatic measurement processing of the learning style based on the description text on the social network.

(About processing of step S134)
As described above, in the analysis process of the learner group, the feature amount of the learning content related to the learning target and the learning style is calculated, and the learning content is clustered based on the feature amount. Furthermore, the belonging cluster is determined based on the user's history learning content, and the learning target or learning style of the user is determined based on the feature amount of the belonging cluster related to the learning target or learning style. Further, as shown in FIG. 42, the learner group analysis module 105 performs soft clustering on the user using the feature amount related to the goal and learning style determined for each user, and determines the user cluster to which each user belongs. decide. That is, a learner group called a user cluster is determined.

  The learner group analysis process has been described above.

[2-5: Rival search / recommendation process]
Next, rival search / recommendation processing will be described with reference to FIGS. The rival search / recommendation process described here is mainly executed by the rival search / recommendation module 106.

  As shown in FIG. 43, first, the rival search / recommendation module 106 determines whether or not to acquire learner input data (S141). When acquiring learner input data, the rival search / recommendation module 106 advances the process to step S142. On the other hand, when the learner input data is not acquired, the rival search / recommendation module 106 advances the process to step S143. When the process proceeds to step S142, the rival search / recommendation module 106 acquires learner input data as shown in FIG. 44 (S142).

  When the process proceeds to step S143, the rival search / recommendation module 106 determines whether to perform rival search / recommendation (S143). When performing rival search / recommendation, the rival search / recommendation module 106 advances the process to step S144. On the other hand, when rival search / recommendation is not performed, the rival search / recommendation module 106 advances the process to step S145. When the process proceeds to step S144, the rival search / recommendation module 106 executes rival search / recommendation as shown in FIG. 45 and stores the result (S144).

  When the process proceeds to step S145, the rival search / recommendation module 106 determines whether to transmit the result to the information integration module 110 (S145). When transmitting the result to the information integration module 110, the rival search / recommendation module 106 advances the process to step S146. On the other hand, when the result is not transmitted to the information integration module 110, the rival search / recommendation module 106 ends a series of processes related to rival search / recommendation. When the process has proceeded to step S146, the rival search / recommendation module 106 transmits the result to the information integration module 110 (S146).

  The rival search / recommendation process has been described above.

[2-6: Learning content search / recommendation process]
Next, the learning content search / recommendation process will be described with reference to FIGS. 46 to 48. The learning content search / recommendation process described here is mainly executed by the learning content search / recommendation module 107.

  As shown in FIG. 46, first, the learning content search / recommendation module 107 determines whether or not to acquire content information, learner input data, and learning achievement stage (S151). When acquiring content information, learner input data, and learning achievement stage, the learning content search / recommendation module 107 advances the process to step S152. On the other hand, when the content information, the learner input data, and the learning achievement stage are not acquired, the learning content search / recommendation module 107 advances the process to step S153. When the process proceeds to step S152, the learning content search / recommendation module 107 acquires content information, learner input data, and a learning achievement stage as shown in FIG. 47 (S152).

  When the process proceeds to step S153, the learning content search / recommendation module 107 determines whether to perform learning content search / recommendation (S153). In the case of performing learning content search / recommendation, the learning content search / recommendation module 107 advances the process to step S154. On the other hand, when the learning content search / recommendation is not performed, the learning content search / recommendation module 107 advances the process to step S155. When the process proceeds to step S154, the learning content search / recommendation module 107 executes learning content search / recommendation and stores the result as shown in FIG. 48 (S154).

  When the process proceeds to step S155, the learning content search / recommendation module 107 determines whether to transmit the result to the information integration module 110 (S155). When transmitting the result to the information integration module 110, the learning content search / recommendation module 107 advances the process to step S156. On the other hand, when the result is not transmitted to the information integration module 110, the learning content search / recommendation module 107 ends a series of processes related to the learning content search / recommendation. When the process proceeds to step S156, the learning content search / recommendation module 107 transmits the result to the information integration module 110 (S156).

  The learning content search / recommendation process has been described above.

[2-7: Learning arrival stage analysis process]
Next, the learning arrival stage analysis process will be described with reference to FIGS. 49 to 51. The learning arrival stage analysis processing described here is mainly executed by the learning arrival stage analysis module 108.

  As shown in FIG. 49, first, the learning achievement stage analysis module 108 determines whether or not to acquire learner input data and history learning content (S161). When acquiring learner input data and history learning content, the learning arrival stage analysis module 108 advances the process to step S162. On the other hand, when learner input data and history learning content are not acquired, the learning arrival stage analysis module 108 advances the process to step S163. When the process proceeds to step S162, the learning arrival stage analysis module 108 acquires learner input data and history learning content as shown in FIG. 50 (S162).

  When the process has proceeded to step S163, the learning attainment stage analysis module 108 determines whether or not the learning attainment stage analysis is performed (S163). When the learning arrival stage analysis is performed, the learning arrival stage analysis module 108 advances the process to step S164. On the other hand, when learning attainment stage analysis is not performed, the learning attainment stage analysis module 108 advances the processing to step S165. When the process has proceeded to step S164, the learning arrival stage analysis module 108 performs the learning arrival stage analysis as shown in FIG. 51, and stores the analysis result (S164).

  When the process has proceeded to step S165, the learning arrival stage analysis module 108 determines whether to transmit the analysis result to the information integration module 110 (S165). When transmitting the analysis result to the information integration module 110, the learning arrival stage analysis module 108 advances the process to step S166. On the other hand, when the analysis result is not transmitted to the information integration module 110, the learning arrival stage analysis module 108 ends a series of processes related to the learning arrival stage analysis. When the process proceeds to step S166, the learning arrival stage analysis module 108 transmits the analysis result to the information integration module 110 (S166).

  The learning arrival stage analysis process has been described above.

[2-8: Information integration processing]
Next, the information integration process will be described with reference to FIGS. The information integration process described here is mainly executed by the information integration module 110.

  As shown in FIG. 52, first, the information integration module 110 determines whether or not to obtain a result of reaction analysis (S171). When acquiring the result of the reaction analysis, the information integration module 110 advances the process to step S172. On the other hand, if the result of the reaction analysis is not acquired, the information integration module 110 advances the process to step S173. When the process proceeds to step S172, the information integration module 110 acquires the result of the reaction analysis from the reaction analysis module 101 (S172).

  When the process proceeds to step S173, the information integration module 110 determines whether or not to acquire the result of the environment analysis (S173). When acquiring the result of the environmental analysis, the information integration module 110 advances the process to step S174. On the other hand, when the result of the environment analysis is not acquired, the information integration module 110 advances the process to step S175. When the process proceeds to step S174, the information integration module 110 acquires the result of the environment analysis from the environment analysis module 102 (S174).

  When the process proceeds to step S175, the information integration module 110 determines whether or not to acquire inter-learner shared information (S175). When acquiring the learner shared information, the information integration module 110 advances the process to step S176. On the other hand, if the inter-learner shared information is not acquired, the information integration module 110 proceeds with the process to step S177 (FIG. 53). When the process proceeds to step S176, the information integration module 110 acquires the inter-learner shared information from the inter-learner information sharing module 104 (S176).

  When the process proceeds to step S177, as illustrated in FIG. 53, the information integration module 110 determines whether or not to acquire a result of the learner group analysis (S177). When acquiring the result of the learner group analysis, the information integration module 110 proceeds with the process to step S178. On the other hand, when the result of the learner group analysis is not acquired, the information integration module 110 advances the process to step S179. When the process proceeds to step S178, the information integration module 110 acquires the result of the learner group analysis from the learner group analysis module 105 (S178).

  When the process has proceeded to step S179, the information integration module 110 determines whether or not to obtain the result of learning attainment stage analysis (S179). When acquiring the result of the learning arrival stage analysis, the information integration module 110 advances the process to step S180. On the other hand, when the result of learning attainment stage analysis is not acquired, the information integration module 110 advances the process to step S181. When the process proceeds to step S180, the information integration module 110 acquires the result of the learning arrival stage analysis from the learning arrival stage analysis module 108 (S180).

  When the process has proceeded to step S181, the information integration module 110 determines whether to obtain a rival search / recommendation result (S181). When acquiring the result of rival search / recommendation, the information integration module 110 advances the process to step S182. On the other hand, when the result of rival search / recommendation is not acquired, the information integration module 110 advances the process to step S183 (FIG. 54). When the process proceeds to step S182, the information integration module 110 acquires the result of rival search / recommendation from the rival search / recommendation module 106 (S182).

  When the process proceeds to step S183, as shown in FIG. 54, the information integration module 110 determines whether or not to acquire a learning content search / recommendation result (S183). When acquiring the learning content search / recommendation result, the information integration module 110 advances the process to step S184. On the other hand, when the learning content search / recommendation result is not acquired, the information integration module 110 advances the process to step S185. When the process proceeds to step S184, the information integration module 110 acquires the learning content search / recommendation result from the learning content search / recommendation module 107 (S184).

  When the process proceeds to step S185, the information integration module 110 integrates various results obtained from the modules, holds the integration results (S185), and ends a series of processes related to the information integration process.

  Here is a brief summary of the flow of information between modules. FIG. 55 summarizes the relationship between the results of various processes and the modules to which the results are input or output. In the case of the module configuration shown in FIG. 1, the results of various processes are transmitted to each module via the information integration module 110.

  As shown in FIG. 55, the result of the reaction analysis is output from the reaction analysis module 101 and input to the learning content search / recommendation module 107. The result of the environment analysis is output from the environment analysis module 102 and input to the learning content search / recommendation module 107. The inter-learner shared information is output from the inter-learner information sharing module 104. The learner group analysis module 105, the rival search / recommendation module 106, the learning content search / recommendation module 107, the learning arrival stage analysis module 108, and the learning experience module 103.

  The result of the learner group analysis is output from the learner group analysis module 105 and input to the rival search / recommendation module 106. The result of the rival search / recommendation is output from the rival search / recommendation module 106 and input to the inter-learner information sharing module 104 and the learning experience module 103. The learning content search / recommendation result is output from the learning content search / recommendation module 107 and input to the inter-learner information sharing module 104 and the learning experience module 103.

  The learning attainment stage analysis result is output from the learning attainment stage analysis module 108 and input to the inter-learner information sharing module 104, the rival search / recommendation module 106, and the learning content search / recommendation module 107. The learning content history is output from the learning experience module 103 and input to the inter-learner information sharing module 104, the learner group analysis module 105, the learning content search / recommendation module 107, and the learning arrival stage analysis module 108.

  The information integration process has been described above.

[2-9: Overall flow of learning experience processing]
Next, the overall flow of the learning experience process will be described with reference to FIGS. The processing described here involves all modules constituting the learning support apparatus 100.

  As shown in FIG. 56, first, the learning support apparatus 100 determines whether to acquire user input information (learner input data) (S301). When acquiring user input information, the learning support apparatus 100 proceeds with the process to step S302. On the other hand, when not acquiring user input information, the learning assistance apparatus 100 advances a process to step S303. When the process proceeds to step S302, the learning support apparatus 100 acquires user input information using a function such as the learning experience module 103 (S302).

  When the process proceeds to step S303, the learning support apparatus 100 determines whether to analyze the user's reaction (S303). When analyzing a user's reaction, the learning assistance apparatus 100 advances a process to step S304. On the other hand, when not analyzing a user's reaction, the learning assistance apparatus 100 advances a process to step S305. When the process proceeds to step S304, the learning support apparatus 100 analyzes the user's reaction using a function such as the reaction analysis module 101 and stores the analysis result (S304).

  When the process has proceeded to step S305, the learning support apparatus 100 determines whether to analyze the user's environment (S305). When analyzing a user's environment, the learning assistance apparatus 100 advances a process to step S306. On the other hand, when not analyzing a user's environment, the learning assistance apparatus 100 advances a process to step S307 (FIG. 57). When the process proceeds to step S306, the learning support apparatus 100 analyzes the user environment using a function such as the environment analysis module 102, and stores the analysis result (S306).

  When the process proceeds to step S307, as illustrated in FIG. 57, the learning support apparatus 100 determines whether to analyze a learner group (S307). When analyzing a learner group, the learning support apparatus 100 proceeds with the process to step S308. On the other hand, when the learner group is not analyzed, the learning support apparatus 100 proceeds with the process to step S309. When the process proceeds to step S308, the learning support apparatus 100 analyzes the learner group using a function such as the learner group analysis module 105 and stores the analysis result (S308).

  When the process proceeds to step S309, the learning support apparatus 100 determines whether or not to analyze the learning arrival stage (S309). When analyzing the learning arrival stage, the learning support apparatus 100 proceeds with the process to step S310. On the other hand, when the learning arrival stage is not analyzed, the learning support apparatus 100 proceeds with the process to step S311. When the process proceeds to step S310, the learning support apparatus 100 analyzes the learning arrival stage using a function such as the learning arrival stage analysis module 108 and stores the analysis result (S310).

  When the process has proceeded to step S311, the learning support apparatus 100 determines whether to analyze the inter-learner shared information (S311). When analyzing inter-learner shared information, the learning support apparatus 100 proceeds with the process to step S312. On the other hand, if the learner shared information is not analyzed, the learning support apparatus 100 proceeds with the process to step S313 (FIG. 58). When the process proceeds to step S312, the learning support apparatus 100 analyzes the inter-learner shared information using a function such as the inter-learner information sharing module 104 and stores the analysis result (S312).

  When the process proceeds to step S313, as illustrated in FIG. 58, the learning support apparatus 100 determines whether to perform information integration (S313). When executing information integration, the learning support apparatus 100 proceeds with the process to step S314. On the other hand, when the information integration is not executed, the learning support apparatus 100 proceeds with the process to step S315. When the process proceeds to step S314, the learning support apparatus 100 executes information integration using a function such as the information integration module 110 and stores the result (S314).

  When the process has proceeded to step S315, the learning support apparatus 100 determines whether to perform rival search / recommendation (S315). When executing rival search / recommendation, the learning support apparatus 100 proceeds with the process to step S316. On the other hand, when rival search / recommendation is not executed, the learning support apparatus 100 proceeds with the process to step S317. When the process proceeds to step S316, the learning support apparatus 100 performs rival search / recommendation using functions such as the rival search / recommendation module 106, and stores the result (S316).

  When the process proceeds to step S317, the learning support apparatus 100 determines whether to execute learning content search / recommendation (S317). When executing the learning content search / recommendation, the learning support apparatus 100 proceeds with the process to step S318. On the other hand, when the learning content search / recommendation is not executed, the learning support apparatus 100 proceeds with the process to step S319. When the process proceeds to step S318, the learning support apparatus 100 executes learning content search / recommendation using functions such as the learning content search / recommendation module 107, and stores the result (S318).

  When the process proceeds to step S319, the learning support apparatus 100 presents the rival, the learning content, or related information of the rival and the learning content to the user by using a function such as the learning experience module 103 (S319). End a series of processes related to the learning experience.

  The overall flow of the learning experience process has been described above.

[2-10: Motivation calculation process]
Next, a method for calculating motivation will be described with reference to FIG.

  The learning experience module 103 presents information related to rivals and learning content to the user in a form as shown in FIG. 21 and urges the user to learn. The learning experience module 103 also provides a place for the user to communicate with rivals. At this time, the information provided by the learning experience module 103 includes information indicating the user's motivation. As shown in FIG. 59, this motivation is calculated based on the extracted subjective expression by performing language analysis on the description text on the social network. For example, the amount of positive subjective expression is compared with the amount of negative subjective expression, and motivation is determined from the comparison result.

  The motivation calculation method has been described above.

[2-11: Progress level calculation process]
Next, a method for calculating the degree of progress will be described with reference to FIG.

  The learning experience module 103 presents information related to rivals and learning content to the user in a form as shown in FIG. 21 and urges the user to learn. The learning experience module 103 also provides a place for the user to communicate with rivals. At this time, the information provided by the learning experience module 103 includes information indicating the degree of progress of the user. As shown in FIG. 60, the degree of progress is calculated based on the amount of increase in the numerical value at the learning achievement stage. For example, the degree of progress is set to “improvement” when the amount of increase in the learning achievement stage per day is 0.1 or more, and is set to “maintain” when 0.05 or more and less than 0.1. When it is less than 05, it is set to “decrease”. In addition, it is preferable that the threshold value used for determination of progress is set appropriately.

  The progress calculation method has been described above.

[2-12: Effect]
As described above, the learning support apparatus 100 according to the present embodiment can search for and recommend rivals according to the user's proficiency level, learning target, and learning style. Examples of the learning target include “professional level” and “hobby level”. Examples of the learning style include “widely shallow”, “narrowly deep”, “early”, and “slowly”. By selecting a suitable rival according to the user's learning goal, learning style, etc., it becomes possible to maintain a high level of motivation for the user's learning.

  In addition, the learning support apparatus 100 according to the present embodiment provides a place for information sharing through a social network so that competition and collaboration with rivals are possible. Therefore, the user can inspire the spirit of competition and collaboration through such a place. In addition, communication such as questions and dialogues with rivals is achieved, so that problem solving is accelerated and learning motivation is improved. In particular, communication with rivals with similar learning objectives and learning styles can be used to create a learning space where learning can proceed more effectively.

  In addition, the learning support apparatus 100 according to the present embodiment searches and recommends rivals and learning content based on analysis of learner groups and analysis of the learning achievement stage according to the user's proficiency level, learning target, and learning style. Do. Therefore, it is possible to appropriately determine the learning state of the user without using an expensive measuring instrument or biosensor. As a result, it is possible to construct a learning system with less burden on the user and at a low cost.

  The effects obtained by using the learning support apparatus 100 according to this embodiment have been described above.

<3: Hardware configuration example>
The function of each component included in the learning support apparatus 100 can be realized using, for example, the hardware configuration of the information processing apparatus illustrated in FIG. That is, the function of each component is realized by controlling the hardware shown in FIG. 61 using a computer program. The form of the hardware is arbitrary, and includes, for example, a personal computer, a mobile phone, a portable information terminal such as a PHS, a PDA, a game machine, or various information appliances. However, the above PHS is an abbreviation of Personal Handy-phone System. The PDA is an abbreviation for Personal Digital Assistant.

  As shown in FIG. 61, this hardware mainly includes a CPU 902, a ROM 904, a RAM 906, a host bus 908, and a bridge 910. Further, this hardware includes an external bus 912, an interface 914, an input unit 916, an output unit 918, a storage unit 920, a drive 922, a connection port 924, and a communication unit 926. However, the CPU is an abbreviation for Central Processing Unit. The ROM is an abbreviation for Read Only Memory. The RAM is an abbreviation for Random Access Memory.

  The CPU 902 functions as, for example, an arithmetic processing unit or a control unit, and controls the overall operation of each component or a part thereof based on various programs recorded in the ROM 904, the RAM 906, the storage unit 920, or the removable recording medium 928. . The ROM 904 is a means for storing a program read by the CPU 902, data used for calculation, and the like. In the RAM 906, for example, a program read by the CPU 902, various parameters that change as appropriate when the program is executed, and the like are temporarily or permanently stored.

  These components are connected to each other via, for example, a host bus 908 capable of high-speed data transmission. On the other hand, the host bus 908 is connected to an external bus 912 having a relatively low data transmission speed via a bridge 910, for example. As the input unit 916, for example, a mouse, a keyboard, a touch panel, a button, a switch, a lever, or the like is used. Further, as the input unit 916, a remote controller (hereinafter referred to as a remote controller) capable of transmitting a control signal using infrared rays or other radio waves may be used.

  As the output unit 918, for example, a display device such as a CRT, LCD, PDP, or ELD, an audio output device such as a speaker or a headphone, a printer, a mobile phone, or a facsimile, etc. Or it is an apparatus which can notify audibly. However, the above CRT is an abbreviation for Cathode Ray Tube. The LCD is an abbreviation for Liquid Crystal Display. The PDP is an abbreviation for Plasma Display Panel. Furthermore, the ELD is an abbreviation for Electro-Luminescence Display.

  The storage unit 920 is a device for storing various data. As the storage unit 920, for example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, a magneto-optical storage device, or the like is used. However, the HDD is an abbreviation for Hard Disk Drive.

  The drive 922 is a device that reads information recorded on a removable recording medium 928 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, or writes information to the removable recording medium 928. The removable recording medium 928 is, for example, a DVD medium, a Blu-ray medium, an HD DVD medium, or various semiconductor storage media. Of course, the removable recording medium 928 may be, for example, an IC card on which a non-contact type IC chip is mounted, an electronic device, or the like. However, the above IC is an abbreviation for Integrated Circuit.

  The connection port 924 is a port for connecting an external connection device 930 such as a USB port, an IEEE 1394 port, a SCSI, an RS-232C port, or an optical audio terminal. The external connection device 930 is, for example, a printer, a portable music player, a digital camera, a digital video camera, or an IC recorder. However, the above USB is an abbreviation for Universal Serial Bus. The SCSI is an abbreviation for Small Computer System Interface.

  The communication unit 926 is a communication device for connecting to the network 932. For example, a wired or wireless LAN, Bluetooth (registered trademark), or a WUSB communication card, an optical communication router, an ADSL router, or various types It is a modem for communication. The network 932 connected to the communication unit 926 is configured by a wired or wireless network, such as the Internet, home LAN, infrared communication, visible light communication, broadcast, or satellite communication. However, the above LAN is an abbreviation for Local Area Network. The WUSB is an abbreviation for Wireless USB. The above ADSL is an abbreviation for Asymmetric Digital Subscriber Line.

(Remarks)
The rival search / recommendation module 106 is an example of a similar learner detection unit and a learner clustering unit. The information integration module 110 and the learning experience module 103 are examples of a similar learner information providing unit. The learner group analysis module 105 includes a clustering unit, a course cluster extraction unit, a feature amount acquisition unit, a learning target determination unit, a learning style determination unit, a relationship extraction unit, a discriminant term extraction unit, a learning target-specific weight value calculation unit, It is an example of the weight value calculation part classified by learning style. The learning content search / recommendation module 107 is an example of a feature vector calculation unit, a feature vector extraction unit, and a learning content recommendation unit. The learning attainment stage analysis module 108 is an example of a learning target feature amount calculation unit, a proficiency level evaluation unit, a proficiency level change observation unit, and a progress level evaluation unit.

  The preferred embodiments according to the present technology have been described above with reference to the accompanying drawings, but it is needless to say that the present technology is not limited to the configuration examples disclosed herein. It will be apparent to those skilled in the art that various changes and modifications can be made within the scope of the claims, and these are naturally within the technical scope of the present technology. Understood.

DESCRIPTION OF SYMBOLS 100 Learning support apparatus 101 Reaction analysis module 1011 Reaction analysis module detection part 1012 Reaction analysis module input part 1013 Reaction analysis module memory | storage part 1014 Reaction analysis module calculating part 102 Environmental analysis module 1021 Environmental analysis module detection part 1022 Environmental analysis module memory | storage part 1023 Environment Analysis module calculation unit 103 Learning experience module 1031 Learning experience module input unit 1032 Learning experience module display unit 1033 Learning experience module storage unit 1034 Learning experience module calculation unit 104 Inter-learner information sharing module 1041 Inter-learner information sharing module storage unit 1042 Learning Inter-person information sharing module calculation unit 105 Learner group analysis module 1051 Learner group analysis module analysis unit 1052 Learner group analysis module storage unit 106 Rival search / recommendation module 1061 Rival search / recommendation module calculation unit 1062 Rival search / recommendation module storage unit 107 Learning content search / recommendation module 1071 Learning content search / recommendation module calculation unit 1072 Learning content search / Recommendation module storage unit 108 Learning attainment stage analysis module 1081 Learning attainment stage analysis module analysis unit 1082 Learning attainment stage analysis module storage unit 109 Learning content management module 1091 Learning content management module calculation unit 1092 Learning content management module storage unit 110 Information integration module 1011 Information integration module management unit 1012 Information integration module storage unit

Claims (15)

A similar learner detection unit that detects similar learners with similar features of the learner information based on learner information including learning objectives, proficiency levels, and learning styles;
A similar learner information providing unit that provides learner information of a similar learner similar to the support target learner detected by the similar learner detection unit to a support target learner;
Comprising
Learning support device. A clustering unit for clustering learning content;
A course cluster extractor that extracts the attribution cluster of the learning content taken by the learner;
A feature amount acquisition unit for acquiring a feature amount for each learning target from the belonging cluster having the maximum degree of belonging among the belonging clusters extracted by the course cluster extracting unit;
A learning target determination unit that selects a learning target corresponding to the maximum value among the feature amounts for each learning target acquired by the feature amount acquisition unit, and determines the selected learning target as the learning target of the learner;
Further comprising
The learning support apparatus according to claim 1. A clustering unit for clustering learning content;
A course cluster extractor that extracts the attribution cluster of the learning content taken by the learner;
A feature quantity acquisition unit that acquires a feature quantity for each learning style from the belonging cluster having the maximum degree of belonging among the belonging clusters extracted by the course cluster extracting unit;
A learning style determination unit that determines the learning style of the learner based on the feature amount for each learning style acquired by the feature amount acquisition unit;
Further comprising
The learning support apparatus according to claim 1. The feature amount acquisition unit further acquires a feature amount for each learning style from the belonging cluster having the largest degree of belonging among the belonging clusters extracted by the course cluster extracting unit,
The learning support device further includes a learning style determination unit that determines the learning style of the learner based on a feature amount for each learning style acquired by the feature amount acquisition unit.
The learning support apparatus according to claim 2. A learner that clusters learners under conditions that allow the same learner to belong to a plurality of clusters based on the feature value for each learning target and the feature value for each learning style acquired by the feature value acquisition unit. A clustering unit;
The learning support device according to claim 4. The learning style determination unit determines the learning style of the learner based on time information indicating a learner's course status and information entropy calculated from a feature amount for each learning style.
The learning support device according to claim 4. The similar learner detection unit detects a similar learner similar to the learner to be supported by performing vector matching using a vector obtained by combining a feature amount for each learning target and a feature amount for each learning style. To
The learning support device according to claim 4. A feature vector calculation unit that calculates a vector that combines a feature value for each learning target and a feature value for each learning style for all learning contents to be recommended;
Among the vectors calculated by the feature vector calculation unit, a vector obtained by combining the feature amount for each learning target and the feature amount for each learning style corresponding to the support target learner acquired by the feature amount acquisition unit. A feature vector extraction unit that extracts a predetermined number of vectors in the closest order;
A learning content recommendation unit that recommends learning content corresponding to the vector extracted by the feature vector extraction unit to the support target learner;
Further comprising
The learning support device according to claim 4. A learning target feature value calculating unit that calculates a learning target feature value obtained by totaling the feature values for each learning target for each of the learners having the same learning target as the support target learner;
A proficiency level evaluation unit that evaluates the proficiency level of the learner of the support target by comparing the maximum value of the target feature value of learning with the target learning feature value calculated for the learner of the support target;
Further comprising
The learning support device according to claim 4. A relationship extraction unit that extracts a relationship between a learning target determination term for determining a predetermined learning target and the predetermined learning target by machine learning;
A discriminant term extraction unit for extracting the learning target discriminant term from the text described by the learner on the social network;
For each learning target discrimination term extracted by the discrimination term extraction unit, a learning target-specific weight value calculation unit that calculates a learning target-specific weight value indicating the strength of the relationship extracted by the relationship extraction unit;
A learning target determining unit that sums the weight values for each learning target calculated for each learning target determination term, and determines a learning target related to the learning target determination term having the maximum total value as the learning target of the learner;
Further comprising
The learning support apparatus according to claim 1. A relationship extraction unit that extracts a relationship between a learning style determination term for determining a predetermined learning style and the predetermined learning style by machine learning;
A discriminant term extraction unit for extracting the learning style discriminant term from the text described by the learner on the social network;
For each learning style discrimination term extracted by the discrimination term extraction unit, a weight value calculation unit by learning style that calculates a weight value by learning style indicating the strength of the relationship extracted by the relationship extraction unit;
A learning style determination unit that sums the weight values for each learning style calculated for each learning style determination term, and determines the learning style related to the learning style determination term that maximizes the total value as the learning style of the learner;
Further comprising
The learning support apparatus according to claim 1. And a subjective expression extraction unit that extracts positive subjective expressions and negative subjective expressions from text written by the learner on the social network,
The similar learner information providing unit compares the amount of positive subjective expression extracted by the subjective expression extraction unit with the amount of negative subjective expression for the similar learner, and compares the comparison result with the motivation of the similar learner Provide to the learner of the support target as learner information indicating
The learning support apparatus according to claim 1. A proficiency level change monitoring unit for observing changes in the proficiency level;
A progress evaluation unit that evaluates the progress according to the increase in the proficiency,
Further comprising
The learning support apparatus according to claim 1. A similar learner detection step for detecting similar learners whose features of the learner information are similar based on learner information including learning objectives, proficiency levels, and learning styles;
A similar learner information providing step of providing learner information of a similar learner similar to the learner of the support target detected in the similar learner detection step to the learner of the support target;
including,
Learning support method. A similar learner detection function for detecting similar learners with similar features of the learner information based on learner information including learning objectives, proficiency levels, and learning styles;
A similar learner information providing function for providing learner information of a similar learner similar to the learner of the support target detected by the similar learner detection function to the support target learner;
A program to make a computer realize.

Images