Information processing device

Abstract

To correctly grasp an object of interest of an interaction partner even if an ambiguous answer is made to a question about an item to be a determination object of the existence / nonexistence of the interest.SOLUTION: An information processing device 1 includes an acquisition part 111, a selection part 112, a voice control part 113, a calculation part 114, and a determination part 115. The selection part 112 selects an item to be a determination object of the existence / nonexistence of interest on the basis of item information D1 and user information D2. The voice control part 113 outputs voice information representing a question about the selected item to a speaker 132. The acquisition part 111 acquires voice information on an answer of a user to the question from a microphone 121. The calculation part 114 calculates an interest value showing the intensity of the interest of the user to the item of the determination object on the basis of a feeling estimated from an expression of the answer showing the acquired voice information and voice of the answer. The determination part 115 determines the existence / nonexistence of the interest of the user to the item of the determination object on the basis of the interest value.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device. [Background technology]

[0002] Inquiry-based learning is gaining importance as a learning method for children. Inquiry-based learning is a learning method in which children are encouraged to independently decide what to explore, collect information for the exploration, analyze the collected information, and derive conclusions from the analysis results. When engaging children in inquiry-based learning, it is important to properly understand what interests the child. Various technologies have been proposed for estimating the interests of a conversation partner through dialogue, one example of which is the technology disclosed in Patent Document 1. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 11-127246 Summary of the Invention [Problem to be solved by the invention]

[0004] Depending on the child's personality, such as being shy, the child may give an ambiguous answer to a question about a subject of interest, either positive or negative. In other words, the child may give an answer that does not clearly express what is on their mind. Therefore, the technology disclosed in Patent Document 1 may not be able to correctly grasp the subject of the child's interest.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to solve the problem of correctly grasping the object of interest of a conversation partner even when the answer is given in ambiguous wording, such as whether it is positive or negative, in a technology for estimating the object of interest of a conversation partner through a dialogue. [Means for solving the problem]

[0006] An information processing device according to one aspect of the present disclosure includes a selection unit, a voice control unit, a calculation unit, and a determination unit. The selection unit selects an item to be determined as to whether a user is interested in the item from among a plurality of items related to one study subject. The voice control unit generates first voice information representing a voice of a question related to the item selected by the selection unit and outputs the generated first voice information to a speaker. The calculation unit calculates an interest value indicating the strength of the user's interest based on a first evaluation value indicating the strength of the user's interest estimated from the wording of the answer represented by second voice information representing the voice of the user's answer to the question, and a second evaluation value indicating the strength of the user's interest estimated from the emotion implied in the voice represented by the second voice information. The determination unit determines the strength of the user's interest in the item selected by the selection unit based on the interest value calculated by the calculation unit. [Effects of the Invention]

[0007] According to the information processing device of the present disclosure, interest is determined based on an interest value calculated from the wording of the answer to the question and the emotions conveyed in the voice of the answer, so that the objects of interest of the user of the information processing device can be correctly understood. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of the configuration of an information processing device 1 according to an embodiment of the present disclosure. [Figure 2] 10 is a diagram showing an example of a tree structure represented by item information D1 stored in the nonvolatile storage device 132 of the information processing device 1. FIG. [Figure 3] 10 is a diagram for explaining the selection of a judgment target item by a selection unit 112. FIG. [Figure 4] 10 is a diagram for explaining the selection of a judgment target item by a selection unit 112. FIG. [Figure 5] 10 is a diagram for explaining the selection of a judgment target item by a selection unit 112. FIG. [Figure 6] 10 is a diagram for explaining the selection of a judgment target item by a selection unit 112. FIG. [Figure 7]This is a diagram for explaining the selection of items to be determined by the selection unit 112. [Figure 8A] This is a flowchart showing the flow of the interest estimation method executed by the processing device 110 in the program P stored in the non-volatile memory device 132 of the information processing device 1. [Figure 8B] This is a flowchart showing the flow of the interest estimation method executed by the processing device 110 in the program P stored in the non-volatile memory device 132 of the information processing device 1. [Figure 9] This is a diagram for explaining an operation example of the information processing device 1. [Figure 10] This is a diagram for explaining another operation example of the information processing device 1.

Mode for Carrying Out the Invention

[0009] <A. Embodiment> FIG. 1 is a diagram showing a configuration example of an information processing device 1 according to an embodiment of the present disclosure. The information processing device 1 is a device that estimates items in which a user has an interest. The items in which the user has an interest are hierarchically classified. The highest-level classification is the learning subject. One learning subject includes a plurality of items. That is, the information processing device 1 estimates items in which the user has an interest from among a plurality of items in each of a plurality of types of learning subjects. Specific examples of the plurality of types of learning subjects include school subjects such as Japanese, arithmetic, science, and social studies in elementary schools and the like. Specific examples of the plurality of items in a learning subject include, for example, celestial bodies and organisms when the learning subject is science. The information processing device 1 is, for example, a smartphone. The information processing device 1 is given to a child by a guardian who intends to let the child conduct inquiry learning. In the present embodiment, the child to whom the information processing device 1 is given becomes the user of the information processing device 1.

[0010] 1, the information processing device 1 includes a processing device 110, an audio input / output device 120, a storage device 130, a communication device 140, and an input device 150. The communication device 140 is a device for performing voice calls via a mobile communication network and data communication via a mobile packet communication network. The input device 150 is a device for accepting input operations by a user to the information processing device 1. Specific examples of the input device 150 include a keyboard with a numeric keypad or the like, or a touch sensor.

[0011] 1, the audio input / output device 120 includes a microphone 121 and a speaker 122. The microphone 121 picks up sounds around the information processing device 1. The microphone 121 generates sound information indicating the picked up sounds. The processing device 110 provides audio information to the speaker 122. The speaker 122 outputs audio represented by the audio information provided by the processing device 110.

[0012] As shown in FIG. 1 , the storage device 130 includes a volatile storage device 131 and a nonvolatile storage device 132. The volatile storage device 131 is, for example, a random access memory (RAM). The volatile storage device 131 is used by the processing device 110 as a work area when executing various programs. The nonvolatile storage device 132 is, for example, a flash read-only memory (ROM). The nonvolatile storage device 132 stores various programs and various data referenced during the execution of the various programs. Specific examples of the programs stored in the nonvolatile storage device 132 include a kernel program that causes the processing device 110 to implement an operating system (OS), and a program P that causes the processing device 110 to implement an interest estimation method that prominently exhibits the features of the present disclosure. Specific examples of the data stored in the nonvolatile storage device 132 include item information D1 and user information D2.

[0013] Item information D1 is information that classifies multiple items for each of multiple types of learning subjects into a tree structure in which lower levels have higher specialization than higher levels. The tree structure of each learning subject indicated by item information D1 is also called an interest tree. Figure 2 is an example of an interest tree for each of science and social studies. The specialization level in Figure 2 is a value that indicates the level of specialization of the hierarchy. In this embodiment, the specialization of an item with a specialization level of 3 is higher than the specialization of an item with a specialization level of 2. Also, in this embodiment, the specialization of an item with a specialization level of 2 is higher than the specialization of an item with a specialization level of 1. An item with a specialization level of 1 corresponds to the highest classification, i.e., a learning subject.

[0014] As shown in FIG. 2, the item with an expertise level of 1 in the science interest tree is "Science." As shown in FIG. 2, the items with an expertise level of 2 in the science interest tree are "Living things" and "Celestial bodies." As shown in FIG. 2, the items below "Living things" in the science interest tree are "Animals" and "Plants," and the items below "Celestial bodies" are "Structure" and "Movement." The expertise level of each of the items "Animals," "Plants," "Structure," and "Movement" is 3. As shown in FIG. 2, in this embodiment, the item with an expertise level of 3 is the lowest item in the science interest tree.

[0015] As shown in FIG. 2, the item with an expertise level of 1 in the social interest tree is "social studies." As shown in FIG. 2, the items with an expertise level of 2 in the social interest tree are "history" and "geography." As shown in FIG. 2, the items below "history" in the social interest tree are "Japanese history" and "world history," and the items below "geography" are "Japan" and "foreign countries." The expertise level of each of the items "Japanese history," "world history," "Japan," and "foreign countries" is 3. As shown in FIG. 2, the items with an expertise level of 3 are also the lowest-level items in the social interest tree. In this embodiment, the multiple items belonging to the learning subjects of "science" and "social studies" are classified into three hierarchies, but they may also be classified into two hierarchies, or four or more hierarchies.

[0016] The user information D2 is information indicating the future actions of the user. In this embodiment, the user information D2 is schedule information indicating the event schedule of the school that the user attends.

[0017] The processing device 110 is, for example, a CPU (Central Processing Unit). The processing device 110 functions as a control center in the information processing device 1 by operating in accordance with a program stored in the nonvolatile storage device 132. When the information processing device 1 is powered on, the processing device 110 first reads a kernel program from the nonvolatile storage device 132 to the volatile storage device 131 and starts executing the kernel program read into the volatile storage device 131. Note that the power supply for the information processing device 1 is not shown in FIG. 1. The processing device 110, which operates in accordance with the kernel program and implements an OS, starts executing another program in response to an operation on the input device 150. For example, when an instruction to execute a program P is received through an operation on the input device 150, the processing device 110 reads the program P from the nonvolatile storage device 132 to the volatile storage device 131 and starts executing the program P read into the volatile storage device 131. The processing device 110 operating according to the program P functions as an acquisition unit 111, a selection unit 112, a voice control unit 113, a calculation unit 114, a determination unit 115, and a decision unit 116, as shown in FIG.

[0018] The acquisition unit 111 acquires the user information D2 by reading the user information D2 from the nonvolatile storage device 132. In this embodiment, the user information D2 is stored in the nonvolatile storage device 132, but the user information D2 may be input by operating the input device 150. When the user information D2 is input by operating the input device 150, the acquisition unit 111 acquires the user information D2 from the input device 150.

[0019] The selection unit 112 selects an item to be used to determine whether the user is interested in the item from among a plurality of items related to one learning subject. In this embodiment, the selection unit 112 selects an item to be used to determine whether the user is interested in the item based on the user information D2 and item information D1 acquired by the acquisition unit 111. Hereinafter, an item to be used to determine whether the user is interested in the item will be referred to as a determination target item. In this embodiment, the selection unit 112 selects an item that matches part or all of the name of an event indicated by the user information D2 as the determination target item. For example, if "astronomy observation" is scheduled as an event at the school attended by the user and the user information D2 indicates "astronomy observation," the selection unit 112 selects "celestial bodies" as the determination target item.

[0020] The audio control unit 113 generates audio information representing the audio of a question regarding the item to be determined. Hereinafter, the audio information representing the audio of a question regarding the item to be determined will be referred to as question audio information. A specific example of a question when the item to be determined is "celestial bodies" is the question "Do you like celestial bodies?" The question audio information is an example of first audio information in the present disclosure. The audio control unit 113 outputs the generated question audio information to the speaker 122.

[0021] The calculation unit 114 acquires, from the microphone 121, sound information indicating the voice of the user's answer to the question indicated by the question voice information. Hereinafter, the sound information indicating the voice of the user's answer will be referred to as answer voice information. The answer voice information is an example of second voice information in the present disclosure. The calculation unit 114 calculates an interest value indicating the user's level of interest in the item to be determined based on the answer voice information. More specifically, the calculation unit 114 first calculates a content evaluation value from the answer voice information. The content evaluation value is a value indicating the level of the user's interest estimated from the content of the answer represented by the answer voice information, i.e., the wording of the answer. In this embodiment, the content evaluation value is a value ranging from 0 to 1. For example, the calculation unit 114 calculates the content evaluation value as 0 for a negative answer such as "I don't like it," as 1 for a positive answer such as "I like it," and as 0.5 for an ambiguous answer that cannot be determined as either positive or negative, such as "I don't really care." Note that existing technology may be used to calculate the content evaluation value. The content evaluation value is an example of a first evaluation value in the present disclosure.

[0022] Next, the calculation unit 114 calculates an emotion evaluation value from the answer voice information. The emotion evaluation value is a value indicating the strength of the user's interest estimated from the emotion conveyed in the voice of the answer represented by the answer voice information. In this embodiment, the emotion evaluation value is a value in the range of 0 to 1. For example, the calculation unit 114 calculates an emotion evaluation value of 0 if the answer gives a negative impression such as "boring" or "cold," 1 if the answer gives a positive impression such as "fun," and 0.5 if the answer gives a neutral impression. Note that existing technology may be used as a method for calculating the emotion evaluation value. The emotion evaluation value is an example of a second evaluation value in the present disclosure.

[0023] The calculation unit 114 then calculates an interest value indicating the user's level of interest in the item to be determined based on the content evaluation value and the emotion evaluation value. The interest value may be calculated by any calculation method as long as it is calculated using a function that uses the content evaluation value and the emotion evaluation value as variables. In this embodiment, the calculation unit 114 calculates the interest value as the product of the expertise level, content evaluation value, and emotion evaluation value of the item to be determined, i.e., (expertise level of the item to be determined) × (content evaluation value) × (emotion evaluation value). However, the interest value may also be the product of the content evaluation value and the emotion evaluation value. Furthermore, the calculation unit 114 may calculate the interest value by (expertise level of the item to be determined) × {(content evaluation value) + (emotion evaluation value)} or by (content evaluation value) + (emotion evaluation value). Alternatively, the calculation unit 114 may calculate the interest value by assigning different weights to the content evaluation value and the emotion evaluation value. In this case, the calculation unit 114 may calculate the interest value by (expertise level of the item to be judged) × {α × (content evaluation value) + β × (emotion evaluation value)} or by α × (content evaluation value) + β × (emotion evaluation value), where α and β are mutually different constants.

[0024] The determination unit 115 determines whether the user is interested in the item to be determined based on the interest value calculated by the calculation unit 114. Specifically, the determination unit 115 determines that the user is interested in the item to be determined if the interest value exceeds the threshold. In other words, the determination unit 115 determines that the user is not interested in the item to be determined if the interest value of the item to be determined is equal to or less than the threshold. Note that the threshold in this embodiment is the product of the expertise level of the item to be determined, the median of the range of values ​​that the content evaluation value can take, and the median of the range of values ​​that the emotion evaluation value can take, but is not limited to this value. In this embodiment, the range of values ​​that the content evaluation value can take is 0 to 1, so the median of the range of values ​​that the content evaluation value can take is 0.5. Similarly, the range of values ​​that the emotion evaluation value can take is 0 to 1, so the median of the range of values ​​that the emotion evaluation value can take is 0.5. For example, if the expertise level of the item to be determined is 2, the threshold is 2 × 0.5 × 0.5 = 0.5.

[0025] Additionally, in this embodiment, in order to thoroughly search for items in which the user of the information processing device 1 is most interested, the selection unit 112, the calculation unit 114, and the determination unit 115 further have the following functions. That is, when a determination target item is determined to be interesting and there is an item in a lower hierarchy than the determination target item, the selection unit 112 selects an item in a lower hierarchy than the determination target item as a new determination target item based on the item information D1. For example, as shown in FIG. 3, assume that the determination target item is "Living Things" in the interest tree related to science. In FIG. 3, the border of the item selected as the determination target item by the selection unit 112 is drawn with a thick line. As described above, in the interest tree related to science, two items, "Plants" and "Animals," exist in the hierarchy below "Living Things." Therefore, if the determination result by the determination unit 115 regarding "Living Things" is "interested," the selection unit 112 selects one of the two items, "Plants" and "Animals," as a new determination target item. 3, the frame of the new determination target item selected by the selection unit 112 is drawn with a dashed line. In FIG. 3, an example is shown in which "Plants" has been selected as the new determination target item.

[0026] When a new item to be determined is selected by the selection unit 112, the audio control unit 113 outputs question audio information representing a question regarding the new item to be determined to the speaker 122. The calculation unit 114 calculates an interest value for the new item to be determined based on the answer audio information output from the microphone 121. The determination unit 115 then determines whether or not the user is interested in the new item to be determined. In the example shown in FIG. 3, an audio question regarding "plants," which is the new item to be determined, is output from the speaker 122, and whether or not the user is interested in "plants" is determined based on the user's answer to this question.

[0027] Furthermore, if the determination target item is determined to be an interest and there are no items in a lower hierarchy than the determination target item, the selection unit 112 sequentially selects unselected items, i.e., items for which interest has not been determined, from among the items that have the same upper hierarchy as the determination target item, based on the item information D1. Hereinafter, an item that has the same upper hierarchy as the determination target item will be referred to as an item in the same hierarchy as the determination target item. The calculation unit 114 calculates an interest value for each of the unselected items sequentially selected by the selection unit 112. Then, the determination unit 115 determines whether the user is interested in each of the unselected items based on the interest value calculated by the calculation unit 114. In FIG. 4, as in FIG. 3, the frame of the item selected as the determination target item by the selection unit 112 is drawn with a thick line. As described above, in the interest tree for science, there is no hierarchy below "Plants." Therefore, if the determination result by the determination unit 115 regarding "Plants" is "interested" and "Animals", an item at the same level as "Plants", has not been selected, the selection unit 112 selects "Animals" as a new item to be determined. In FIG. 4, similar to the case in FIG. 3, the frame of the new item to be determined selected by the selection unit 112 is drawn with a dashed line. Thereafter, in the example shown in FIG. 4, an audio question regarding "Animals", which is the new item to be determined, is output from the speaker 122, and whether or not the user is interested in "Animals" is determined based on the user's answer to this question.

[0028] Also, in the first state where a determination is made that the user is not interested in an item to be determined and there are unselected items at the same level as the item to be determined, the selection unit 112 selects one of the unselected items based on the item information D1. For example, in the example shown in FIG. 4, if a determination is made that the user is not interested in "plants" and "animals" has not been selected, the selection unit 112 selects "animals" as a new item to be determined. In this case, too, an audio question about "animals," which is the new item to be determined, is output from the speaker 122, and the user's interest in "animals" is determined based on the user's answer to this question.

[0029] In a second state in which a determination is made that the user is not interested in a determination target item, there are no items in the same hierarchical level as the determination target item for which interest has not yet been determined, and there are items in a higher hierarchical level than the determination target item, the selection unit 112 selects an item in a higher hierarchical level than the determination target item as a new determination target item based on the item information D1. For example, as shown in FIG. 5, assume that "Biology" in the interest tree related to science is the determination target item, and that "Celestial Bodies," an item in the same hierarchical level as "Biology," has already been determined as "not interested." In FIG. 5, the borders of the determination target items are drawn with thick lines, and the borders of items for which interest has already been determined are drawn with dashed lines. In the example shown in FIG. 5, if the determination result for "Biology" is "not interested," there are no items in the same hierarchical level as "Biology," and "Science" exists as an item in a higher hierarchical level than "Biology." Therefore, the selection unit 112 selects "Science" as a new determination target item. Thereafter, a voice question about "science", which is a new item to be determined, is output from the speaker 122, and based on the user's answer to this question, it is determined whether the user is interested in "animals".

[0030] When there are multiple items determined to interest the user, the determination unit 116 determines the item with the highest interest value as the user's subject of interest. More specifically, the determination unit 116 determines the item with the highest interest value as the user's subject of interest in the third state described below. The third state is a state in which the user is determined to be interested in the item to be determined, there are no items at a lower level than the item to be determined, and the user's interest in items at the same level as the item to be determined has already been determined. For example, as shown in FIG. 6, assume that "animals" is the item to be determined, and "plants" and "living things" have already been determined to interest the user. In FIG. 6, the borders of the items to be determined are drawn with thick lines, and the borders of items for which the user's interest has already been determined are drawn with dashed lines. In the example shown in Figure 6, if it is determined that there is an interest in "Animals", there is no hierarchy below "Animals" and the user has already determined whether or not there is an interest in "Plants", which is an item at the same hierarchy as "Animals", so the determination unit 116 determines the item with the highest interest value among "Living Things", "Plants", and "Animals", for which the user has already determined whether or not there is an interest, as the subject of the user's interest.

[0031] Furthermore, the determination unit 116 determines that the user is not interested in the learning subject including the evaluation target item in the following fourth state. The fourth state is a state in which the user is determined to be not interested in the evaluation target item, the interest status of all other items at the same level as the evaluation target item has been determined, there are no items determined to be of interest, and there are no items at a higher level than the evaluation target item. Note that if there are no other items at the same level as the evaluation target item, the requirement that the interest status of all other items at the same level as the evaluation target item has been determined is unconditionally met. For example, as shown in FIG. 7, assume that "science" is the evaluation target item and that the user has been determined to be not interested in the items "biology" and "astronomy." In the example shown in FIG. 7, if the user is determined to be not interested in "science," there are no other items at the same level as "science" in the interest tree of "science," no items at a higher level than "science," and no items determined to be of interest, so the determination unit 116 determines that the user is not interested in "science." If the determining unit 116 determines that the user has no interest in a certain learning subject, the selecting unit 112 selects an item belonging to a different type of learning subject from the learning subject determined to have no interest to the user as a new item to be determined. For example, if it is determined that the user has no interest in "science," the selecting unit 112 selects an item belonging to the "social studies" interest tree as a new item to be determined.

[0032] Furthermore, the processing device 110 operating in accordance with the program P executes an interest estimation method that prominently exhibits the features of the present disclosure. Figures 8A and 8B are flowcharts showing the flow of the interest estimation method executed by the processing device 110 operating in accordance with the program P. As shown in Figures 8A and 8B, this interest estimation method includes the processes of steps S100 to S230.

[0033] In step S100, the processing device 110 functions as an acquisition unit 111 and a selection unit 112. In step S100, the processing device 110 first acquires user information D2. Next, the processing device 110 selects an item to be determined based on the acquired user information D2 and item information D1.

[0034] In step S110 following step S100, the processing device 110 functions as the voice control unit 113. In step S110, first, the processing device 110 generates question voice information representing the voice of a question regarding the item to be determined. Next, the processing device 110 outputs the generated question voice information to the speaker 122.

[0035] In step S120, which follows step S110, the processing device 110 functions as the calculation unit 114 and the determination unit 115. In step S120, the processing device 110 first acquires, from the microphone 121, answer voice information indicating the voice of the user's answer to the question represented by the question voice information generated in step S110. Next, the processing device 110 calculates an interest value based on the expertise level of the item to be determined and the acquired answer voice information. The processing device 110 then determines whether the calculated interest value is equal to or less than a threshold value. As shown in FIG. 8A, if the determination result in step S120 is "Yes," the processing device 110 executes the process of step S130. Conversely, if the determination result in step S120 is "No," the processing device 110 executes the process of step S190, as shown in FIGS. 8A and 8B.

[0036] In step S130, the processing device 110 determines whether there is an undetermined item in the same hierarchical level as the item to be determined. If the determination result in step S130 is "Yes," the processing device 110 executes the process of step S150 and then executes the process of step S110 again. In step S150, the processing device 110 functions as the selection unit 112. In step S150, the processing device 110 selects a new item to be determined from the undetermined items in the same hierarchical level as the item to be determined, based on the item information D1.

[0037] If the determination result in step S130 is "No", the processing device 110 executes the process of step S140. In step S140, the processing device 110 determines whether or not there is an item whose interest value exceeds a threshold value among the items for which interest has been determined, i.e., whether or not there is an item determined to be of interest. If the determination result in step S140 is "Yes", the processing device 110 executes the process of step S190. If the determination result in step S140 is "No", the processing device 110 executes the process of step S160.

[0038] In step S160, the processing device 110 determines whether or not there is an item in a higher hierarchy among the items to be determined. If the determination result in step S160 is "Yes," the processing device 110 executes the process of step S170 and then executes the process of step S110 again. In step S170, the processing device 110 functions as the selection unit 112. In step S170, the processing device 110 selects an item in a higher hierarchy as the item to be determined based on the item information D1.

[0039] If the determination result in step S160 is "No," the processing device 110 executes the process of step S180 and then executes the process of step S110 again. In step S180, the processing device 110 functions as the determination unit 116 and the selection unit 112. In step S180, the processing device 110 determines that the user is not interested in the learning subject including the item to be determined. Then, in step S180, the processing device 110 selects an item that belongs to a different type of learning subject from the learning subject including the item to be determined as a new item to be determined. This is because the determination result in step S160 being "No" means that the user is not interested in the learning subject including the item to be determined selected in step S100.

[0040] In step S190, the processing device 110 determines whether there is an item in a lower hierarchical level than the item to be determined. If the determination result in step S190 is "Yes", the processing device 110 executes the process of step S200 and then executes the process of step S110. In step S200, the processing device 110 functions as the selection unit 112. In step S200, an item in the hierarchical level immediately below the item to be determined is selected as a new item to be determined based on the item information D1.

[0041] If the determination result of step S190 is "No", the processing device 110 executes the process of step S210. In step S210, the processing device 110 determines whether there is an undetermined item in the same hierarchical level as the item to be determined. If the determination result of step S210 is "Yes", the processing device 110 executes the process of step S220 and then executes the process of step S110 again. In step S220, the processing device 110 functions as the selection unit 112. In step S220, the processing device 110 selects a new item to be determined from the undetermined items in the same hierarchical level as the item to be determined. If the determination result of step S210 is "No", the processing device 110 executes the process of step S230. In step S230, the processing device 110 functions as the determination unit 116. In step S230, the processing device 110 determines the item with the largest interest value as the item of interest of the user.

[0042] (Example 1) For example, when the user of the information processing device 1 is interested in "animals" and user information D2 indicating "astronomy" is stored in the nonvolatile storage device 132, the information processing device 1 operates as follows. In the operation example described below, it is assumed that the user of the information processing device 1 is expressive in emotions, but tends to respond to questions about items in which he or she is not interested with vague phrases such as "not really" or "well, I guess." In addition, in the operation example described below, it is not determined whether the user is interested in any of the items "astronomy," "biology," "science," and "social studies."

[0043] The processing device 110, which operates according to the program P and is executing the interest estimation method shown in Figures 8A and 8B, selects "celestial bodies" as a determination target item based on the user information D2 in step S100. Then, the processing device 110 outputs question audio information representing the question "Do you like celestial bodies?" to the speaker 122 in step S110. Since the question audio information representing the question "Do you like celestial bodies?" is output to the speaker 122, the question Q01 "Do you like celestial bodies?" is output as audio from the speaker 122 of the information processing device 1 to the user U of the information processing device 1, as shown in Figure 9.

[0044] A user U of the information processing device 1 is interested in "animals," and when asked the question, "Do you like celestial bodies?", the user U replies with a cold, indifferent answer A01, "Not really." The audio of the answer A01 is picked up by the microphone 121, and in step S120, the processing device 110 acquires answer audio information representing the answer A01 from the microphone 121. Because the wording of the answer A01 is neither negative nor positive, the content evaluation value is 0.5. Furthermore, because the audio of the answer A01 is cold, i.e., contains negative emotions, the emotion evaluation value is 0. In this embodiment, the expertise level for "celestial bodies" is 2, so in step S120, the interest value is calculated as 2 × 0.5 × 0 = 0. The threshold for an expertise level of 2 is 0.5, and the calculated interest value is below this threshold. Therefore, the determination result in step S120 for the answer A01 is "Yes," and the determination in step S130 is executed.

[0045] As shown in FIG. 2, the interest tree for "science" in this embodiment has "living things" as an item at the same level as "celestial bodies," and as described above, "living things" has not been determined. Therefore, the determination result at step S130 is "Yes," and the processing device 110 executes the process of step S150. At this step S150, the processing device 110 selects "living things" as the item to be determined. After executing step S150, the processing device 110 executes the process of step S110 again, and as shown in FIG. 9, the speaker 122 of the information processing device 1 outputs a voice message for the question Q02, "Do you like living things?"

[0046] Since "animals," which user U is interested in, is included in "living things," user U, upon receiving question Q02, replies with a neutral answer A02, "Yeah, I guess so." The wording of answer A02 is somewhat positive, so the content evaluation value is 0.7. Furthermore, the voice of answer A02 does not contain much emotion, so the emotion evaluation value is 0.5. Since the expertise level of "living things" in the science interest tree is 2, the interest value calculated in step S120 is 2 × 0.7 × 0.5 = 0.7, which exceeds the threshold (0.5) when expertise level = 2. Therefore, the determination result in step S120 for answer A02 is "No," and the processing of step S190 is executed.

[0047] As shown in Figure 2, the interest tree for "Science" has two items, "Plants" and "Animals," as items in the hierarchy below "Biology." Therefore, the determination result in step S190 is "Yes," and the process of step S200 is executed. In this operation example, in step S200, "Plants" is selected as a new item to be determined.

[0048] 8A and 8B, after executing the process of step S200, the processing device 110 executes the process of step S110 again. That is, as shown in Fig. 9, the speaker 122 of the information processing device 1 outputs a voice of the question Q03, "Do you like plants?"

[0049] Since "plants" are included in "living things" but not "animals," a user who is asked the question "Do you like plants?" will respond with a neutral answer A03, "I don't dislike them." Although the wording of answer A03 is positive, the strength of the affirmation is low, so the content evaluation value is 0.6. Furthermore, the voice of answer A03 does not contain much emotion, so the emotion evaluation value is 0.50. Since the expertise level of "plants" is 3, the interest value calculated in step S120 is 3 × 0.6 × 0.5 = 0.9, which exceeds the threshold (0.75) for an expertise level of 3. Therefore, the determination result in step S120 for answer A03 is "No," and the processing of step S190 is executed.

[0050] As shown in FIG. 2, the interest tree for "Science" in this embodiment does not have any items in the hierarchy below "Plants," so the determination result in step S190 is "No," and the process of step S210 is executed. The interest tree for "Science" in this embodiment has "Animals" as an item in the same hierarchy as "Plants," and "Animals" has not been determined. Therefore, the determination result in step S210 is "Yes," and step S220 is executed. In step S220, the processing device 110 selects "Animals" as the item to be determined. After executing step S220, the processing device 110 executes the process of step S110. That is, as shown in FIG. 9, the question Q04, "Do you like animals?", is output as audio from the speaker 122 of the information processing device 1.

[0051] Since the user U of the information processing device 1 is interested in "animals," when asked the question Q04, the user U enthusiastically replies with the answer A04, "I like them." Because the wording of the answer A04 is affirmative, the content evaluation value is 1. Furthermore, because the voice of the answer A04 conveys positive emotion, the emotion evaluation value is also 1. Therefore, the interest value calculated in step S120 is 3×1×1=3, which exceeds the threshold value (0.75) when the expertise level is 3. Therefore, the determination result in step S120 is "No," and the process of step S190 is executed.

[0052] As shown in FIG. 2 , in this embodiment, the interest tree for “Science” does not have a hierarchy lower than “Animals.” Therefore, the determination result in step S190 is “No,” and processing in step S210 is executed. In this operation example, since both “Plants” and “Animals” have been determined, the determination result in step S210 is “No,” and processing in step S230 is executed. As described above, the interest values ​​for the items “Celestial Bodies,” “Living Things,” “Plants,” and “Animals” are 0, 0.7, 0.9, and 1, respectively, with “Animals” having the highest interest value. Therefore, in step S230, the processing device 110 determines “Animals” as the subject of interest for user U. Note that if the user of the information processing device 1 is interested in “the structure of celestial bodies” and “Animals,” it is likely that the user will respond to the initial question, “Do you like celestial bodies?” with a neutral, somewhat positive response like “Yeah, I guess.” The determination result in step S120 for this response is “No,” and processing in step S190 is executed. In other words, a search for interests in the hierarchy lower than “Celestial Bodies” is performed. In this case, there is a concern that interest exploration for "living things" and the hierarchical levels below "living things" will not be performed. However, since interest exploration for "living things" and the hierarchical levels below "living things" can be performed on another occasion, no particular problem will arise. For example, if the processing device 110 is caused to start execution of the program P when the user information D2 is updated, interest exploration for "living things" and the hierarchical levels below "living things" will be performed by starting execution of the program P when the user information D2 is updated to schedule information representing, for example, "interactive experience with living things."

[0053] (Example 2) The operation of the information processing device 1 when the user U is interested in "history" but not "animals" is as follows. Note that in the operation example described below, it is assumed that the user information D2 indicates "astronomy", and no determination is made as to whether the user is interested in any of the items "celestial bodies", "biology", "science", and "society".

[0054] As in the case of the above-described (Operation Example 1), the processing device 110 selects "celestial bodies" as the determination target item based on the user information D2 in step S100. Next, in step S110, the processing device 110 outputs question audio information representing the question "Do you like celestial bodies?" to the speaker 122. That is, as shown in Fig. 10 , the speaker 122 of the information processing device 1 outputs audio of the question Q11 "Do you like celestial bodies?"

[0055] Since user U is interested in "history," when asked the question "Do you like celestial bodies?", user U replies with a cold, indifferent answer A11, "Not really." Because the wording of answer A11 is neither positive nor negative, the content evaluation value is 0.5. Furthermore, because the voice of answer A11 contains negative emotions, the emotion evaluation value is 0. Therefore, in step S120, the interest value is calculated as 2×0.5×0=0. Because the threshold value when the expertise level is 2 is 0.5, the determination result in step S120 is "Yes," and the determination in step S130 is executed. Thereafter, as in the case of (Operation Example 1), the voice of question Q12, "Do you like living things?" is output from speaker 122 of information processing device 1 as shown in FIG. 10.

[0056] As described above, since the user U is interested in "history," when asked the question Q12, "Do you like living things?", the user U responds with a cold, indifferent "Not really." The determination result in step S120 is again "Yes," and the process of step S130 is executed again. However, since determinations have already been made for both "celestial bodies" and "living things," the determination result in step S130 is "No." Since the determination result in step S130 is "No," the processing device 110 executes the process of step S140. In this step S140, the processing device 110 determines whether there is an item whose interest value exceeds the threshold. In this operation example, the interest values ​​for both "celestial bodies" and "living things" are below the threshold, so the determination result in step S140 is "No," and the processing device 110 executes the process of step S160. In step S160, the processing device 110 determines whether there is an item in a higher hierarchy than the item to be determined, i.e., "living things."

[0057] In this operation example, as shown in FIG. 2, there is an item called "Science" in a higher level than "Biology", so the determination result in step S160 is "Yes". Since the determination result in step S160 is "Yes", the processing device 110 executes the process of step S170. In this operation example, in step S170, the processing device 110 selects "Science", which is an item in a higher level than "Biology", as the item to be determined. Then, after executing step S170, the processing device 110 executes the process of step S110 again. That is, as shown in FIG. 10, the question Q13 "Do you like science?" is output as audio from the speaker 122 of the information processing device 1.

[0058] As described above, since user U is interested in "history," when asked the question Q13, "Do you like science?", user U responds with a cold, indifferent "Not really." The determination result in step S120 is again "Yes," and the process of step S130 is executed again. However, since there is no item at the same level as "science" in the interest tree related to science, the determination result in step S130 is "No," and the determination in step S140 is executed. In this operation example, the interest values ​​for "celestial bodies," "living things," and "science" are all below the threshold, so the determination result in step S140 is "No," and the process of step S160 is executed. In step S160, the processing device 110 determines whether there is an item at a higher level than the item to be determined, i.e., "science."

[0059] In this embodiment, the interest tree for science does not have any items in a higher hierarchy than "science," so the determination result in step S160 is "No." If the determination result in step S160 is "No," the processing device 110 executes the process of step S180, and then executes the process of step S110 again. In this operation example, in step S180, the processing device 110 selects a subject of study other than "science," specifically "social studies," as the item to be determined. That is, as shown in FIG. 10 , the speaker 122 of the information processing device 1 outputs a voice message of the question Q14, "Do you like social studies?"

[0060] Since the "history" that user U is interested in is included in "society", user U who received question Q14 returns answer A14 of "Well, so-so" without much emotion. Since the text of answer A14 is somewhat affirmative, the content evaluation value is 0.7. Also, since not much emotion is put into the voice of answer A02, the emotion evaluation value is 0.5. As shown in Figure 2, since the expertise level of "society" is 1, the interest value calculated in step S120 is 1×0.7×0.5 = 0.35, which exceeds the threshold value (0.25) when the expertise level = 1. Therefore, the determination result of step S120 for answer A14 is "No", and the process of step S190 is executed. Thereafter, the search for the user's interest target is performed in accordance with the interest tree shown in Figure 2.

[0061] As described above, even if an ambiguous answer is given to a question regarding an item to be determined for the presence or absence of interest, the information processing apparatus 1 of the present disclosure can correctly determine the item that is the target of the user's interest.

[0062] <B. Variation> Although one embodiment of the present disclosure has been described above, this embodiment may be modified as follows. The user information D2 in the above embodiment was information indicating the school schedule, but it may be information indicating the schedule of the user's actions unrelated to school events such as family trips. Also, the user information D2 may be information indicating the past actions of the user. As a specific example of information indicating the past actions of the user, information indicating the web pages that the user has browsed in the past using the information processing apparatus 1 can be mentioned. Also, when the information processing apparatus 1 includes an imaging device, as another specific example of information indicating the past actions of the user, image information representing the images that the user has captured in the past using the information processing apparatus 1 can be mentioned. Since the user's preferences are reflected in the information indicating the past actions of the user, by selecting the determination target item based on the user information D2 indicating the past actions of the user, the efficiency of searching for the items that the user is interested in is improved.

[0063] In addition, the user information D2 is not limited to information indicating the user's planned actions or past actions, and may be, for example, information indicating the user's preferences. When the information indicating the user's preferences is used as the user information D2, the user information D2 may be generated by analyzing information indicating the user's past actions, or may be input by the user's guardian. Also, information obtained from statistics on the preferences of a large number of children of the same age as the user may be used as the user information D2.

[0064] <C: Others> (1) In each of the above embodiments and modifications, the non-volatile memory device 132 may include a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory device (e.g., a card, a stick, a key drive), a CD-ROM (Compact Disc-ROM), a register, a removable disk, a hard disk, a floppy (registered trademark) disk, a magnetic strip, a database, a server, and other suitable storage media. Also, the program may be transmitted from a network via a telecommunication line.

[0065] (2) Each of the above embodiments and modifications may be applied to a system that uses LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), and other suitable systems and / or next-generation systems extended based on these.

[0066] (3) The information described in each of the above embodiments and modifications may be represented using any of a variety of different technologies. For example, data, information, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields, magnetic particles, optical fields, photons, or any combination thereof. It should be noted that terms explained in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0067] (4) In each of the above embodiments and modifications, input and output information may be stored in a specific location (e.g., the volatile storage device 131) or managed by a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0068] (5) In each of the above embodiments and variations, the determination may be based on a value represented by one bit (0 or 1), a Boolean (true or false), or a comparison of numerical values ​​(e.g., a comparison with a predetermined value).

[0069] (6) The order of the illustrated processing procedures, sequences, or flowcharts in each of the above embodiments and variations may be changed as long as there is no contradiction. For example, the methods described herein present elements of various steps in an exemplary order, and are not limited to the specific order presented.

[0070] (7) Each function illustrated in FIG. 1 is realized by any combination of hardware and software. Furthermore, there are no particular limitations on how each function is realized. That is, each function may be realized by using a single device that is physically or logically coupled, or by using two or more physically or logically separated devices that are connected directly or indirectly (for example, by wire, wirelessly, etc.) and these multiple devices. A functional block may be realized by combining software with the single device or the multiple devices. Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how each is implemented.

[0071] (8) The programs exemplified in each of the above embodiments and variations should be broadly construed to mean instructions, instruction sets, code, code segments, program code, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, or functions, regardless of whether they are called software, firmware, middleware, microcode, hardware description language, or by other names. Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0072] (9) The information processing device 1 may be a mobile station, which may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term.

[0073] (10) In each of the above embodiments and modifications, unless otherwise specified, the phrase "based on" does not mean "based only on." In other words, the phrase "based on" means both "based only on" and "based at least on."

[0074] (11) In each of the above embodiments and variations, to the extent that the terms "including," "comprising," and variations thereof are used in this specification or the claims, these terms are intended to be inclusive, similar to the term "comprise." Furthermore, the term "or" used in this specification or the claims is not intended to be an exclusive or.

[0075] (12) Throughout this application, where articles have been added by translation, such as a, an and the in English, these articles include the plural unless the context clearly indicates otherwise.

[0076] (13) In this specification, the term "device" may be read as other terms such as circuit, device or unit.

[0077] (14) It is obvious to those skilled in the art that the present invention is not limited to the embodiments described in this specification. The present invention can be implemented as modifications and variations without departing from the spirit and scope of the present invention determined based on the description of the claims. Therefore, the description of this specification is for the purpose of exemplary explanation and has no restrictive meaning for the present invention. Also, a plurality of aspects selected from the aspects exemplified in this specification may be combined.

[0078] <D: Aspects grasped from the above embodiments or modified examples> The following aspects are grasped from at least one of the above embodiments or modified examples. The information processing apparatus according to the first aspect includes a selection unit, an audio control unit, a calculation unit, and a determination unit. The selection unit selects an item to be determined for the presence or absence of the user's interest from among a plurality of items related to one learning subject. The audio control unit generates first audio information representing the audio of a question related to the item selected by the selection unit. The audio control unit outputs the generated first audio information to the speaker. The calculation unit generates an interest value indicating the strength of the user's interest in the item selected by the selection unit based on second audio information representing the audio of the user's answer to the question indicated by the first audio information. The calculation unit calculates the interest value based on a first evaluation value indicating the strength of the user's interest estimated from the text of the answer represented by the second audio information and a second evaluation value indicating the strength of the user's interest estimated from the emotion contained in the audio represented by the second audio information. The determination unit determines the presence or absence of the user's interest in the item selected by the selection unit based on the interest value calculated by the calculation unit. The information processing apparatus according to the first aspect can determine the presence or absence of the user's interest in an item selected from a plurality of items related to one learning subject based on the text of the answer given by the user to a question related to the selected item and the emotion contained in the answer.

[0079] In the example of the first aspect (second aspect), the information processing device may further include an acquisition unit that acquires user information related to the user's behavior. In this second aspect, the selection unit may select an item based on the user information acquired by the acquisition unit. The information processing device according to the second aspect can select an item to be used to determine whether the user is interested in the item based on the user information related to the user's behavior.

[0080] In an example of the first or second aspect (third aspect), the selection unit may select an item to be judged based on item information in which a plurality of items related to one learning subject are classified into a tree structure in which lower levels have higher specialization than higher levels. In the second aspect, the judgment unit may judge that the user is interested in the item to be judged if the interest value exceeds a threshold. In the second aspect, when the judgment unit judges that the user is interested in the item to be judged and there is an item in a lower level than the item to be judged, the selection unit may select an item in a lower level than the item to be judged as a new item to be judged based on the item information. In the second aspect, the judgment unit may further judge whether the user is interested in the new item to be judged. The information processing device according to the third aspect can search for items of interest to the user in a direction of increasing specialization in accordance with the tree structure indicated by the item information.

[0081] In an example of the third aspect (fourth aspect), when the determination unit determines that the user is interested in the item to be determined and there are no items at a lower level than the item to be determined, the selection unit may sequentially select unselected items at the same level as the item to be determined based on the item information. In the fourth aspect, the calculation unit may calculate an interest value for each of the unselected items sequentially selected by the selection unit. The information processing device in the fourth aspect may further include a determination unit. When the determination unit determines that the user is interested in the item to be determined, there are no items at a lower level than the item to be determined, and the user's interest in items at the same level as the item to be determined has already been determined, the determination unit determines the item with the largest interest value as the item of interest to the user. The information processing device according to the fourth aspect can widely search for items of interest to the user in accordance with the tree structure indicated by the item information.

[0082] In an example of the third or fourth aspect (fifth aspect), the determination unit may determine that the user is not interested in the item to be determined when the interest value of the item to be determined is equal to or less than a threshold. In the fifth aspect, the selection unit may select one of the unselected items based on the item information in a first state in which the determination unit determines that the user is not interested in the item to be determined and there are unselected items in the same hierarchical level as the item to be determined. Also, in the fifth aspect, the selection unit may select an item in a higher hierarchical level based on the item information in a second state in which the determination unit determines that the user is not interested in the item to be determined and there are no unselected items in the same hierarchical level as the item to be determined. Also, in the fifth aspect, the determination unit may further determine whether the user is interested in one of the selected unselected items in the first state, and may determine whether the user is interested in the selected item in a higher hierarchical level in the second state. Also, in the fifth aspect, the determination unit may determine the item with the largest interest value as the user's target of interest in a third state described below. The third state is a state in which the judgment unit judges that the user is not interested in the item to be judged, and the presence or absence of interest has been judged for all other items in the same hierarchical level as the item to be judged, and there is an item judged to be of interest. Also, in the fifth aspect, the determination unit may determine that the user is not interested in a certain learning subject in the following fourth state. The fourth state is a state in which the judgment unit judges that the user is not interested in the item to be judged, and the presence or absence of interest has been judged for all other items in the same hierarchical level as the item to be judged, and there is no item judged to be of interest, and there is no item in a higher hierarchical level than the item to be judged. The information processing device according to the fifth aspect can widely search for items of interest to the user in accordance with the tree structure indicated by the item information.

[0083] In an example of the fifth aspect (sixth aspect), the item information may classify multiple items for each of multiple types of learning subjects, including one learning subject, into a tree structure in which lower levels have higher specialization than higher levels. In the sixth aspect, when the determination unit determines that the user is not interested in the one learning subject, the selection unit may newly select an item that belongs to a type of learning subject different from the one learning subject. The information processing device according to the sixth aspect can search for an item that interests the user from among multiple types of learning subjects. [Explanation of symbols]

[0084] 1...information processing device, 110...processing device, 111...acquisition unit, 112...selection unit, 113...audio control unit, 114...calculation unit, 115...judgment unit, 116...decision unit, 120...audio input / output device, 121...microphone, 122...speaker, 130...storage device, 131...volatile storage device, 132...non-volatile storage device, 140...communication device, 150...input device.

Claims

1. a selection unit for selecting an item to be used to determine whether or not a user is interested in the item from among a plurality of items related to one learning subject; a voice control unit that generates first voice information representing a voice of a question related to the item selected by the selection unit and outputs the generated first voice information to a speaker; a calculation unit that calculates an interest value that indicates the strength of the user's interest based on a first evaluation value that indicates the strength of the user's interest estimated from the wording of the answer represented by second voice information that indicates the voice of the user's answer to the question, and a second evaluation value that indicates the strength of the user's interest estimated from the emotion contained in the voice represented by the second voice information; a determination unit that determines whether the user is interested in the item selected by the selection unit based on the interest value calculated by the calculation unit; an acquisition unit that acquires user information related to the user's behavior, the selection unit selects an item based on the user information acquired by the acquisition unit, The user information is information indicating the user's future behavior, information indicating the user's past behavior, or information indicating the user's preferences. Information processing device.

2. The selection unit selects the item to be judged based on item information in which a plurality of items related to the one learning subject are classified into a tree structure in which lower levels have higher specialization than higher levels, the determination unit determines that the user is interested in the item to be determined when the interest value exceeds a threshold value; the selection unit, when the determination unit determines that the item to be determined is of interest and there is an item at a lower level than the item to be determined, selects, based on the item information, an item at a lower level than the item to be determined as a new item to be determined; the determination unit determines whether the user is interested in the new item to be determined. The information processing device according to claim 1 .

3. When the determination unit determines that the user is interested in the item to be determined and there is no item at a lower level than the item to be determined, the selection unit sequentially selects unselected items at the same level as the item to be determined based on the item information, the calculation unit calculates an interest value for each of the unselected items sequentially selected by the selection unit; a determination unit that determines an item with a maximum interest value as an item of interest to the user when the determination unit determines that the user is interested in the item to be determined, there are no items in a lower hierarchy than the item to be determined, and the user's interest in items in the same hierarchy as the item to be determined has already been determined; The information processing device according to claim 2 .

4. The determination unit determines that the user is not interested in the item to be determined when an interest value for the item to be determined is equal to or less than the threshold value, The selection unit In a first state in which the determination unit determines that the user is not interested in the item to be determined and there are unselected items in the same hierarchical level as the item to be determined, the determination unit selects one of the unselected items based on the item information; In a second state in which the determination unit determines that the user is not interested in the item to be determined, there is no undetermined item in the same hierarchical level as the item to be determined, and there is an item in a higher hierarchical level than the item to be determined, the determination unit selects the item in the higher hierarchical level based on the item information, The determination unit further In the first state, determining whether the user is interested in any of the selected and unselected items; In the second state, determining whether the user is interested in the selected item in the higher hierarchy; The determination unit In a third state in which the determination unit determines that the user is not interested in the item to be determined, and the presence or absence of interest has been determined for all other items in the same hierarchical level as the item to be determined, and there is an item determined to be of interest, the item with the largest interest value is determined to be the subject of the user's interest, In a fourth state in which the judgment unit judges that the user is not interested in the item to be judged, and the presence or absence of interest has been judged for all other items at the same hierarchical level as the item to be judged, and there is no item judged to be interested, and there is no item at a higher hierarchical level than the item to be judged, it is determined that the user is not interested in the one learning subject. The information processing device according to claim 3 .

5. In the item information, for each of a plurality of types of learning subjects including the one learning subject, a plurality of items are classified into a tree structure in which the specialization of a lower level is higher than the specialization of a higher level, the selection unit, when the determination unit determines that the user is not interested in the one learning subject, newly selects an item that belongs to a different type of learning subject from the one learning subject; The information processing device according to claim 4 .

Images