Information processing device and learning system

JP2024159610APending Publication Date: 2024-11-08NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE & TECHNOLOGY
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024069082
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-04-28
Filing Date
2024-04-22
Publication Date
2024-11-08

AI Technical Summary

Benefits of technology

【0009】 本発明の一態様によれば、学習に適した行動の提案を行うことができる。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024159610000001_ABST
    Figure 2024159610000001_ABST
Patent Text Reader

Abstract

To propose behaviors appropriate for learning.SOLUTION: According to an aspect of the present invention, an information processing device (4) includes an acquisition part (410) for acquiring first information showing at least either a learning environment around a user and a body condition of the user, a calculation part (411) for calculating at least either the adaption degree of the learning environment and the body condition to the user's learning, and an output part (412) for outputting information showing behaviors to improve the adaption degree in the case that the adaption degree is determined not to satisfy a first threshold.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device and a learning system including the information processing device. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there are known systems that provide study content so as to improve the study effect according to a user's study history, and systems that determine whether or not a study environment is suitable for study.

[0003] Patent Document 1 discloses a content presentation system that allows a user to automatically obtain information about a state suitable for content presentation when content such as e-learning is presented to the user. The content presentation system presents the content to the user when the user is in a state suitable for content presentation. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2015-179212 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-mentioned conventional technology does not assume that the learning environment or the user's physical condition is improved to a state suitable for learning when the learning environment or the user's physical condition is not suitable for learning. In other words, the above-mentioned conventional technology is insufficient in terms of improving the learning environment or the user's physical condition to a state suitable for learning when the learning environment or the user's physical condition is not suitable for learning.

[0006] One aspect of the present invention has been made in consideration of the above problems, and aims to suggest actions suitable for learning. [Means for solving the problem]

[0007] In order to solve the above problems, an information processing device according to one embodiment of the present invention includes an acquisition unit that acquires first information indicating at least one of the learning environment around a user and the physical condition of the user, a calculation unit that calculates the suitability of at least one of the learning environment and the physical condition for the user to study by referring to the first information, and an output unit that outputs information indicating an action to be taken to improve the suitability when it is determined that the suitability does not satisfy a first threshold value.

[0008] In order to solve the above problem, a learning system according to one aspect of the present invention is a learning system including the information processing device according to the above aspect of the present invention, a wearable device, and a terminal device. In this learning system, the wearable device includes one or more sensors that generate the first information and outputs the first information, the information processing device outputs information indicating an action to improve the degree of conformance when it is determined that the degree of conformance does not satisfy a first threshold, and the terminal device outputs information indicating an action to improve the degree of conformance. Effect of the Invention

[0009] According to one aspect of the present invention, it is possible to suggest actions suitable for learning. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a learning system according to a first embodiment of the present invention. [Diagram 2] 1 is a schematic diagram showing the configuration of a learning system according to a first embodiment of the present invention. [Diagram 3] FIG. 4 is a diagram illustrating an example of a process executed by an output unit according to the first embodiment of the present invention. [Figure 4] 3 is a sequence diagram showing the flow of processing executed in the learning system according to the first embodiment of the present invention. FIG. [Diagram 5]5 is a flowchart showing a process for generating information to be output by an output unit according to the first embodiment of the present invention. [Figure 6] 13 is a flowchart showing a process for generating information to be output by an output unit according to the first modification. [Figure 7] FIG. 11 is a sequence diagram showing the flow of processes executed in a learning system according to the second modification. [Figure 8] 13 is a flowchart showing a process for generating information to be output by an output unit according to Modification 2. [Figure 9] FIG. 11 is a sequence diagram showing the flow of processing executed in a learning system according to the third modified example. [Figure 10] 13 is a flowchart showing a process for generating information to be output by an output unit according to Modification 3. [Figure 11] FIG. 13 is a sequence diagram showing the flow of processes executed in a learning system according to the fourth modified example. [Figure 12] 13 is a flowchart showing a process for generating information to be output by an output unit according to Modification 4. [Figure 13] FIG. 13 is a sequence diagram showing the flow of processing executed in a learning system according to the sixth modified example. [Figure 14] 13 is a flowchart showing a process for generating information to be output by an output unit according to Modification 6. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] [Embodiment 1] Hereinafter, one embodiment of the present invention will be described in detail.

[0012] [Overview and configuration of the learning system] The outline and configuration of a learning system 100 according to one embodiment of the present invention (embodiment 1) will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a block diagram showing the configuration of the learning system 100 according to this embodiment. Fig. 2 is a schematic diagram showing the configuration of the learning system 100 according to this embodiment.

[0013] As shown in Fig. 1 and Fig. 2, the learning system 100 includes a wearable device 1, a smartphone 2 (terminal device), a learning server 3, and an information processing device 4. As shown in Fig. 1, the wearable device 1, the smartphone 2, the learning server 3, and the information processing device 4 are connected to each other via a network N so as to be able to communicate with each other. Note that the wearable device 1 and the smartphone 2 may be configured to communicate directly without going through the network N (see Fig. 2), or may be configured to communicate via the network N. One example of a method for the wearable device 1 and the smartphone 2 to communicate directly is close-proximity communication such as Bluetooth (registered trademark).

[0014] The learning system 100 is a system used for user learning. An example of learning in the learning system 100 is learning using e-learning. The learning system 100 is a system that suggests at least one of the following: a user's behavior that makes the user's learning environment suitable for learning, and a user's behavior that makes the user's physical condition suitable for learning.

[0015] The wearable device 1 is a device worn by a user. Examples of the wearable device 1 include a wristwatch-type smart watch, eyeglass-type smart glasses, and a finger-type smart ring. The wearable device 1 may be a device that can be attached to hair, a hat, clothing, shoes, or the like. The above-mentioned "worn by a user" in the case of the wearable device 1 is not limited to being in physical contact with the user. The "device worn by a user" also includes a device placed inside an object held by the user. The concept of "worn by a user" includes, for example, a case in which the device is placed in a bag and the user holds the bag.

[0016] The smartphone 2 is a terminal device carried by a user. The learning system 100 will be described by taking as an example a case in which the learning system 100 includes a smartphone 2, but instead of the smartphone 2, a tablet or a notebook computer may be included.

[0017] The learning server 3 and the information processing device 4 are servers arranged on a network. Examples of the learning server 3 and the information processing device 4 include a desktop computer. Also, for example, one computer (such as a desktop computer) may be configured to have both the functions of the learning server 3 and the information processing device 4.

[0018] <Wearable device configuration> As shown in FIG. 1, the wearable device 1 includes a control unit 11, a communication unit 12, a storage unit 13, and one or more sensor units 14 (sensors).

[0019] The communication unit 12 is an interface that transmits and receives information via the network N. As an example, the communication unit 12 transmits first information (described later) output from the control unit 11 to the smartphone 2, and supplies information indicating a request for the first information transmitted from the smartphone 2 to the control unit 11. Examples of the communication unit 12 include communication chips in various communication standards such as Ethernet (registered trademark) and Wi-Fi (registered trademark), and a USB-compliant connector. These examples also apply to communication units (communication units 22, 32, and 42) included in other devices.

[0020] The storage unit 13 stores information referenced by the control unit 11. An example of the information stored in the storage unit 13 is the first information. An example of the storage unit 13 is a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination of these. These examples also apply to storage units (storage unit 23, storage unit 33, and storage unit 43) included in other devices.

[0021] The sensor unit 14 senses at least one of the learning environment around the user wearing the wearable device 1 and the user's physical condition, and outputs information indicating at least one of the sensed learning environment and the user's physical condition. Hereinafter, the information output by the sensor unit 14 is also referred to as first information. Examples of the sensor unit 14 include a three-axis acceleration sensor, a three-axis angular velocity sensor, a three-axis gyro sensor, an illuminance sensor, and a microphone. Another example of the sensor unit 14 is a clock. In this embodiment, the clock is a sensor unit that senses the time, which is an example of the learning environment. The sensor unit 14 may be configured to be provided in an external device of the wearable device 1. When the sensor unit 14 is provided in an external device, the wearable device 1 communicates with the external device using communication via the communication unit 12 or direct communication such as close-proximity communication to acquire the first information.

[0022] Examples of information indicating the learning environment around the user include information indicating surrounding sounds, temperature, humidity, illuminance, odors, carbon dioxide (CO2) concentration, vibrations, etc. For example, the CO2 concentration may be detected by the wearable device 1, or may be acquired by the wearable device 1 from a measuring device that measures the CO2 concentration. Examples of information indicating the user's physical condition include information indicating heart rate, body temperature, blood pressure, blood sugar level, respiratory rate, and degree of sweating, etc.

[0023] The control unit 11 controls each component included in the wearable device 1. Examples of the control unit 11 include a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. These examples are also applicable to control units (control unit 21, control unit 41, and control unit 41) included in other devices. In addition, the control unit 11 includes an acquisition unit 110 and an output unit 111 as shown in FIG. 1.

[0024] The acquisition unit 110 acquires information output from the communication unit 12 or the sensor unit 14. Examples of information acquired by the acquisition unit 110 include information indicating a request for the first information and the first information. The acquisition unit 110 stores the acquired information in the storage unit 13. The acquisition unit 110 may also associate the acquired information with the date and time of acquisition and store the information in the storage unit 13 as a log.

[0025] The output unit 111 outputs information via the communication unit 12. An example of the information output by the output unit 111 is the first information stored in the storage unit 13.

[0026] <Smartphone configuration> A smartphone 2, which is an example of a terminal device, includes a control unit 21, a communication unit 22, a storage unit 23, an operation input unit 24, a display unit 25, and a location information receiving unit 26, as shown in FIG.

[0027] The communication unit 22 is an interface that transmits and receives information via the network N. As an example, the communication unit 22 transmits the first information output from the control unit 21 to the information processing device 4, and supplies the learning content transmitted from the learning server 3 to the control unit 21.

[0028] The storage unit 23 stores information referenced by the control unit 21. Examples of the information stored in the storage unit 23 include first information and information for identifying the user of the smartphone 2 (hereinafter, also referred to as “third information”).

[0029] Operation input unit 24 is an interface that accepts operations from the user. As an example, operation input unit 24 accepts an operation to request display of study content. Operation input unit 24 supplies information indicating the accepted operation to control unit 21. An example of operation input unit 24 is a touch pad superimposed on display unit 25.

[0030] The display unit 25 is a device that displays text, images, etc. As an example, the display unit 25 displays an image including information supplied from the control unit 21. Examples of the display unit 25 include a liquid crystal display and an organic EL display.

[0031] The position information receiving unit 26 receives position information (information indicating the current location of the user who owns the smartphone 2) indicating the position of the smartphone 2. The position information receiving unit 26 supplies the received position information to the control unit 21. An example of the position information receiving unit 26 is a device that receives a GPS (Global Positioning System) signal based on a satellite positioning system.

[0032] The control unit 21 controls each component of the smartphone 2. As an example, the control unit 21 installs a study application and uses the study application to play study content and output information including suggestions, which will be described later. The control unit 21 also includes an acquisition unit 210 and an output unit 211, as shown in FIG. 1.

[0033] The acquisition unit 210 acquires information supplied from the communication unit 22, the operation input unit 24, and the location information receiving unit 26. Examples of information acquired by the acquisition unit 210 include the first information, information indicating an operation, and location information. The acquisition unit 210 stores the acquired information in the storage unit 23. The acquisition unit 210 may also associate the acquired information with the date and time of acquisition and store the information in the storage unit 23 as a log.

[0034] Output unit 211 outputs information to an external device via communication unit 22. Examples of information output by output unit 211 include first information stored in memory unit 13, information indicating a request for study content, and information indicating an action to improve suitability, which will be described later. Output unit 211 also provides the user with various information, including the study content, by displaying text, images, and the like on display unit 25.

[0035] <Learning server configuration> As shown in FIG. 1, the learning server 3 includes a control unit 31, a communication unit 32, and a storage unit 33.

[0036] The communication unit 32 is an interface that transmits and receives information via the network N. As an example, the communication unit 32 transmits the study content output from the control unit 31 to the smartphone 2, and supplies the control unit 31 with information indicating a request for the study content transmitted from the smartphone 2.

[0037] Storage unit 33 stores information referenced by control unit 31. An example of information stored in storage unit 33 is study content.

[0038] The control unit 31 controls each component included in the learning server 3. The control unit 31 also includes an acquisition unit 310 and an output unit 311, as shown in FIG.

[0039] The acquisition unit 310 acquires information provided by the communication unit 32. An example of the information acquired by the acquisition unit 310 is information indicating a request for study content. Another example of the information acquired by the acquisition unit 310 is a learning result as a result of studying using the study content. In this case, the acquisition unit 310 associates the acquired learning result with the study content and stores it in the storage unit 33. Furthermore, the acquisition unit 310 may acquire third information that identifies the user who performed the study. In this case, the acquisition unit 310 associates the study content, the learning result, and the third information and stores them in the storage unit 33. Furthermore, the acquisition unit 310 may associate the acquired information with the date and time of acquisition and store it as a log in the storage unit 33.

[0040] Output unit 311 outputs information via communication unit 32. An example of the information output by output unit 311 is study content.

[0041] <Configuration of information processing device> As shown in FIG. 1, the information processing device 4 includes a control unit 41, a communication unit 42, and a storage unit 43.

[0042] The communication unit 42 is an interface that transmits and receives information via the network N. As an example, the communication unit 42 transmits information output from the control unit 41 to the smartphone 2 and supplies first information transmitted from the smartphone 2 to the control unit 41.

[0043] The storage unit 43 stores information referred to by the control unit 41. Examples of the information stored in the storage unit 43 include the first information, a degree of compatibility calculated by a calculation unit 411 described later, and information generated by an output unit 412 described later.

[0044] The control unit 41 controls each component included in the information processing device 4. The control unit 41 also includes an acquisition unit 410, a calculation unit 411, an output unit 412, and a learning unit 413, as shown in FIG.

[0045] The acquisition unit 410 acquires information provided by the communication unit 42. As an example, the acquisition unit 410 acquires first information indicating at least one of a learning environment around the user and a physical condition of the user. The acquisition unit 410 stores the acquired first information in the storage unit 43.

[0046] The calculation unit 411 calculates the suitability of at least one of the learning environment and the physical condition for the user to study. As an example, the calculation unit 411 calculates the suitability of at least one of the learning environment and the physical condition for the user to study, by referring to the first information stored in the storage unit 43. The calculation unit 411 stores the calculated suitability in the storage unit 43.

[0047] An example of a method in which the calculation unit 411 calculates the fitness is a method using a trained model constructed by machine learning. The trained model used by the calculation unit 411 is a trained model that receives the first information as an input and outputs the fitness or information corresponding to the fitness. Examples of the trained model include a support vector machine, a deep neural network, and a trained model based on Bayesian statistics, etc.

[0048] The calculation unit 411 may directly output (calculate) the degree of conformance output by the trained model based on the first information, or may estimate an index of a specific learning environment or physical condition estimated as a result of integrating or converting the first information, and then calculate the degree of conformance using the estimated information. For example, the calculation unit 411 may estimate the degree of conformance using a result of estimating "inside a train" by machine learning from information such as sound and vibration that indicates the learning environment, or may estimate the degree of conformance using the degree of stress estimated from the heart rate and sweating as a physical condition. In this case, the calculation unit 411 may calculate the degree of conformance by performing a predetermined calculation on the information estimated by the trained model.

[0049] The output unit 412 generates information indicating an action to improve the degree of suitability. As an example, when it is determined that the degree of suitability calculated by the calculation unit 411 is not sufficient to the first threshold, the output unit 412 generates information indicating an action to improve the degree of suitability. In other words, when it is determined that at least one of the learning environment around the user and the physical condition of the user is not suitable for the user to study, the output unit 412 generates information indicating the user's action to create a suitable learning environment or the user's action to create a suitable physical condition.

[0050] Furthermore, the output unit 412 outputs information via the communication unit 42. An example of the information output by the output unit 412 is information indicating the above-mentioned action for improving the degree of compatibility.

[0051] An example of a process in which the output unit 412 determines an action for improving the degree of compatibility will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of a process executed by the output unit 412 according to this embodiment. As an example, the output unit 412 may determine an action for improving the degree of compatibility using a state transition model.

[0052] First, the output unit 412 refers to the first information stored in the storage unit 43 and identifies the current state. Next, the output unit 412 calculates the cost for transitioning to a target state (in other words, a state with a high degree of compatibility). Then, the output unit 412 generates information indicating an action with the smallest cost. An example of a method by which the output unit 412 calculates the smallest cost is the Dijkstra algorithm.

[0053] For example, FIG. 3 shows that the current state is state b, and the target state is state e. In this case, the output unit 412 calculates the transition cost of transitioning from state b to state e. For example, when transitioning from state b to state c by action C, transitioning from state c to state d by action D, and transitioning from state d to state e by action E, the transition cost is "3". On the other hand, when transitioning from state b to state e by action F, the transition cost is "2". Therefore, the output unit 412 generates information indicating action F with the smallest transition cost.

[0054] The method by which the output unit 412 determines the target state is not limited, and may be determined, for example, by referring to at least one of the learning environment around the user and the user's physical condition, as well as the learning history and learning results managed by the learning server 3. In this case, the output unit 412 determines the state that improves the learning results as the target state.

[0055] As an example, if the user's surrounding learning environment is his / her own room and there is a history of the learning performance improving when the user studies English from 19:00 to 21:00, the output unit 412 determines the state of studying English in his / her own room from 19:00 to 21:00 as the target state.

[0056] As another example, if there is a history that the learning performance improves when the user studies in a state where the user's heart rate is low, the output unit 412 determines the state where the user's heart rate is low as the target state.

[0057] The output unit 412 may determine an action for improving the degree of compatibility using a state transition model of the learning environment when the first information indicates the learning environment around the user, and may determine an action for improving the degree of compatibility using a state transition model of the physical state when the first information indicates the physical state of the user. Also, when the first information indicates the learning environment around the user and the physical state of the user, the output unit 412 may determine an action for improving the degree of compatibility using a state transition model of the learning environment and the physical state.

[0058] Furthermore, when the first information includes learning environment information indicating the learning environment around the user and physical condition information indicating the physical condition of the user (in other words, when the acquisition unit 410 acquires the first information including the learning environment information and the physical condition information), the first threshold value can be expressed using a curve on a two-dimensional plane defined by a coordinate axis indicating the degree of conformance to the learning environment information and a coordinate axis indicating the degree of conformance to the physical condition information. In such a case, the degree of conformance to the learning environment information and the degree of conformance to the physical condition information calculated with reference to the first information are expressed by a point on the two-dimensional plane. The output unit 412 compares the position of this point with the position of the curve indicating the first threshold value to determine the degree of conformance, and if the degree of conformance does not meet the first threshold value, generates information indicating an action to improve the degree of conformance and outputs the generated information. In other words, when it is determined that the degree of conformance to the learning environment information and the degree of conformance to the physical condition information calculated with reference to the first information does not meet the first threshold value on the two-dimensional plane, the output unit 412 outputs information indicating an action to increase the degree of conformance.

[0059] The method by which the output unit 412 determines an action for improving the degree of compatibility is not particularly limited. The output unit 412 may be configured to determine an action for improving the degree of compatibility based on a predetermined program, or may be configured to determine an action for improving the degree of compatibility using a trained model constructed by machine learning. In this embodiment, the latter configuration is described. In the latter configuration, the trained model used by the output unit 412 is a trained model that takes the degree of compatibility as an input and outputs an action for improving the degree of compatibility. In addition, the output unit 412 may use the first information together with the degree of compatibility when determining an action for improving the degree of compatibility. In this case, the trained model described above may be configured to take the degree of compatibility and the first information as an input and output an action for improving the degree of compatibility.

[0060] An example of the trained model used by the output unit 412 is a natural language generation model (hereinafter, the "natural language generation model" is also referred to as a "language model" or "language generation model") constructed by machine learning. An example of the language model is a language model configured to generate and output a natural language describing an action to improve the degree of suitability, using as input a prompt (a sentence written in natural language and describing an instruction to the trained model) instructing to output an action to improve the degree of suitability and first information. As an example, the language model is a model that learns from the first information and a description of the interpretation of the first information, and natural language data regarding the degree of suitability of the learning content and state transitions and costs due to the action, and is trained to generate a natural language according to the prompt. An example of the learning data to be trained in the language model is data spoken by a cram school teacher regarding the degree of suitability between the learning content and the user's state, but is not limited to this.

[0061] Specific examples of language generation models used by the output unit 412 include large-scale language models such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT). Other examples of language models used by the output unit 412 include language models (e.g., Chat Generative Pre-trained Transformer (ChatGPT)) created by fine-tuning a pre-trained large-scale language model using conversation data.

[0062] Furthermore, when the output unit 412 uses a language generation model, the output unit 412 selects a prompt to be input to the language model from a plurality of prompt candidates. If necessary, the user may directly select a prompt to be input to the language model from a plurality of prompt candidates. The plurality of prompt candidates are set in advance by a system designer. A configuration may also be adopted in which a plurality of prompt candidates created by the user are stored in advance in the storage unit 43. The user may interactively create or select a prompt in response to a question in natural language from the generation model.

[0063] As an example, each of the multiple candidate prompts may be associated with a type of learning environment or physical information, e.g., prompt P1 may be associated with ambient sounds, prompt P2 may be associated with ambient temperature, prompt P3 may be associated with heart rate, and prompt P4 may be associated with body temperature.

[0064] In this case, the output unit 412 selects a prompt to be input to the language model from a plurality of prompt candidates based on the first information to be input to the language model. For example, if the first information is information indicating the volume of surrounding sounds, the output unit 412 selects prompt P1 associated with the surrounding sounds. Also, if the first information is information indicating a heart rate, the output unit 412 selects prompt P3 associated with the heart rate. The output unit 412 may select prompt candidates according to at least one of a specific time and a location according to a user's prior setting.

[0065] In addition, the size of the data of the first information input to the language model is not particularly limited. For example, if the first information is data indicating the number of steps of the user, the first information input to the language model may be the number of steps the user has walked in the past hour from the current time, the number of steps the user has walked on the day, or the number of steps the user has walked in the past week from the current time.

[0066] The learning unit 413 uses the training data to construct a trained model used by the calculation unit 411. Here, the training data used by the learning unit 413 is training data that includes a pair of the first information and information corresponding to the degree of compatibility.

[0067] Furthermore, the learning unit 413 may be configured to use training data to construct a trained model used by the output unit 412. Here, the training data is training data that pairs a fitness level and an action for improving the fitness level. Furthermore, when the trained model used by the output unit 412 receives the fitness level and the first information as input and outputs an action for improving the fitness level, the training data is training data that pairs a fitness level, the first information, and an action for improving the fitness level.

[0068] [Processing Executed in the Learning System] The process executed in the learning system 100 will be described with reference to Fig. 4. Fig. 4 is a sequence diagram showing the flow of the process S100 executed in the learning system 100 according to this embodiment.

[0069] <Step S11> In step S11, the output unit 211 of the smartphone 2 requests the study content from the study server 3.

[0070] For example, when the acquisition unit 210 acquires information indicating an operation to display study content from the operation input unit 24, the acquisition unit 210 supplies the information to the output unit 211. The output unit 211 refers to the information supplied from the acquisition unit 210, and when the information indicates an operation to display study content, the output unit 211 outputs information indicating a request for the study content to the study server 3, thereby requesting the study content from the study server 3.

[0071] <Step S12> In step S12, the output unit 311 of the learning server 3 outputs the requested learning content to the smartphone 2.

[0072] For example, when acquiring unit 310 acquires information output from smartphone 2 indicating a request for study content, it supplies the acquired information to output unit 311. Output unit 311 refers to the information supplied from acquiring unit 310, and if the information indicates a request for study content, acquires the study content from storage unit 33. Output unit 311 outputs the acquired study content to smartphone 2.

[0073] <Step S13> In step S13, the acquisition unit 210 of the smartphone 2 acquires the study content output from the study server 3. The acquisition unit 210 stores the acquired study content in the memory unit 23. The study content stored in the memory unit 23 may be output at any time unless otherwise limited. As an example, the output unit 211 of the smartphone 2 may display the study content after executing step S22 described below, or may display the study content after the acquisition unit 210 acquires information indicating an operation to display the study content again.

[0074] <Step S14> In step S14, the output unit 211 of the smartphone 2 requests the wearable device 1 for the first information.

[0075] For example, when acquisition unit 210 acquires the study content in step S13, output unit 211 outputs information indicating a request for the first information to wearable device 1. Note that the timing at which output unit 211 requests the first information from wearable device 1 is not limited to the above configuration, and output unit 211 may request the first information from wearable device 1 at predetermined time intervals (e.g., 10 seconds). As another configuration, wearable device 1 may push the first information to smartphone 2 at predetermined time intervals (e.g., 10 seconds).

[0076] <Step S15> In step S15, the output unit 111 of the wearable device 1 outputs the first information to the smartphone 2.

[0077] For example, when the acquisition unit 110 acquires information output from the smartphone 2 indicating a request for the first information, the acquisition unit 110 supplies the acquired information to the output unit 111. The output unit 111 refers to the information supplied from the acquisition unit 110, and if the information indicates a request for the first information, acquires the first information from the storage unit 13. Alternatively, the output unit 111 acquires the first information output from the sensor unit 14. The output unit 111 outputs the acquired first information to the smartphone 2.

[0078] <Step S16> In step S16, the acquisition unit 210 of the smartphone 2 acquires the first information output from the wearable device 1. The acquisition unit 210 of the smartphone 2 stores the acquired first information in the storage unit .

[0079] <Step S17> In step S17, the output unit 211 of the smartphone 2 outputs the first information stored in the storage unit 23 to the information processing device 4.

[0080] <Step S18> In step S18, the acquisition unit 410 of the information processing device 4 acquires the first information output from the smartphone 2. The acquisition unit 410 stores in the storage unit 43 the acquired first information.

[0081] <Step S19> In step S19, the output unit 412 of the information processing device 4 generates information to be output. The process of step S19 will be described later with reference to different drawings.

[0082] <Step S20> In step S20, the output unit 412 of the information processing device 4 outputs to the smartphone 2 the information generated in step S19.

[0083] <Step S21> In step S21, the acquisition unit 210 of the smartphone 2 acquires the information output from the information processing device 4. The acquisition unit 210 stores the acquired information in the storage unit .

[0084] <Step S22> In step S22, the output unit 211 of the smartphone 2 displays the information stored in the storage unit 23 in step S21 on the display unit 25. Note that in step S22, instead of or in addition to being configured to display on the display unit 25, the output unit 211 may be configured to output the information stored in the storage unit 23 in step S21 from an audio output unit (e.g., a speaker) not shown in FIG.

[0085] <Processing of step S19> The process of step S19 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the process of generating information to be output by the output unit 412 according to this embodiment.

[0086] (Step S191) In step S191, the calculation unit 411 calculates the degree of compatibility by referring to the first information stored in the storage unit 43. The process in which the calculation unit 411 calculates the degree of compatibility is as described above.

[0087] (Step S192) In step S192, the output unit 412 determines whether the degree of compatibility calculated in step S191 is equal to or greater than a first threshold value.

[0088] (Step S193) If it is determined in step S192 that the degree of fitness is less than the first threshold (step S192: NO), in step S193, the output unit 412 determines an action that minimizes the transition cost to the target state.

[0089] (Step S194) In step S194, the output unit 412 generates information indicating the action corresponding to the minimum transition cost calculated in step S193 as an action for improving the goodness of fit.

[0090] (Step S195) On the other hand, if it is determined in step S192 that the degree of compatibility is equal to or higher than the first threshold (step S192: YES), in step S195, the output unit 412 generates information indicating that the degree of compatibility is high. Note that, if step S195 is executed, the above-mentioned step S22 does not have to be executed. In other words, in the learning system 100, if the learning environment around the user and the user's physical condition are suitable for learning, the user may be allowed to learn without being notified of this.

[0091] (Example 1 of the process executed in step S19) An example of a process executed in step S19 when the acquisition unit 410 of the information processing device 4 acquires the CO2 concentration in the learning environment around the user as the first information in step S18 described above will be described.

[0092] In this case, if it is determined in step S192 that the degree of compatibility calculated in step S191 is less than the first threshold (for example, if the CO2 concentration is higher than a predetermined value), the output unit 412 determines a state in which the CO2 concentration around the user is low as a target state in step S193. Then, the output unit 412 determines an action with the smallest transition cost among actions that transition to the target state.

[0093] As another example, in step S193, the output unit 412 inputs the first information indicating the CO2 concentration and a prompt to the language model. As an example, the output unit 412 selects a prompt, "This is CO2 concentration data. Considering existing research on stress, etc., please analyze whether the environment is suitable for learning, and if not, please suggest an action that will make the environment suitable," from a plurality of prompt candidates, and inputs the selected prompt to the language model. Then, the output unit 412 determines the action for improving the fitness output from the language model to be the action that minimizes the transition cost to the target state.

[0094] For example, if the action determined in step S193 is "open a window," the output unit 412 generates information including a suggestion "Let's open a window" in step S194. In this case, the smartphone 2 displays an image including the text "Let's open a window" in step S22 described above.

[0095] In this way, the output unit 412 can make suggestions so that the learning environment around the user becomes an environment suitable for learning.

[0096] (Example 2 of the process executed in step S19) An example of the process executed in step S19 when the acquisition unit 410 of the information processing device 4 acquires the number of steps today, which is the user's physical condition, as the first information in step S18 described above, will be described.

[0097] In this case, if it is determined in step S192 that the degree of compatibility calculated in step S191 is less than the first threshold (for example, if the number of steps taken today up to the present time is less than a predetermined value), the output unit 412 determines the state in which the number of steps taken today is the predetermined value as the target state in step S193. Then, the output unit 412 determines the action with the smallest transition cost among the actions that transition to the target state.

[0098] For example, if the action determined in step S193 is "take a walk", in step S194 the output unit 412 generates information including a suggestion such as "You seem to be stressed due to lack of exercise. Let's take a short walk." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "You seem to be stressed due to lack of exercise. Let's take a short walk."

[0099] In this way, the output unit 412 can provide a suggestion for making the user's physical condition suitable for learning.

[0100] (Example 3 of the process executed in step S19) In the above-mentioned step S18, when the acquisition unit 410 of the information processing device 4 acquires the current time, which is the learning environment around the user, and the heart rate, which is the user's physical condition, as the first information, an example of processing to be executed in step S19 will be described.

[0101] In this case, in step S191, the calculation unit 411 calculates a first degree of suitability calculated using the learning environment around the user as the first information, and a second degree of suitability calculated using the physical condition of the user as the first information.

[0102] Next, in step S192, output unit 412 determines whether or not each of the first degree of match and the second degree of match calculated in step S191 is equal to or greater than a first threshold value.

[0103] For example, if it is determined that the second conformance is equal to or greater than the first threshold but the first conformance is less than the first threshold (for example, if the time is earlier than the time suitable for learning), in step S193, the output unit 412 determines the state to be learned at the time suitable for learning as the target state. Then, the output unit 412 determines the action with the smallest transition cost among the actions for transitioning to the target state.

[0104] For example, if the action determined in step S193 is "study from 7 pm", in step S194 the output unit 412 generates information including a suggestion "it's still early, so let's start studying from 7 pm." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "it's still early, so let's start studying from 7 pm."

[0105] On the other hand, if it is determined that the first compatibility level is equal to or greater than the first threshold but the second compatibility level is less than the first threshold (for example, if the heart rate is higher than a predetermined value), the output unit 412 determines the state in which the heart rate is the predetermined value as the target state in step S193. Then, the output unit 412 determines the action with the smallest transition cost among the actions that transition to the target state.

[0106] For example, if the action determined in step S193 is "take a one-hour break," the output unit 412 generates information including a suggestion "take a one-hour break" in step S194. In this case, the smartphone 2 displays an image including the text "take a one-hour break" in step S22 described above.

[0107] If the level of the first compatibility is less than the first threshold and the level of the second compatibility is less than the first threshold (for example, if the time is earlier than the time suitable for learning and the heart rate is higher than a predetermined value), in step S193, the output unit 412 determines a state where the time is suitable for learning and the heart rate is low as the target state. Then, the output unit 412 determines an action with the smallest transition cost among actions that transition to the target state.

[0108] For example, if the action determined in step S193 is "study 30 minutes before going to bed," in step S194 the output unit 412 generates information including a suggestion that "it's still early, so let's study 30 minutes before going to bed." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text that says "it's still early, so let's study 30 minutes before going to bed."

[0109] In this way, the output unit 412 can make suggestions so that any of (1) the learning environment around the user, (2) the user's physical condition, and (3) the learning environment around the user and the user's physical condition, will be suitable for learning.

[0110] (Example 4 of the process executed in step S19) In the above-mentioned step S18, when the acquisition unit 410 of the information processing device 4 acquires the sounds and vibrations around the user, which are the learning environment around the user, and the number of steps, which is the user's physical condition, as the first information, an example of the processing to be executed in step S19 will be described.

[0111] In this case, if the first information indicates that the sound around the user is louder than a predetermined volume, the vibration matches the vibration inside a train, and the number of steps indicates that the user is not currently walking, in step S191, the calculation unit 411 determines that the user is on a train. Then, the calculation unit 411 calculates the degree of suitability.

[0112] If it is determined in step S192 that the degree of conformance calculated in step S191 is less than the first threshold (for example, if the inside of a train is inappropriate for learning), the output unit 412 determines the state in which the user is at home as the target state in step S193. Then, the output unit 412 determines the action with the smallest transition cost among the actions that transition to the target state.

[0113] For example, if the action determined in step S193 is "go home", in step S194 the output unit 412 generates information including a suggestion "It is inappropriate to do it on a train. Let's go home and do it at home." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "It is inappropriate to do it on a train. Let's go home and do it at home."

[0114] In this way, even when the first information includes a plurality of pieces of information, the output unit 412 can make a suggestion that will create a state suitable for learning.

[0115] [Variation 1] A modified example of this embodiment will be described below. In this modified example, only when it is determined that the minimum value of the transition cost for transitioning from a state before the action to a state after the action is less than the second threshold value, the output unit 412 outputs information indicating the action for improving the compatibility determined in step S193.

[0116] Step S19A in this modification, which corresponds to step S19 described above, will be described with reference to Fig. 6. Fig. 6 is a flowchart showing a process for generating information to be output by output unit 412 in this modification.

[0117] (Steps S191 to S193, and S195) Steps S191 to S193 and step S195 are as described above.

[0118] (Step S196) In step S196, the output unit 412 determines whether or not the transition cost to the action determined in step S193 (that is, the action with the smallest transition cost) is equal to or greater than the second threshold.

[0119] (Step S194) If it is determined in step S196 that the transition cost does not satisfy the second threshold value (step S196: NO), in step S194, the output unit 412 generates information indicating the action corresponding to the minimum transition cost calculated in step S193 as an action for improving the degree of compatibility.

[0120] (Step S197) On the other hand, if it is determined in step S196 that the transition cost is equal to or greater than the second threshold (step S196: YES), in step S197, the output unit 412 generates information indicating that there is no appropriate behavior. Note that, if step S197 is executed, the above-mentioned step S22 does not have to be executed. In other words, in the learning system 100, if there is no appropriate behavior for achieving a state suitable for learning, the user may be allowed to learn without being notified of this fact.

[0121] [Modification 2] Another variation of this embodiment will be described. In this variation, the acquisition unit 410 acquires second information that identifies the study content that the user is to study. The calculation unit 411 calculates the degree of suitability by referring to the first information and the second information. The output unit 412 outputs information indicating an action to be taken to improve the degree of suitability when it is determined that the degree of suitability calculated by referring to the first information and the second information does not satisfy the first threshold.

[0122] The second information may include information identifying the study content, information identifying the subject, information identifying the level of difficulty, and information indicating the user's study history for the study content. The second information may be stored in the memory 23 of the smartphone 2, or in the memory 33 of the study server 3. In this modification, a case in which the second information is stored in the memory 33 of the study server 3 will be described.

[0123] As described above, one example of a method for the calculation unit 411 to calculate the degree of compatibility is a method using a trained model constructed by machine learning. In this modification, the trained model used by the calculation unit 411 is a trained model that receives the first information and the second information as input and outputs the degree of compatibility or information corresponding to the degree of compatibility.

[0124] In addition, in this modification, the training data used by the learning unit 413 is training data that includes a set of the first information, the second information, and information corresponding to the degree of conformity.

[0125] <Processing Executed in Modification 2> The flow of process S101, which corresponds to process S100 executed in the learning system 100 described above and is executed in the learning system 100 according to this modification, will be described with reference to Figures 7 and 8. Figure 7 is a sequence diagram showing the flow of process S101 executed in the learning system 100 according to this modification. Figure 8 will be described later.

[0126] The processes from step S11, in which the smartphone 2 requests the study content from the study server 3, to step S18, in which the information processing device 4 acquires the first information output by the smartphone 2, are as described above.

[0127] (Step S31) In step S31, the output unit 412 of the information processing device 4 requests the learning server 3 for the second information, which is information related to the learning content output by the learning server 3 in step S12.

[0128] For example, when the acquisition unit 410 acquires the first information in step S18, it supplies the first information to the output unit 412. Upon acquiring the first information from the acquisition unit 410, the output unit 412 outputs, to the learning server 3, information indicating a request for second information, thereby requesting the learning server 3 for the second information.

[0129] (Step S32) In step S32, the output unit 311 of the learning server 3 outputs the second information to the information processing device 4.

[0130] For example, when acquiring unit 310 acquires information indicating a request for second information output from information processing device 4, it supplies the acquired information to output unit 311. Output unit 311 references the information supplied from acquiring unit 310, and outputs the information related to the study content output in step S12 to information processing device 4 as second information.

[0131] (Step S33) In step S33, the acquisition unit 410 of the information processing device 4 acquires the second information output from the learning server 3. The acquisition unit 410 stores the acquired second information in the storage unit 43.

[0132] (Step S34) In step S34, the output unit 412 of the information processing device 4 generates information to be output. The process of step S34 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the process of generating information to be output by the output unit 412 according to this modified example.

[0133] In step S341, the calculation unit 411 refers to the first information and the second information stored in the storage unit 43 to calculate the degree of compatibility.

[0134] In this modification, an example of a method in which the calculation unit 411 calculates the degree of conformance is a method using a trained model, similar to the above-mentioned method. The trained model used by the calculation unit 411 is a trained model that receives the first information and the second information as input and outputs information corresponding to the degree of conformance.

[0135] Incidentally, steps S192 to S195 are as described above.

[0136] (Step S20 to Step S22) The processes from step S20 in which the output unit 412 of the information processing device 4 outputs the generated information to step S22 in which the smartphone 2 displays the information are as described above.

[0137] (Example 1 of the process executed in step S34) In the above-mentioned step S18, the acquisition unit 410 of the information processing device 4 acquires sounds around the user, which are the learning environment around the user, as first information, and in the above-mentioned step S33, the acquisition unit 410 acquires second information that identifies the subject of the learning content and indicates mathematics. An example of the processing executed in step S34 will be described below.

[0138] In this case, if it is determined in step S192 that the degree of compatibility calculated in step S341 is less than the first threshold (for example, if the volume of the sound around the user is greater than a predetermined value and learning mathematics is inappropriate in an environment where the sound around the user is loud), the output unit 412 determines in step S193 as a target state a state in which the sound around the user becomes quieter. Then, the output unit 412 determines an action with the smallest transition cost among actions that transition to the target state. For example, if the action determined in step S193 is "memorize English words," in step S194 the output unit 412 generates information including a suggestion such as "The train is a good time to memorize English words." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "The train is a good time to memorize English words."

[0139] For example, if the action determined in step S193 is "move to a quiet place", in step S194 the output unit 412 generates information including a suggestion such as "A quiet place is recommended for studying mathematics." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "A quiet place is recommended for studying mathematics."

[0140] (Example 2 of the process executed in step S34) In the above-mentioned step S18, the acquisition unit 410 of the information processing device 4 acquires sounds and vibrations around the user, which are the learning environment around the user, as first information, and in the above-mentioned step S33, the acquisition unit 410 acquires second information that identifies the subject of the learning content and indicates mathematics. An example of the processing executed in step S34 will be described below.

[0141] In this case, if it is determined in step S192 that the degree of suitability calculated in step S341 does not satisfy the first threshold (for example, if studying mathematics is inappropriate on a train), the output unit 412 determines in step S193 the state of studying a subject suitable for on a train as the target state. Then, the output unit 412 determines the action with the smallest transition cost among the actions that transition to the target state.

[0142] (Example 3 of the process executed in step S34) In the above-mentioned step S18, the acquisition unit 410 of the information processing device 4 acquires sounds around the user, which are the learning environment around the user, as the first information, and in the above-mentioned step S33, the acquisition unit 410 acquires them as the second information indicating mathematics. An example of processing that is executed when a language model is used in step S34 will be described.

[0143] In this case, in step S193, the output unit 412 uses a language model configured to receive the first information, the second information, and the prompt as input and to output an action for improving the degree of compatibility.

[0144] In this case, each of the multiple prompt candidates that are candidates for the prompt input to the language model may be further associated with a subject in addition to the type of learning environment or physical information. As an example, when the output unit 412 inputs first information indicating sounds and vibrations around the user and second information indicating mathematics into the language model, the output unit 412 selects, as a prompt, a prompt "This is data indicating sounds and vibrations around the user. Please suggest a transition to an environment suitable for mathematics, or a subject suitable for the environment," in which the type of learning environment or physical information is associated with sounds and vibrations around the user and the subject is further associated with mathematics. Then, the output unit 412 inputs the first information, the second information, and the selected prompt into the language model, and determines the action for improving the output fitness to be the action that minimizes the transition cost to the target state.

[0145] Other suggestions for learning content besides the examples mentioned above include, for example, "This level of difficulty is difficult in the current environment (or current physical state), so try solving easier problems" or "The last test you took in the same environment (or in the same physical state) as the current one did poorly, so try the test in a different environment (or in a different physical state)."

[0146] [Modification 3] Another modified example of the present embodiment will be described. In the learning system 100 according to this modified example, a configuration including a plurality of wearable devices 1 and a plurality of smartphones 2 will be described. In other words, in the learning system 100 according to this modified example, a case will be described in which there are a plurality of users who wear the wearable device 1 and carry the smartphone 2.

[0147] In this modification, the acquisition unit 410 acquires third information that identifies the individual user. The storage unit 43 of the information processing device 4 stores a history of learning contents previously studied by each user, in which (1) the third information that identifies the user, (2) the second information that identifies each learning content, (3) the first information acquired when the user studied the learning content identified by the second information, and (4) fourth information that indicates the level of learning performance when the user studied the learning content identified by the second information are associated with each other. When it is determined that the suitability does not meet the first threshold, the output unit 412 refers to the history and outputs information indicating an action to be taken by the user identified by the third information to improve the suitability and improve the learning performance before the user studies.

[0148] By referring to the history, the output unit 412 can obtain the first information and the second information when the user achieved a high learning result, and can output not only the degree of suitability but also information indicating actions for improving the learning result.

[0149] <Processing Executed in the Learning System According to Modification 3> The flow of process S102 executed in learning system 100 according to this modification, which corresponds to process S100 executed in learning system 100 described above, will be described with reference to Fig. 9. Fig. 9 is a sequence diagram showing the flow of process S102 executed in learning system 100 according to this modification.

[0150] The processes from step S11, in which the smartphone 2 requests the study content from the study server 3, to step S16, in which the smartphone 2 obtains the first information from the wearable device 1, are as described above.

[0151] (Step S41) In step S41, the output unit 211 of the smartphone 2 outputs the first information and the third information stored in the storage unit 23 to the information processing device 4.

[0152] (Step S42) In step S42, the acquisition unit 410 of the information processing device 4 acquires the first information and the third information output from the smartphone 2. The acquisition unit 410 stores in the storage unit 43 the acquired first information and third information.

[0153] (Step S43) In step S43, the output unit 412 of the information processing device 4 generates information to be output. The process of step S43 will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the process of generating information to be output by the output unit 412 according to this modified example.

[0154] Steps S191, S192, and S195 are as described above.

[0155] If it is determined in step S192 that the level of the compatibility is less than the first threshold (step S192: NO), in step S431, the output unit 412 refers to the third information and determines an action for improving the compatibility. For example, in step S431, the output unit 412 determines an action taken by the user when the user's learning performance was good as an action for improving the compatibility.

[0156] In step S432, the output unit 412 generates information indicating the action determined in step S431 as an action for improving the degree of compatibility.

[0157] (Step S20 to Step S22) The processes from step S20 in which the output unit 412 of the information processing device 4 outputs the generated information to step S22 in which the smartphone 2 displays the information are as described above.

[0158] (Example 1 of the process executed in step S43) In the above-mentioned step S42, the acquisition unit 410 of the information processing device 4 acquires the heart rate, which is the physical condition of the user, as the first information, and an example of the processing executed in step S43 will be described in the case where the learning performance is good when the user identified by the third information takes a deep breath.

[0159] In this case, if it is determined in step S192 that the level of the compatibility calculated in step S191 is less than the first threshold (for example, if the heart rate is higher than a predetermined value), in step S431, the output unit 412 determines that the user takes a deep breath as an action for improving the compatibility. Then, in step S432, the output unit 412 generates information including a suggestion such as "Take a deep breath." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "Take a deep breath."

[0160] (Example 2 of the process executed in step S43) In the above-mentioned step S42, the acquisition unit 410 of the information processing device 4 acquires the current time, which is the learning environment around the user, as the first information, and an example of the processing executed in step S43 will be described when the user identified by the third information has good learning results when studying in the morning.

[0161] In this case, if it is determined in step S192 that the level of suitability calculated in step S191 does not satisfy the first threshold (for example, when the current time is 8 p.m.), in step S431, the output unit 412 determines that studying in the morning is an action for improving the suitability. Then, in step S432, the output unit 412 generates information including a suggestion such as "Study in the morning." In this case, in the above-mentioned step S22, the smartphone 2 displays an image including the text "Study in the morning."

[0162] (Example 3 of the process executed in step S43) In the above-mentioned step S42, the acquisition unit 410 of the information processing device 4 acquires the current time, which is the learning environment around the user, as the first information, and the user identified by the third information has better learning results when studying in the morning. An example of processing that is executed using a language model in step S43 will be described.

[0163] In this case, in step S431, the output unit 412 uses a language model configured to receive the prompt and the first information and output an action for improving the degree of compatibility. As an example, the output unit 412 selects a prompt from a plurality of prompt candidates associated with the type of learning environment or physical information, as in the above-mentioned configuration, and further refers to the third information to include in the prompt an action taken by the user when the user's learning performance was good.

[0164] For example, the output unit 412 first selects a prompt associated with the current time, "This is the current time. Please suggest an environment suitable for studying and an action for doing so." Next, the output unit 412 refers to third information indicating that the learning performance was good when the user studied in the morning, and changes the prompt to a prompt saying "This is the current time. Please suggest an environment suitable for studying and an action for doing so, taking into consideration that the user is a morning person." Next, the output unit 412 inputs the changed prompt and the first information into the language model. Then, the output unit 412 determines the action for improving the fitness output from the language model to be the action that minimizes the transition cost to the target state.

[0165] [Modification 4] Another modified example of this embodiment will be described. In this modified example, the acquisition unit 410 acquires information indicating the user's current location. Furthermore, the output unit 412 outputs information indicating an action for improving the compatibility level by referring to the information. As an example, the output unit 412 outputs information including a destination from the current location as information indicating an action for improving the compatibility level.

[0166] <Processing Executed in the Learning System According to Modification Example 4> The flow of process S103 executed in learning system 100 according to this modification, which corresponds to process S100 executed in learning system 100 described above, will be described with reference to Fig. 11. Fig. 11 is a sequence diagram showing the flow of process S103 executed in learning system 100 according to this modification.

[0167] The processes from step S11, in which the smartphone 2 requests the study content from the study server 3, to step S16, in which the smartphone 2 obtains the first information from the wearable device 1, are as described above.

[0168] (Step S51) In step S51, the smartphone 2 outputs, to the information processing device 4, the first information and information indicating the current location.

[0169] For example, upon acquiring the first information in step S16, the acquisition unit 210 of the smartphone 2 acquires location information indicating the location of the smartphone 2 from the location information receiving unit 26. The acquisition unit 210 of the smartphone 2 supplies the acquired first information and location information to the output unit 211. The output unit 211 outputs the location information supplied from the acquisition unit 210 together with the first information as information indicating the current location.

[0170] (Step S52) In step S52, the acquisition unit 410 of the information processing device 4 acquires the first information and the information indicating the current location output from the smartphone 2. The acquisition unit 410 stores in the storage unit 43 the acquired first information and the information indicating the current location.

[0171] (Step S53) In step S53, the output unit 412 of the information processing device 4 generates information to be output. The process of step S53 will be described with reference to Fig. 12. Fig. 12 is a flowchart showing the process of generating information to be output by the output unit 412 according to this modified example.

[0172] (Steps S191 to S193, and S195) Steps S191 to S193 and step S195 are as described above.

[0173] (Step S531) In step S531, the output unit 412 determines the destination of the action determined in step S193. For example, if the action determined in step S193 is moving to a quiet place, in step S531, the output unit 412 determines the library, which is a quiet place, as the destination.

[0174] (Step S532) In step S532, the output unit 412 generates information including the action determined in step S193 and the destination determined in step S532 as the action for improving the degree of compatibility.

[0175] (Step S20 to Step S22) The processes from step S20 in which the output unit 412 of the information processing device 4 outputs the generated information to step S22 in which the smartphone 2 displays the information are as described above.

[0176] (Example 1 of the process executed in step S53) As described above, when the library is determined as the destination in step S531, in step S532 the output unit 412 generates information including a suggestion such as "Let's move to the library." In this case, in step S22 described above, the smartphone 2 displays an image including the text "Let's move to the library."

[0177] Furthermore, in step S532, the output unit 412 may generate information including a route to the destination library. For example, in step S532, the output unit 412 may generate information including a route to the library and a suggestion such as "The nearest library is here."

[0178] (Example 2 of the process executed in step S53) An example of the process executed when a language model is used in step S53 will be described.

[0179] In this case, in step S531, the output unit 412 uses a language model configured to output an action for improving the compatibility with the first information, the information indicating the current location, and the prompt as inputs. The language model may be configured to be able to refer to a map provided by an external server.

[0180] In this case, the output unit 412 first selects, as a prompt to be input to the language model, a prompt associated with the first information, "This is data indicating sounds and vibrations around the user. Please suggest an environment suitable for learning," in the same manner as in the configuration described above. Next, in order to input information indicating the current location to the language model, the output unit 412 changes the prompt to a prompt saying, "This is data indicating sounds and vibrations around the user and the current position. Please suggest an environment suitable for learning." Next, the output unit 412 inputs the changed prompt and the first information to the language model.

[0181] Since the language model can refer to a map provided by an external server, it can make a suggestion such as "Let's go to the library." In addition, similar to the above-described configuration, when the language model outputs information including a route to the destination library, the output unit 412 may generate information including a route to the destination library.

[0182] [Modification 5] In the learning system 100 according to this modification, one or more components included in each device may be included in another device.

[0183] For example, in the learning system 100, the sensor unit 14 of the wearable device 1 may be included in the smartphone 2. In this case, the learning system 100 may be configured to include the smartphone 2, a learning server 3, and an information processing device 4.

[0184] As another example, in the learning system 100, the components of the learning server 3 may be configured to be included in the information processing device 4. In this case, the learning system 100 may be configured to include the information processing device, the wearable device 1, and the smartphone 2.

[0185] As yet another example, the study system 100 may be configured by an information processing device 4. In other words, the information processing device 4 may include the components that the wearable device 1, the smartphone 2, and the study server 3 each include.

[0186] [Variation 6] A modified example of this embodiment will be described. In this modified example, a case where study content is not acquired will be described. In this modified example, information related to study content that can be provided to a user is stored in the storage unit 43 of the information processing device 4. The information related to study content in this modified example may be information indicating the study content itself, or information indicating the subject of the study content.

[0187] <Processing Executed in Modification 6> The flow of process S104, which corresponds to process S100 executed in the above-mentioned learning system 100 and is executed in the learning system 100 according to this modification, will be described with reference to Figures 13 and 14. Figure 13 is a sequence diagram showing the flow of process S101 executed in the learning system 100 according to this modification. Figure 14 will be described later.

[0188] As shown in FIG. 13, in this modification, the process from step S11 in which the smartphone 2 requests the study content from the study server 3 to step S12 in which the smartphone 2 acquires the study content is not executed.

[0189] Moreover, the processes from step S14 in which the smartphone 2 requests the wearable device 1 to send the first information to step S18 in which the information processing device 4 acquires the first information output by the smartphone 2 are as described above.

[0190] (Step S61) In step S61, the output unit 412 of the information processing device 4 generates information to be output. The process of step S61 will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the process of generating information to be output by the output unit 412 according to this modified example.

[0191] (Step S611) In step S611, calculation unit 411 calculates the degree of suitability for each study content by referring to the first information stored in memory unit 43 and information relating to each of the plurality of study contents stored in memory unit 43. The process by which calculation unit 411 calculates the degree of suitability is as described above.

[0192] (Step S612) In step S612, output unit 412 determines whether or not there is any study content whose degree of suitability is equal to or greater than a first threshold among the degrees of suitability for each study content calculated in step S611. Note that the first threshold used by output unit 412 in step S612 may be a threshold whose value differs for each study content.

[0193] (Step S613) If it is determined in step S612 that there is no study content whose suitability is equal to or greater than the first threshold (step S612: NO), in other words, if it is determined that all of the suitabilities of the study contents do not meet the first threshold, then in step S613, output unit 412 generates information indicating an action to improve the suitability of the user studying any of the multiple study contents. Examples of the process in which output unit 412 generates information indicating an action to improve the suitability in step S613 include the above-mentioned processes (for example, the above-mentioned steps S193 and S194, or a process using a language model).

[0194] (Step S614) If it is determined in step S612 that there is study content whose suitability is equal to or greater than the first threshold (step S612: YES), then in step S614, information indicating the study content with high suitability (suitability equal to or greater than the first threshold) is generated.

[0195] (Step S20) In step S20, the output unit 412 of the information processing device 4 outputs to the smartphone 2 the information generated in step S19.

[0196] (Step S21 to Step S22) The processes from step S20 in which the output unit 412 of the information processing device 4 outputs the generated information to step S22 in which the smartphone 2 displays the information are as described above.

[0197] (Example of processing executed in step S61) An example of the process executed in step S61 when the acquisition unit 410 of the information processing device 4 acquires the CO2 concentration in the learning environment around the user as the first information in the above-mentioned step S18 will be described.

[0198] In this case, in step S611, calculation unit 411 references the first information indicating the CO2 concentration and the information indicating each of the multiple pieces of study content, and calculates the degree of suitability for each piece of study content.

[0199] Next, in step S612, output unit 412 determines whether or not there is any learning content whose degree of conformance is equal to or greater than a first threshold value among the degrees of conformance of each learning content calculated in step S611. In other words, it determines whether or not there is any learning content that conforms to the CO2 concentration indicated by the first information.

[0200] If there is no learning content that matches the CO2 concentration indicated by the first information, in step S613, output unit 412 generates information indicating an action to improve the compatibility by setting a state in which the CO2 concentration is low as a target state. Here, in step S613, output unit 412 may determine, as the target state, a state that matches the learning content with the highest compatibility among the compatibility degrees calculated in step S611. For example, if the compatibility degree of the mathematics learning content is 70 and the compatibility degree of the English learning content is 60, output unit 412 may generate information indicating an action to improve the compatibility of mathematics.

[0201] Also, similarly to the above-described embodiment and modified examples, in step S613, the output unit 412 may input the first information and the prompt to a language model, and generate information indicating an action for improving the degree of compatibility.

[0202] For example, if the action for improving the suitability determined in step S613 is "open a window," the output unit 412 generates information including a suggestion "Let's open a window." The output unit 412 may also generate information including learning content that is suggested to the user for learning. As an example, if the suggested action is an action for improving the suitability of learning content for mathematics, the output unit 412 may generate information including a suggestion "Open a window and learn mathematics."

[0203] [Software implementation example] The functions of the wearable device 1, the smartphone 2, the learning server 3, and the information processing device 4 can be realized by a program for causing a computer to function as the device, and a program for causing a computer to function as each control block of the device (particularly each part included in the control units 11, 21, 31, 41).

[0204] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program to realize each function described in each of the above embodiments.

[0205] The program may be non-transitory and may be recorded in one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be provided to the device via any wired or wireless transmission medium.

[0206] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0207] 〔summary〕 The information processing device 4 according to aspect 1 of the present invention includes an acquisition unit 410 that acquires first information indicating at least one of the learning environment around the user and the physical condition of the user, a calculation unit 411 that calculates the suitability of at least one of the learning environment and the physical condition for the user to study by referring to the first information, and an output unit 412 that outputs information indicating an action to be taken to improve the suitability when it is determined that the suitability does not satisfy a first threshold value.

[0208] The information processing device 4 can suggest to the user an action suitable for learning, according to the first information indicating at least one of the learning environment around the user and the physical condition of the user.

[0209] In the information processing device 4 according to the second aspect of the present invention, in the first aspect, it is preferable that the calculation unit 411 calculates the goodness of fit using a trained model constructed by machine learning. An input of the trained model is the first information, and an output of the trained model is the goodness of fit.

[0210] In this way, by the calculation unit 411 calculating the compatibility using a trained model constructed by machine learning, the accuracy of the calculation of the compatibility can be improved by calculating the compatibility based on the recognition of complex features and patterns that are difficult to describe manually, compared to when the compatibility is calculated based on a specified program.

[0211] In an information processing device 4 according to aspect 3 of the present invention, in aspect 1 or 2, the output unit 412 selects a prompt to be input to a natural language generation model constructed by machine learning from a plurality of prompt candidates, and uses the natural language generation model to output information indicating an action for improving the degree of compatibility, the input of the natural language generation model being the prompt and the first information, and the output of the natural language generation model being natural language describing the action for improving the degree of compatibility.

[0212] The information processing device 4 uses a language model to output information indicating actions to improve compatibility, making it possible to understand background knowledge based on natural language. Compared to outputting information indicating actions to improve compatibility based on a specified program, the information processing device 4 can improve accuracy by determining actions to improve compatibility while taking into account background information that is difficult to describe in its entirety in a manual program, such as similarities between actions and learning contents and linguistic meanings.

[0213] In the information processing device 4 of aspect 4 of the present invention, in any of aspects 1 to 3, the acquisition unit 410 acquires second information identifying the learning content to be studied by the user, the calculation unit 411 calculates the degree of suitability by referring to the first information and the second information, and the output unit 412 outputs information indicating an action to be taken to improve the degree of suitability when it is determined that the degree of suitability calculated by referring to the first information and the second information does not satisfy a first threshold value.

[0214] When calculating the degree of suitability, information processing device 4 refers to the second information that identifies the study content in addition to the first information, and is therefore able to calculate the degree of suitability taking into account the content of the study content.

[0215] In an information processing device 4 according to aspect 5 of the present invention, in aspect 4, the calculation unit 411 calculates the goodness of fit using a trained model constructed by machine learning, the input of the trained model is the first information and the second information, and the output of the trained model is the goodness of fit.

[0216] The information processing device 4 according to the fifth aspect has the same effect as that achieved by using machine learning in the calculation unit 411 in the information processing device 4 according to the second aspect.

[0217] The information processing device 4 according to the sixth aspect of the present invention is the same as in the fourth or fifth aspect, and further includes a memory unit 43 that stores a history of learning contents previously studied by each user, in which (1) third information identifying the user, (2) the second information identifying each learning content, (3) the first information acquired when the user studied the learning content identified by the second information, and (4) fourth information indicating the learning performance of the user when the user studied the learning content identified by the second information. When it is determined that the suitability does not satisfy the first threshold, the output unit 412 refers to the history and outputs information indicating an action to improve the suitability and the learning performance before the user identified by the third information studies.

[0218] The information processing device 4 can output information indicating actions that can improve not only the fitness but also the performance before the user performs the study, thereby making it possible to further improve the results that can be obtained by the study.

[0219] An information processing device 4 according to aspect 7 of the present invention, in any one of aspects 1, 2, 4 to 6, includes learning environment information indicating the learning environment and physical condition information indicating the physical condition, the first threshold is represented by a curve in a two-dimensional plane defined by a coordinate axis representing the suitability of the learning environment information and a coordinate axis representing the suitability of the physical condition information, and the output unit outputs information indicating an action to improve the suitability when it is determined that the suitability of the learning environment information and the suitability of the physical condition information calculated by referring to the first information in the two-dimensional plane does not satisfy the first threshold.

[0220] Since the first information includes learning environment information and physical condition information, the information processing device 4 can output information indicating actions to improve fitness taking into account the learning environment around the user and the user's physical condition.

[0221] In the information processing device 4 according to aspect 8 of the present invention, in any one of aspects 1 to 7, the acquisition unit 410 acquires information indicating the current location of the user, and the output unit 412 outputs information including a destination from the current location as information indicating an action for improving the compatibility degree.

[0222] The information processing device 4 can prompt the user to move to a destination that is assumed to be an environment more suitable for learning.

[0223] In the information processing device 4 according to aspect 9 of the present invention, in any one of aspects 1 to 8, the output unit 412 outputs information indicating an action for improving the degree of compatibility only when it is determined that, for the action for improving the degree of compatibility, the minimum value of the transition cost for transitioning from a pre-action state to a post-action state does not satisfy a second threshold value.

[0224] Even if at least one of the learning environment around the user and the user's physical condition is not suitable for learning, if the cost of transitioning to an action to bring the user into a state suitable for learning is high, the information processing device 4 does not suggest the action. Therefore, the information processing device 4 does not suggest an action that is burdensome to the user, and therefore a user-friendly device can be realized.

[0225] In the information processing device 4 of aspect 10 of the present invention, in any one of aspects 1 to 3, the calculation unit 411 calculates the suitability for each learning content by referring to the first information and information relating to each of the multiple learning contents, and when it is determined that all of the suitability for each learning content does not satisfy a first threshold, the output unit 412 outputs information indicating an action to be taken by the user to improve the suitability of studying any of the multiple learning contents.

[0226] Information processing device 4 can suggest to the user an action that is suitable for learning a certain learning content among a plurality of learning contents, given at least one of the learning environment around the user and the user's physical condition.

[0227] In the information processing device 4 according to aspect 11 of the present invention, the output unit 412 outputs the information including study content that suggests study to the user.

[0228] Information processing device 4 can suggest to the user, from among a plurality of pieces of study content, a study content whose suitability is improved by performing the study content together with the study content.

[0229] A learning system according to aspect 12 of the present invention is a learning system 100 comprising an information processing device 4 according to any one of aspects 1 to 11, a wearable device 1, and a terminal device (smartphone 2), wherein the wearable device has one or more sensors that generate the first information and outputs the first information, and when it is determined that the degree of conformance does not satisfy a first threshold, the information processing device outputs information indicating an action to be taken to improve the degree of conformance, and the terminal device outputs information indicating an action to be taken to improve the degree of conformance.

[0230] The learning system 100 achieves the same effects as the information processing device 4.

[0231] [Additional Notes] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0232] 100 Learning System 1. Wearable devices 2. Smartphone 3 Learning Server 4. Information processing equipment 41 Control section 42 Communications Department 410 Acquisition Department 411 Calculation Unit 412 Output section 413 Learning Department 43 Storage section

Claims

1. An acquisition unit that acquires first information indicating at least one of a learning environment around a user and a physical condition of the user; a calculation unit that calculates a suitability of at least one of the learning environment and the physical condition for the user to study by referring to the first information; an output unit that outputs information indicating an action to be taken to improve the degree of conformance when it is determined that the degree of conformance is less than a first threshold value; An information processing device comprising:

2. The calculation unit calculates the fitness using a trained model constructed by machine learning, The input of the trained model is the first information, The output of the trained model is the fitness.

2. The information processing apparatus according to claim 1,

3. The output unit is Select a prompt from multiple prompt candidates to input to a natural language generation model built using machine learning, outputting information indicating an action to be taken to improve the degree of compatibility using the natural language generation model; an input of the natural language generation model is the prompt and the first information; The output of the natural language generation model is a natural language describing an action to improve the fitness.

2. The information processing apparatus according to claim 1,

4. The acquisition unit acquires second information that identifies the study content that the user is to study; The calculation unit calculates the degree of conformity by referring to the first information and the second information, the output unit outputs information indicating an action to improve the degree of conformance when it is determined that the degree of conformance calculated with reference to the first information and the second information does not satisfy a first threshold value.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus further comprises: a first input section;

5. The calculation unit calculates the fitness using a trained model constructed by machine learning, The input of the trained model is the first information and the second information, The output of the trained model is the fitness.

5. The information processing apparatus according to claim 4.

6. a storage unit that stores a history of learning content previously studied by each user, the history corresponding to (1) third information that identifies the user, (2) the second information that identifies each learning content, (3) the first information acquired when the user studied the learning content identified by the second information, and (4) fourth information that indicates the level of learning achievement of the user when the user studied the learning content identified by the second information; When it is determined that the degree of suitability is less than a first threshold, the output unit refers to the history, and outputs information indicating an action for improving the degree of suitability and the learning performance of the user identified by the third information before the user performs a study.

5. The information processing apparatus according to claim 4.

7. The first information includes learning environment information indicating the learning environment and physical condition information indicating the physical condition, the first threshold is represented by a curve on a two-dimensional plane defined by a coordinate axis representing the conformance of the learning environment information and a coordinate axis representing the conformance of the physical state information, when it is determined that the conformance of the learning environment information and the conformance of the physical condition information calculated with reference to the first information in the two-dimensional plane do not satisfy the first threshold, the output unit outputs information indicating an action to be taken to improve the conformance.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

8. The acquisition unit acquires information indicating a current location of the user, The output unit outputs information including a destination from the current location as information indicating an action for improving the degree of compatibility.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus further comprises: a first input section;

9. the output unit outputs information indicating an action for improving the fitness only when it is determined that a minimum value of a transition cost for transitioning from a pre-action state to a post-action state is less than a second threshold value for the action for improving the fitness.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus further comprises: a first input section;

10. the calculation unit calculates the degree of suitability for each of the plurality of study contents by referring to the first information and information relating to each of the plurality of study contents; When it is determined that all of the degrees of suitability for each of the study contents do not meet a first threshold, the output unit outputs information indicating an action for improving the degree of suitability of the user studying any of the plurality of study contents.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus further comprises: a first input section;

11. The output unit outputs the information including study content that is suggested to the user for study.

11. The information processing apparatus according to claim 10,

12. A learning system comprising the information processing device according to any one of claims 1 to 3, a wearable device, and a terminal device, The wearable device includes one or more sensors that generate the first information and outputs the first information; when it is determined that the degree of conformance is less than a first threshold, the information processing device outputs information indicating an action to improve the degree of conformance; The terminal device outputs information indicating an action to improve the degree of conformity. A learning system characterized by:

Citation Information

Patent Citations

  • Content presentation system, method, and program

    JP2015179212A