Recommendation by analysis of brain information

Abstract

To provide a mechanism capable of further appropriately selecting or generating content tailored to a user's preference by using data relating to a brain.SOLUTION: An information processing method causes one or a plurality of processors included in an information processing device to: while outputting content to the user, acquire first data relating to serotonin and second data relating to noradrenaline based on a signal acquired by a brain information measuring device worn by a user; input learning data including the first data and the second data into a learning model for learning a user's emotion or state based on the first data and the second data using a neural network and cause the learning model to learn them; and output a result of the learning.SELECTED DRAWING: Figure 6

Description

Technical field

[0001] The present invention relates to an information processing method, program, and information processing device that can provide recommendations based on analysis of brain information. [Background technology]

[0002] Conventionally, there is a known technology that can control the user's emotions and make them listen to enjoyable music by estimating the user's emotion from brain wave signals and playing music that matches that emotion ( For example, see Non-Patent Document 1). [Prior art documents] [Non-patent literature]

[0003] [Non-patent document 1] Ehrlich SK, Agres KR, Guan C, Cheng G (2019), "A closed-loop, music-based brain-computer interface for emotion mediation", [online], March 18, 2019, PLOS ONE, [Reiwa 4 Retrieved September 22], Internet <URL: https: / / doi.org / 10.1371 / journal.pone.0213516> [Summary of the invention] [Problem to be solved by the invention]

[0004] In the prior art, it is not easy to estimate a user's emotions from brain wave signals that differ from user to individual, and it is not easy to appropriately estimate a user's emotions and provide content tailored to the user's preferences.

[0005] In addition, with conventional technology, even if a user's emotions are estimated from brain wave signals, it only determines the user's preference for the content being output, and it is not possible to generate the content itself in accordance with the user's preference. There wasn't.

[0006] Therefore, one of the objects of the present invention is to provide a mechanism that uses brain-related data to more appropriately select or generate content according to the user's preferences. [Means to solve the problem]

[0007] An information processing method according to one aspect of the present invention is such that one or more processors included in an information processing device are based on a signal acquired by a brain information measuring device worn by the user while outputting content to the user. acquiring first data regarding serotonin and second data regarding noradrenaline; and creating learning data including the first data and the second data based on the first data and the second data using a neural network. Inputting the emotion or state of the user into a learning model for learning and performing learning, and outputting the result of the learning.

Effect of the invention

[0008] According to the present invention, a mechanism is provided that uses brain-related data to more appropriately select or generate content according to the user's preferences. [Brief explanation of drawings]

[0009]

Figure 1

Figure 2

[0010] Embodiments of the present invention will be described with reference to the accompanying drawings. In addition, in each figure, those with the same reference numerals have the same or similar configurations.

[0011] <System configuration> FIG. 1 is a diagram showing an example of a system configuration according to each embodiment. In the example shown in FIG. 1, the server 10 and each biological information measuring device 20A, 20B, 20C, and 20D are connected to be able to transmit and receive data via a network. When each biological information measuring device is not individually distinguished, it is also referred to as biological information measuring device 20.

[0012] The server 10 is an information processing device that can collect and analyze data, and may be composed of one or more information processing devices. The biological information measuring device 20 is a measuring device that measures biological information such as brain activity, heartbeat, pulse, and blood flow. For example, when an electroencephalograph is used as the biological information measuring device 20, the electroencephalograph is a measuring device having invasive or non-invasive electrodes for sensing brain activity. The electroencephalograph may be any device that has electrodes, such as a head-mounted type or an earphone type. The biological information measuring device 20 may be a device that includes this electroencephalograph and is capable of analyzing, transmitting and receiving brain information. Furthermore, the biological information measuring device 20 may be a brain information measuring device capable of measuring single molecules, which will be described below.

[0013] Here, when using brain activity data as an example of biological information, there is research that uses machine learning to detect the single-molecule waveforms of the neurotransmitters dopamine, noradrenaline, and serotonin using radio waveforms obtained by single-molecule measurements. being done. For example, "Time-resolved neurotransmitter detection in mouse brain tissue using an artificial intelligence-nanogap"( Yuki Komoto,Takahito Ohshiro, Takeshi Yoshida, Etsuko Tarusawa, Takeshi Yagi, Takashi Washio, & Masateru Taniguchi, "Time-resolved neurotransmitter detection in mouse According to the paper "brain tissue using an artificial intelligence-nanogap", [online], July 9, 2020, <https: / / www.nature.com / articles / s41598-020-68236-3>), single-molecule measurement The three types of neurotransmitters are identified using an identification method that uses machine learning to identify the signals of unknown samples using a classifier that has learned the single-molecule waveforms of dopamine, noradrenaline, and serotonin.

[0014] According to the above-mentioned brain information measurement device that can measure single molecules, serotonin, which generally indicates the level of calmness and relaxation, and norepinephrine, which indicates the degree of brain arousal and has an excitatory effect that increases concentration and judgment. It is possible to measure these separately. In addition to the brain information measuring device capable of measuring single molecules described above, serotonin and noradrenaline may be measured from the user's blood or the like.

[0015] <Hardware configuration> FIG. 2 is a diagram showing an example of the physical configuration of the server information processing device 10 according to each embodiment. The server 10 includes one or more CPUs (Central Processing Unit) 10a corresponding to a calculation unit, a RAM (Random Access Memory) 10b corresponding to a storage unit, and a ROM (Read only Memory) 10c corresponding to a storage unit. It has a communication section 10d, an input section 10e, and a display section 10f. These components are connected to each other via a bus so that they can transmit and receive data.

[0016] In each embodiment, a case will be described in which the information processing device 10 is composed of one information processing device, but the information processing device 10 may be realized by combining a plurality of computers or a plurality of calculation units. Further, the configuration shown in FIG. 2 is an example, and the information processing device 10 may have configurations other than these, or may not have some of these configurations.

[0017] The CPU 10a is a control unit that performs control related to the execution of programs stored in the RAM 10b or ROM 10c, and performs calculations and processing of data. The CPU 10a is a calculation unit that executes a program (learning program) that performs learning using a learning model that estimates the user's emotion or state (for example, comfort level (or discomfort level)) from biological information. The CPU 10a receives various data from the input section 10e and the communication section 10d, and displays the data calculation results on the display section 10f or stores them in the RAM 10b.

[0018] The RAM 10b is a storage section in which data can be rewritten, and may be composed of, for example, a semiconductor storage element. The RAM 10b may store data such as programs executed by the CPU 10a, data related to brain activity, and related data indicating the correspondence between content and an index related to user discomfort based on brain information. Note that these are just examples, and the RAM 10b may store data other than these, or some of them may not be stored.

[0019] The ROM 10c is a storage section from which data can be read, and may be composed of, for example, a semiconductor storage element. The ROM 10c may store, for example, a learning program or data that is not rewritten.

[0020] The communication unit 10d is an interface that connects the information processing device 10 to other devices. The communication unit 10d may be connected to a communication network such as the Internet.

[0021] The input unit 10e receives data input from the user, and may include, for example, a keyboard and a touch panel.

[0022] The display unit 10f visually displays the calculation results by the CPU 10a, and may be configured by, for example, an LCD (Liquid Crystal Display). Displaying the calculation results on the display unit 10f can contribute to XAI (eXplainable AI). The display unit 10f may display, for example, learning results.

[0023] The learning program may be provided by being stored in a computer-readable non-temporary storage medium such as the RAM 10b or ROM 10c, or may be provided via a communication network connected by the communication unit 10d. In the information processing device 10, the CPU 10a executes the learning program to realize various operations described below using FIGS. 3 and 7. Note that these physical configurations are merely examples, and do not necessarily have to be independent configurations. For example, the information processing device 10 may include an LSI (Large-Scale Integration) in which a CPU 10a, a RAM 10b, and a ROM 10c are integrated. Further, the information processing device 10 may include a GPU (Graphical Processing Unit) or an ASIC (Application Specific Integrated Circuit).

[0024] [First embodiment] A first embodiment using the system 1 described above will be described below. In the first embodiment, a brain information measuring device is used as the biological information measuring device 20, and the measured data includes first data regarding serotonin and second data regarding noradrenaline. Furthermore, serotonin and noradrenaline are neurotransmitter substances in the brain, and can more appropriately represent activities in the brain.

[0025] In the first embodiment, first data regarding serotonin and second data regarding noradrenaline are acquired, and the user's emotion or state is estimated using learning data including the first data and the second data. The user's emotion or state includes, for example, whether the user feels comfortable or comfortable. For example, the first data can be used to analyze whether the person is relaxed or calm, and the second data can be used to determine whether the brain is in an alert state. In the first embodiment, the user defines a normal and awake state as comfortable or comfortable.

[0026] Furthermore, in the first embodiment, the user's brain is stimulated by outputting content to the user. The content includes, for example, sounds such as music, images including moving images and still images, smells, tactile sensations, and the like. While the user's brain is being stimulated by the content, first data and second data are measured by the biological information measuring device 20. By inputting the measured first data and second data into a trained learning model, it becomes possible to estimate the user's emotion or state. The trained learning model includes a learning model that is a result of machine learning of a learning model that estimates the user's emotion or state using the first data and the second data as training data.

[0027] Thus, according to the first embodiment, since brain activity is estimated using brain nerve substances, it is possible to more appropriately estimate the user's brain state, that is, the user's emotion or state. Furthermore, in the first embodiment, it is also possible to provide content to the user based on the estimated user's emotion or state.

[0028] <Processing configuration example> FIG. 3 is a diagram showing an example of processing blocks of the information processing device 10 according to the first embodiment. The information processing device 10 includes an acquisition section 11, a learning section 12, an output section 13, an association section 14, a selection section 15, and a storage section 16. For example, the learning unit 12, the association unit 14, and the selection unit 15 shown in FIG. can be realized by RAM 10b and / or ROM 10c. The information processing device 10 may be configured with a quantum computer or the like.

[0029] The acquisition unit 11 acquires first data regarding serotonin and second data regarding noradrenaline based on a signal acquired by a biological information measuring device 20 worn by the user while content is being output to the user. do. For example, the biological information measuring device 20 acquires first data regarding serotonin and second data regarding noradrenaline, which are classified by a trained classifier (learning model) using radio waveforms obtained by single molecule measurement. .

[0030] The learning unit 12 inputs learning data including first data and second data into a learning model 12a that uses a neural network, and learns the user's emotion or state. For example, the learning unit 12 uses the first data and the second data to learn to output an index value representing a normal and awake state. The learning performed in the learning unit 12 is performed by asking the user to annotate emotions indicating comfort, pleasantness, discomfort, etc. while measuring the first data and second data, and using training data labeled with the user's emotions. It may also include supervised learning using .

[0031] FIG. 4 is a diagram showing the state of the user according to the first embodiment. In the example shown in FIG. 4, when the first data is large, the degree of relaxation is high, and when the second data is large, the degree of alertness is high, so the first quadrant shown in FIG. 4 is defined as the user being comfortable.

[0032] On the other hand, in the example shown in Fig. 4, when the first data is small, the degree of relaxation is low, and when the second data is small, the degree of arousal is low, so the third quadrant shown in Fig. 4 is defined as uncomfortable for the user. . The sizes of the first data and the second data may be determined to be large if they are greater than or equal to the threshold, and small if they are less than the threshold, using thresholds set for each. Each threshold may be set by being learned using emotional labeled training data. Note that it may be defined that the user feels uncomfortable in areas other than the first quadrant.

[0033] Returning to FIG. 3, the learning model 12a is a learning model including a neural network, for example, a sequential data analysis model, and specific examples include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), DNN (Deep Neural Network), LSTM (Long Short-Term Memory), bidirectional LSTM, DQN (Deep Q-Network), etc. may be used.

[0034] Furthermore, the learning model 12a includes a model obtained by pruning, quantizing, distilling, or transferring a trained model. Note that these are just examples, and the learning unit 12 may perform machine learning using other learning models.

[0035] The loss function used in the learning unit 12 includes a function that is defined so that the user's discomfort level based on the first data and the second data is reduced. For example, the loss function is a function that reduces the error between the index value indicating the user's comfort determined by the first data and the second data and the ideal index value or annotation result corresponding to the first quadrant. defined.

[0036] Here, the user's comfort can be defined using the first data and the second data. Since the first data is data related to serotonin, the degree of relaxation (normality) of the user can be measured, and the second data is data related to noradrenaline, so the degree of alertness of the user can be measured. For example, the loss function is set so that the index value indicating a normal and awake state based on the first data and the second data becomes large (so that the difference from the ideal index value becomes small).

[0037] Further, the learning unit 12 may learn the user's emotion or state when outputting any content. For example, the learning unit 12 learns first data and second data of a user listening to various music, and learns what kind of music the user feels comfortable with. Specifically, the learning unit 12 learns which music the user is listening to when the user's first data and second data are included in the first quadrant shown in FIG. As described above, if the first data and the second data are classified into the first quadrant, it is presumed that the user feels comfortable with the music. On the other hand, if the first data and the second data are classified into the third quadrant (or the second or fourth quadrant), it is presumed that the user feels uncomfortable with the music. The learning unit 12 adjusts the bias and weight of the learning model 12a using the error backpropagation method so that the output value of the loss function can be minimized.

[0038] Furthermore, the learning unit 12 may use different learning models 12a for each user. For example, the learning unit 12 identifies a user based on the user information when logging into the system 1, and performs learning using the learning model 12a corresponding to this user. Thereby, by using the user's personal learning model 12a, it becomes possible to perform learning according to the user's preferences.

[0039] The output unit 13 outputs the results of learning by the learning unit 12. For example, the output unit 13 may output the trained learning model 12a, the comfort index value estimated by the learning model 12a, or information indicating the emotion or state classified by learning. Good too.

[0040] Through the above processing, it is possible to provide a mechanism that uses brain-related data to more appropriately select or generate content according to the user's preferences. For example, data regarding the brain can be used to generate a learning model that allows content to be more appropriately selected or generated according to the user's preferences. Specifically, since a learning model trained using data regarding serotonin and noradrenaline is used, it becomes possible to more appropriately estimate the user's emotion or state. Therefore, by using this learning model, it becomes possible to provide content that more appropriately corresponds to the user's condition.

[0041] The association unit 14 associates the index value indicating the user's comfort (or degree of discomfort) predicted by learning by the learning unit 12 with the content being output to the user at that time. For example, if the index value indicating comfort included in the predicted value of the learning result is larger than a predetermined value, that is, the user feels comfortable, the association unit 14 sends information for specifying the content, Associate with index value. Thereby, by associating content with an index value indicating comfort based on information on the user's brain activity, it is possible to create a content list in order of index values ​​indicating comfort, for example.

[0042] FIG. 5 is a diagram showing an example of related data according to the first embodiment. In the example shown in FIG. 5, the related data is data that associates content identification information (eg, data A, etc.) with an index value (eg, S1, etc.). The related data shown in FIG. 5 is an example, and it is sufficient that the content that the user feels comfortable with is associated with the index value at that time.

[0043] Furthermore, when a data set of content that the user feels comfortable with is stored in the storage unit 16, the association unit 14 may include this content in the data set. This makes it possible to generate a data set that collects content that indicates comfort based on information on the user's brain activity.

[0044] Returning to FIG. 3, the selection unit 15 may select at least one content from the plurality of contents based on the index value or classification result indicating user comfort included in the learning results of the learning unit 12. . For example, when the index value or the classification result indicates discomfort, the selection unit 15 selects one content from the list of contents associated by the association unit 14 that the user feels comfortable with. Specifically, the selection unit 15 may select the contents in order of increasing index value (order of comfort) or may select the contents at random.

[0045] In this case, the output unit 13 may output at least one content selected by the selection unit 15. The output unit 13 selects an output device according to the contents of the content, and outputs the content to the selected output device. For example, when the content is music, the output unit 13 selects a speaker as the output device and outputs the music from the speaker. Furthermore, when the content is a still image, the output unit 13 selects the display unit 10f as the output device and outputs the still image from the display unit 10f.

[0046] This makes it possible to estimate the state the user is currently feeling based on serotonin and noradrenaline, and to better control the user's emotions or state.

[0047] The storage unit 16 stores the data related to learning described above. For example, the storage unit 16 stores neural network information, hyperparameters, etc. used in the learning model. The storage unit 16 also stores biological information 16a including the acquired first data and second data, learned learning models, related data 16b shown in FIG. 5, and a content list that the user feels comfortable with. You may memorize it.

[0048] <Operation example> FIG. 6 is a flowchart showing an example of processing of the information processing device 10 according to the first embodiment. In the example shown in FIG. 6, serotonin and noradrenaline are detected and obtained using already known techniques.

[0049] In step S102, the acquisition unit 11 acquires first data regarding serotonin and second data regarding noradrenaline based on signals acquired by a brain information measuring device worn by the user. For example, the first data indicates the amount of serotonin secreted, and the second data indicates the amount of noradrenaline secreted.

[0050] In step S104, the learning unit 12 performs learning by inputting learning data including first data and second data acquired when outputting content to the user into the learning model 12a using a neural network. Here, the learning model 12a is a learning model that learns the user's emotion or state based on the first data and the second data.

[0051] In step S106, the output unit 13 outputs the learning result by the learning unit 12. The learning result may include an index value indicating the user's emotion or state. Furthermore, the output unit 13 may output a learned model.

[0052] According to the first embodiment, by using neurotransmitters, it is possible to more appropriately estimate brain activity, and it is possible to generate a learning model that more appropriately estimates brain activity. Become.

[0053] Furthermore, in the first embodiment, according to the technique of "Time-resolved neurotransmitter detection in mouse brain tissue using an artificial intelligence-nanogap" described above, it is also possible to detect dopamine as a neurotransmitter. In 11, dopamine may be acquired as the third data. In this case, in the three-dimensional space of the first data to third data, the learning unit 12 identifies a region where comfort or comfort is felt, and uses the first data to third data to determine the user's emotion or state. You may also choose to learn.

[0054] The acquisition unit 11 acquires the radio waveform obtained by single molecule measurement, and the learning unit 12 acquires the PUC (Positive Dopamine, noradrenaline, and serotonin may be detected using machine learning (and Unlabeled Classification). The learning unit 12 may further learn the user's emotion or state described above using at least the detected serotonin and noradrenaline.

[0055] [Second embodiment] Next, a second embodiment using the above system 1 will be described. In the second embodiment, the biometric information measured by the biometric information measuring device 20 is used to regenerate the digital data currently being output to the user so that the user feels more comfortable. The biological information used in the second embodiment includes at least one of the first data related to serotonin and the second data related to norepinephrine used in the first embodiment, and data such as brain waves, blood flow, pulse, heartbeat, and body temperature. Including one.

[0056] In the second embodiment, a generative adversarial network mechanism called GANs (Generative adversarial networks) is used. A generative model that generates digital data is used as a generator of GANs, and a learning model that estimates the user's emotion or state described in the first embodiment is used as a discriminator.

[0057] For example, in the second embodiment, the discriminator determines "true" if the user's emotion or state indicates comfort, and determines "false" if the user indicates discomfort. Thus, according to the second embodiment, it becomes possible to regenerate digital data until the user feels comfortable.

[0058] <Processing configuration> FIG. 7 is a diagram showing an example of processing blocks of the information processing device 30 according to the second embodiment. The information processing device 30 includes an acquisition section 302, a generation section 304, a determination section 310, an output section 312, and a database (DB) 314. The information processing device 30 may be configured with a quantum computer or the like.

[0059] The acquisition unit 302 and the output unit 312 can be realized by the communication unit 10d shown in FIG. 2, for example. The generation unit 304 and the determination unit 310 can be realized by, for example, the CPU 10a shown in FIG. 2. The DB 314 can be realized, for example, by the ROM 10c and / or the RAM 10b shown in FIG.

[0060] The acquisition unit 302 acquires biological information measured by the biological information measuring device 20. The biological information includes, for example, at least one of neurotransmitters such as dopamine, serotonin, and noradrenaline, and information such as brain waves, pulse, heartbeat, body temperature, and blood flow. Furthermore, the acquisition unit 302 acquires biometric information of the stimulated user using predetermined digital data. The acquisition unit 302 outputs the acquired biological information to the discriminator 308.

[0061] The generation unit 304 generates predetermined digital data by, for example, executing generative adversarial networks (GANs). As a specific example, the generation unit 304 uses generative adversarial networks (GANs) including a generator 306 and a discriminator 308 to generate digital spaces, images, music, control signals for robots, home appliance devices, and the like.

[0062] The generator 306 generates digital data using input noise and the like. The noise may be a random number. For example, the generator 306 may be a neural network having any predetermined structure of GANs. Generator 306 outputs the generated digital data to discriminator 308.

[0063] The identifier 308 acquires, from the acquisition unit 302, the biometric information of the user whose digital data is output or provided. The identifier 308 estimates the user's emotion or state using the acquired biometric information on the digital data generated by the generator 306. The classifier 308 learns and identifies the digital data as "true" if the estimated user's emotion or state indicates comfort. On the other hand, the discriminator 308 identifies the digital data as "false" if the learned and estimated user's emotion or state indicates discomfort. Judgment that an emotion or state indicates comfort or discomfort is determined based on the classification result if the learning result indicates an emotion classification result, or based on the threshold and index if the learning result indicates an index value of the emotion or state. Judgment is made based on comparison with the value.

[0064] If the identification result of the discriminator 308 is "false" (uncomfortable), the determination unit 310 instructs the generator 306 to regenerate digital data, and if the identification result of the discriminator 308 is "true" (comfortable). ), it is output to the output unit 312. The determination unit 310 may output the identification result to the output unit 312 regardless of the content of the identification result.

[0065] The generation unit 304 may update the parameters of the generator 306 and the discriminator 308 based on the authenticity determination result by the discriminator 308. For example, the generation unit 304 may update the parameters of the classifier 308 using backpropagation so that the classifier 308 can more appropriately estimate the user's emotion or state. The generator 304 may also update the parameters of the generator 306 using backpropagation so that the discriminator 308 identifies the digital data generated by the generator 306 as true. The generation unit 304 outputs the finally generated digital data to the output unit 312.

[0066] When the identification result indicates "true" (comfortable), the output unit 312 outputs information indicating that the digital data is comfortable for the user. For example, the output unit 312 outputs any one of a sound, an image, a mark, etc. indicating comfort to the user, so that the user can understand his / her own condition.

[0067] Furthermore, the output unit 312 may output to the user digital data that the user ultimately feels comfortable with. The above processing makes it possible to regenerate digital data until the user feels comfortable.

[0068] Further, the determination unit 310 may include determining the identification result or instructing the generator 306 to generate digital data when a predetermined condition regarding the determination timing is satisfied. For example, if new digital data is generated immediately after the digital data newly generated by the generator 306 is output to the user, the user does not have enough time to feel emotions toward one piece of digital data. Therefore, the determining unit 310 may determine the identification result obtained from the discriminator 308 after a predetermined period of time has elapsed since determining whether the identification result is "true" or "false."

[0069] Further, the determining unit 310 may determine whether the digital data is “true” or “false” using a plurality of identification results obtained at a predetermined time. For example, the determination unit 310 determines which of the identification results obtained during a predetermined period of time is the one with the largest number, the maximum absolute value of the index value indicating "true", and the maximum absolute value of the index value indicating "false". The larger one may be adopted.

[0070] Through the above processing, it is possible to give the user a sense of time for one piece of digital data. Furthermore, unnecessary switching of digital data does not make the user feel rushed, anxious, or suspicious. Furthermore, it is also possible to reduce the processing load on the information processing device 30.

[0071] Further, the generated digital data may include at least one of data related to virtual space, data related to robot control, data related to automatic driving, and data related to home appliance devices.

[0072] Data related to virtual space includes, for example, metaverse space and data used for metaverse space. For example, if the generator 306 generates the metaverse space, the generator 306 generates the metaverse space until the user is stimulated by the metaverse space, the discriminator 308 estimates the user's emotion or state, and the user feels comfortable. be able to generate.

[0073] Data related to robot control includes, for example, robots that assist human movements, nursing care robots, and the like. A user who receives a service provided by a robot's movements feels comfortable or uncomfortable with the robot's movements. For robot movements that the user feels uncomfortable, the generator 306 regenerates control data that the user feels comfortable with. This allows the generator 306 to generate control data to the robot until the user feels comfortable.

[0074] Data related to autonomous driving includes, for example, speed data of an autonomous vehicle and content output inside the vehicle during autonomous driving. For example, when the generator 306 generates a moving image to be displayed inside the vehicle during autonomous driving, the discriminator 308 estimates whether the user riding in the autonomous vehicle feels comfortable with the moving image. This allows the generator 306 to generate moving images to be displayed inside the autonomous vehicle until the user feels comfortable.

[0075] Data regarding home appliance devices includes, for example, temperature control data of an air conditioner. For example, when the generator 306 generates temperature control data for an air conditioner, the discriminator 308 estimates whether a user who is in a room with an air conditioner feels comfortable at the room temperature. This allows the generator 306 to automatically adjust the temperature of the air conditioner until the user feels comfortable.

[0076] DB 314 stores data processed by generator 306 and discriminator 308. For example, DB 314 may store digital content generated for each user.

[0077] <Operation> FIG. 8 is a flowchart showing an example of processing of the information processing device 30 according to the second embodiment. The process shown in FIG. 8 shows an example of continuing to generate digital data until the user feels comfortable.

[0078] In step S202, the generator 306 of the information processing device 30 generates predetermined digital data.

[0079] In step S204, the discriminator 308 of the information processing device 30 inputs the biometric information of the user stimulated using predetermined digital data into a discriminator that uses a learning model that learns the user's emotions or state, and Obtain an identification result including the user's emotion or state regarding the digital data.

[0080] In step S206, the determination unit 310 of the information processing device 30 determines whether the identification result indicates comfort. For example, if the identification result indicates comfort (“true”) (step S206-YES), the process proceeds to step S210; if the identification result indicates discomfort (“false”) (step S206-NO), the process proceeds to step Proceed to S208.

[0081] In step S208, the determination unit 310 of the information processing device 30 instructs the generator 306 to generate digital data. After that, the process returns to step S202.

[0082] In step S210, the output unit 312 of the information processing device 30 outputs information indicating that the digital data is comfortable for the user.

[0083] Through the above processing, according to the second embodiment, it is possible to provide a mechanism that allows content to be more appropriately generated according to the user's preferences using biometric information including data related to the brain. Furthermore, according to the second embodiment, it becomes possible to regenerate digital data until the user feels comfortable.

[0084] The embodiments described above are intended to facilitate understanding of the present invention, and are not intended to be interpreted as limiting the present invention. Each element included in the embodiment, as well as its arrangement, material, conditions, shape, size, etc., are not limited to those illustrated, and can be changed as appropriate. Further, it is possible to partially replace or combine the structures shown in different embodiments. [Explanation of symbols]

[0085] 10... Information processing device, 10a... CPU, 10b... RAM, 10c... ROM, 10d... Communication unit, 10e... Input unit, 10f... Display unit, 11... Acquisition unit, 12... Learning unit, 12a... Learning model, 13... Output section, 14... Association section, 15... Selection section, 16... Storage section, 16a... Biological information, 16b... Related data, 302... Acquisition section, 304... Generation section, 306... Generator, 308... Discriminator, 310... Judgment section, 312...output section

Claims

1. One or more processors included in an information processing device, acquiring biological information of a user stimulated using predetermined digital data from a biological information measuring device attached to the user; inputting the biometric information into a classifier that uses a learning model in which the emotion or state of the user based on the biometric information of the user is learned using a neural network, and obtaining a classification result for the predetermined digital data; instructing a generator that generates digital data to generate digital data when the identification result indicates discomfort, and outputting information indicating that the predetermined digital data is comfortable for the user when the identification result indicates comfort; An information processing method that performs the above.

2. The information processing method according to claim 1 , wherein determining whether the identification result is comfortable or uncomfortable is performed when a predetermined condition regarding timing of the determination is satisfied.

3. The information processing method according to claim 1 , wherein the digital data includes at least one of data relating to a virtual space, data relating to robot control, data relating to autonomous driving, and data relating to a home appliance device.

4. One or more processors included in the information processing device acquiring biological information of a user stimulated using predetermined digital data from a biological information measuring device attached to the user; inputting the biometric information into a classifier that uses a learning model in which the emotion or state of the user based on the biometric information of the user is learned using a neural network, and obtaining a classification result for the predetermined digital data; instructing a generator that generates digital data to generate digital data when the identification result indicates discomfort, and outputting information indicating that the predetermined digital data is comfortable for the user when the identification result indicates comfort; A program that executes.

5. An information processing device including one or more processors, the one or more processors: acquiring biological information of a user stimulated using predetermined digital data from a biological information measuring device attached to the user; inputting the biometric information into a classifier that uses a learning model in which the emotion or state of the user based on the biometric information of the user is learned using a neural network, and obtaining a classification result for the predetermined digital data; instructing a generator that generates digital data to generate digital data when the identification result indicates discomfort, and outputting information indicating that the predetermined digital data is comfortable for the user when the identification result indicates comfort; An information processing device that executes the above.

Images