Learning device, recommendation device, methods therefor, and program

The learning device and recommendation system analyze biometric data to recommend music features that enhance athletic performance by identifying the most effective music for improving motor ability, addressing the lack of understanding in existing methods about music's impact on athletic enhancement.

WO2024236632A1PCT designated stage expired Publication Date: 2024-11-21NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2023/017896
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Current research has shown that listening to music can enhance athletic performance, but the specific music features that improve motor ability are not well understood, and existing methods lack a systematic approach to recommend music for improving user-specific athletic ability.

Method used

A learning device and recommendation system that utilize biometric data and music feature analysis to estimate the most effective music for enhancing motor ability, using a model to predict music features that improve athletic performance based on user-specific biometric information.

Benefits of technology

The system effectively recommends music that can temporarily enhance a user's athletic ability by identifying music features that have the greatest improvement effect on motor skills, tailored to individual users based on their biometric data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2023017896_21112024_PF_FP_ABST
    Figure JP2023017896_21112024_PF_FP_ABST
Patent Text Reader

Abstract

From music feature values serving as information about the features of pieces of music, biological information about a user before the user listens to music, and information about improvement of user's capacity for locomotion by listening to music, an estimation model is learned on the basis of biological information about the user serving as a target of music recommendation to obtain, as a recommendation result, the music feature value of music that is estimated to be most effective in improving the user's capacity for locomotion with the biological information, and the music feature value of music that is estimated to be most effective in improving the user's capacity for locomotion with the biological information is obtained as the recommendation result on the basis of the biological information about the user serving as a target of music recommendation by using the estimation model obtained by learning.
Need to check novelty before this filing date? Find Prior Art

Description

Learning device, recommendation device, their methods, and programs

[0001] The present invention relates to a technique for obtaining recommendation information about music pieces that are presented to a user in order to temporarily improve the athletic ability of the user.

[0002] Research into the effects of listening to music on bodily activity, such as the autonomic nervous system and the sympathetic nervous system, has been conducted for some time. For example, Non-Patent Document 1 describes that listening to music changes the heart rate. Also, for example, Non-Patent Document 2 describes that listening to relaxing music causes the brain to release oxytocin, which leads to relaxation.

[0003] Bernardi, L., Porta, C., & Sleight, P., "Cardiovascular, cerebrovascular, and respiratory changes induced by different types of music in musicians and non-musicians: The importance of silence", Heart, 2006, 92(4), 445-452.Ooishi, Y., Mukai, H., Watanabe, K., Kawato, S., & Kashino, M., "Increase in salivary oxytocin and decrease in salivary cortisol after listening to relaxing slow-tempo and exciting fast-tempo music", PLoS ONE, 2017, 12(12), 1-16.

[0004] Previous studies such as Non-Patent Documents 1 and 2 have examined the effects of listening to music on the activity of internal organs and nerves, but no research results are known on the effects of listening to music on athletic ability. The present invention aims to provide a technology for obtaining recommendation information about songs to be presented to a user to temporarily improve their athletic ability, taking into account the effects of listening to music on athletic ability.

[0005] In order to solve the above problem, according to one aspect of the present invention, a learning device includes a learning unit that uses input learning data and biometric information to learn an estimation model that obtains the musical features of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information, and the learning data includes a learning information set for each song that is a combination of music features that are information that represent the musical characteristics of the song, biometric information obtained for each of the target users who are the users to be learned before listening to the song, and an index value for each of the target users regarding the improvement of athletic ability due to listening to the song, using the input learning data and the biometric information as input.

[0006] In order to solve the above problem, according to another aspect of the present invention, a recommendation device has an estimation model pre-stored therein that uses biometric information as input to obtain musical features, which are information representing the musical characteristics of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information, and includes a song recommendation information generation unit that uses the estimation model to obtain musical features of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information, and uses the biometric information of a recommendation target user, who is a user to whom a song is recommended, as input.

[0007] According to the present invention, it is possible to obtain recommendation information about music pieces that are presented to a user in order to temporarily improve the user's athletic ability.

[0008] Fig. 1 is a block diagram showing an example of a recommendation system configured with a learning device and a recommendation device. Fig. 2 is a diagram showing an example of the processing flow of the learning device. Fig. 3 is a diagram showing an example of the processing flow of the recommendation device. Fig. 4 is a diagram showing an example of the configuration of a computer that functions as at least one of the learning device and the recommendation device.

[0009] <Background of the Invention> It is known that sympathetic nervous activity is stimulated during exercise. Considering the results of the above-mentioned prior research showing that listening to music affects the sympathetic nervous system, it is hypothesized that listening to music may lead to improved athletic performance. Therefore, the inventor investigated the effects of listening to music on athletic performance. Specifically, using vertical jump as a specific example of exercise, the inventor conducted an experiment in which multiple subjects were asked to perform a first jump before listening to several pieces of music, measuring the height, and then a second jump after listening to the music, to confirm whether and to what extent the jump height improved. The results of the experiment confirmed that listening to music improved the jump height. In other words, it was confirmed that having subjects listen to music temporarily improves their athletic performance. However, it was also confirmed that the improvement in jump height depended on the subject and the piece of music.

[0010] Although the scientific mechanism behind the improvement of athletic ability from listening to music is not yet fully understood, previous research and the experimental results confirmed in this study suggest that if a set of music information for a plurality of songs, a user's biometric information before listening to the songs, and information regarding the improvement of the user's athletic ability as a result of listening to the songs, is acquired in advance, it should be possible to use this acquired information to recommend music to a user based on the user's biometric information when the user wants to temporarily improve their athletic ability. Therefore, the present invention trains an estimation model for recommending music from the set of music information for a plurality of songs, the user's biometric information before listening to the songs, and information regarding the improvement of the user's athletic ability as a result of listening to the songs, and then uses the learned estimation model to obtain recommendation information about music that is expected to temporarily improve the athletic ability of the user to whom the music is to be recommended, based on the biometric information of the user to whom the music is to be recommended.

[0011] First Embodiment A recommendation system according to a first embodiment obtains, as a recommendation result, information representing the musical characteristics of songs (hereinafter referred to as "musical features") and / or information about the songs themselves, which are presented to a user in order to temporarily improve the user's athletic ability. As shown in FIG. 1 , a recommendation system 300 according to the first embodiment includes a learning device 100 and a recommendation device 200.

[0012] The learning device and the recommendation device are special devices configured by loading a special program into a publicly known or dedicated computer having, for example, a central processing unit (CPU) and a main memory (RAM). The learning device and the recommendation device execute each process under the control of the central processing unit. Data input to the learning device and the recommendation device and data obtained from each process are stored in the main memory, for example, and the data stored in the main memory is read by the central processing unit as needed and used for other processes. At least a portion of each processing unit of the learning device and the recommendation device may be configured with hardware such as an integrated circuit. Each memory unit of the learning device and the recommendation device may be configured with, for example, a main memory such as a random access memory (RAM) or middleware such as a relational database or key-value store. However, each memory unit does not necessarily have to be internal to the learning device and the recommendation device. It may be configured with an auxiliary storage device consisting of a non-transitory storage medium such as a hard disk or optical disk and installed externally to the learning device and the recommendation device.

[0013] First, the learning device 100 will be described. [Learning device 100] Learning data is input to the learning device 100, and the learning data includes music feature values, which are information representing the musical characteristics of a plurality of pieces of music, biometric information of the user before listening to the pieces of music, and information regarding improvement in the user's athletic ability as a result of listening to the pieces of music. Using the input learning data, the learning device 100 learns an estimation model that, based on the input biometric information, obtains as a recommendation the music feature values ​​of the piece of music that is estimated to have the greatest effect on improving the athletic ability of the user in that biometric information state, and outputs the trained estimation model. As illustrated in FIG. 1, the learning device 100 includes a learning data acquisition unit 110, a learning unit 120, and a model output unit 130. The learning device 100 performs the processes of steps S110, S120, and S130 illustrated in FIG. 2.

[0014] [Learning Data Acquisition Unit 110] The learning data acquisition unit 110 functions at least as an interface for loading learning data acquired by a device other than the learning device 100 and / or learning data stored in a device other than the learning device 100 into the learning device 100. The learning data acquisition unit 110 receives the learning data input to the learning device 100. The learning data acquisition unit 110 outputs the input learning data to the learning unit 120 (step S110).

[0015] The training data consists of a training information set for each of a plurality of songs. Each training information set for a song is a combination of song information, biometric information acquired for each of the target users (hereinafter referred to as "target users") before listening to the song, and an index value for each target user regarding the improvement of athletic ability as a result of listening to the song. For example, let j represent each of the song indices 1, ..., J, and k represent each of the user indices 1, ..., K at the time of learning. Then, the training information set S(j) for each song M(j) is a set S(j) = {A(j), B(j,1), ..., B(j,K), C(j,1), ..., C(j,K)} consisting of song information A(j) for song M(j), biometric information B(j,k) for each user U(k) before listening to song M(j), and index value C(j,k) for each user U(k) regarding improvement in athletic ability due to listening to song M(j). The training data consists of J training information sets S(1), ..., S(J).

[0016] Song information A(j) is a musical feature that represents the musical characteristics of one song M(j) among multiple songs M(1), ..., M(J). If there are multiple types of musical feature, the musical feature may be, for example, key, harmony, melody, acoustics, rhythm, or tempo, and song information A(j) may be a vector of values ​​of each musical feature. If there is only one type of musical feature, song information A(j) may be information for identifying the genre into which the song is categorized. Song information A(j) may be manually assigned to song M(j), or may be obtained by analyzing song M(j) using known music analysis technology. Biometric information B(j,k) is biometric information of user U(k) acquired before user U(k) listens to song M(j), such as an electrocardiogram, heart rate, respiration, mental sweating, pupil diameter, etc. acquired by a sensor worn by user U(k) a first predetermined time before user U(k) starts listening to song M(j). Index value C(j,k) related to improvement of athletic ability is an index value related to improvement of athletic ability due to listening to song (j), obtained from the results of user U(k) performing a predetermined exercise a second predetermined time before user U(k) starts listening to song M(j) and the results of user U(k) performing the same predetermined exercise a third predetermined time after user U(k) finishes listening to song M(j). For example, it is a value representing the amount or degree of improvement in athletic ability due to listening to song (j). For example, if the predetermined exercise is a vertical jump, and the height of the vertical jump performed by the user U(k) a second predetermined time before the user U(k) starts listening to the song M(j) is H1(k), and the height of the vertical jump performed by the user U(k) a third predetermined time after the user U(k) finishes listening to the song M(j) is H2(k), then, for example, the value H2(k)-H1(k) obtained by subtracting H1(k) from H2(k) or the value H2(k) divided by H1(k) may be used. The index value C(j,k) relating to improvement in athletic ability may be set to the following value: H2(k) / H1(k), or (H2(k)-H1(k)) / H1(k), obtained by subtracting H1(k) from H2(k) and dividing the result by H1(k), or (H2(k)-H1(k)) / H2(k), obtained by subtracting H1(k) from H2(k) and dividing the result by H2(k). The first, second, and third predetermined times may be determined in advance by experiment or the like.It is preferable to set the first predetermined time to be longer than the second predetermined time so that the biological information B(j,k) is not affected by exercise.

[0017] The learning data acquiring unit 110 may obtain different biometric information B'(j,k) from the input biometric information B(j,k) and output the biometric information B'(j,k) instead of the biometric information B(j,k). For example, the learning data acquiring unit 110 may obtain biometric information B'(j,k) representing the psychological state of user U(k) from the biometric information B(j,k) acquired from user U(k), and output the biometric information B'(j,k) representing the psychological state of user U(k) instead of the biometric information B(j,k) acquired from user U(k). The biometric information B'(j,k) may be, for example, an index value of tension. For example, if the input biometric information B(j,k) is an electrocardiogram waveform and the amount of mental sweating, the learning data acquiring unit 110 may obtain and output an index value of tension as biometric information B'(j,k) from the electrocardiogram waveform and the amount of mental sweating. That is, the learning data acquiring unit 110 may convert a part of the input learning data and output the converted data to the learning unit 120 as learning data.

[0018] [Learning Unit 120] The learning unit 120 receives as input the learning data output by the learning data acquisition unit 110. Using the input learning data, the learning unit 120 learns an estimation model that uses biometric information as input and obtains musical feature quantities, which are information representing the musical characteristics of a piece of music that is estimated to have the greatest effect on improving the athletic ability of a user in that state of biometric information (step S120), and outputs the trained estimation model to the model output unit 130. Well-known learning techniques may be used to train the estimation model, and the amount of training data may be sufficient for training the estimation model.

[0019] The learning unit 120 may train the estimation model using the biometric information and index values ​​related to the improvement of athletic ability of all users at the time of learning, or may train the estimation model using the biometric information and index values ​​related to the improvement of athletic ability of users who satisfy predetermined conditions among the users at the time of learning, or may train the estimation model using the biometric information and index values ​​related to the improvement of athletic ability of a specific user among the users at the time of learning. When the learning unit 120 trains using the biometric information and index values ​​related to the improvement of athletic ability of all users, an estimation model that is less dependent on the user can be obtained. When the learning unit 120 trains using the biometric information and index values ​​related to the improvement of athletic ability of users who satisfy predetermined conditions, an estimation model that is more dependent on the user who satisfies the conditions can be obtained. When the learning unit 120 trains using the biometric information and index values ​​related to the improvement of athletic ability of a specific user, an estimation model specialized for that user can be obtained.

[0020] [Model Output Unit 130] The model output unit 130 receives the trained estimation model output by the learning unit 120. The model output unit 130 outputs the trained estimation model to the recommendation device 200 as an output of the learning device 100 (Step S130).

[0021] Next, the recommendation device 200 will be described. [Recommendation Device 200] Biometric information of a user to whom a song is to be recommended (hereinafter referred to as a "recommendation target user") is input to the recommendation device 200. Using a trained estimation model, the recommendation device 200 receives the biometric information of the recommendation target user as input, and obtains and outputs, as a recommendation result, music feature quantities of a song that is estimated to have the greatest effect on improving athletic ability when the recommendation target user is in the biometric information state and / or information about the song itself. As illustrated in FIG. 1 , the recommendation device 200 includes a biometric information acquisition unit 210, a song recommendation information generation unit 220, and a song recommendation information output unit 230. The recommendation device 200 performs the processes of steps S210, S220, and S230 illustrated in FIG. 3 .

[0022] [Biometric Information Acquisition Unit 210] The biometric information acquisition unit 210 receives biometric information of the recommendation target user input to the recommendation device 200. The biometric information acquisition unit 210 outputs the input biometric information to the music recommendation information generation unit 220 (step S210).

[0023] The biometric information of the recommendation target user may be, for example, an electrocardiogram, heart rate, respiration, mental sweating, or pupil diameter acquired by a sensor worn by the recommendation target user. If the learning data acquisition unit 110 of the corresponding learning device 100 acquires and outputs other biometric information from the input biometric information, the biometric information acquisition unit 210, like the learning data acquisition unit 110, also acquires and outputs other biometric information from the input biometric information. An example of the other biometric information is a tension index value. For example, if the learning data acquisition unit 110 of the corresponding learning device 100 acquires and outputs a tension index value as biometric information from the input electrocardiogram waveform and the amount of mental sweating, the biometric information acquisition unit 210 also acquires and outputs a tension index value as biometric information from the input electrocardiogram waveform and the amount of mental sweating. That is, the biometric information acquisition unit 210 may convert the input biometric information and output it as biometric information to the music recommendation information generation unit 220.

[0024] 1, the music recommendation information generation unit 220 includes a model storage unit 225. The model storage unit 225 stores in advance a trained estimation model output by the corresponding learning device 100. The trained estimation model stored in advance in the model storage unit 225 is an estimation model that receives biometric information as input and obtains musical features of a piece of music that is estimated to have the greatest effect on improving the athletic ability of a user in a state of that biometric information.

[0025] The music recommendation information generation unit 220 receives as input the biometric information output by the biometric information acquisition unit 210. Using a trained estimation model pre-stored in the model storage unit 225, the music recommendation information generation unit 220 receives as input the biometric information of the recommendation target user, obtains, as music recommendation information, music feature quantities of songs that are estimated to have the greatest effect on improving the athletic ability of the recommendation target user in the state of the biometric information (step S220), and outputs the obtained music recommendation information to the music recommendation information output unit 230.

[0026] The music recommendation information generation unit 220 may use a trained estimation model stored in advance in the model storage unit 225 to input biometric information of a recommendation target user and obtain music features of songs that are estimated to have the greatest effect on improving the athletic ability of the recommendation target user in the state of the biometric information (step S220-1), obtain information on songs corresponding to the music features obtained in step S220-1 from a music database storing a plurality of songs and / or song information (step S220-2), and output the obtained music recommendation information to the music recommendation information output unit 230. In step S220-2, the music recommendation information generation unit 220 may determine, as songs corresponding to the music features obtained in step S220-1, one or more songs having music features closest to the music features obtained in step S220-1, a predetermined number of songs in descending order of the music features closest to the music features obtained in step S220-1, a predetermined number of songs whose music features are within a predetermined range of similarity to the music features obtained in step S220-1, or the like.

[0027] The music recommendation information generation unit 220 may output both the music feature values ​​obtained in step S220-1 and the music information obtained in step S220-2 as music recommendation information to the music recommendation information output unit 230. Note that the music database storing multiple songs and / or music information may be stored in a storage unit (not shown) within the music recommendation information generation unit 220, or may be provided by a music distribution service or music database service connected to the music recommendation information generation unit 220 via a network such as the Internet.

[0028] The trained estimation model pre-stored in the model storage unit 225 may be obtained by any type of learning performed by the learning unit 120 of the learning device 100. That is, the trained estimation model pre-stored in the model storage unit 225 may be an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of all users at the time of learning, an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of users who satisfy predetermined conditions among the users at the time of learning, or an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of a specific user among the users at the time of learning. However, when using an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of users who satisfy predetermined conditions among the users at the time of learning, it is preferable to use an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of users who satisfy conditions that are met by a recommendation target user. Furthermore, when using an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of a specific user among the users at the time of learning, it is preferable to use an estimation model trained using the biometric information and index values ​​related to the improvement of athletic ability of the recommendation target user.

[0029] [Music recommendation information output unit 230] The music recommendation information output by the music recommendation information generation unit 220 is input to the music recommendation information output unit 230. The music recommendation information output unit 230 outputs the input music recommendation information as an output of the recommendation device 200 (step S230).

[0030] <Other Examples> In the first embodiment, the predetermined exercise is described using an example in which the predetermined exercise is a vertical jump. However, the predetermined exercise is not limited to a vertical jump and can be any type of exercise. However, given the background of the invention described above, it is desirable that the predetermined exercise be an explosive exercise such as a ball throw, a throwing event, a sprint, or a long jump. In other words, the recommendation system 300 of the first embodiment is expected to be particularly effective when targeting explosive exercises. That is, it is sufficient to use an index value related to the exercise results of explosive exercises as the index value related to the improvement of athletic ability included in the learning information set handled by the learning device 100. More specifically, it is sufficient to use a value representing the amount or degree of improvement in the exercise results of explosive exercises. In this way, the learning device 100 can learn an estimation model that obtains music features of songs that are estimated to have the greatest effect on improving the exercise results of a user's explosive exercises, and the recommendation device 200 can obtain music features of songs that are estimated to have the greatest effect on improving the exercise results of a recommendation target user's explosive exercises.

[0031] <Program and Recording Medium> The processing of each unit of the learning device and recommendation device described above may be realized by a computer, in which case the processing content of the functions that each device should have is described by a program. Then, by loading this program into the storage unit 1020 of the computer 1000 shown in Figure 4 and operating the arithmetic processing unit 1010, input unit 1030, output unit 1040, etc., the various processing functions of each of the above devices are realized on the computer.

[0032] The program describing the processing contents can be recorded on a computer-readable recording medium, such as a non-transitory recording medium, specifically a magnetic recording device, an optical disk, or the like.

[0033] The program may be distributed, for example, by selling, transferring, lending, etc. a portable recording medium such as a DVD or CD-ROM on which the program is recorded. Furthermore, the program may be stored in a storage device of a server computer, and then transferred from the server computer to another computer via a network, thereby distributing the program.

[0034] A computer executing such a program, for example, first stores the program recorded on a portable recording medium or transferred from a server computer in its own non-transitory storage device, auxiliary storage unit 1050. Then, when executing a process, the computer loads the program stored in auxiliary storage unit 1050, its own non-transitory storage device, into storage unit 1020 and executes processing in accordance with the loaded program. Alternatively, as another form of execution of this program, the computer may load the program directly from a portable recording medium into storage unit 1020 and execute processing in accordance with the program. Furthermore, the computer may execute processing in accordance with the received program each time a program is transferred from a server computer to the computer. Alternatively, the server computer may not transfer the program to the computer, but may instead execute the processing function by issuing an execution instruction and obtaining the results, thereby executing the above-described processing through a so-called ASP (Application Service Provider) type service. Note that, in this embodiment, the program includes information used for processing by a computer that is equivalent to a program (e.g., data that is not a direct instruction to the computer but has properties that define computer processing).

[0035] Furthermore, in this embodiment, the device is configured by executing a predetermined program on a computer, but at least a part of the processing contents may be realized by hardware.

[0036] It goes without saying that other modifications are possible without departing from the spirit of the present invention.

Claims

1. The learning data consists of a set of learning information for each of a plurality of songs, and the set of learning information for each song is a combination of music features, which are information that represents the musical characteristics of the song, biometric information obtained for each of the target users who are the subjects of learning before listening to the song, and an index value for each of the target users regarding improvement in athletic ability due to listening to the song, and the learning device includes a learning unit that uses the input learning data and biometric information as input to learn an estimation model to obtain music features of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information.

2. A recommendation device including: an estimation model that uses input biometric information to obtain musical features, which are information representing the musical characteristics of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information; and a music recommendation information generation unit that uses the estimation model to obtain musical features of a song that is estimated to have the greatest effect on improving the athletic ability of the recommendation target user in the state of the input biometric information, and uses the estimation model to input biometric information of a recommendation target user, who is a user to whom songs are recommended.

3. A recommendation device as described in claim 2, wherein the music recommendation information generation unit further obtains, as music recommendation information, a song and / or song information corresponding to the obtained music feature from a music database in which a plurality of songs and / or song information are stored.

4. The learning data consists of a set of learning information for each of a plurality of songs, and the set of learning information for each song is a combination of music features, which are information representing the musical characteristics of the song, biometric information obtained for each of the target users who are the subjects of learning before listening to the song, and an index value for each of the target users regarding improvement in athletic ability due to listening to the song, and the learning method includes a learning step in which a learning unit uses the input learning data and biometric information as input to learn an estimation model for obtaining music features of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information.

5. A recommendation method including a memory unit that pre-stores an estimation model that uses biometric information as input to obtain musical feature values, which are information representing the musical characteristics of a song that is estimated to have the greatest effect on improving the athletic ability of a user in the state of the input biometric information, and a song recommendation information generation step in which a song recommendation information generation unit uses the estimation model as input to obtain musical feature values ​​of a song that is estimated to have the greatest effect on improving the athletic ability of the recommendation target user in the state of the input biometric information, and 6. A program for causing a computer to function as the learning device according to claim 1.

7. A program for causing a computer to function as the recommendation device according to claim 2 or 3.

Citation Information

Patent Citations

  • Content reproducing device, content reproducing system, and content reproducing method

    JP2018085015A

  • ubiquitous biometric information detection system

    KR1020120033530A

  • Spherical Input and Output Methods and Devices

    US20200371622A1

  • Server device, conference assisting system, conference assisting method, and program

    WO2021171606A1