JP2019032857A5 - Support system - Google Patents
Support system Download PDFInfo
- Publication number
- JP2019032857A5 JP2019032857A5 JP2018175586A JP2018175586A JP2019032857A5 JP 2019032857 A5 JP2019032857 A5 JP 2019032857A5 JP 2018175586 A JP2018175586 A JP 2018175586A JP 2018175586 A JP2018175586 A JP 2018175586A JP 2019032857 A5 JP2019032857 A5 JP 2019032857A5
- Authority
- JP
- Japan
- Prior art keywords
- data
- users
- practice
- individual user
- support system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010801 machine learning Methods 0.000 claims description 4
- 210000003205 Muscles Anatomy 0.000 description 5
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003252 repetitive Effects 0.000 description 1
Description
本発明は、ユーザが自己向上のために繰り返し行うプラクティスを人工知能を利用して支援する支援システムに関する。 The present invention relates to a support system that uses artificial intelligence to support practices that users repeatedly perform to improve themselves .
本発明は、かかる実情に鑑み考え出されたものであり、その目的は、機械学習の結果の一般的なモデルを用いたサービスがユーザにマッチしない場合が生じる不都合を解決することである。 The present invention has been devised in view of such circumstances, and its object is to service using the generic model results of the machine learning to solve the inconvenience that may not match the user occurs.
本発明は、ユーザが自己向上のために繰り返し行うプラクティス(例えば、暗記学習、筋トレ等)を人工知能を利用して支援する支援システム(例えば、図9と図10等)であって、
前記プラクティスを行う複数のユーザのデータを収集するデータ収集手段(例えば、S182、S211等)と、
前記データ収集手段により収集された複数ユーザ分のデータに基づいて機械学習(例えば、強化学習、回帰等)を行うことにより生成された一般的モデル(例えば、暗記学習モデルTi=T0・i、筋トレモデルFi=F0+(i-1)/a等)を記憶する記憶手段(例えば、人工知能DB17等)と、
前記記憶手段に記憶された一般的モデルと前記データ収集手段により収集されたユーザ1人分の個別データとに基づいて、当該個別ユーザにパーソナライズ化されたパーソナライズデータを生成し、当該個別ユーザが繰り返しプラクティスを行う際の実行すべきプラクティス内容を特定するパーソナライズ化手段(例えば、S191とS204、S223とS228等)と、
前記個別ユーザが前記特定されたプラクティス内容を行うためのサービス(例えば、最も効率的な復習計画に基づいた学習事項の提供、最も効率的な筋トレ計画に基づいた筋トレメニューの提供等)を提供するサービス提供手段(例えば、S206、S229等)と、を備え、
前記一般的モデルは、前記繰り返し行うプラクティスを効率化するために生成された複数のユーザに当てはまるモデル(例えば、図15の暗記学習モデルTi=T 0 ・i、筋トレモデルFi=F 0 +(i-1)/a等)であり、
前記パーソナライズデータは、前記個別ユーザが前記繰り返し行うプラクティスを効率化するために生成された当該個別ユーザ専用のデータである(例えば、S204、S228等)。
The present invention allows a user practices repeated for self improvement (e.g., rote learning, muscle training, etc.) The assistance system for the using artificial intelligence support (e.g., FIGS. 9 and 10, etc.),
Data collection means (for example, S182, S211, etc.) for collecting data of a plurality of users who perform the practice;
A general model (for example, memorizing learning model Ti = T 0 · i, generated by performing machine learning (for example, reinforcement learning, regression, etc.) based on data for a plurality of users collected by the data collection means Storage means (for example, artificial intelligence DB 17 etc.) for storing the muscle training model Fi = F 0 + (i-1) / a etc. , and
Based on the individual data of the user 1 persons collected by the data collecting means and the general model stored in the storage means, generates a personalized data personalized to the individual user, the individual user repeatedly Personalizing means (for example, S191 and S204, S223 and S228, etc.) for specifying the content of the practice to be performed when performing the practice ;
Services for the individual user to perform the contents of the specified practice (eg, provision of learning items based on the most efficient review plan, provision of a muscle training menu based on the most efficient muscle training plan, etc.) Service providing means (eg, S206, S229, etc.) to be provided;
The general model is a model that applies to a plurality of users generated to streamline the repetitive practice (for example, the memorization learning model Ti = T 0 · i, muscle training model Fi = F 0 + ( FIG. 15 ) i-1) / a etc),
The personalization data is data dedicated to the individual user, which is generated to streamline the practice that the individual user performs repeatedly (for example, S204, S228, etc.).
このような構成によれば、機械学習の結果の一般的モデルを用いたサービスがユーザにマッチしない場合が生じる不都合を解決することができる。 According to such a configuration, it is possible to solve the inconvenience that the service using the general model of the result of machine learning does not match the user.
好ましくは、前記データ収集手段は、前記複数のユーザ(例えば、図9の各ユーザ70等)から直接送られてくる当該各ユーザのデータを収集する。 Preferably, the data collection means collects data of each of the users directly sent from the plurality of users (for example, each user 70 of FIG. 9, etc.).
好ましくは、前記データ収集手段は、前記プラクティスをユーザに提供する専門業者(例えば、図9の専門業者71等)から送られてくる複数のユーザのデータを収集する。 Preferably, the data collection means collects data of a plurality of users sent from a specialized vendor (for example, the specialized vendor 71 in FIG. 9 or the like) that provides the user with the practice.
Claims (3)
前記プラクティスを行う複数のユーザのデータを収集するデータ収集手段と、
前記データ収集手段により収集された複数ユーザ分のデータに基づいて機械学習を行うことにより生成された一般的モデルを記憶する記憶手段と、
前記記憶手段に記憶された一般的モデルと前記データ収集手段により収集されたユーザ1人分の個別データとに基づいて、当該個別ユーザにパーソナライズ化されたパーソナライズデータを生成し、当該個別ユーザが繰り返しプラクティスを行う際の実行すべきプラクティス内容を特定するパーソナライズ化手段と、
前記個別ユーザが前記特定されたプラクティス内容を行うためのサービスを提供するサービス提供手段と、を備え、
前記一般的モデルは、前記繰り返し行うプラクティスを効率化するために生成された複数のユーザに当てはまるモデルであり、
前記パーソナライズデータは、前記個別ユーザが前記繰り返し行うプラクティスを効率化するために生成された当該個別ユーザ専用のデータである、支援システム。 A support system that uses artificial intelligence to support practices that users repeatedly perform to improve themselves,
Data collection means for collecting data of a plurality of users who perform the practice;
Storage means for storing a general model generated by performing machine learning based on data for a plurality of users collected by the data collection means;
Based on the individual data of the user 1 persons collected by the data collecting means and the general model stored in the storage means, generates a personalized data personalized to the individual user, the individual user repeatedly Personalization means to identify the content of the practice to be performed when doing the practice, and
Service providing means for providing a service for the individual user to perform the specified content of the practice ;
The general model is a model that applies to a plurality of users generated to streamline the recurring practice,
The support system , wherein the personalization data is data dedicated to the individual user, which is generated to streamline the repeated practice of the individual user .
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018175586A JP6562328B2 (en) | 2018-09-20 | 2018-09-20 | Support system |
JP2019128889A JP6899103B2 (en) | 2018-09-20 | 2019-07-11 | Service provision system and program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2018175586A JP6562328B2 (en) | 2018-09-20 | 2018-09-20 | Support system |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2014172512A Division JP6432859B2 (en) | 2014-08-27 | 2014-08-27 | Service providing system and program |
Related Child Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2019097630A Division JP6617263B2 (en) | 2019-05-24 | 2019-05-24 | Learning support system |
JP2019128912A Division JP2019215880A (en) | 2019-07-11 | 2019-07-11 | Support system |
JP2019128889A Division JP6899103B2 (en) | 2018-09-20 | 2019-07-11 | Service provision system and program |
Publications (3)
Publication Number | Publication Date |
---|---|
JP2019032857A JP2019032857A (en) | 2019-02-28 |
JP2019032857A5 true JP2019032857A5 (en) | 2019-07-04 |
JP6562328B2 JP6562328B2 (en) | 2019-08-21 |
Family
ID=65523568
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2018175586A Active JP6562328B2 (en) | 2018-09-20 | 2018-09-20 | Support system |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP6562328B2 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7464240B2 (en) | 2019-04-26 | 2024-04-09 | Necソリューションイノベータ株式会社 | Prediction model generation device, travel suitability prediction device, prediction model production method, travel suitability prediction method, program and recording medium |
KR20220024718A (en) * | 2019-06-18 | 2022-03-03 | 몰로코, 인크. | Methods and systems for providing machine learning services |
KR102257082B1 (en) * | 2020-10-30 | 2021-05-28 | 주식회사 애자일소다 | Apparatus and method for generating decision agent |
KR102244419B1 (en) * | 2020-11-10 | 2021-04-27 | 옴니스랩스 주식회사 | Method for artificial intelligence service based on user participation and apparatus for performing the same |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002162989A (en) * | 2000-11-28 | 2002-06-07 | Ricoh Co Ltd | System and method for sound model distribution |
JP2002304114A (en) * | 2001-04-03 | 2002-10-18 | World Vision:Kk | System for supporting learning, recording medium and program thereof |
JP2003049703A (en) * | 2001-08-07 | 2003-02-21 | Mazda Motor Corp | Vehicle development data acquiring server, vehicle development data acquiring method and vehicle development data acquiring program |
JP4092710B2 (en) * | 2006-02-14 | 2008-05-28 | ソニー株式会社 | Program search method and apparatus |
KR100979516B1 (en) * | 2007-09-19 | 2010-09-01 | 한국전자통신연구원 | Service recommendation method for network-based robot, and service recommendation apparatus |
JP5694206B2 (en) * | 2012-01-11 | 2015-04-01 | 日本電信電話株式会社 | Exercise management device, exercise management method and program |
US8429103B1 (en) * | 2012-06-22 | 2013-04-23 | Google Inc. | Native machine learning service for user adaptation on a mobile platform |
-
2018
- 2018-09-20 JP JP2018175586A patent/JP6562328B2/en active Active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2019032857A5 (en) | Support system | |
McLeod et al. | Children's speech: An evidence-based approach to assessment and intervention | |
Leary et al. | Comparing bystander response to a sudden cardiac arrest using a virtual reality CPR training mobile app versus a standard CPR training mobile app | |
Rea et al. | Out of hospital cardiac arrest: Past, present, and future | |
JP2018533138A5 (en) | ||
JP2009541832A5 (en) | ||
JP2019527403A5 (en) | ||
Woollard et al. | Achy breaky makey wakey heart? A randomised crossover trial of musical prompts | |
Sasso et al. | RN4CAST@ IT: why is it important for Italy to take part in the RN4CAST project | |
Tan et al. | Retrogaming as visual feedback for speech therapy | |
JP2019046465A5 (en) | Providing device, providing method, and providing program | |
JP2018000946A5 (en) | ||
JP2019106163A (en) | Life log image generation device, life log image generation method, and program | |
Haeger et al. | A smartphone based approach to enhance older persons' mobility in daily life. | |
Jomâa et al. | A clinical didactics analysis of the use of proxemics forms in the teaching-learning process of sports and physical education setting: a case study in Tunisia | |
Biever | Consciousness: Get with the programs | |
Bassett | Spiritual interventions in child and adolescent psychotherapy | |
Barton et al. | Improving work placement for international students, their supervisors and other stakeholders: final report 2016 | |
Thomson | Sundberg, Molly: Training for Model Citizenship. An Ethnography of Civic Education and State-Making in Rwanda | |
Bird et al. | Improve Health Literacy Responsiveness; Improve Client Outcomes | |
Palermo et al. | Professional development in public health nutrition | |
Tolosa | Digital Technologies as Catalysts for Reflective Language Teacher Education | |
Thalen et al. | First Steps in Making an Intervention Transmissible to Other Care Providers: From Practice-Based Evidence to Evidence-Based Practice | |
MIHALCICA et al. | Using Motion Analisys Software to Gather Sports Experimental Data | |
JP2021168200A5 (en) |