ペパボ研究所がOneLoveな理由/Why pepaken is one love

ペパボ研究所 やさしい発表会 - ペパボ研究所で事業を差別化する -

1. - ϖύϘݚڀॴͰࣄۀΛࠩผԽ͢Δ - ࡾ୐༔հ / Pepabo R&D Institute, GMO Pepabo, Inc. 2017.07.06 ϖύϘݚڀॴ ༏͍͠ൃදձ ϖύϘݚڀॴ͕OneLoveͳཧ༝
2. ϓϦϯγύϧΤϯδχΞ ࡾ୐ ༔հ / @monochromegane 2 http://blog.monochromegane.com Yusuke Miyake ϖύϘݚڀॴ ݚڀһ
3. 1. ϖύϘݚڀॴͷϛογϣϯ 2. ϖύݚͱαʔϏεͷؔ܎ 3. ݚڀ։ൃࣄྫͷ঺հ 3 ໨࣍
4. 1. ϖύϘݚڀॴͷϛογϣϯ
5. 5 ϖύϘݚڀॴ(ུশʮϖύݚʯ)͸ɺࣄۀΛࠩผԽ Ͱ͖Δٕज़Λ࡞Γग़ͨ͢ΊʹʮͳΊΒ͔ͳγες Ϝʯͱ͍͏ίϯηϓτͷԼͰݚڀ։ൃʹऔΓ૊Ή ૊৫Ͱ͢ɻ ❝ ϖύϘݚڀॴʹ͍ͭͯ http://rand.pepabo.com/
6. ͳͥݚڀ͔
7. • ݚڀ͸ɺࣄ࣮΍ཧ࿦Λ໌Β͔ʹ͢Δʹ͋ͨΓɺ৽نੑɺ༗ޮੑɺ৴པੑΛ٬؍ తʹࣔ͞ͳ͚Ε͹ͳΒͳ͍ • طଘख๏ͷௐࠪ(వ)ɺ뱌(ઈ)ɺ࿦จԽ(࿅)Λܦͯɺख๏΁ͷঢ՚(ൃ)ʹࢸΔ • ݚڀతΞϓϩʔνͷ൓෮ʹΑͬͯɺཧ࿦΍ख๏͕લਐ͢Δ(Ԡ༻ɺܥ౷) • ٕज़͕ҰൠԽ͢Δ࣌୅Ͱ͸ɺݚڀΛ௨ͯ͋͠Δख๏ʹ͓͚Δ৽نੑΛݗҾͰ͖ ΔଘࡏͱͳΔ͜ͱ͕ɺࠩผԽͰ͖Δٕज़Λ࣋ͭ͜ͱʹͭͳ͕Δ 7 ͳͥݚڀ͔ ࠩผԽͰ͖Δٕज़Λ࡞Γग़ͨ͢Ίʹ͸ɺݚڀతΞϓϩʔν͕༗ޮ
8. 2. ϖύݚͱαʔϏεͷؔ܎
9. 9 ΞΧσϛοΫͳਫ४ʹ͓͚Δ৽نੑɾ༗ޮੑɾ৴ པੑΛ௥ٻ͢ΔݚڀΛߦ͏ͱͱ΋ʹɺݚڀ։ൃ͠ ٕͨज़Λ࣮ࡍͷγεςϜͱ࣮ͯ͠૷ɾఏڙ͢Δ͜ ͱΛ௨ͯ͠ɺࣄۀͷ੒௕ʹߩݙ͠·͢ɻ ❝ ϖύϘݚڀॴʹ͍ͭͯ http://rand.pepabo.com/
10. 10 ϖύݚͱαʔϏεͷؔ܎ ࣄۀΛࠩผԽ͢ΔͨΊʹ͸ɺݚڀॴͱαʔϏεͷ࿈ܞ͕ඞਢ ݚڀ ։ൃ ӡ༻ ՝୊ͷڞ༗ ݚڀʹΑΔղܾ ಋೖ࣌ͷΤϯδχΞؒ࿈ܞ ݚڀ։ൃ݁ՌΛଈ࣌αʔϏεʹಋೖ͢Δ࢓૊ΈͱɺಋೖޙͷϑΟʔυόοΫʹΑΔαΠΫϧͷߴ ଎ԽʹΑͬͯɺݚڀ։ൃͷߴ౓ԽͱࣄۀͷࠩผԽʹͭͳ͛Δ
12. 3. ݚڀ։ൃࣄྫͷ঺հ
13. ಛ௃நग़ثͷֶशͱߪങཤྺΛ ඞཁͱ͠ͳ͍ྨࣅը૾ʹΑΔ ؔ࿈঎඼ݕࡧγεςϜ
14. 14 ՝୊ͷڞ༗ େ͖ͳ୯ҐͰͷ՝୊ʢઓུʣͷڞ༗ • minneʹ͓͍ͯɺ࡞඼ͱͷग़ձ͍ͷ֬཰Λ্͛Δ͜ͱ͕ઓུͷͻͱͭͱ্ͯ͠ ͛ΒΕ͍ͯΔɻݱࡏɺminneʹ͸਺ඦສ఺ͷ࡞඼͕ొ࿥͞Ε͓ͯΓɺαʔϏε ར༻ऀͷ௨ৗͷߦಈͰ͸શͯͷ࡞඼ΛݟͯճΔ͜ͱ͸ࠔ೉Ͱ͋Δɻ • ඞવతʹαʔϏεར༻ऀ͕ߪೖ͍ͨ͠ͱࢥ͏࡞඼ͱग़ձ͏֬཰͸௿Լ͖ͯͯ͠ ͓Γɺ͜ͷ֬཰Λ্͛Δ͜ͱ͕ɺ͓ങ͍෺ମݧͷ࠷େԽͷͨΊʹٻΊΒΕ͍ͯ Δɻ
15. • ճ༡ͷಋઢΛ૿΍͢ඞཁ͕͋ΔɻAmazon΍ָఱͱ͍ͬͨECαΠτͰ͸ؔ࿈ ࡞඼Λఏࣔ͢Δ͜ͱͰ঎඼ͷݕ౼Λܧଓͤ͞Δճ༡͕͋ΓɺͦͷͨΊʹ͸ͳΜ Β͔ͷ؍఺Ͱؔ࿈͍ͯ͠Δ͜ͱΛγεςϜతʹѻ͑Δঢ়ଶʹ͢Δඞཁ͕͋Δ 15 ண؟఺ͱํࣜ • ௨ৗɺDB্ʹؚ·ΕΔ৘ใʢߏ଄Խͨ͠৘ใʣʹΑͬͯಉҰࢹͰ͖Δ΋ͷ ʢminneͰݴ͑͹ಉ͡ΧςΰϦɺಉ͡৭ʣͳͲΛ༻͍Δ͕ɺ͜Ε·Ͱʹͳ͍ؔ ࿈࡞඼ͷಋઢΛ૿΍ͨ͢Ίɺ·ͩߏ଄Խ͞Ε͍ͯͳ͍৘ใΛminne಺ͰऔΓѻ ͑ΔΑ͏ʹ͍ͯ͘͠ɻ
16. • ߪങཤྺ౳ͷ৘ใ͕ෆཁͰ෼ྨ༻ͷ௥Ճ৘ใͱͯ͠Ͱ͸ͳ͘ɺৗʹઃఆ͞ΕΔ ঎඼ը૾Λର৅ • ಋೖઌͷECαΠτͷ঎඼ʹґଘ͠ͳֶ͍शෆཁͰ൚༻తͳֶशࡁΈωοτ ϫʔΫΛಛ௃நग़ثͱͯ͠࠾༻ • ಛ௃நग़ث͔ΒಘΒΕͨಛ௃ྔΛ΋ͱʹۙࣅۙ๣୳ࡧʹΑΓྨࣅը૾Λݕࡧ 16 ఏҊख๏
18. ಛ௃ྔม׵ 18 Service Object Storage GCP image to data data to feature vectorizer by Inception-v3 Annoy Workers • ͋Δ࣌఺·Ͱͷ࡞඼ը૾ҰཡΛಛ௃ྔʹม׵͢Δ • ม׵ͨ͠ಛ௃ྔҰཡΛۙࣅۙ๣୳ࡧσʔλϕʔεʹ౤ೖ͢Δ
19. • ۙࣅۙ๣୳ࡧσʔλϕʔεΛmruby-annoy + ngx_mrubyʹͯAPIԽ • ࡞඼ৄࡉʹྨࣅը૾Λ༻͍ͨؔ࿈࡞඼Λදࣔ͢Δ 19 ྨࣅը૾ݕࡧ Nyah mruby-annoy on ngx_mruby products#show product_id nearest products CTR Analytics NNS ˞ۙࣅۙ๣୳ࡧ࣌ʹେ෦෼ͷΠϯσο Ϋε΁ͷΞΫηε͕ൃੜ͢ΔͨΊ࣮༻ తͳ଎౓ΛಘΔͨΊʹ͸σʔλϕʔε ϑΝΠϧ͕શͯϖʔδΩϟογϡʹࡌ ΔαΠζͷϝϞϦ͕ඞཁ
20. ྨࣅը૾ʹΑΔؔ࿈࡞඼ݕࡧ 20
21. ྨࣅը૾ʹΑΔؔ࿈࡞඼ݕࡧ 21
22. ΫϦοΫ཰ͱίϯόʔδϣϯ཰ 22 طଘ ఏҊ $53   $73   ˞ఏҊख๏ʹΑΔબఆ͕ߦ͑ͳ͍৔߹ʹαʔϏεͷ ػձଛࣦΛආ͚ΔͨΊطଘख๏ʹΑΔબఆΛߦͬͯ ͍ΔͨΊݕূظؒதͷ֤ख๏ͷදׂࣔ߹͸طଘ ɺఏҊͰ͋ͬͨ
    ˞ίϯόʔδϣϯ཰͸ΫϦοΫ਺ʹର͢Δߪೖ਺͔ ΒٻΊͨ طଘ ఏҊ ૉࡐɾࡐྉγΣϧ   ૉࡐɾࡐྉϦϘϯɾςʔϓ   ૉࡐɾࡐྉϘλϯ   ͵͍͙ΔΈɾਓܗ͋Έ͙ΔΈ   χοτɾฤΈ෺ηʔλʔɾΧʔσΟΨϯ   ఏҊख๏͕༗ޮͰ͋ͬͨΧςΰϦ
23. ݚڀใࠂΠϯλʔωοτͱӡ༻ٕज़ʢIOTʣ 23 ࡾ୐ ༔հ, দຊ ྄հ, ྗ෢ ݈࣍, ܀ྛ ݈ଠ࿠, ಛ௃நग़ثͷֶ शͱߪങཤྺΛඞཁͱ͠ͳ͍ྨࣅը૾ʹΑΔؔ࿈঎඼ݕࡧγ εςϜ, ݚڀใࠂΠϯλʔωοτͱӡ༻ٕज़ʢIOTʣ, Vol.2017-IOT-37(4), pp.1-8, May 2017 http://id.nii.ac.jp/1001/00178892/
24. ϑΟʔυόοΫ
25. Gannoy Approximate nearest neighbor search server and dynamic index written in Golang. https://github.com/monochromegane/gannoy
26. GannoyʹΑΔಈతΠϯσοΫεߋ৽+ྨࣅը૾ݕࡧ 26 Features Similar items Gannoy [2048]float64 query by http find similar features mapping similar features to items response Deep CNN index Features [2048]float64 Deep CNN register by http
27. ΞΫηεස౓༧ଌʹجͮ͘ Ծ૝αʔόͷܭըతΦʔτεέʔϦϯά
28. 28 ՝୊ͷڞ༗
29. • ैྔ՝ۚͷԾ૝αʔόӡ༻ʹ͓͍ͯ࠷దͳϦιʔεधཁͷ༧ଌ͸ίετΧοτʹͭͳ͕Δ • WebαʔϏεͷϦιʔεधཁ͸ϦΫΤετॲཧ݅਺ɺͭ·ΓΞΫηε਺ͱ૬͕ؔ͋Δ͸ͣ • Ϧιʔεͷ૿ݮʹ΋͋Δఔ౓ͷ͕͔͔࣌ؒΔͨΊɺϦΞϧλΠϜͰ͸ͳ͘ҰఆִؒͰͷΞ Ϋηε਺༧ଌͰे෼ͱߟ͑Δ 29 ண؟఺ͱํࣜ ΞΫηε਺Λ༧ଌͰ͖ΔΑ͏ʹͳΕ ͹ɺϐʔΫλΠϜʹ͋Θͤͨ୆਺ݟੵ ΋Γ͔Β࣌ؒ͝ͱͷ࠷దʢͱࢥΘΕ Δʣ୆਺ݟੵ΋Γ͕ՄೳʹͳΔ
30. • WebαʔϏεશମͰҰఆ࣌ؒʹॲཧͨ͠ΞΫηεස౓Ͱ͋ΔεϧʔϓοτΛ ࢦඪͱ͠ɺӡ༻্ɺܦݧతʹ೺Ѳ͞Ε͍ͯΔ҆ఆͯ͠ӡ༻Մೳͳ஋Λ໨ࢦ͢ • աڈͷΞΫηεස౓܏޲ͱෆఆظͳมಈཁҼ͔Β༧ଌϞσϧΛಋ͘ • ༧ଌతͳߏ੒มߋΛ՝ۚ୯ҐͰ͋Δ1࣌ؒΛ୯Ґʹߦ͏ 30 ఏҊख๏
31. 31 ఏҊख๏
32. 32 ΞΫηεස౓༧ଌϞσϧ ΞΫηεස౓༧ଌϞσϧ ֶशσʔλ͸Ϋϥ΢υαʔϏεͷඪ४՝ ۚ୯ҐͰ͋Δ࣌ؒΛཻ౓ͱ͢Δ 8FCαʔϏεͷ࠷୹ఆৗੑΛ֬ೝͰ͖Δ࣌ؒ෼ͷσʔλ Λೖྗͱ͠ɺ࣍ͷ࣌ؒ෼ͷΞΫηεස౓༧ଌΛग़ྗͱ͢Δ
    ˞࣌ؒޙҎ߱͸༧ଌ෼ΛؚΊͨظΛೖྗͱ͢Δ
33. 33 Ծ૝αʔό୆਺ࢉग़ • ༧ଌͨ͠ΞΫηεස౓ΛجʹɺWebαʔϏεΛ҆ఆͯ͠ӡ༻ Ͱ͖Δ໨҆ͱͳΔεϧʔϓοτ஋Λ֬อͰ͖Δ୆਺ΛٻΊΔ ༧ଌΞΫηεස౓ʹର͠εϧʔϓοτΛ
    ֬อͰ͖Δ୆਺Λࢉग़͢Δ
    
    
    5
    <ΞΫηεස౓෼>
    
    
    1
    <༧ଌΞΫηεස౓࣌>
    
    
    -
    αʔό୆਺Լݶ஋
34. • ࠓճͷධՁͰ͸ɺର৅ͷ WebαʔϏεʹ͓͍ͯཌ೔ ͕ฏ೔ͷ৔߹ɺ໷ؒʹΞΫ ηεස౓͕૿Ճ͢Δͱ͍͏ ܦݧଇΛཁҼͱͯ͠Ճ͑ͨ 34 ඇఆৗͷཁҼͷՃຯʹΑΔ༧ଌਫ਼౓ͷධՁ
35. 35 ඇఆৗͷཁҼͷՃຯʹΑΔ༧ଌਫ਼౓ͷධՁ ໷ؒʹීஈͱҟͳΔ܏޲ͱͳΔಛੑΛଊ ͑ͨ༧ଌ͕ߦΘΕ͍ͯΔɻ
36. 36 ܭըతΦʔτεέʔϦϯάͷධՁ Ծ૝αʔό୆਺ͷਪҠ
    ೔͋ͨΓͷαʔό૯ىಈ࣌ؒ͸"܈ ը૾্ Ͱ͔࣌ؒΒ࣌ؒʹɺ#܈ ը૾Լ Ͱ ͸ ͔࣌ؒΒ࣌ؒʹ࡟ݮ
    ˞"܈ͷ࣌͸ࢉग़୆਺͕୆਺Լݶ஋ΛԼ ճͬͨͨΊɺ୆਺ͷมಈ͸ݟΒΕͳ͍
37. 37 ܭըతΦʔτεέʔϦϯάͷධՁ ΞΫηεස౓ͷਪҠ
    ೔͋ͨΓΞΫηεස౓ͷඪ४ภࠩ͸"܈ ը ૾্ Ͱ໿͔Β໿ʹɺ#܈ ը ૾Լ Ͱ͸໿͔Β໿ʹมԽɻ ख๏ద༻ޙʹεϧʔϓοτ͕҆ఆ͍ͯ͠Δ ͜ͱ͕Θ͔Δɻ
    ˞"܈ͷ૿Ճ͸Լݶ୆਺ӡ༻ͱͳͬͨ࣌ؒଳ ͷ୆͋ͨΓͷεϧʔϓοτ஋૿ՃʹΑΔ΋ ͷͱߟ͑ΒΕΔ
38. ݚڀใࠂΠϯλʔωοτͱӡ༻ٕज़ʢIOTʣ 38 ࡾ୐ ༔հ, দຊ ྄հ, ྗ෢ ݈࣍, ܀ྛ ݈ଠ࿠, ΞΫηεස౓༧ ଌʹجͮ͘Ծ૝αʔόͷܭըతΦʔτεέʔϦϯά, ݚڀใࠂ Πϯλʔωοτͱӡ༻ٕज़ʢIOTʣ, Vol.2017-IOT-38(13), pp.1-8, June 2017 http://id.nii.ac.jp/1001/00182375/
39. ݚڀ݁ՌͷαʔϏεಋೖ
40. 1. ج൫ԽɺAPIԽʹΑΔݚڀ؀ڥͱαʔϏεͷγʔϜϨεͳ࿈ܞ 2. ίʔυ؅ཧɺόʔδϣϯ؅ཧʹΑΔݚڀͱӡ༻ͷฒߦ 40 ݚڀ݁ՌͷαʔϏεಋೖ ݚڀ݁ՌͷαʔϏεಋೖ͸ଈ͔࣌ͭશࣾల։Ͱ͖Δ͜ͱ͕๬·͍͠
41. 1. ϩά΍DBͳͲͷαʔϏεࢿ࢈ͱ࿈ܞͰ͖Δ 2. ൺֱత༰қʹϞσϧͷߏஙͱࢼߦ͕ߦ͑Δ 3. ֶश݁ՌΛར༻͢ΔͨΊͷखஈͱͯ͠APIΛఏڙ͢Δ 1. ֶश݁ՌͷϩʔΧϧར༻͕Ͱ͖Δͱͳ͓Α͍ 4. ্هͷ࢓૊Έ͕εέʔϥϒϧͰ͋Δ͜ͱ 41 ػցֶशج൫ʹٻΊΒΕΔ΋ͷ
42. 1. ೖग़ྗ͕Cloud Storageܦ༝ 2. ܇࿅ϓϩάϥϜͱͯ͠TensorFlowΛ࠾༻ 3. ΦϯϥΠϯ༧ଌαʔϏεʹΑΓϞσϧͷAPIԽ 1. ֶश݁Ռ͸Cloud StorageʹอଘɺϩʔΧϧͰͷར༻΋ 4. ෼ࢄܕͷτϨʔχϯάΠϯϑϥͱෛՙ෼ࢄαʔϏεͱͷ࿈ܞ 42 Google Cloud ML EngineͰߟ͑Δ ※ ݕ౼ʹؔ͢Δৄࡉ: 
 http://rand.pepabo.com/article/2017/01/18/pepabo-ml-platform-and-workflow/
43. StarChart StarChart is a tool to manage Google Cloud Machine Learning training programs and model versions https://github.com/monochromegane/starchart
44. • όʔδϣϯ؅ཧͷ੾ସʹ͓͚Δ൑அج४ͱͳΔ܇࿅ϓϩάϥϜɺύϥϝλɺδϣ ϒ৘ใ·ͰؚΊͯίʔυͰ؅ཧ • ֶश࣌ͷδϣϒID΍Cloud Storageͷύεɺόʔδϣϯʹඥͮ͘ύϥϝλ৘ใ ͷऔಘʹ·ͭΘΔCloud MLͷࡉ͔ͳ࢖͍উख΋վળ 44 StarChart
45. ·ͱΊ
46. • ϖύݚͱαʔϏεͰେ͖ͳ୯ҐͰͷ՝୊ͷڞ༗Λܧଓ͢Δ • ݚڀ݁ՌͷಋೖͱϑΟʔυόοΫΛߴ଎ʹ͢Δ͜ͱ͕ࣄۀͷࠩผԽʹͭͳ͕Δ • ϖύݚ͸ݚڀ݁ՌΛଈ͔࣌ͭશࣾͰར༻Ͱ͖Δج൫Λ • αʔϏε͸ಋೖɺӡ༻࣌ͷΤϯδχΞؒ࿈ܞΛ 46 ·ͱΊ ͍·ΑΓ΋ʮΈΜͳʯͷ෯Λ޿͛ɺͦͷʮΈΜͳʯʹରͯؔ͠৺Λ͍࣋ͬͯ͘ One Love ❝ http://blog.kentarok.org/entry/2016/12/21/002537
47. ݚڀһɺੵۃతʹืूதʂ http://rand.pepabo.com/
48. • ϖύϘݚڀॴ • http://rand.pepabo.com/ • ಛ௃நग़ثͷֶशͱߪങཤྺΛඞཁͱ͠ͳ͍ྨࣅը૾ʹΑΔؔ࿈঎඼ݕࡧγεςϜ • http://rand.pepabo.com/article/2017/06/19/iot37-miyakey/ • ΞΫηεස౓༧ଌʹجͮ͘Ծ૝αʔόͷܭըతΦʔτεέʔϦϯά • http://rand.pepabo.com/article/2017/06/28/iot38-miyakey/ • Google Cloud ML Λ༻͍ͨػցֶशج൫ͷߏஙͱӡ༻ • https://speakerdeck.com/monochromegane/pepabo-ml-infrastructure-starchart • 2017೥ͷςʔϚ: One Love • http://blog.kentarok.org/entry/2016/12/21/002537 48 ࢀߟ