Ringkasan (Dialogflow)
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Actions on Google memungkinkan Anda memperluas fungsi Asisten Google dengan
Action. Tindakan memungkinkan pengguna menyelesaikan berbagai hal melalui antarmuka percakapan yang dapat berupa perintah cepat untuk menyalakan lampu atau percakapan yang lebih panjang, seperti bermain game trivia.
Dialogflow adalah platform percakapan yang memungkinkan Anda mendesain dan membuat
Tindakan dengan membungkus fungsi Actions SDK
dan menyediakan fitur tambahan seperti IDE yang mudah digunakan, natural language
understanding (NLU), machine learning, dan banyak lagi.
Untuk memperluas Google Assistant, Anda membuat Tindakan dengan langkah-langkah berikut.
Mendesain Percakapan Anda
Sebelum mengembangkan, Anda harus mendesain percakapan, atau antarmuka pengguna
untuk Action Anda. Percakapan ini menjelaskan cara pengguna memanggil Action Anda, hal-hal valid yang dapat mereka ucapkan kepada Action Anda, dan cara Action Anda merespons mereka.
Pelajari lebih lanjut
Membuat project developer Actions on Google dan Agen Dialogflow
Buka konsol Actions dan buat project developer.
Project ini memungkinkan Anda menentukan metadata tentang Action dan mengelola serta melacak Action melalui proses persetujuan. Setelah memiliki project, Anda dapat
membuat agen Dialogflow yang menentukan semua Actions Anda.
Pelajari lebih lanjut
Menentukan Tindakan
Anda menentukan Tindakan di agen Dialogflow dengan maksud yang menentukan titik
entri ke fungsi Tindakan Anda. Misalnya, Anda ingin membuat
Action yang dapat membeli beberapa barang, memeriksa status pesanan, dan menampilkan
beberapa penawaran harian. Anda dapat menentukan intent yang dipicu dengan mengucapkan:
- "Ok Google, bicara dengan My Favorite Shoe Store untuk membeli sepatu"
- "Oke Google, bicara dengan My Favorite Shoe Store untuk memeriksa pesanan saya"
- "Ok Google, bicara dengan My Favorite Shoe Store untuk menunjukkan penawaran hari ini"
Pelajari lebih lanjut
Membangun dan men-deploy fulfillment
Saat Action di Action Anda dipanggil, Action tersebut akan memanggil fulfillment untuk memulai percakapan dengan pengguna guna memenuhi Action.
Untuk membuat percakapan, Anda menentukan intent di Dialogflow untuk membuat tata bahasa percakapan, atau hal-hal yang dapat diucapkan pengguna ke Action Anda.
Saat pengguna benar-benar mengatakan sesuatu untuk memicu intent, fulfillment Anda akan
dipanggil dan menampilkan respons kembali kepada pengguna.
Permintaan dan respons ini terjadi berulang kali hingga pemenuhan Anda memiliki informasi yang cukup untuk menyelesaikan tugas.
Pelajari lebih lanjut
Kirimkan Action Anda untuk mendapatkan persetujuan dan sediakan Action tersebut bagi pengguna
Pelajari lebih lanjut
Kecuali dinyatakan lain, konten di halaman ini dilisensikan berdasarkan Lisensi Creative Commons Attribution 4.0, sedangkan contoh kode dilisensikan berdasarkan Lisensi Apache 2.0. Untuk mengetahui informasi selengkapnya, lihat Kebijakan Situs Google Developers. Java adalah merek dagang terdaftar dari Oracle dan/atau afiliasinya.
Terakhir diperbarui pada 2025-07-24 UTC.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Informasi yang saya butuhkan tidak ada","missingTheInformationINeed","thumb-down"],["Terlalu rumit/langkahnya terlalu banyak","tooComplicatedTooManySteps","thumb-down"],["Sudah usang","outOfDate","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Masalah kode / contoh","samplesCodeIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-07-24 UTC."],[[["\u003cp\u003eActions on Google lets you build Actions to extend Google Assistant functionality, enabling users to interact through voice commands for tasks or conversations.\u003c/p\u003e\n"],["\u003cp\u003eDialogflow simplifies Action development by providing tools like an IDE, NLU, and machine learning, wrapping the Actions SDK functionality.\u003c/p\u003e\n"],["\u003cp\u003eBuilding an Action involves designing the conversation flow, creating a developer project and Dialogflow agent, defining Actions with intents, and building and deploying fulfillment logic.\u003c/p\u003e\n"],["\u003cp\u003eBefore submitting your Action for approval, it's essential to thoroughly design the user interaction and define how users invoke and interact with your Action.\u003c/p\u003e\n"],["\u003cp\u003eActions are invoked through specific phrases or commands, triggering intents within your Dialogflow agent, which then execute fulfillment logic to handle the user request.\u003c/p\u003e\n"]]],["Actions on Google enhance Google Assistant's capabilities through conversational interfaces. Developers use Dialogflow to build these Actions. The process involves designing the conversation flow and creating a developer project and Dialogflow agent. Define Actions using intents within the Dialogflow agent, which are triggered by user phrases. When triggered, intents call on fulfillment to complete the requested task, creating an interactive conversation until the task is done. Finally, the action is submitted for approval.\n"],null,["# Overview (Dialogflow)\n\nActions on Google lets you extend the functionality of Google Assistant with\n***Actions***. Actions let users get things done through a conversational\ninterface that can range from a quick command to turn on some lights or a\nlonger conversation, such as playing a trivia game.\n\nDialogflow is a conversational platform that lets you design and build\nActions by wrapping the functionality of the [Actions SDK](/assistant/df-asdk/actions-sdk)\nand providing additional features such as an easy-to-use IDE, natural language\nunderstanding (NLU), machine learning, and more.\n\nTo extend Google Assistant, you build an Action with the following steps.\n\nDesign your Conversation\n------------------------\n\nBefore developing, you should design your conversation, or the user interface\nfor your Action. The conversation describes how users invoke your Action, the\nvalid things that they can say to your Action, and how your Action responds to\nthem.\n\n[Learn more](/assistant/df-asdk/design)\n\nCreate an Actions on Google developer project and Dialogflow Agent\n------------------------------------------------------------------\n\nGo to the [Actions console](https://console.actions.google.com/) and create a developer project.\nThe project lets you define metadata about your Action and manage and track\nyour Action through the approval process. Once you have a project, you can\ncreate a Dialogflow agent that defines all your Actions.\n\n[Learn more](/assistant/df-asdk/dialogflow/project-agent)\n\nDefine Actions\n--------------\n\nYou define Actions in your Dialogflow agent with intents that define entry\npoints into your Action's functionality. For example, say you wanted to build an\nAction that could purchase some goods, check the status of orders, and to show\nsome daily deals. You can define intents that are triggered by saying:\n\n- *\"Ok Google, talk to My Favorite Shoe Store to purchase some shoes\"*\n- *\"Ok Google, talk to My Favorite Shoe Store to check on my order\"*\n- *\"Ok Google, talk to My Favorite Shoe Store to show me today's deals\"*\n\n[Learn more](/assistant/df-asdk/dialogflow/define-actions)\n\nBuild and deploy fulfillment\n----------------------------\n\nWhen an Action in your Action is invoked, it calls fulfillment to start a\nconversation with users to fulfill the Action.\n\nTo create your conversation, you define intents in Dialogflow to create your\nconversation's grammar, or the things users can actually say to your Action.\nWhen users actually say something to trigger an intent, your fulfillment is\ncalled and returns a response back to the user.\n\nThis back and forth request and response happens repeatedly until your\nfulfillment has enough information to complete the task.\n\n[Learn more](/assistant/df-asdk/dialogflow/fulfillment)\n\nSubmit your Action for approval and make it available to users\n--------------------------------------------------------------\n\n[Learn more](/assistant/df-asdk/submit-project)"]]
