Question

我是Node.JS和Microsoft Bot Framework的初学者。我正在创建一个聊天机器人，并且已经弄清楚了如何与LUIS服务进行通信，但是我仍然遇到一个小问题。我已经尝试了很多不同的方法，并且应该注意，我正在Azure中使用在线应用程序服务编辑器。

我无法弄清楚如何与用户打招呼，我觉得这很容易。问候，是指在用户单击链接以与我的机器人打开对话框时向用户发送消息。我知道我应该使用onMember⚓命令，但是当我尝试添加它时，我总是弄乱其他东西。这是我当前的代码：

bot.js

const { ActivityHandler } = require('botbuilder');
const { BotFrameworkAdapter } = require('botbuilder');
const { LuisRecognizer } = require('botbuilder-ai');

class LuisBot {
    constructor(application, luisPredictionOptions) {
        this.luisRecognizer = new LuisRecognizer(application, luisPredictionOptions, true);
        }   
    async onTurn(turnContext) {
        // Make API call to LUIS with turnContext (containing user message)
        try {
            const results = await this.luisRecognizer.recognize(turnContext);

            //console.log(results);
            // Extract top intent from results
            const topIntent = results.luisResult.topScoringIntent;
            switch (topIntent.intent) {
                    case 'Greeting':
                    await turnContext.sendActivity('Hello!');
break;          
                    default:
                    await turnContext.sendActivity('Oops, looks like something went wrong');
            }
        } catch (error) {
        }
    }
}
module.exports.LuisBot = LuisBot;

index.js

const dotenv = require('dotenv');
const path = require('path');
const restify = require('restify');

// Import required bot services.
// See https://aka.ms/bot-services to learn more about the different parts of a bot.
const { BotFrameworkAdapter } = require('botbuilder');

// This bot's main dialog.
// const { EchoBot } = require('./bot');
const { LuisBot } = require('./bot');

// Import required bot configuration.
const ENV_FILE = path.join(__dirname, '.env');
dotenv.config({ path: ENV_FILE });

// Create HTTP server
const server = restify.createServer();
server.listen(process.env.port || process.env.PORT || 3978, () => {
    console.log(`\n${ server.name } listening to ${ server.url }`);
    console.log(`\nGet Bot Framework Emulator: https://aka.ms/botframework-emulator`);
    console.log(`\nTo talk to your bot, open the emulator select "Open Bot"`);
});

// Create adapter.
const adapter = new BotFrameworkAdapter({
    appId: process.env.MicrosoftAppId,
    appPassword: process.env.MicrosoftAppPassword,
    channelService: process.env.ChannelService,
    openIdMetadata: process.env.BotOpenIdMetadata
});

const luisApplication = {
    applicationId: process.env.LuisAppId,
    endpointKey: process.env.LuisAuthoringKey,
    azureRegion: process.env.LuisAzureRegion
};
const luisPredictionOptions = {
    includeAllIntents: true,
    log: true,
    staging: false
};

// Catch-all for errors.
adapter.onTurnError = async (context, error) => {
    // This check writes out errors to console log .vs. app insights.
    console.error(`\n [onTurnError]: ${ error }`);
    // Send a message to the user
    await context.sendActivity(`Oops. Something went wrong!`);
};

// Create the main dialog.
// const bot = new EchoBot();
// Create the main dialog.
const bot = new LuisBot(luisApplication, luisPredictionOptions);

// Listen for incoming requests.
server.post('/api/messages', (req, res) => {
    // console.log(process.env.LuisAppId);
    adapter.processActivity(req, res, async (context) => {
        // Route to main dialog.
        // console.log(process.env.LuisAppId);
        await bot.onTurn(context);
    });
});

我显然对此并不陌生，如果这是一个不好的问题，我深表歉意，但是我已经尝试了一切。

Answer 1

仅需一点点代码即可实现。请注意，我只显示相关代码。

首先，将问候语保存在单独的“机器人”文件中。在此示例中，我在名为welcomeCard.json的文件中定义了一个简单的自适应卡。问候文件welcomeBot.js中引用了此文件，该文件扩展了主要的“机器人”文件mainBot.js。

welcomeBot.js

const { CardFactory } = require('botbuilder');
const { MainBot } = require('./mainBot');
const WelcomeCard = require('../resources/json/welcomeCard');

class WelcomeBot extends MainBot {
  constructor(conversationState, userState, dialog, conversationReferences) {
    super(conversationState, userState, dialog, conversationReferences);

    this.onMembersAdded(async (context, next) => {
      const membersAdded = context.activity.membersAdded;
      for (let cnt = 0; cnt < membersAdded.length; cnt++) {
        if (membersAdded[cnt].id !== context.activity.recipient.id) {
          const welcomeCard = CardFactory.adaptiveCard(WelcomeCard);
          await context.sendActivity({ attachments: [welcomeCard] });
        }
      }

      await next();
    });
  }
}

module.exports.WelcomeBot = WelcomeBot;

接下来，在index.js文件中，我同时引用welcomeBot文件和我的mainDialog来实例化机器人。

index.js

const { WelcomeBot } = require( './bots/welcomeBot' );
const { MainDialog } = require( './dialogs/mainDialog' );

[...other code...]

const dialog = new MainDialog( 'MainDialog', userState, conversationState );
const bot = new WelcomeBot( conversationState, userState, dialog );

当用户首次连接到bot时，此应该使您开始使用问候语渲染。

希望有帮助！

打开漫游器后问候用户

1 个答案: