luis

问题 I'm trying to migrate my luis account to Azure resource and i get this error: BadArgument: You have prediction keys assigned in collaborators' apps. These apps will lose access to these keys. What am I doing wrong? What have I to do? 回答1: I had this same issue, the problem was that there was a prediction resource assigned to an app. In LUIS, click on "Manage" in the top bar then under "Application Settings" > "Azure Resources" unassign any resources listed, then try the migration again. Once

问题 I'm trying to migrate my luis account to Azure resource and i get this error: BadArgument: You have prediction keys assigned in collaborators' apps. These apps will lose access to these keys. What am I doing wrong? What have I to do? 回答1: I had this same issue, the problem was that there was a prediction resource assigned to an app. In LUIS, click on "Manage" in the top bar then under "Application Settings" > "Azure Resources" unassign any resources listed, then try the migration again. Once

问题 I have a bot made using framework v4 in c#. I want that my bot take user feedback once the bot goes idle, or in the case user doesn't responded to bot.I have made my card but not getting any logic to implement above mention feature in my bot. I am also attaching the code of card i made. Also the image of my card. Can any look into it and help me out with this implementation. enter image description here { "type": "AdaptiveCard", "body": [ { "type": "TextBlock", "size": "Medium", "weight":

问题 After a bout of repeated training and deleting patterns and intense scrutiny of what might be happening to our LUIS models, it seems as though Luis is completely down. Here is what is repeatedly happening when trying to train a LUIS model. The reason why I was questioning the error being something on our part is because of this previous stackoverflow QA on the subject. Also, this article. These previous reported instances of training failures do not address this issue but they seem closely

问题 I added an authoring resource in the Luis Portal and imported a few apps. The added authoring resource appeared both in the Azure portal and the Luis portal initially. Then suddenly the resource disappeared in the Luis portal and now I am unable to select the resource using the drop down in the Apps page as it is no longer showing in there. (screenshot below) What is going on? The resource still shows up in the Azure portal. I tried logging out and in and refreshing the page multiple times.

问题 Please help me in LUIS training. I want to add new utterances to intent using LUIS API. But I can't find any examples in the documentation. 回答1: You might want to try the Add Label operation from the LUIS Programatic API. 来源： https://stackoverflow.com/questions/44389065/how-to-add-new-utterance-to-luis-intent

问题 If I give the message "open the door and turn on the lights" come out two intents "OpenDoor" "TurnOnLights" does luis support this? thanks 回答1: Short answer would be "no, you will not be sure of the number of valid intents found". LUIS is providing a scoring for all the intents of your project when you test a sentence, it is not giving one or two intents. Then it will be what you do with these scorings that will help you to define if there are 1, 2, 3 valid information. For example if I

问题 I'm using the Microsoft Bot Framework v4 to do some fairly basic date and date range recognition. The most straightforward use of the LUIS recognizer that most examples use and is used in the enterprise template doesn't return the complete DateTimeV2 structure. The example below is for "last week" corresponding to a daterange. These results are in recognizer.result.entities: { "$instance": { "datetime": [ { "startIndex": 8, "endIndex": 17, "text": "last week", "type": "builtin.datetimeV2

问题 I am working with Microsoft Cognitive Service's Language Understanding Service API, LUIS.ai. Whenever text is parsed by LUIS, whitespace tokens are always inserted around punctuation. This behavior is intentional, according to the documentation. "English, French, Italian, Spanish: token breaks are inserted at any whitespace, and around any punctuation." For my project, I need to preserve the original query string, without these tokens, as some entities trained for my model will include

问题 I have implemented the None Intent as follows.. [LuisIntent("None")] public async Task None(IDialogContext context, LuisResult result) { await context.PostAsync("I'm sorry. I didn't understand you."); context.Wait(MessageReceived); } But looks like i need to train some utterance at luis side, which i don't want. I am looking something whichever is not found or recognize at luis, should fire the None Intent handler. How do I achieve this ? 回答1: Add also the following line to your None method: