Train rasa_core to predict the next intent according to stories.md

Need help for this one. I want to know how can I train my bot to predict the next intent according to what I have in stories.md.

To be clear: I have an intent ‘problem’ in this intent I don’t know what the user could tape. It can be every thing that the user qualify that it’s a problem for him. All what I know is that this intent will occur in a certain phase of the conversation . for example:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

* probleme

    - action_SendIntentProbleme

    - utter_probleme_site

So here I know that always after utter_step1 the user will give me his problem, and I don’t need to understand it I just need the bot to qualify it as intent problem to be able after this to execute action_sendintentproblem and then utter_problem_site. The bot answer for this intent is general. no matter what is the content of this intent.

I want my bot when listening to the user after Utter_step1 to know that the next input will be intent ‘probleme’, can I specify this in my data.md file? or do I need to add this in the configuration file and how?

Thank you for your help

asked Nov 28 '18 at 10:29

chemssou

My first Idea to counter this is to tell the user to begin his sentance with : "the problem is: " and then in my data.md I declare an intent problem that contain : "the problem is:" But not sure if this will work always and then If I have a lot of these kind of intents I'll be asking the user each time to begin the sentance with something which is not good

– chemssou
Nov 28 '18 at 13:28

what kind of problems come under probleme intent? Are they specific health related issues that you are trying to capture?

– Srikar
Nov 30 '18 at 8:29

In fact it's about problems in management. It's in french but I'll try to give examples. One person can say: I can't find a way to make my project work. Another user will say: We don't communicate in our group. Another user will say: I have hard time with my employees, etc. And These are just examples that I came with, I don't know nothing about what a user could judge as problem for him

– chemssou
Nov 30 '18 at 11:07

One way is to treat it a default_fallback and then in the fallback action you could capture it and utter what you need and then fall back to the previous state.

– Srikar
Nov 30 '18 at 11:38

Thank you Srikar, can you please give an example on how to do this, or a documentation. I know what the default_fallback action is but I don't know how to use it as I want to. I'am new to this

– chemssou
Nov 30 '18 at 16:29

|
show 1 more comment

Need help for this one. I want to know how can I train my bot to predict the next intent according to what I have in stories.md.

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

* probleme

    - action_SendIntentProbleme

    - utter_probleme_site

Thank you for your help

asked Nov 28 '18 at 10:29

chemssou

My first Idea to counter this is to tell the user to begin his sentance with : "the problem is: " and then in my data.md I declare an intent problem that contain : "the problem is:" But not sure if this will work always and then If I have a lot of these kind of intents I'll be asking the user each time to begin the sentance with something which is not good

– chemssou
Nov 28 '18 at 13:28

what kind of problems come under probleme intent? Are they specific health related issues that you are trying to capture?

– Srikar
Nov 30 '18 at 8:29

In fact it's about problems in management. It's in french but I'll try to give examples. One person can say: I can't find a way to make my project work. Another user will say: We don't communicate in our group. Another user will say: I have hard time with my employees, etc. And These are just examples that I came with, I don't know nothing about what a user could judge as problem for him

– chemssou
Nov 30 '18 at 11:07

One way is to treat it a default_fallback and then in the fallback action you could capture it and utter what you need and then fall back to the previous state.

– Srikar
Nov 30 '18 at 11:38

Thank you Srikar, can you please give an example on how to do this, or a documentation. I know what the default_fallback action is but I don't know how to use it as I want to. I'am new to this

– chemssou
Nov 30 '18 at 16:29

|
show 1 more comment

Need help for this one. I want to know how can I train my bot to predict the next intent according to what I have in stories.md.

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

* probleme

    - action_SendIntentProbleme

    - utter_probleme_site

Thank you for your help

asked Nov 28 '18 at 10:29

chemssou

Need help for this one. I want to know how can I train my bot to predict the next intent according to what I have in stories.md.

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

* probleme

    - action_SendIntentProbleme

    - utter_probleme_site

Thank you for your help

rasa-nlu rasa-core

asked Nov 28 '18 at 10:29

chemssou

asked Nov 28 '18 at 10:29

chemssou

asked Nov 28 '18 at 10:29

chemssou

asked Nov 28 '18 at 10:29

chemssou

asked Nov 28 '18 at 10:29

chemssou

My first Idea to counter this is to tell the user to begin his sentance with : "the problem is: " and then in my data.md I declare an intent problem that contain : "the problem is:" But not sure if this will work always and then If I have a lot of these kind of intents I'll be asking the user each time to begin the sentance with something which is not good

– chemssou
Nov 28 '18 at 13:28

what kind of problems come under probleme intent? Are they specific health related issues that you are trying to capture?

– Srikar
Nov 30 '18 at 8:29

In fact it's about problems in management. It's in french but I'll try to give examples. One person can say: I can't find a way to make my project work. Another user will say: We don't communicate in our group. Another user will say: I have hard time with my employees, etc. And These are just examples that I came with, I don't know nothing about what a user could judge as problem for him

– chemssou
Nov 30 '18 at 11:07

One way is to treat it a default_fallback and then in the fallback action you could capture it and utter what you need and then fall back to the previous state.

– Srikar
Nov 30 '18 at 11:38

Thank you Srikar, can you please give an example on how to do this, or a documentation. I know what the default_fallback action is but I don't know how to use it as I want to. I'am new to this

– chemssou
Nov 30 '18 at 16:29

|
show 1 more comment

My first Idea to counter this is to tell the user to begin his sentance with : "the problem is: " and then in my data.md I declare an intent problem that contain : "the problem is:" But not sure if this will work always and then If I have a lot of these kind of intents I'll be asking the user each time to begin the sentance with something which is not good

– chemssou
Nov 28 '18 at 13:28

what kind of problems come under probleme intent? Are they specific health related issues that you are trying to capture?

– Srikar
Nov 30 '18 at 8:29

In fact it's about problems in management. It's in french but I'll try to give examples. One person can say: I can't find a way to make my project work. Another user will say: We don't communicate in our group. Another user will say: I have hard time with my employees, etc. And These are just examples that I came with, I don't know nothing about what a user could judge as problem for him

– chemssou
Nov 30 '18 at 11:07

One way is to treat it a default_fallback and then in the fallback action you could capture it and utter what you need and then fall back to the previous state.

– Srikar
Nov 30 '18 at 11:38

Thank you Srikar, can you please give an example on how to do this, or a documentation. I know what the default_fallback action is but I don't know how to use it as I want to. I'am new to this

– chemssou
Nov 30 '18 at 16:29

My first Idea to counter this is to tell the user to begin his sentance with : "the problem is: " and then in my data.md I declare an intent problem that contain : "the problem is:" But not sure if this will work always and then If I have a lot of these kind of intents I'll be asking the user each time to begin the sentance with something which is not good

– chemssou
Nov 28 '18 at 13:28

what kind of problems come under probleme intent? Are they specific health related issues that you are trying to capture?

– Srikar
Nov 30 '18 at 8:29

In fact it's about problems in management. It's in french but I'll try to give examples. One person can say: I can't find a way to make my project work. Another user will say: We don't communicate in our group. Another user will say: I have hard time with my employees, etc. And These are just examples that I came with, I don't know nothing about what a user could judge as problem for him

– chemssou
Nov 30 '18 at 11:07

One way is to treat it a default_fallback and then in the fallback action you could capture it and utter what you need and then fall back to the previous state.

– Srikar
Nov 30 '18 at 11:38

Thank you Srikar, can you please give an example on how to do this, or a documentation. I know what the default_fallback action is but I don't know how to use it as I want to. I'am new to this

– chemssou
Nov 30 '18 at 16:29

|
show 1 more comment

1 Answer
1

active

oldest

votes

You could use forms for this use case.

The story should look like:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

    - problem_form

    - form{"name": "problem_form"}

    - form{"name": null}

    - action_SendIntentProbleme

    - utter_probleme_site

In your domain file add:

intents:

  ...



slots:

  problem_message

    type: unfeaturized

  ...



forms:

  - problem_form



actions:

  - utter_ask_problem_message



templates:

  utter_ask_problem_message:

    text: "What is your problem?"

In your core policy configuration add the forms policy:

policies:

  - name: FormPolicy

  ...

And then have a form like:

from rasa_core_sdk.forms import FormAction



class ProblemForm(FormAction):

    """Accept free text input from the user for suggestions"""



    def name(self):

        return "problem_form"



    @staticmethod

    def required_slots(tracker):

        return ["problem_message"]



    def slot_mappings(self):

        return {"problem_message": self.from_text()}



    def submit(self, dispatcher, tracker, domain):

        return

This form will call utter_ask_problem_message until the slot is filled by the user. As we call self.from_text() the slot will be filled with the whole message.

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

|
show 3 more comments

Your Answer

StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});

}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53517297%2ftrain-rasa-core-to-predict-the-next-intent-according-to-stories-md%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

1 Answer
1

active

oldest

votes

1 Answer
1

active

oldest

votes

You could use forms for this use case.

The story should look like:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

    - problem_form

    - form{"name": "problem_form"}

    - form{"name": null}

    - action_SendIntentProbleme

    - utter_probleme_site

In your domain file add:

intents:

  ...



slots:

  problem_message

    type: unfeaturized

  ...



forms:

  - problem_form



actions:

  - utter_ask_problem_message



templates:

  utter_ask_problem_message:

    text: "What is your problem?"

In your core policy configuration add the forms policy:

policies:

  - name: FormPolicy

  ...

And then have a form like:

from rasa_core_sdk.forms import FormAction



class ProblemForm(FormAction):

    """Accept free text input from the user for suggestions"""



    def name(self):

        return "problem_form"



    @staticmethod

    def required_slots(tracker):

        return ["problem_message"]



    def slot_mappings(self):

        return {"problem_message": self.from_text()}



    def submit(self, dispatcher, tracker, domain):

        return

This form will call utter_ask_problem_message until the slot is filled by the user. As we call self.from_text() the slot will be filled with the whole message.

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

|
show 3 more comments

You could use forms for this use case.

The story should look like:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

    - problem_form

    - form{"name": "problem_form"}

    - form{"name": null}

    - action_SendIntentProbleme

    - utter_probleme_site

In your domain file add:

intents:

  ...



slots:

  problem_message

    type: unfeaturized

  ...



forms:

  - problem_form



actions:

  - utter_ask_problem_message



templates:

  utter_ask_problem_message:

    text: "What is your problem?"

In your core policy configuration add the forms policy:

policies:

  - name: FormPolicy

  ...

And then have a form like:

from rasa_core_sdk.forms import FormAction



class ProblemForm(FormAction):

    """Accept free text input from the user for suggestions"""



    def name(self):

        return "problem_form"



    @staticmethod

    def required_slots(tracker):

        return ["problem_message"]



    def slot_mappings(self):

        return {"problem_message": self.from_text()}



    def submit(self, dispatcher, tracker, domain):

        return

This form will call utter_ask_problem_message until the slot is filled by the user. As we call self.from_text() the slot will be filled with the whole message.

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

|
show 3 more comments

You could use forms for this use case.

The story should look like:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

    - problem_form

    - form{"name": "problem_form"}

    - form{"name": null}

    - action_SendIntentProbleme

    - utter_probleme_site

In your domain file add:

intents:

  ...



slots:

  problem_message

    type: unfeaturized

  ...



forms:

  - problem_form



actions:

  - utter_ask_problem_message



templates:

  utter_ask_problem_message:

    text: "What is your problem?"

In your core policy configuration add the forms policy:

policies:

  - name: FormPolicy

  ...

And then have a form like:

from rasa_core_sdk.forms import FormAction



class ProblemForm(FormAction):

    """Accept free text input from the user for suggestions"""



    def name(self):

        return "problem_form"



    @staticmethod

    def required_slots(tracker):

        return ["problem_message"]



    def slot_mappings(self):

        return {"problem_message": self.from_text()}



    def submit(self, dispatcher, tracker, domain):

        return

This form will call utter_ask_problem_message until the slot is filled by the user. As we call self.from_text() the slot will be filled with the whole message.

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

You could use forms for this use case.

The story should look like:

## story1

* greet

    - utter_greet

* confirm

    - utter_step1

    - problem_form

    - form{"name": "problem_form"}

    - form{"name": null}

    - action_SendIntentProbleme

    - utter_probleme_site

In your domain file add:

intents:

  ...



slots:

  problem_message

    type: unfeaturized

  ...



forms:

  - problem_form



actions:

  - utter_ask_problem_message



templates:

  utter_ask_problem_message:

    text: "What is your problem?"

In your core policy configuration add the forms policy:

policies:

  - name: FormPolicy

  ...

And then have a form like:

from rasa_core_sdk.forms import FormAction



class ProblemForm(FormAction):

    """Accept free text input from the user for suggestions"""



    def name(self):

        return "problem_form"



    @staticmethod

    def required_slots(tracker):

        return ["problem_message"]



    def slot_mappings(self):

        return {"problem_message": self.from_text()}



    def submit(self, dispatcher, tracker, domain):

        return

This form will call utter_ask_problem_message until the slot is filled by the user. As we call self.from_text() the slot will be filled with the whole message.

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

edited Dec 14 '18 at 13:47

answered Nov 28 '18 at 16:27

Tobias

590311

answered Nov 28 '18 at 16:27

Tobias

590311

answered Nov 28 '18 at 16:27

Tobias

590311

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

|
show 3 more comments

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it has nothing to loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:31

Yes I see, but the problem in my intent problem is that the user can realy say anything that come in mind. I can give 30 examples of intent problem and the one the user give will be very different. For my counter idea I know it loses the fact that I'am using an intellegent bot. But I didn't find another way to do it.

– chemssou
Nov 29 '18 at 8:41

@chemssou I now had a similar problem to yours, and solved it using forms. I edited my answer with the suggested solution.

– Tobias
Dec 14 '18 at 13:48

thank you very much

– chemssou
Dec 20 '18 at 13:18

You're welcome :-) please accept the answer as correct if this did help you so that other users can find it.

– Tobias
Dec 20 '18 at 14:54

|
show 3 more comments

draft saved

draft discarded

Thanks for contributing an answer to Stack Overflow!

Please be sure to answer the question. Provide details and share your research!

But avoid …

Asking for help, clarification, or responding to other answers.

Making statements based on opinion; back them up with references or personal experience.

To learn more, see our tips on writing great answers.

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Name

Required, but never shown

Name

Required, but never shown

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Btukfyl