When I created A Parameter and I assigned it to te entity called #sys.unit-information-name,
I keep getting this warning: *The annotated text 'diabetes' in training phrase 'show me results on diabetes' does not correspond to entity type '#sys.unit-information-name'. And as a result my chatbot does not give me the right result, basically it will just keep asking the question under the Prompts under the Action and parameters.
If I remove this parameter it works. But I want to use the parameter & Entity
Any Help
Thanks
The problem you are facing is because you are explicitly creating a parameter and adding the system entity #sys.unit-information-name. This entity is used to refer to information about units as per system Entities documentation.
Since you are referring to a disease “diabetes” as per your expression “show me results on diabetes”, this entity cannot be used to map diabetes or any other disease also. There is no system Entities for Diseases, so it's better that we create a custom entity defining most of the disease names.
When giving the training Phrases if the word matches with values defined in entity, then entity mapping for that word will be done and the response will be generated.
Related
I have the following custom entity named 'department'. The entity defines like below:
department [Define synonyms - checked]:
appliances| stove, washer, appliance has, appliance part, appliances, appliances department.
An intent uses this entity type (department) in training phrases. ML is enabled for the corresponding intent.
The issue:
when in the DF console I enter 'appliances department', DF does not evaluate the value as 'appliances' and set it to be equals to original value (appliances department). If I use other synonyms, the value is evaluated correctly.
Could you please help me to resolve this case.
Thank you in advance!
I have reproduced the entity, and it is working for me.
I believe that maybe Dialog Flow is seeing the synonym ‘appliances department’ as redundant since the value is ‘appliances’ and it is contained in the synonym list, as well.
Also, there is a possibility that the same value is being overlapped by other entities.
Since #sys.airport only exists for the default English locale, I want to create a custom entity that emulates it for other locales.
From what I've read here, you can put subentity types into the value fields, say, the system entity #sys.geo-city:city and a custom entity #usr.iata-code:iata, and it will match either one or the other.
But I don't understand how you would tell Dialogflow which city and which IATA code go together, so that Dialogflow (ES) would know to send the complete object {"city":"Amsterdam", "iata": "AMS"} to the webhook after matching either "Amsterdam" or "AMS", as it does happen with #sys.airport.
Thanks for any input!
It will be difficult to create a custom entity that works just like #sys.airport. The #sys entities are special and can do somethings custom entities can't, for instance, pairing values together.
As you pointed out, you can put multiple entities together in one single entity by using Composite Entities, but the only thing this does is allow you to recognize two values made up from other #sys or custom entities in a single entity. It doesn't give you the option to create pairs between the values of the entities.
If you would want to create something like this, you would need some code that does a look up in a dictionary or list. So when "AMS" is matched, the code fills in the missing property "Amsterdam" or vice versa.
I want to create an entity that has any value except the values that are defined in another entity.
For example, i have an entity that contains all the possible products categories that i use in the bot, and if the user type a value that is not in that entity i want to react in some way.
It's like a fallback but only triggered when that condition is met.
Any suggestion?
Entity extraction is based on some definite value that can be identified and separated. There should be some basic features defined for the agent to train on. Based on these trained features, the agent will look for an entity and extract it from the user's response.
If you have already defined an entity to look for, it will be extracted by the Dialogflow based on the training data. If there is nothing defined it will not be identified as an entity as the agent will be not sure what to look for.
So, what you can do is,
Make the entity (already defined) as not required. Uncheck the "required" checkbox in the Dialogflow.
Add the "#sys.any" in the Entity you defined and make it a composite Entity with the combination of your Entity and "#sys.any" something in the line of
Train your agent to look for this new Entity with your Basic Entity data and Anything else data.
Collect this in the webhook.
OR
You when you want to collect anything else, you can collect user utterance from the agent object and parse the data using Regex pattern of your choice.
I'm using dialogflow to let users query for keywords of my product and give them the value of those specific keywords.
But the problem is, when user's search for the synonyms of those keywords, which are already defined in my entity list.
Its HTTP call, returns me the root word, and not the synonym due to which I am not able to find the dropped words.
How do I retrieve the exact word which was fetched?
Please look at the screenshots below for better understanding
Look at the KPIs, as it fetched "Death Rate"
Look at parameters that are fetched, under KPIs, it is fetched as "Mortality"
Screenshot of my entities, Mortality has a synonym "Death Rate"
I need to fetch the exact keyword that is entered
I know, I can put each word in entities, with synonyms apart, but it is too vague for large amount of data. As there is restrictions in number of entities too
To fetch the keywords you just use your returned entities ($entity_name). To fetch the exact synonym matched you use $entity_name.original. What you see at the training phrases is the resolved value but if you check the JSON (from the diagnostic info, bottom right corner, you'll see that the entity that returns is the one defined.
following you example, my entity is named Mortality and one of the synonyms is 'death rate'. You can see the difference between the resolved value and the actual entity name being returned
In a JSF page I have to display the data from an entity.
This entity has some int fields which cannot be displayed directly but need to be translated into a descriptive string.
Between them some can have a limited number of values, others have lots of possible values (such as a wordlwide Country_ID) and deserve a table on the Db with the association (ID, description).
This latter case can easily be solved navigating via relationship from the original entity to the entity corresponding to the dictionary table (ID, description) but I don't want to introduce new entities just to solve translations form ID to description.
Besides another integer field has special needs: the hundred thousand number should be changed with a letter according to a rule such as 100015 -> A00015, 301023 -> C01023.
Initially I put the translation code inside the entity itself but I know the great limits and drawbacks of this solution.
Then I created a singletone (EntityTranslator) with all the methods to translate the different fields. For cases where the field values are a lot I put them inside a table which is loaded from the singletone and transformed in a TreeMap, otherwise the descriptions are in arrays inside the class.
In the ManagedBean I wrote a getter for EntityTranslator and inside the jsf I use quite long el statements like the following:
#{myManagedBean.entityTranslator.translateCountryID(myManagedBean.selectedEntity.countryID)}
I think the problem is quite general and I'm looking for a standard way to solve it but, as already stated, I don't want to create new 'stupid' entities only to associate an ID to a description, I think it is overkill.
Another possibility is the use of converters Object(Integer) <-> String but I'm more comfortable in having all the translation needs for an Entity inside the same class.
Your question boils down to the following simple line:
How can I display a field different from id of my entity in my view and how can I morph an integer field into something more meaningful.
The answer is that it depends on a situation.
If you solely want to input/output data, you don't need id at all apart from the possible view parameter like ?id=12345. In this case you can input/output anything you want in your view: the id is always there.
If you want to create a new entity most possibly you have a way of generating ids via JPA, or database, or elsehow besides the direct input from the user. In this situation you don't need to mess with ids as well.
If you want to use information on other entities like show user a dropdown box with e.g. a list of countries, you always have the option to separate label (let it be name) and value (let it be id), or even have a unique not null column containing the country name in your database table that will serve as a natural identifier. If you'd like to get data from the user using an input text field you always can create a converter that will do the job of transforming user input strings to actual entity objects.
Regarding the transformation of your integers, you've actually got several choices: the first one is to attach a converter for these fields that will roughly do 301023 -> C01023 and C01023 -> 301023 transformations, the second one is to write a custom EL function and the third one is to prepare the right model beforehand / do the transformations on-the-fly.