Automatic development of a service-specific chatbot

1. A computer-implemented method, comprising:

receiving a user input comprising a request to generate a service-specific chatbot on a chatbot development platform;

retrieving, by the chatbot development platform, a service descriptor file and a service metadata descriptor file associated with the service descriptor file from a remote database by using a service root uniform resource identifier of the service descriptor file, wherein the service descriptor file lists top-level data feeds that correspond to the service-specific chatbot requested by a user and the service descriptor file comprises a service that corresponds to the service-specific chatbot requested by the user and addresses of the top-level data feeds;

parsing the service descriptor file to obtain a capability and relevant service data associated with the service, wherein the capability comprises a query associated with the service and wherein the relevant service data comprises a vocabulary object in a corresponding data structure;

parsing the service metadata descriptor file to extract metadata information;

generating a service-specific language by mapping the metadata information extracted from the service metadata descriptor file to the vocabulary object extracted from the service descriptor file;

generating the service-specific chatbot with at least one object that is based on the capability and the service-specific language, wherein the at least one object comprises intents, expressions, and skills that correspond to the service, wherein the intents define contexts of the service, the expressions are organized in intents and constitute a knowledge of the service-specific chatbot, and the skills comprise conversational blocks executable to achieve a goal; and

providing the service-specific chatbot to the user through at least one channel to enable an interaction with the service-specific chatbot with a graphical user interface.

2. The computer-implemented method of claim 1 , wherein the service descriptor file is comprised of at least one programming language and comprises information for generating the service-specific chatbot.

3. The computer-implemented method of claim 1 , wherein generating the service-specific chatbot comprises:

for each capability described in the service descriptor file, generating an intent for the service-specific chatbot;

for each generated intent, generating at least one expression according to descriptions of the capability included in the service descriptor file;

for each generated intent, creating a skill, wherein the skill comprises an action and corresponding data that is extracted from the service descriptor file; and

generating a service-specific chatbot based on the intent, the at least one expression, and the skill.

4. The computer-implemented method of claim 1 , wherein the service-specific chatbot is stored in a cloud-computing environment.

5. The computer-implemented method of claim 1 , wherein the skills comprise:

at least one trigger, wherein whether to activate the skill is determined based on at least one condition defined in the at least one trigger;

at least one requirement that determines information the service-specific chatbot is required to retrieve from the user and a method to retrieve the information; and

at least one action that is performed by the service-specific chatbot when the at least one requirement is satisfied.

6. The computer-implemented method of claim 1 , wherein the at least one channel comprises chat platforms executing in web browsers or on mobile computing devices.

7. The computer-implemented method of claim 1 , wherein the service-specific chatbot can automatically adapt to a change of the service.

8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

receiving a user input comprising a request to generate a service-specific chatbot on a chatbot development platform;

retrieving, by the chatbot development platform, a service descriptor file and a service metadata descriptor file associated with the service descriptor file from a remote database by using a service root uniform resource identifier of the service descriptor file, wherein the service descriptor file lists top-level data feeds that correspond to the service-specific chatbot requested by a user and the service descriptor file comprises a service that corresponds to the service-specific chatbot requested by the user and addresses of the top-level data feeds;

parsing the service descriptor file to obtain a capability and relevant service data associated with the service, wherein the capability comprises a query associated with the service and wherein the relevant service data comprises a vocabulary object in a corresponding data structure;

parsing the service metadata descriptor file to extract metadata information;

generating a service-specific language by mapping the metadata information extracted from the service metadata descriptor file to the vocabulary object extracted from the service descriptor file;

generating the service-specific chatbot with at least one object that is based on the capability and the service-specific language, wherein the at least one object comprises intents, expressions, and skills that correspond to the service, wherein the intents define contexts of the service, the expressions are organized in intents and constitute a knowledge of the service-specific chatbot, and the skills comprise conversational blocks executable to achieve a goal; and

providing the service-specific chatbot to the user through at least one channel to enable an interaction with the service-specific chatbot with a graphical user interface.

9. The non-transitory, computer-readable medium of claim 8 , wherein the service descriptor file is comprised of at least one programming language and comprises information for generating the service-specific chatbot.

10. The non-transitory, computer-readable medium of claim 8 , wherein generating the service-specific chatbot comprises one or more instructions to:

for each capability described in the service descriptor file, generate an intent for the service-specific chatbot;

for each generated intent, generate at least one expression according to descriptions of the capability included in the service descriptor file;

for each generated intent, create a skill, wherein the skill comprises an action and corresponding data that is extracted from the service descriptor file; and

generate a service-specific chatbot based on the intent, the at least one expression, and the skill.

11. The non-transitory, computer-readable medium of claim 8 , wherein the service-specific chatbot is stored in a cloud-computing environment.

12. The non-transitory, computer-readable medium of claim 8 , wherein the wherein the skills comprise:

at least one trigger, wherein whether to activate the skill is determined based on at least one condition defined in the at least one trigger;

at least one requirement that determines information the service-specific chatbot is required to retrieve from the user and a method to retrieve the information; and

at least one action that is performed by the service-specific chatbot when the at least one requirement is satisfied.

13. The non-transitory, computer-readable medium of claim 8 , wherein the at least one channel comprises chat platforms executing in web browsers or on mobile computing devices.

14. The non-transitory, computer-readable medium of claim 8 , wherein the service-specific chatbot can automatically adapt to a change of the service.

15. A computer-implemented system, comprising:

one or more computers; and

one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:

receiving a user input comprising a request to generate a service-specific chatbot on a chatbot development platform;

retrieving, by the chatbot development platform, a service descriptor file and a service metadata descriptor file associated with the service descriptor file from a remote database by using a service root uniform resource identifier of the service descriptor file, wherein the service descriptor file lists top-level data feeds that correspond to the service-specific chatbot requested by a user and the service descriptor file comprises a service that corresponds to the service-specific chatbot requested by the user and addresses of the top-level data feeds;

parsing the service descriptor file to obtain a capability and relevant service data associated with the service, wherein the capability comprises a query associated with the service and wherein the relevant service data comprises a vocabulary object in a corresponding data structure;

parsing the service metadata descriptor file to extract metadata information;

generating a service-specific language by mapping the metadata information extracted from the service metadata descriptor file to the vocabulary object extracted from the service descriptor file;

generating the service-specific chatbot with at least one object that is based on the capability and the service-specific language, wherein the at least one object comprises intents, expressions, and skills that correspond to the service, wherein the intents define contexts of the service, the expressions are organized in intents and constitute a knowledge of the service-specific chatbot, and the skills comprise conversational blocks executable to achieve a goal; and

providing the service-specific chatbot to the user through at least one channel to enable an interaction with the service-specific chatbot with a graphical user interface.

16. The computer-implemented system of claim 15 , wherein generating the service-specific chatbot comprises one or more operations to:

for each capability described in the service descriptor file, generate an intent for the service-specific chatbot;

for each generated intent, generate at least one expression according to descriptions of the capability included in the service descriptor file;

for each generated intent, create a skill, wherein the skill comprises an action and corresponding data that is extracted from the service descriptor file; and

generate a service-specific chatbot based on the intent, the at least one expression, and the skill.

17. The computer-implemented system of claim 15 , wherein the service-specific chatbot is stored in a cloud-computing environment.

18. The computer-implemented system of claim 15 , wherein the wherein the skills comprise:

at least one trigger, wherein whether to activate the skill is determined based on at least one condition defined in the at least one trigger;

at least one requirement that determines information the service-specific chatbot is required to retrieve from the user and a method to retrieve the information; and

at least one action that is performed by the service-specific chatbot when the at least one requirement is satisfied.

19. The computer-implemented system of claim 15 , wherein the at least one channel comprises chat platforms executing in web browsers or on mobile computing devices.

20. The computer-implemented system of claim 15 , wherein the service-specific chatbot can automatically adapt to a change of the service.