Creating a digital assistant
View Patent ↗A query-processing system processes an input audio stream that represents a succession of queries spoken by a user. The query-processing system listens continuously to the input audio stream, parses queries and takes appropriate actions in mid-stream. In some embodiments, the system processes queries in parallel, limited by serial constraints. In some embodiments, the system parses and executes queries while a previous query's execution is still in progress. To accommodate users who tend to speak slowly and express a thought in separate parts, the query-processing system halts the outputting of results corresponding to a previous query if it detects that a new speech utterance modifies the meaning of the previous query.
1 . A method for creating a digital assistant, comprising:
in response to receiving a request for creating a digital assistant, presenting a first configuration area for receiving settings information for the digital assistant to be created and a second configuration area for receiving processing component information for at least one processing component;
providing guidance information for guiding a first user to provide the settings information for creating the digital assistant, the guidance information comprising a template for the settings information;
receiving, from the first user, the settings information expressed in a natural language, the settings information being configured to generate one or more prompts for providing instructions to a model to be called by the digital assistant; and
creating the digital assistant based on the settings information, wherein the digital assistant is to be published and is configured to determine, in response to receipt of a user input from a second user, a response to the user input based on output of the model,
wherein the settings information comprises at least one of:
a definition of a response style of the digital assistant,
a description of functions to be supported by the digital assistant,
a definition of at least one workflow of the digital assistant, or
a definition of at least one response format of the digital assistant,
wherein the settings information further comprises one or more constraints on the response of the digital assistant, and the one or more constraints comprise at least one of: a constraint on a response topic, a constraint on a number of words in the response, or a constraint on a word prohibited for use by the digital assistant.
2 . The method of claim 1 , wherein the settings information further comprises a response language of the digital assistant.
3 . The method of claim 1 , wherein the settings information comprises: an identification of a repository for defining a response style of the digital assistant, the repository comprising language data that matches the response style.
4 . The method of claim 1 , wherein the guidance information comprises at least one of: a description of the settings information, or an example of the settings information.
5 . An electronic device comprising:
at least one processing unit; and
at least one memory, the at least one memory being coupled to the at least one processing unit and being configured to store instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform operations comprising:
in response to receiving a request for creating a digital assistant, presenting a first configuration area for receiving settings information for the digital assistant to be created and a second configuration area for receiving processing component information for at least one processing component;
providing guidance information for guiding a first user to provide the settings information for creating the digital assistant, the guidance information comprising a template for the settings information;
receiving, from the first user, the settings information expressed in a natural language, the settings information being configured to generate one or more prompts for providing instructions to a model to be called by the digital assistant; and
creating the digital assistant based on the settings information, wherein the digital assistant is to be published and is configured to determine, in response to receipt of a user input, a response to the user input based on output of the model,
wherein the settings information comprises at least one of:
a definition of a response style of the digital assistant,
a description of functions to be supported by the digital assistant,
a definition of at least one workflow of the digital assistant, or
a definition of at least one response format of the digital assistant,
wherein the settings information further comprises one or more constraints on the response of the digital assistant, and the one or more constraints comprise at least one of: a constraint on a response topic, a constraint on a number of words in the response, or a constraint on a word prohibited for use by the digital assistant.
6 . The device of claim 5 , wherein the settings information further comprises a response language of the digital assistant.
7 . The device of claim 5 , wherein the settings information comprises: an identification of a repository for defining a response style of the digital assistant, the repository comprising language data that matches the response style.
8 . The device of claim 5 , wherein the guidance information comprises at least one of: a description of the settings information, or an example of the settings information.
9 . A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform operations comprising:
in response to receiving a request for creating a digital assistant, presenting a first configuration area for receiving settings information for the digital assistant to be created and a second configuration area for receiving processing component information for at least one processing component;
providing guidance information for guiding a first user to provide the settings information for creating the digital assistant, the guidance information comprising a template for the settings information;
receiving, from the first user, the settings information expressed in a natural language, the settings information being configured to generate one or more prompts for providing instructions to a model to be called by the digital assistant; and
creating the digital assistant based on the settings information, wherein the digital assistant is to be published and is configured to determine, in response to receipt of a user input, a response to the user input based on output of the model,
wherein the settings information comprises at least one of:
a definition of a response style of the digital assistant,
a description of functions to be supported by the digital assistant,
a definition of at least one workflow of the digital assistant, or
a definition of at least one response format of the digital assistant,
wherein the settings information further comprises one or more constraints on the response of the digital assistant, and the one or more constraints comprise at least one of: a constraint on a response topic, a constraint on a number of words in the response, or a constraint on a word prohibited for use by the digital assistant.
10 . The medium of claim 9 , wherein the settings information further comprises a response language of the digital assistant.
11 . The medium of claim 9 , wherein the settings information comprises: an identification of a repository for defining a response style of the digital assistant, the repository comprising language data that matches the response style.
12 . The medium of claim 9 , wherein the guidance information comprises at least one of: a description of the settings information, or an example of the settings information.