Query response device

A query response device comprising:

• an input adapted to receive user queries;
• a memory adapted to store one or more routing rules;
• one or more live agent engines configured to support interactions with one or more live agents;
• one or more virtual assistant engines configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module;
• and
• a routing module coupled to said one or more live agent engines and to said one or more virtual assistant engines, the routing module comprising a processing device configured:
• to select, based on content of at least a first user message, from a first user and relating to a first user query, and based on said one or more routing rules, a first live agent engine, of said one or more live agent engines, or a first virtual assistant engine of said one or more virtual assistant engines, as a selected engine, and
• to route one or more further user messages relating to the first user query to the selected engine,
• wherein, when the selected engine is the first live agent engine, the processing device is further configured to:
• intercept one or more messages between the first live agent engine and the first user, and
• supply content of the one or more intercepted messages to a machine learning module in order to modify capabilities of the artificial intelligence module,
• wherein said one or more routing rules are based on a presence of keywords in the at least the first user message, the presence of said keywords in said at least one first user message indicating either:
• that the one or more further user messages are related to the first user query should be routed to said first virtual assistant engine;
• or
• that the one or more further user messages are related to the first user query should be routed to said first live agent engine,
• wherein each of said keywords is associated with a significance level determining a likelihood of a live agent engine being selected by the routing module, and
• wherein the machine learning module is adapted to modify the significance level of at least one keyword, of said keywords, based on the content of the one or more intercepted messages.

A method of processing, by a query response device, a user query, the method comprising:

• receiving a first user message relating to a first user query from a first user at an input of said query response device;
• selecting, by a processing device of a routing module, based on content of said first user message, based on one or more routing rules stored in a memory, and as a selected engine, either:
• a first live agent engine of one or more live agent engines configured to support interactions with one or more live agents;
• or
• a first virtual assistant engine of one or more virtual assistant engines configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module;
• and
• routing, by said routing module, one or more further user messages relating to said first user query to the selected engine,
• wherein, when the selected engine is the first live agent engine, the method further comprises:
• intercepting one or more messages between the first live agent engine and the first user;
• and
• supplying content of the one or more intercepted messages to a machine learning module in order to modify capabilities of the artificial intelligence module, and
• wherein, when the selected engine is the first virtual assistant engine, the method further comprises:
• inviting one of the one or more live agent engines to communicate with the first user following N further messages between the first user and the first virtual assistant engine,
• where N is a positive integer,
• wherein the method further comprises:
• determining a value of N based on a content of one or more of the further messages and based on a user satisfaction threshold.

A method comprising:

• receiving a first user message relating to a first user query from a first user at an input of a query response device;
• selecting, by a processing device of a routing module, based on content of said first user message, based on one or more routing rules stored in a memory, and as a selected engine, either:
• a first live agent engine of one or more live agent engines configured to support interactions with one or more live agents;
• or
• a first virtual assistant engine of one or more virtual assistant engines configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module;
• and
• routing, by said routing module, one or more further user messages relating to said first user query to the selected engine,
• wherein, when the selected engine is the first live agent engine, the method further comprises:
• intercepting one or more messages between the first live agent engine and the first user;
• and
• supplying content of the one or more intercepted messages to a machine learning module in order to modify capabilities of the artificial intelligence module,
• wherein said one or more routing rules are based on a presence of keywords in at least the first user message, the presence of said keywords in said first user message indicating either:
• that the one or more further user messages are related to the first user query should be routed to said first virtual assistant engine;
• or
• that the one or more further user messages are related to the first user query should be routed to said first live agent engine,
• wherein each of said keywords is associated with a significance level determining a likelihood of a live agent engine being selected by the routing module,
• the method further comprising:
• modifying, by the machine learning module, the significance level of at least one keyword, of the keywords, based on the content of the one or more intercepted messages.

A non-transitory computer-readable storage medium storing instructions, the instructions comprising:

• one or more instructions that, when executed by a query response device, cause the query response device to:
• receive a first user message relating to a first user query from a first user at an input of the query response device;
• select, based on content of at least said first user message, based on one or more routing rules stored in a memory, and as a selected engine, either:
• a first live agent engine of one or more live agent engines configured to support interactions with one or more live agents;
• or
• a first virtual assistant engine of one or more virtual assistant engines configured to support interactions with one or more virtual assistants instantiated by an artificial intelligence module;
• and
• route one or more further user messages relating to said first user query to the selected engine,
• wherein, when the selected engine is the first live agent engine, the instructions further comprise:
• one or more instructions that, when executed by the query response device, cause the query response device to:
• intercept one or more messages between the first live agent engine and the first user, and
• supply content of the one or more intercepted messages to a machine learning module in order to modify capabilities of the artificial intelligence module,
• wherein, when the selected engine is the first virtual assistant engine, the instructions further comprise:
• one or more instructions that, when executed by the query response device, cause the query response device to:
• invite one of the one or more live agent engines to communicate with the first user following N further messages between the first user and the first virtual assistant engine,
• where N is a positive integer,
• wherein the instructions further comprise:
• one or more instructions that, when executed by the query response device, cause the query response device to:
• determine a value of N based on a content of one or more of the further messages and based on a user satisfaction threshold.