Chatbot orchestration
Utilizing a computing device executing a master chatbot and one or more modular chatbots to respond to one or more chat messages. A computing device executing the master chatbot receives one or more chat messages. The computing device parses the received one or more chat messages to discover an intent and entities contained within the chat messages. A ranking algorithm is employed to rank the master chatbot and a plurality of modular chatbots, the ranking algorithm scoring the master chatbot and the plurality of modular chatbots based upon the intent and entities contained within the one or more chat messages. The master chatbot responds to the chat message if the ranking algorithm rates the master chatbot highest or forwards automatically the one or more chat messages to a ranked modular chatbot for response if the ranking algorithm rates the ranked modular chatbot highest.
1. A method of utilizing a computing device executing chatbots to initiate and hold a conversation in chat messaging software between the computing device and a user of a website, the chatbots comprise a master chatbot and a plurality of modular chatbots, the method comprising:
receiving, by the computing device, one or more chat messages from the user in the chat messaging software;
parsing, by the computing device, the received one or more chat messages to discover an intent of the one or more chat messages and one or more entities contained within the one or more chat messages;
employing a ranking algorithm to rank the chatbots, the ranking algorithm scoring the chatbots based upon the intent of the one or more chat messages and the one or more entities contained within the one or more chat messages;
presenting a list of top-ranked chatbots from the ranked chatbots for selection by the user within a timeframe;
determining a user selected chatbot among the list of top-ranked chatbots, and forwarding the one or more chat messages to the user selected chatbot;
in response to the timeframe expiring, selecting the highest ranked chatbot among the list of top-ranked chatbots, and forwarding automatically the one or more chat messages to the selected highest ranked chatbot; and
responding, by either the user selected chatbot or the selected highest ranked chatbot, to the one or more chat messages.
2. The method of claim 1 , wherein the top-ranked chatbot is ranked by the ranking algorithm.
3. The method of claim 1 , wherein the ranking algorithm ranks the master chatbot and the plurality of modular chatbots based upon the intent of the one or more chat messages and the one or more entities contained within the one or more chat messages and according to one or more of the following:
a historical record of achieving satisfaction by each of the master chatbot and the plurality of modular chatbots from prior users regarding the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages;
a high similarity factor between the one or more chat messages and historical chat messages serviced by each of the master chatbot and the plurality of modular chatbots;
a high similarity factor regarding the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages versus a profile for each of the master chatbot and the plurality of modular chatbots; and
a ranking based upon recommendations from chatbot to chatbot among the master chatbot and the plurality of modular chatbots regarding the intent and one or more entities.
4. The method of claim 1 , wherein the master chatbot and the plurality of modular chatbots function as peers in a peer-to-peer network.
5. The method of claim 4 , further comprising after determining that the master chatbot is not capable of responding to the one or more received chat messages, performing the following steps of:
issuing by the master chatbot a request on the peer-to-peer network for a subset of the plurality of modular chatbots capable of serving the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages;
receiving responses from the subset of the plurality of modular chatbots indicating they are capable; and
validating the one or more of the subset of the plurality of modular chatbots are capable of serving the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages.
6. The method of claim 1 , wherein the one or more chat messages comprise selectively one of the following: a text message, a vocal message, and an image.
7. A method of utilizing a computing device executing a master chatbot and a plurality of modular chatbots to initiate and hold a conversation in chat messaging software between the computing device and a user of a website, the method comprising:
receiving by a computing device executing a master chatbot one or more chat messages from the user in the chat messaging software;
parsing by the computing device the received one or more chat messages to discover an intent of the one or more chat messages and one or more entities contained within the one or more chat messages;
employing a ranking algorithm to rank the master chatbot and the plurality of modular chatbots, the ranking algorithm scoring the master chatbot and the plurality of modular chatbots based upon the intent of the one or more chat messages and the one or more entities contained within the one or more chat messages, wherein the master chatbot and the plurality of modular chatbots function as peers in a peer-to-peer network;
after determining that the master chatbot is not capable of responding to the one or more received chat messages, performing the following steps of:
issuing by the master chatbot a request on the peer-to-peer network for a subset of the plurality of modular chatbots capable of serving the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages,
receiving responses from the subset of the plurality of modular chatbots indicating they are capable, and
validating the one or more of the subset of the plurality of modular chatbots are capable of serving the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages;
determining a top-ranked chatbot among the plurality of modular chatbots; and
responding in the chat messaging software by the top-ranked chatbot to the one or more chat messages.
8. The method of claim 7 , wherein the top-ranked chatbot is ranked by the ranking algorithm.
9. The method of claim 7 , wherein the ranking algorithm ranks the master chatbot and the plurality of modular chatbots based upon the intent of the one or more chat messages and one or more entities contained within the one or more chat messages and according to one or more of the following:
a historical record of achieving satisfaction by each of the master chatbot and the plurality of modular chatbots from prior users regarding the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages;
a high similarity factor between the one or more chat messages and historical chat messages serviced by each of the master chatbot and the plurality of modular chatbots;
a high similarity factor regarding the intent of the one or more received chat messages and the one or more entities contained within the one or more chat messages versus a profile for each of the master chatbot and the plurality of modular chatbots; and
a ranking based upon recommendations from chatbot to chatbot among the master chatbot and the plurality of modular chatbots regarding the intent and one or more entities.
10. The method of claim 7 , wherein the one or more chat messages comprise selectively one of the following: a text message, a vocal message, and an image.