Artificial intelligence conversation engine
Systems, methods, and devices of the various embodiments may provide an artificial intelligence (AI) conversation system, such as an AI driven virtual assistant, that can participate in automated conversations with users. The AI conversation system may be configured to respond to user inquiries or requests and implement conversations to achieve tasks.
1 . A method for automated conversations with users by an artificial intelligence (AI) conversation system, the method comprising:
receiving an N number of messages from a customer in a conversation, where N is a value greater than 1 and each of the N number of messages includes message text;
for each of the N number of messages:
applying to the received message text a topic category model that has been trained to compare a text feature vector of the message text and a set of topic category reference feature vectors determining a highest similarity topic category reference feature vector to the text feature vector;
determining a topic category represented by the highest similarity topic category reference feature vector;
applying to the received message text an intent model that has been trained to compare the text feature vector of the message text and a set of intent class reference feature vectors determining a highest similarity intent class reference feature vector to the text feature vector;
determining an intent class represented by the highest similarity intent class reference feature vector;
determining a requested intent for the message based at least in part on the message text using one or more machine learning models; and
storing the requested intent in a dataset associated with the customer;
receiving a new message from the customer in the conversation after receiving the N number of messages, the new message including received message text;
extracting, from the received message text, one or more entities included in the received message text;
determining a state of the conversation based at least in part on the new message;
predicting information based on the extracted one or more entities and the 1 to N requested intents stored in the dataset for use in a response to the received message text; and
constructing the response to the received message text based on the extracted one or more entities, the determined state of the conversation, the topic category, the intent class, and the predicted information.
2 . The method of claim 1 , wherein the extracted one or more entities comprise one or more general entities, one or more industry specific entities, or one or more learned entities.
3 . The method of claim 1 , further comprising:
determining whether a state change has occurred during the conversation based at least in part on a state change rule;
changing the conversation to a second state in response to determining that a state change has occurred; and
constructing another response based at least in part on the extracted one or more entities and the second state of the conversation.
4 . The method of claim 1 , wherein the conversation comprises one or more text messages and the received message text is one or more sentences of at least one of the one or more text messages.
5 . A conversation system, comprising:
a conversation engine configured to perform operations comprising:
receiving an N number of messages from a customer in a conversation, where N is a value greater than 1 and each of the N number of messages includes message text; for each of the N number of messages:
applying to the received message text a topic category model that has been trained to compare a text feature vector of the message text and a set of topic category reference feature vectors determining a highest similarity topic category reference feature vector to the text feature vector;
determining a topic category represented by the highest similarity topic category reference feature vector;
applying to the received message text an intent model that has been trained to compare the text feature vector of the message text and a set of intent class reference feature vectors determining a highest similarity intent class reference feature vector to the text feature vector;
determining an intent class represented by the highest similarity intent class reference feature vector;
determining a requested intent for the message based at least in part on the message text using one or more machine learning models; and
storing the requested intent in a dataset associated with the customer;
receiving a new message from the customer in the conversation after receiving the N number of messages, the new message including received message text;
extracting, from the received message text, one or more entities included in the received message text;
determining a state of the conversation based at least in part on the new message;
predicting information based on the extracted one or more entities and the 1 to N requested intents stored in the dataset for use in a response to the received message text; and
constructing the response to the received message text based on the extracted one or more entities, the determined state of the conversation, the topic category, the intent class, and the predicted information.
6 . The conversation system of claim 5 , wherein the conversation engine is configured to perform operations such that the extracted one or more entities comprise one or more general entities, one or more industry specific entities, or one or more learned entities.
7 . The conversation system of claim 5 , wherein the conversation engine is configured to perform operations further comprising:
determining whether a state change has occurred during the conversation based at least in part on a state change rule;
changing the conversation to a second state in response to determining that a state change has occurred; and
constructing another response based at least in part on the extracted one or more entities and the second state of the conversation.
8 . The conversation system of claim 5 , wherein the conversation comprises one or more text messages and the received message text is one or more sentences of at least one of the one or more text messages.
9 . A non-transitory processor-readable medium having stored thereon processor-executable instructions configured to cause a processor to perform operations comprising:
receiving an N number of messages from a customer in a conversation, where N is a value greater than 1 and each of the N number of messages includes message text;
for each of the N number of messages:
applying to the received message text a topic category model that has been trained to compare a text feature vector of the message text and a set of topic category reference feature vectors determining a highest similarity topic category reference feature vector to the text feature vector;
determining a topic category represented by the highest similarity topic category reference feature vector;
applying to the received message text an intent model that has been trained to compare the text feature vector of the message text and a set of intent class reference feature vectors determining a highest similarity intent class reference feature vector to the text feature vector;
determining an intent class represented by the highest similarity intent class reference feature vector;
determining a requested intent for the message based at least in part on the message text using one or more machine learning models; and
storing the requested intent in a dataset associated with the customer;
receiving a new message from the customer in the conversation after receiving the N number of messages, the new message including received message text;
extracting, from the received message text, one or more entities included in the received message text;
determining a state of the conversation based at least in part on the new message;
predicting information based on the extracted one or more entities and the 1 to N requested intents stored in the dataset for use in a response to the received message text; and
constructing the response to the received message text based on the extracted one or more entities, the determined state of the conversation, the topic category, the intent class, and the predicted information.
10 . The non-transitory processor-readable medium of claim 9 , wherein the stored processor-executable instructions are configured to cause a processor to perform operations such that the extracted one or more entities comprise one or more general entities, one or more industry specific entities, or one or more learned entities.
11 . The non-transitory processor-readable medium of claim 9 , wherein the stored processor-executable instructions are configured to cause a processor to perform operations further comprising:
determining whether a state change has occurred during the conversation based at least in part on a state change rule;
changing the conversation to a second state in response to determining that a state change has occurred; and
constructing another response based at least in part on the extracted one or more entities and the second state of the conversation.
12 . The non-transitory processor-readable medium of claim 9 , wherein the stored processor-executable instructions are configured to cause a processor to perform operations such that the conversation comprises one or more text messages and the received message text is one or more sentences of at least one of the one or more text messages.