Chat communication support assistants

1. A computer-implemented communication support method comprising:

receiving an indication that a communication support assistant is available, the communication support assistant trained to detect a conversational triggering condition;

identifying retraining data comprising a plurality of past communications labeled with indications of whether the conversational triggering condition is present in the plurality of past communications;

updating a machine-learned discriminator model using the identified retraining data;

analyzing a second plurality of past communications between a first communication participant and other communication participants;

determining, using the machine-learned discriminator model, that the conversational triggering condition detected by the communication support assistant occurs in the second plurality of past communications at a rate that is above a threshold; and

providing a suggestion, in a graphical user interface, that the first communication participant activate the communication support assistant.

2. The computer-implemented communication support method of claim 1 , wherein activating the communication support assistant comprises:

downloading a plug-in containing the communication support assistant; and

activating the plug-in.

3. The computer-implemented communication support method of claim 1 , wherein the conversational triggering condition is a condition related to content and meaning of a communication.

4. The computer-implemented communication support method of claim 3 , wherein the conversational triggering condition includes at least one of use of impersonal language, use of informal language, use of disrespectful language, lack of responsiveness to upsell opportunities, or language that indicates the first communication participant is not familiar with a particular product.

5. The computer-implemented communication support method of claim 1 , further comprising:

receiving a communication from the first communication participant and to a second communication participant, prior to a transmission of the communication to the second communication participant;

determining, using the communication support assistant, at least one corrective action, the at least one corrective action including a change to a content of the communication;

causing a graphical user interface to be displayed to the first communication participant, the graphical user interface including a selectable control and the at least one corrective action;

receiving an indication that the selectable control has been selected by the first communication participant;

responsive to receiving the indication that the selectable control has been selected, modifying the communication in accordance with the at least one corrective action; and

transmitting the modified communication to the second communication participant.

6. The computer-implemented communication support method of claim 5 , further comprising:

determining, using a plurality of communications occurring subsequent to the transmitting the modified communication to the second communication participant, that the communication support assistant has provided fewer corrective actions than a second threshold number of corrective actions over a predetermined time period; and

responsive to determining that the communication support assistant has provided fewer corrective actions than the second threshold number of corrective actions over a predetermined time period, recommending, in a user interface, that the first communication participant deactivate the communication support assistant.

7. The computer-implemented communication support method of claim 1 , further comprising:

receiving a communication from the first communication participant and to a second communication participant, prior to a transmission of the communication to the second communication participant;

determining, using a second communication support assistant, at least one corrective action, the at least one corrective action including a referral to another agent;

causing a graphical user interface to be displayed to the first communication participant, the graphical user interface including a selectable control and the at least one corrective action;

receiving an indication that the selectable control has been selected by the first communication participant;

responsive to receiving the indication that the selectable control has been selected, connecting the another agent into a communication conversation between the first communication participant and the second communication participant.

8. A computer-implemented communication support method comprising:

receiving a selection of a communication support assistant, the communication support assistant trained to detect a conversational triggering condition;

identifying training data comprising a first plurality of past communications labeled with indications from the communication support assistant indicating whether the conversational triggering condition occurred in respective communications of the first plurality of past communications and a threshold;

training, using the identified training data, a machine learning model to determine whether the conversational triggering condition was detected by the communication support assistant in communications at a rate that traverses the threshold; and

outputting the trained machine learning model.

9. The computer-implemented communication support method of claim 8 , wherein the conversational triggering condition is a condition related to content and meaning of a communication.

10. The computer-implemented communication support method of claim 9 , wherein the conversational triggering condition is at least one of use of impersonal language, use of informal language, use of disrespectful language, lack of responsiveness to upsell opportunities, or language that indicates a first communication participant is not familiar with a particular product.

11. The computer-implemented communication support method of claim 8 , further comprising:

identifying updated training data including a third plurality of past communications labeled with indications of whether the conversational triggering condition occurred in respective communications of the third plurality of past communications;

updating the machine learning model using the identified updated training data.

12. A computer-implemented communication support method comprising:

receiving an indication of a first conversational trigger condition;

identifying first training data including a first plurality of past communications labeled with indications of whether the conversational trigger condition occurred in the first plurality of past communications;

training, using the identified first training data, a first communication support assistant to indicate the first conversational trigger condition occurred;

receiving an indication of a second conversational trigger condition;

identifying second training data including a second plurality of past communications labeled with indications of whether the second conversational trigger condition occurred in the second plurality of past communications;

training, using the identified second training data, a second communication support assistant to indicate the second conversational trigger condition occurred; and

outputting the first communication support assistant and the second communication support assistant.

13. The computer-implemented communication support method of claim 12 , further comprising:

analyzing a third plurality of past communications involving a first communication participant;

determining, using a machine learning trained model, that the first conversational trigger condition or the second conversational trigger condition occurred in the third plurality of past communications at a rate above a threshold;

in response to the determination, activating the first communication support assistant or the second communication support assistant.

14. The computer-implemented communication support method of claim 13 , further comprising:

responsive to determining that the first conversational trigger condition and the second conversational trigger condition occurred in the plurality of past communications at the rate above the threshold, activating the first communication support assistant and the second communication support assistant.

15. The computer-implemented communication support method of claim 14 , further comprising:

receiving a communication from a first communication participant and to a second communication participant;

monitoring the communication for the first conversational trigger condition using the first communication support assistant; and

monitoring the communication for the second conversational trigger condition using the second communication support assistant.

16. The computer-implemented communication support method of claim 15 , wherein monitoring the communication for the first conversational trigger condition using the first communication support assistant includes:

downloading a plug-in containing the first communication support assistant; and

activating the plug-in.

17. The computer-implemented communication support method of claim 12 , wherein the first conversational trigger condition is a condition related to content and meaning of a communication.

18. The computer-implemented communication support method of claim 12 , wherein the first conversational trigger condition is one of: use of impersonal language, use of informal language, use of disrespectful language, lack of responsiveness to upsell opportunities, or language that indicates a first communication participant is not familiar with a particular product.