Systems and methods for identifying a behavioral target during a conversation
A conversation may be monitored in real time using a trained machine learning model. This real-time monitoring may detect attributes of a conversation, such as a conversation type, a state of a conversation, as well as other attributes that help specify a context of a conversation. Contextually appropriate behavioral targets may be provided by machine learning model to an agent participating in a conversation. In some embodiments, these “behavioral targets” are identified by applying a set of rules to the contemporaneously identified conversation attributes. The behavioral targets may be defined in advance prior to the start of a conversation. In this way, the machine learning model may be trained to associate particular behavioral target(s) with one or more conversation attributes (or collections of attributes). This facilitates the real-time monitoring of a conversation and contemporaneous guidance of an agent with machine-identified behavioral targets.
1. One or more non-transitory computer-readable media storing instructions, which when executed by one or more hardware processors, cause performance of operations comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation, wherein applying the set of guidance rules to the detected attributes comprises determining a current conversation state based on the attributes of the conversation;
associating at least one behavioral opportunity with the behavioral target;
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
identifying a threshold number of actions associated with the at least one behavioral opportunities as having been performed; and
responsive to the threshold number of actions being performed, identifying the behavioral target as completed.
2. The non-transitory computer-readable media of claim 1 , wherein the behavioral target includes an objective within a conversation to be accomplished by one or more statements corresponding to, but different, from the behavioral target.
3. The non-transitory computer-readable media of claim 1 , wherein the attributes of a conversation comprise one or more of a conversation type, at least one keyword, at least one key phrase, or conversation metadata.
4. The non-transitory computer-readable media of claim 1 , further comprising determining a target conversation state subsequent to the current conversation state.
5. The non-transitory computer-readable media of claim 1 , further comprising presenting a confirmation identifying the behavioral target as completed.
6. The non-transitory computer-readable media of claim 1 , wherein the threshold number of actions is based on one or more of (1) a threshold ratio of completed actions divided by total detected opportunities or (2) an absolute number of completed actions.
7. The non-transitory computer-readable media of claim 1 , wherein the behavioral target is a first behavioral target, and the operations further comprise identifying a second behavioral target upon completion of the first behavioral target.
8. The non-transitory computer-readable media of claim 1 , wherein monitoring the conversation comprises monitoring a verbal exchange or a text exchange.
9. The non-transitory computer-readable media of claim 1 , wherein the operations further comprise selecting the set of guidance rules, from a plurality of rules, based on user attributes.
10. The non-transitory computer-readable media of claim 1 , wherein applying the set of guidance rules further comprises generating a user-specific set of guidance rules for the attributes of the conversation, the user-specific set of guidance rules based on at least one prior conversation conducted by a user, the prior conversation having at least one prior attribute in common with the conversation.
11. The non-transitory computer-readable media of claim 1 , wherein the behavioral target corresponding to the conversation can be established by two or more statements transmitted during the conversation, the two or more statements corresponding to a set of one or more opportunities associated with the behavioral target.
12. The non-transitory computer-readable media of claim 1 , wherein presenting the suggestion comprises presenting a prompt that is (a) separate from the behavioral target, and (b) helps reach the behavioral target.
13. The non-transitory computer-readable media of claim 12 , further comprising determining a performance metric based on a ratio of a number of prompts followed during the conversation divided by a total number of presented prompts.
14. The non-transitory computer-readable media of claim 1 , further comprising determining a performance metric based on a ratio of a number of behavioral targets completed divided by a number of detected behavioral opportunities.
15. The non-transitory computer-readable media of claim 14 , further comprising presenting the performance metric for evaluation.
16. The non-transitory computer-readable media of claim 1 , wherein presenting the suggestion is in response to determining that the behavioral target has not been met.
17. One or more non-transitory computer-readable media storing instructions, which when executed by one or more hardware processors, cause performance of operations comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation; and
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
wherein presenting the suggestion further comprises selecting a time to present the suggestion based on presentation criteria associated with the conversation; and
wherein the presentation criteria comprise one or more of a typing rate, a speaking rate, or a number of open windows.
18. The non-transitory computer-readable media of claim 1 , further storing instructions that cause training of a machine learning model for one or both of detecting conversation attributes and applying the set of guidance rules to identify the behavioral target, the training using one or more of: a set of policies based on keywords and key phrases, an elapsed time of a conversation, or a neural network.
19. The non-transitory computer-readable media of claim 1 , wherein the operations further comprise selecting the set of guidance rules, from a plurality of rules, based on conversation characteristics.
20. The non-transitory computer-readable media of claim 19 , wherein the conversation characteristics comprise one or more of an industry, a product line, a customer profile.
21. The non-transitory computer-readable media of claim 1 , wherein presenting the suggestion based on the behavioral target comprises presenting direction to a user to achieve the behavioral target.
22. A method comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation, wherein applying the set of guidance rules to the detected attributes comprises determining a current conversation state based on the attributes of the conversation;
associating at least one behavioral opportunity with the behavioral target;
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
identifying a threshold number of actions associated with the at least one behavioral opportunities as having been performed; and
responsive to the threshold number of actions being performed, identifying the behavioral target as completed.
23. A system comprising:
at least one device including a hardware processor;
the system being configured to perform operations comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation, wherein applying the set of guidance rules to the detected attributes comprises determining a current conversation state based on the attributes of the conversation;
associating at least one behavioral opportunity with the behavioral target;
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
identifying a threshold number of actions associated with the at least one behavioral opportunities as having been performed; and
responsive to the threshold number of actions being performed, identifying the behavioral target as completed.
24. A method comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation; and
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
wherein presenting the suggestion further comprises selecting a time to present the suggestion based on presentation criteria associated with the conversation; and
wherein the presentation criteria comprise one or more of a typing rate, a speaking rate, or a number of open windows.
25. A system comprising:
at least one device including a hardware processor;
the system being configured to perform operations comprising:
monitoring a conversation to detect attributes of the conversation in real-time;
based on the attributes of the conversation, applying a set of guidance rules to the detected attributes of the conversation to identify a behavioral target for the conversation; and
presenting a suggestion based on the behavioral target corresponding to the attributes of the conversation;
wherein presenting the suggestion further comprises selecting a time to present the suggestion based on presentation criteria associated with the conversation; and
wherein the presentation criteria comprise one or more of a typing rate, a speaking rate, or a number of open windows.