System and method for dialogue tree generation

1. A method for constructing a deterministic dialogue tree for generating a chatbot, using a plurality of transcripts of interactions between a first party and a second party, the method comprising the steps of:

grouping similar phrases of phrases comprising the interactions from the first party of a cluster;

for each group of similar phrases:

computing a percentage of interaction of the cluster containing at least one phrase from the group of similar phrases;

determining whether the percentage exceeds a threshold occurrence rate; and

in response to determining that the percentage exceeds the threshold occurrence rate, generating an anchor corresponding to the group of similar phrases;

projecting the anchors onto the interactions of the cluster to represent the interactions as sequences of anchors;

computing dialogue flows by aligning the sequences of anchors representing the interactions of the clusters;

computing a topic-specific dialogue tree from the dialogue flows, wherein:

each node of the topic-specific dialogue tree corresponds to one of the anchors, and

each edge of the topic-specific dialogue tree connects a first node of the topic-specific dialogue tree to a second node of the topic-specific dialogue tree, and the edge corresponds to a plurality of keyphrases characterizing the customer phrases appearing, in the transcripts, in response to the first party phrases of the anchor corresponding to the first node and the first party phrases of the anchor corresponding to the second node are in response to the second party phrases of the edge; and

modifying the topic-specific dialogue tree to generate the deterministic dialogue tree;

outputting the chatbot, the chatbot being configured to use the deterministic dialogue tree to automatically generate responses to messages from a customer.

2. The method of claim 1 , further comprising:

displaying, on a user interface, respective labels of the clusters;

receiving a command to edit a label of the labels; and

updating the label of the labels in accordance with the command.

3. The method of claim 1 , wherein the modifying comprising pruning the topic-specific dialogue tree.

4. The method of claim 3 , wherein the pruning the topic-specific dialogue tree comprises:

identifying nodes of the topic-specific dialogue tree having at least two outgoing edges having overlapping customer phrases, each of the outgoing edges connecting a corresponding first node to a corresponding second node;

identifying one edge from among the at least two outgoing edges corresponding to sequences of first party phrases of the second nodes of the at least two outgoing edges most frequently observed in the transcripts of the cluster and identifying the remaining edges among the at least two outgoing edges; and

removing the remaining edges from the tropic-specific dialogue tree.

5. The method of claim 3 , wherein the pruning the topic-specific dialogue tree comprises:

identifying a first edge and second edge having overlapping customer phrases, the first edge corresponding to sequences of first party phrases most frequently observed in the transcripts of the cluster; and

removing the second edge.

6. The method of claim 1 , wherein the modifying the topic-specific dialogue tree comprises modifying the phrases characterizing a transition.

7. The method of claim 6 , wherein the modifying phrases comprises inserting phrases.

8. The method of claim 6 , wherein the modifying phrases comprises removing phrases.

9. The method of claim 1 , wherein the modifying the topic-specific dialogue tree comprises adding a new edge between two nodes.

10. The method of claim 4 , wherein the pruning of the topic-specific dialogue tree further comprises:

displaying the topic-specific dialogue tree on a user interface;

receiving, via the user interface, a command to modify the topic-specific dialogue tree; and

updating the topic-specific dialogue tree in accordance with the command.

11. The method of claim 5 , wherein the pruning of the topic-specific dialogue tree further comprises:

displaying the topic-specific dialogue tree on a user interface;

receiving, via the user interface, a command to modify the topic-specific dialogue tree; and

updating the topic-specific dialogue tree in accordance with the command.

12. A system comprising:

a processor; and

memory storing instructions that, when executed by the processor, cause the processor to construct a deterministic dialogue tree for generating a chatbot using a plurality of transcripts of interactions between a first party and a second party, including instructions that cause the processor to:

group similar phrases of phrases comprising the interactions from the first party of a cluster;

for each group of similar phrases:

compute a percentage of interaction of the cluster containing at least one phrase from the group of similar phrases;

determine whether the percentage exceeds a threshold occurrence rate; and

in response to determining that the percentage exceeds the threshold occurrence rate, generating an anchor corresponding to the group of similar phrases;

project the anchors onto the interactions of the cluster to represent the interactions as sequences of anchors;

compute dialogue flows by aligning the sequences of anchors representing the interactions of the clusters;

compute the topic-specific dialogue tree from the dialogue flows, wherein:

each node of the topic-specific dialogue tree corresponds to one of the anchors, and

each edge of the topic-specific dialogue tree connects a first node of the topic-specific dialogue tree to a second node of the topic-specific dialogue tree, and the edge corresponds to a plurality of keyphrases characterizing the customer phrases appearing, in the transcripts, in response to the first party phrases of the anchor corresponding to the first node and the first party phrases of the anchor corresponding to the second node are in response to the second party phrases of the edge; and

modify the topic-specific dialogue tree to generate a deterministic dialogue tree;

output the chatbot, the chatbot being configured to use the deterministic dialogue tree to automatically generate responses to messages from a customer.