Systems and methods for configuring knowledge sets and AI algorithms for automated message exchanges
View Patent ↗Systems and methods for configuring AI algorithms and knowledge sets within an automated messaging system are providing. In some embodiments, a message is received. A subsection of text from the training message is selected. Likewise, a knowledge set is selected. The knowledge set includes probabilistic associations between a term and a category. The terms in the selected subsection of text are compared to the knowledge sets to generate insights and contexts. The insights enable the categorization of the training message. This categorization has an associated confidence value based upon how strongly the terms in the text subsection are associated with the category (per the selected knowledge set). A low confidence value causes the message to be a candidate for training (a training message). Once identified as a training message, it may be displayed to an AI developer for approval or rejection of the categorization. The probabilities of the associations within the knowledge sets are updated in response to these approvals and/or rejections.
1. In a computerized knowledge learning system, a method for configuring knowledge sets and AI algorithms, useful in association with an automated messaging system, the method comprising:
receiving at least one training message;
selecting a subsection of text from the at least one training message;
selecting a knowledge set from a plurality of knowledge sets for the selected subsection of text based upon user, industry, and service type, wherein each knowledge set includes probabilistic associations between a term and a category;
selecting an insight from a plurality of insights for the selected subsection of text based upon associations of the terms within the subsection of text given the selected knowledge set;
categorizing the training message based upon the insight;
receiving one of approval or rejection of the categorization; and
updating the probabilistic associations in response to the received approval or rejection to improve classification accuracy.
2. The method of claim 1 , wherein the training message is a textual message.
3. The method of claim 1 , wherein the categorization includes a confidence value, and wherein the confidence value is based on the probabilistic associations.
4. The method of claim 3 , wherein the training message is selected based upon a low confidence value.
5. The method of claim 1 , further comprising selecting a context from a plurality of contexts for the training message, wherein each context is a collection of documents with commonality.
6. The method of claim 1 , further comprising generating a new insight in the plurality of insights.
7. The method of claim 5 , further comprising generating a new context in the plurality of contexts.
8. The method of claim 1 , further comprising generating a new knowledge set in the plurality of knowledge sets.
9. The method of claim 8 , wherein each knowledge set is bound to at least one insight.
10. The method of claim 9 , further comprising editing the probabilistic associations within at least one knowledge set.
11. A system for configuring knowledge sets and AI algorithms, useful in association with an automated messaging system, the system comprising:
an AI trainer configured to:
receive a at least one training message;
select a subsection of text from the at least one training message;
select a knowledge set from a plurality of knowledge sets for the selected subsection of text based upon user, industry, and service type, wherein each knowledge set includes probabilistic associations between a term and a category;
select an insight from a plurality of insights for the selected subsection of text based upon associations of the terms within the subsection of text given the selected knowledge set;
categorize the training message based upon the insight;
receive one of approval or rejection of the categorization; and
update the probabilistic associations in response to the received approval or rejection to improve classification accuracy.
12. The system of claim 11 , wherein the training message is a textual message.
13. The system of claim 11 , wherein the categorization includes a confidence value, and wherein the confidence value is based on the probabilistic associations.
14. The system of claim 13 , wherein the training message is selected based upon a low confidence value.
15. The system of claim 11 , wherein the AI trainer is further configured to select a context from a plurality of contexts for the training message, wherein each context is a collection of documents with commonality.
16. The system of claim 1 , further comprising an insight manager configured to generate a new insight in the plurality of insights.
17. The system of claim 15 , further comprising a context manager configured to generate a new context in the plurality of contexts.
18. The system of claim 11 , further comprising a knowledge set manager configured to generate a new knowledge set in the plurality of knowledge sets.
19. The system of claim 18 , wherein each knowledge set is bound to at least one insight.
20. The system of claim 19 , wherein the knowledge set manager is further configured to edit the probabilistic associations within at least one knowledge set.