Bank of America Corporation

Isaac Persing

Emad Noorizadeh

Ramakrishna R Yannam

Sushil Golani

Hari Gopalkrishnan

Dana Patrice Morrow Branch

Apparatus and methods for leveraging machine learning and artificial intelligence to generate a response to an utterance expressed by a user during an interaction between an interactive response system and the user is provided. The methods may include a natural language processor processing the utterance to output an utterance intent. The methods may also include a signal extractor processing the utterance, the utterance intent and previous utterance data to output utterance signals. The methods may additionally include an utterance sentiment classifier using a hierarchy of rules to extract, from a database, a label, the extracting being based on the utterance signals. The methods may further include a sequential neural network classifier using a trained algorithm to process the label and a sequence of historical labels to output a sentiment score. The methods may further include, based on the utterance intent, the label and the score, to output a response.

Methods and apparatus for leveraging machine learning for generating responses in an interactive response system

Aspects of the disclosure relate to using an apparatus for flagging and removing real time workflows that produce sub-optimal results. Such an apparatus may include an utterance sentiment classifier. The apparatus stores a hierarchy of rules. Each of the rules is associated with one or more rule signals. In response to receiving the one or more utterance signals, the classifier iterates through the hierarchy of rules in sequential order to identify a first rule for which the one or more utterance signals are a superset of the rule's one or more rule signals. In response to receiving the one or more alternate utterance signals from the signal extractor, the classifier may iterate through the hierarchy of rules in sequential order to identify the first rule in the hierarchy for which the one or more alternate utterance signals are a superset of the first rule's one or more rule signals.

Methods and apparatus for leveraging sentiment values in flagging and/or removal of real time workflows

Aspects of the disclosure relate to receiving a stateless application programming interface ('API') request. The API request may store an utterance, previous utterance data and a sequence of labels, each label in the sequence of labels being associated with a previous utterance expressed by a user during an interaction. The previous utterance data may, in certain embodiments, be limited to a pre-determined number of utterances occurring prior to the utterance. Embodiments process the utterance, using a natural language processor in electronic communication with the first processor, to output an utterance intent, a semantic meaning of the utterance and an utterance parameter. The utterance parameter may include words in the utterance and be associated with the intent. The natural language processor may append the utterance intent, the semantic meaning of the utterance and the utterance parameter to the API request. A signal extractor processor may append the plurality of utterance signals to the API request.

Methods and apparatus for leveraging an application programming interface ('API') request for storing a list of sentiment values in real time interactive response systems

Apparatus and methods for leveraging machine learning and artificial intelligence to assess a sentiment of an utterance expressed by a user during an interaction between an interactive response system and the user is provided. The methods may include a natural language processor processing the utterance to output an utterance intent. The methods may also include a signal extractor processing the utterance, the utterance intent and previous utterance data to output utterance signals. The methods may additionally include an utterance sentiment classifier using a hierarchy of rules to extract, from a database, a label, the extracting being based on the utterance signals. The methods may further include a sequential neural network classifier using a trained algorithm to process the label and a sequence of historical labels to output a sentiment score.

Multi-tier rule and AI processing for high-speed conversation scoring and selecting of optimal responses

Multi-tier rule and AI processing for high-speed conversation scoring

Methods for mapping intents to utterances using a three-tiered system is provided. Methods may include receiving a plurality of predetermined action-topic pairs and a plurality of predetermined intents. Methods may include mapping the plurality of predetermined action-topic pairs to the plurality of predetermined intents via a one-to-many mapping. Methods may include receiving a linguistic utterance at a first tier of the three-tiered system. Methods may include translating the linguistic utterance at the first tier of the three-tiered system. Methods may include mapping the textual representation to one or more action-topic pairs included in the plurality of action-topic pairs. The mapping may be executed at the second tier of the three-tiered system. Methods may include identifying one or more intents that correlate to the textual representation. The identifying may be executed at the third tier. The identifying may be based on the mapping between the action-topics pairs and the predetermined intents.

System for introducing scalability of an action-topic approach to deriving intents from utterances

A device configured to receive a data request comprising instructions for retrieving data. The device is further configured to input the instructions into a machine learning model that is configured to output a plurality of search token predictions for an entity based on the instructions. The device is further configured to generate a set of search query candidates based on the plurality of search token predictions. Each search query candidate comprises zero or more search tokens. The device is further configured to select a search query candidate based on a score that is associated with the search query candidate and to generate a search query using the search tokens from the selected search query candidate. The device is further configured to receive search results in response to sending the search query to the database and to output search results based on the search.

Growing community of inventors

Sierra Vista, AZ, United States of America

Isaac Persing