Intuit, Inc.

Alexander Zhicharevich

Oren Sar Shalom

Yair Horesh

Shlomi Medalion

Elik Sror

Yehezkel Shraga Resheff

Adi Shalev

Rami Cohen

Sigalit Bechler

Ido Meir Mintz

Noa Haas

Shir Meir Lador

Yonatan Ben-Simhon

Erez Katzenelson

Onn Bar

Shimon Shahar

Sheer Dangoor

Daniel Ben David

Liron Hayman

Zhewen Fan

Byungkyu Kang

Natalie Bar Eliyahu

Talia Tron

Shiomi Medalion

Kate Elizabeth Swift-Spong

Elad Shmidov

Yerucham Meir Berkowitz

Ido Farhi

Lior Tabori

Ariel Simhon

Liat Ben Porat Roda

Nitzan Gado

Tom Jacobe

Gal Keinan

A method including training, using training data including a first ontological hierarchical level, trained machine learning models (MLMs) to predict a first output type including a second ontological hierarchical level different than the first ontological hierarchical level. The method also includes generating instances of the first output type by executing the trained MLMs on unknown data including the first ontological hierarchical level. Outputs of the trained MLMs include the instances at the second ontological hierarchical level. The method also includes training, using the instances, a voting classifier MLM to predict a selected instance from the instances. The voting classifier MLM is trained to predict the selected instance to satisfy a criterion including a third ontological hierarchical level different than the first ontological hierarchal level and the second ontological hierarchical level.

Cross-hierarchical machine learning prediction

A processor may receive a request to display a user interface (UI) for a user account. The processor may determine a context for the UI from information specific to the user account. The processor may select one of a plurality of UI elements based on the determining. In some embodiments, the selecting may include evaluating a value function taking the information specific to the user account and information about the context as inputs. The processor may cause the UI including the selected one of the plurality of UI elements to be displayed in response to the request.

Automatic user interface customization based on machine learning processing

A method including extracting data from disparate data sources. The data includes data pairs including a corresponding data point and a corresponding time associated with the corresponding data point. The method also includes extracting insights from the data at least by identifying a trend in the data pairs. The method also includes forming a model vector including the insights and an additional attribute to the insights. The additional attribute characterizes the insights. The additional attribute includes at least user feedback including a user ranking of a ranked subset of the insights from a user. The method also includes inputting the model vector into a trained insight machine learning model to obtain a predicted ranking of the insights. The method also includes selecting, based on the predicted user ranking, a pre-determined number of insights to form predicted relevant insights. The method also includes reporting the predicted relevant insights.

Computer prediction of relevant data from multiple disparate sources

A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Methods and systems for generating problem description

Aspects of the present disclosure provide techniques for predicting content relevant to questions based on reference links. Embodiments include receiving a set of question and answer (Q/A) pairs and identifying a set of references in the set of Q/A pairs that link pairs of Q/A pairs of the set of Q/A pairs. Embodiments include identifying popular Q/A pairs of the set of Q/A pairs based on the set of references. The popular Q/A pairs may be referenced by a subset of the set of Q/A pairs and each respective Q/A pair of the subset of the set of Q/A pairs may comprise a respective question of a plurality of questions. Embodiments include training a model based on the plurality of questions, the popular Q/A pairs, and the set of references, to predict Q/A pairs of the set of Q/A pairs that are relevant to a given question.

Document similarity through reference links

Aspects of the present disclosure provide techniques for detecting sensitive information. Embodiments include determining a first likelihood that a record contains at least a given type of sensitive information using a first detection technique that involves providing one or more inputs to a machine learning model based on the record and receiving the first likelihood as an output from the machine learning model based on the one or more inputs. Embodiments include determining a second likelihood that the record contains at least the given type of sensitive information using a second detection technique comprising a search of the record. Embodiments include applying a policy to determine whether the record contains sensitive information based on the first likelihood and the second likelihood. Embodiments include performing one or more actions based on whether the record contains sensitive information.

Detecting sensitive information in records using context and decoys

A method may including obtaining a voice transcript corpus and a chat transcript corpus, extracting voice transcript sentences from the voice transcript corpus and chat transcript sentences from the chat transcript corpus, encoding, by a series of neural network layers, the voice transcript sentences to generate voice sentence vectors, encoding, by the series of neural network layers, the chat transcript sentences to generate chat sentence vectors, determining, for each voice sentence vector, a matching chat sentence vector to obtain matching voice-chat vector pairs, and adding, to a parallel corpus, matching voice-chat sentence pairs using the matching voice-chat vector pairs. Each of the matching voice-chat sentence pairs may include a voice transcript sentence and a matching chat transcript sentence. The method may further include training a disfluency remover model using the parallel corpus.

Disfluency removal using machine learning

A method of score prediction uses hierarchical attention. Word features, positioning features, participant embedding features, and metadata are extracted from a transcript of a conversation. A word encoder vector is formed by multiplying weights of a word encoder layer to one or more word features. A sentence vector is formed by multiplying weights of a word attention layer to word encoder vectors. An utterance encoder vector is formed by multiplying weights of an utterance encoder layer to the sentence vector. A conversation vector is formed by multiplying weights of an utterance attention layer to utterance encoder vectors. The utterance encoder vector is combined with one or more positioning features and one or more participant embedding features. A predicted net promoter score is generated by multiplying weights of an output layer to the conversation vector combined with the metadata. The predicted net promoter score is presented in a list of conversations.

Score prediction using hierarchical attention

Embodiments disclosed herein may extract trending topics from phone call transcripts or any type of text data. The phone call transcripts may be collected for a time period and the time period may be divided into time spans. For each time span having more than a threshold number of phone call transcripts, n-grams from the phone call transcripts may be extracted. The extracted n-grams may be contextually clustered by converting the n-grams into their embedding vectors, reducing the dimensionality of the embedding vectors, and clustering similar reduced dimensionality embedding vectors. Normalized occurrences of one or more clusters may be generated. The recent mean of the number of occurrences of the normalized clusters may be compared with the historical mean and offset by historical standard deviation to generate a modified Z-score. N-grams corresponding to the clusters with high Z-scores may be identified as trending topics.

Unsupervised extraction of trends from call center transcripts

A method including transcribing, into digital tokens, utterances from a conversation between an agent and a person. The method also includes embedding the digital tokens into an utterances tensor including sequences of the digital tokens. The method also includes obtaining a metadata tensor by encoding metadata related to the utterances into the metadata tensor. The method also includes executing a machine learning model which takes, as input, the utterances tensor and the metadata tensor, and which outputs a predicted source article predicted to be related to the utterances. The method also includes generating an interactive link to the predicted source article.

Automated search and presentation computing system

A method may include extracting, from a transaction, a routing transit number (RTN) and an account number, embedding the RTN to obtain an RTN vector, embedding the account number to obtain an account number matrix, combining, using a trained machine learning model, the RTN vector and the account number matrix to obtain a combined matrix, and classifying the account number as invalid. The classifying may include applying the trained machine learning model to the combined matrix.

Automated validation of digit sequences in transactions

A method including inputting, into a phrase recognition model comprising a neural network, a vector comprising a plurality of ngrams of text. The method also includes applying, using the phrase recognition model, a filter to the plurality of ngrams during execution. The filter has a skip word setting of at least one. The method also includes determining, based on the skip word setting, at least one ngram in the vector to be skipped to form at least one skip word. The method also includes outputting an intermediate score for a set of ngrams that match the filter. The method also includes calculating a scalar number representing a semantic meaning of the at least one skip word. The method also includes generating based on the scalar number and the intermediate score, a final score for the set of ngrams. A computer action is performed using the final score.

Machine learning models with improved semantic awareness

Automatic keyphrase labeling and machine learning training may include a processor extracting a plurality of keywords from at least one search query that resulted in a selection of a document appearing in a search result. For each of the plurality of keywords, the processor may determine a probability that the keyword describes the document. The processor may generate one or more keyphrases by performing processing including selecting each of the plurality of keywords having a probability greater than a predetermined threshold value for insertion into at least one of the one or more keyphrases and assembling the one or more keyphrases from the selected plurality of keywords. The processor may label the document with the keyphrase.

Automatic keyphrase labeling using search queries

In one aspect, the present disclosure relates to a method of generating business descriptions performed by a server, said method may include: receiving a plurality of invoices, each invoice being associated with a business of a plurality of businesses; extracting a plurality of texts from the plurality of invoices; embedding the plurality of texts to a vector space to obtain a plurality of invoice vectors; generating a plurality of clusters in the vector space, each cluster of the plurality of clusters comprising at least one invoice vector of the plurality of invoice vectors; generating a description for a cluster, the description for the cluster representing all invoice vectors assigned to the cluster; for each business of the plurality of businesses that has at least one invoice vector assigned to the cluster, associating the business with the description; and indexing the plurality of businesses within a database by the generated descriptions.

Growing community of inventors

Petah Tikva, Israel

Alexander Zhicharevich