Abstract: A method and system for dimension estimation based on duplication identification is disclosed. In some embodiments, the method includes receiving a set of images of an object. The method includes detecting, from each image in the set of images, a respective image segmentation representing a damage of the object. The method then includes determining a respective dimension for the damage represented by each of the image segmentations. The method further includes determining whether two or more of the image segmentations represent a same damage of the object. Responsive to two or more of the image segmentations representing a same damage of the object, the method includes combining the respective dimensions determined for the damage represented by the two or more image segmentations to obtain a final dimension for the same damage.

Abstract: A method and system are provided for assessing damage to a structure. According to one embodiment, the method includes detecting one or more external parts of the structure from a video of the structure using a first machine learning (ML) module trained to identify in one or more frames of a video of a structure an external part of the structure. The method also includes using a second ML module, trained to detect and classify damaged regions of a structure from one or more frames of the video: (i) identifying one or more damaged regions of the structure, and (ii) classifying the one or more damaged regions based on damage types. The method further includes associating the one or more damaged regions and corresponding damage types with the one or more external parts, providing a respective vision-based damage estimate for each of the one or more external parts.

Abstract: A method and system for processing an audio stream include receiving an audio stream by a node, splitting the audio stream into segments using a producer-consumer algorithm in the memory of the node, where the audio stream is split into the segments based on silence detection, transcribing voice included in a segment into text using a voice-to-text conversion engine, and performing natural language processing on the text to identify situational insights from the segment.

Abstract: A method and system are provided for assessing damage to a structure. According to one embodiment, the method includes detecting one or more external parts of the structure from a video of the structure using a first machine learning (ML) module trained to identify in one or more frames of a video of a structure an external part of the structure. The method also includes using a second ML module, trained to detect and classify damaged regions of a structure from one or more frames of the video: (i) identifying one or more damaged regions of the structure, and (ii) classifying the one or more damaged regions based on damage types. The method further includes associating the one or more damaged regions and corresponding damage types with the one or more external parts, providing a respective vision-based damage estimate for each of the one or more external parts.

Abstract: The disclosure relates to a method for receiving labelled data from data sources; generating a plurality of segments from the labelled data using tokenizers, wherein each of the segments is associated with one or more classes, and wherein the plurality of segments comprises a sub-plurality of unique segments; calculating an entropy value for each of the sub-plurality of unique segments; for each class, generating one or more rules based on each of the segments associated with the class and the entropy value of each such segment; and combining the generated one or more rules with a model to improve prediction performance of the model. The labelled data is input data for a classifier model to form predictions and false positives are extracted from the predictions. The model explainability techniques and the false positives are used to create additional rule.

Abstract: A method for aspect-based sentiment analysis includes receiving a collection of textual data, extracting a set of aspects and a set of sentiment words from the textual data, identifying a set of aspect-sentiment word pairs from the extracted aspects and sentiment words, identifying a subset of aspect-sentiment word pairs according to a set of predefined rules, and grouping a plurality of aspects associated with the subset of aspect-sentiment word pairs into one or more clusters. Each of the set of aspect-sentiment word pairs includes an aspect word from the set of aspects and a sentiment word from the set of sentiment words. Each of the subset of aspect-sentiment word pairs is determined to have an aspect-sentiment relationship according to the set of predefined rules.

Abstract: A method and system for dimension estimation based on duplication identification is disclosed. In some embodiments, the method includes receiving a set of images of an object. The method includes detecting, from each image in the set of images, a respective image segmentation representing a damage of the object. The method then includes determining a respective dimension for the damage represented by each of the image segmentations. The method further includes determining whether two or more of the image segmentations represent a same damage of the object. Responsive to two or more of the image segmentations representing a same damage of the object, the method includes combining the respective dimensions determined for the damage represented by the two or more image segmentations to obtain a final dimension for the same damage.

Abstract: A method and system are provided for training a machine-learning (ML) system/module and to provide an ML model. In one embodiment, a method includes using a labeled entities set to train a machine learning (ML) system, to obtain an ML model, and using the trained ML model to predict labels for entities in an unlabeled entities set, yielding a machine-labeled entities set. One or more individual ML models may be trained and used in this way, where each individual ML model corresponds to a respective document source. The document sources can be identified via classification of a corpus of documents. The prediction of labels provides a respective confidence score for each machine-labeled entity. The method also includes selecting from the machine-labeled entities set, a subset of machine-labeled entities having a respective confidence score at least equal to a threshold confidence score; and updating the labeled entities set by adding thereto the selected subset of machine-labeled entities.

Abstract: A method for dimension estimation based on duplication identification. In some embodiments, the method includes receiving a set of images of an object. The method then includes detecting, using a first machine learning system trained to perform image segmentation, a first image segmentation representing a damage of the object on a first image and a second image segmentation representing a damage of the object on a second image. The method further includes determining, using a second machine learning system trained to perform dimension estimation, a first dimension for the damage represented by the first image segmentation and a second dimension for the damage represented by the second image segmentation. The method includes determining whether the first and second image segmentations represent a same damage. If these image segmentations represent the same damage, the method intelligently combines the first and second dimensions to obtain a final dimension for the damage.

Abstract: A method and system for generating and correcting chatbot responses based on reinforcement learning (RL) are disclosed. In some embodiments, the method includes receiving user data associated with a user in a chatbot conversation. The method includes providing a first recommendation to the user. The method includes detecting user feedback to the first recommendation in the chatbot conversation. The method then includes determining whether to assign a positive reward or a negative reward to the user feedback based on sentiment analysis performed on the user feedback. If the negative reward is assigned to the user feedback, the method further includes calculating a negative reward score for the first recommendation; retraining the one or more of RL models using one or more of the negative reward score, the user data, the first recommendation, and the user feedback; and determining a second recommendation using the one or more retrained RL models.

Abstract: A method and system for time series forecasting on a big data set are provided. The method includes receiving a plurality of time series, each of the time series representing a historical demand pattern for an item, performing a domain-based segmentation to identify a plurality of statistically forecastable time series from the plurality of time series, grouping the plurality of statistically forecastable time series into one or more clusters, for each cluster, generating an aggregate time series based on time series included in the cluster, performing a future demand forecast at a cluster level by performing time series forecasting of the aggregate time series for each cluster, and determining a future demand forecast for each item based on the time series forecasting of the aggregate time series.

Abstract: A method and system for detecting deviation between invoices and receipts are disclosed. In some embodiments, the method includes receiving invoice data and receipt data. The method includes filtering the received data to generate filtered data. The method includes performing line-level matching on the filtered data based on one or more line-level attributes and one or more distance based algorithms. The method then includes determining, from the line-level matching, matched line items and unmatched line items between each pair of the invoice and receipts. The method also includes calculating one or more types of claims for both the matched line items and the unmatched line items to measure a total deviation between the invoices and receipts. The method further includes determining a level of match between the invoices and receipts and generating a recommended matching pair of invoice and receipt based on the level of match.

Abstract: A method and system for handling unlabeled interaction data with contextual understanding are disclosed. In some embodiments, the method includes receiving the interaction data describing agent-consumer interactions associated with a contact center. The method includes analyzing the interaction data to identify a plurality of features. The method includes automatically performing taxonomy driven classification on the plurality of features to generate a first set of labels associated with the interaction data. The method includes training a deep learning model using the first set of labels and the interaction data to determine a second set of labels. The method then includes intelligently combining the first and second sets of labels to obtain a combined set of labels associated with the interaction data.

Abstract: A method and system for generating and correcting chatbot responses based on reinforcement learning (RL) are disclosed. In some embodiments, the method includes receiving user data associated with a user in a chatbot conversation. The method includes providing a first recommendation to the user. The method includes detecting user feedback to the first recommendation in the chatbot conversation. The method then includes determining whether to assign a positive reward or a negative reward to the user feedback based on sentiment analysis performed on the user feedback. If the negative reward is assigned to the user feedback, the method further includes calculating a negative reward score for the first recommendation; retraining the one or more of RL models using one or more of the negative reward score, the user data, the first recommendation, and the user feedback; and determining a second recommendation using the one or more retrained RL models.

Abstract: A method for dimension estimation based on duplication identification. In some embodiments, the method includes receiving a set of images of an object. The method then includes detecting, using a first machine learning system trained to perform image segmentation, a first image segmentation representing a damage of the object on a first image and a second image segmentation representing a damage of the object on a second image. The method further includes determining, using a second machine learning system trained to perform dimension estimation, a first dimension for the damage represented by the first image segmentation and a second dimension for the damage represented by the second image segmentation. The method includes determining whether the first and second image segmentations represent a same damage. If these image segmentations represent the same damage, the method intelligently combines the first and second dimensions to obtain a final dimension for the damage.

Abstract: A method and system are provided for assessing damage to a structure. According to one embodiment, the method includes detecting one or more external parts of the structure from a video of the structure using a first machine learning (ML) module trained to identify in one or more frames of a video of a structure an external part of the structure. The method also includes using a second ML module, trained to detect and classify damaged regions of a structure from one or more frames of the video: (i) identifying one or more damaged regions of the structure, and (ii) classifying the one or more damaged regions based on damage types. The method further includes associating the one or more damaged regions and corresponding damage types with the one or more external parts, providing a respective vision-based damage estimate for each of the one or more external parts.

Abstract: A method and system are provided where a module employing reinforcement learning (RL) can learn to solve the vehicle selection and space allocation problems for the transportation and/or storage of goods. In one embodiment, a method includes: (a) obtaining a specification of a load that includes enclosures of one or more enclosure types, and the specification includes, for each enclosure type: (i) dimensions of an enclosure of the enclosure type, and (ii) a number of enclosures of the enclosure type. The method also includes (b) obtaining a specification of vehicles of one or more vehicle types, where the specification includes, for each vehicle type: (i) dimensions of space available within a vehicle of the vehicle type, and (ii) a number of vehicles of the vehicle type that are available for transportation. The method further includes (c) providing a simulation environment for simulating loading of a vehicle.

Abstract: A method and system are provided for training a machine-learning (ML) system/module and to provide an ML model. In one embodiment, a method includes using a labeled entities set to train a machine learning (ML) system, to obtain an ML model, and using the trained ML model to predict labels for entities in an unlabeled entities set, yielding a machine-labeled entities set. One or more individual ML models may be trained and used in this way, where each individual ML model corresponds to a respective document source. The document sources can be identified via classification of a corpus of documents. The prediction of labels provides a respective confidence score for each machine-labeled entity. The method also includes selecting from the machine-labeled entities set, a subset of machine-labeled entities having a respective confidence score at least equal to a threshold confidence score; and updating the labeled entities set by adding thereto the selected subset of machine-labeled entities.