Abstract: There is provided a method for retrieving data, the method being executed by at least one processor, the method comprising: receiving a natural language query; decomposing the natural language query into query elements; generating, by providing the query elements to at least one classifier, a query type characterizing the natural language query; identifying a subset of the query elements based on the query type; generating a structured database query including the subset of the query elements; and retrieving data based on the structured database query.

Abstract: Systems and methods for adding process actions to the design of a robotic software process. A context-recognition module recognizes a current state of a process being designed, and passes information on that current state to a recommendation module. The recommendation module evaluates the current state and identifies at least one suitable process action to recommend in response to that current state. The recommendation module then recommends the at least one process action to the human designer. If the designer accepts the recommendation, a design module adds the process action to the process design. The recommendation module may also use information about previous actions in the process and in other processes when identifying suitable process actions. The context-recognition module and the recommendation module may each comprise at least one machine learning module, which may or may not be neural network based.

Abstract: There is provided a method and a system for generating an interactive search interface in response to a search request by using at least one machine learning (ML) model. A search request such as one of a word, a sentence, a paragraph, and a document is received, and a semantic representation of the search request is received. Semantically similar documents are received by: comparing the search request semantic representation with document representations to obtain semantic similarity scores, and selecting semantically similar documents based on the scores. For each of the set of semantically similar documents, a respective set of similar paragraphs, sentences, and words are determined based on associated representations. An interactive search interface is generated and displayed to a user interface. A selection of a given document is received, and each of the respective set of similar paragraphs, sentences, and similar words associated with the given document are displayed.

Abstract: Systems and methods for adding process actions to the design of a robotic software process. A context-recognition module recognizes a current state of a process being designed, and passes information on that current state to a recommendation module. The recommendation module evaluates the current state and identifies at least one suitable process action to recommend in response to that current state. The recommendation module then recommends the at least one process action to the human designer. If the designer accepts the recommendation, a design module adds the process action to the process design. The recommendation module may also use information about previous actions in the process and in other processes when identifying suitable process actions. The context-recognition module and the recommendation module may each comprise at least one machine learning module, which may or may not be neural network based.

Abstract: A system identifying anomalies in an image of an object is first trained using first sets of images corresponding to first anomaly types for the object. A model of the object is formed in a latent space. A label for each anomalous image is used to calculate vectors containing means and standard deviations for each first anomaly types. The means and standard deviations are used to calculate a log-likelihood loss for each first anomaly type. The system is retrained using second sets of images corresponding to second anomaly types for the object. The vectors are supplemented using labels for each second anomaly types. A statistically sufficient sample of information in the means and standard deviations vectors is supplied to the latent space. A log-likelihood loss for each of the first and second anomaly types is calculated based on their respective mean and standard deviation.

Abstract: Systems for use in data retrieval. A natural language processing module is used in conjunction with a classifier module to analyze and decompose a user query into its elements, and to determine a type of query. These modules are also used to determine the parameters for the query. The type of query and the parameters are then used to find a suitable function that creates a structured database query with the fields in the database query being populated using the parameters and query elements found by the NLP module. The completed structured database query is then used to retrieve relevant data records in response to the query. The retrieved records are then further processed and formatted as necessary to result in a suitable response to the query.

Abstract: There is provided a method and system for training an embedding model to perform relation predictions in a knowledge hypergraph to output a trained embedding model. A training dataset comprising tuples representing relations between entities in the knowledge hypergraph are received. The embedding model is trained to perform relation predictions for each given tuple from a subset of tuples in the training dataset by generating a respective entity vector for each entity and a respective relation matrix representing relations between the entities. The entity vectors and relation matrix are split into a plurality of windows, and interaction values between elements in each window are calculated. A relation score indicative of the relation in the given tuple being true is calculated. Parameters of the embedding model are updated based on the relation scores for the subset of tuples. The trained embedding model is then output.

Abstract: Systems and methods relating to the replacement or removal of sensitive data in images of documents. An initial image of a document with sensitive data is received at an execution module and changes are made based on the execution module's training. The changes include replacing or effectively removing the sensitive data from the image of the document. The resulting sanitized image is then sent to a user for validation of the changes. The feedback from the user is then used in training the execution module to refine its behaviour when applying changes to other initial images of documents. To train the execution module, training data sets of document images with sensitive data manually tagged by users are used. The execution module thus learns to identify sensitive data and its submodules replace that sensitive data with suitable replacement data. The feedback from the user works to improve the resulting sanitized images from the execution module.

Abstract: Systems and methods for detecting and predicting text within images. An image is passed to a feature-extraction module. Each image typically contains at least one text object, and each text object contains at least one character. Based on the image, the feature-extraction module generates at least one feature map indicating text object(s) in the image. The feature map(s) is then passed to a decoder module. In son implementations, the decoder module applies a weighted mask to the feature map(s). Based on the feature map(s), the decoder module predicts a sequence of characters in the text object(s). In some embodiments, that prediction is based on previous known data. The decoder module is directed by a query that indicates at least one desired characteristic of the text object(s). An output module then refines the predicted content. At least one neural network may be used.

Abstract: There is provided a non-transitory storage medium and a system for generating an abstractive summary of a document using an abstractive machine learning algorithm (MLA). A document including a plurality of text sequences is received. An extractive summary of the document is generated, the extractive summary including a set of summary text sequences which is a subset of the plurality of text sequences. The abstractive MLA generates, based on the set of summary text sequences and at least a portion of the plurality of text sequences, an abstractive summary of the document including a set of abstractive text sequences, at least one abstractive text sequence not being included in the plurality of text sequences.

Abstract: Systems and methods for determining similarities between an input data set and a target data set with the data sets being vector representations of the features of a candidate potential copy and a target original. A feature extraction module receives an image of the potential copy and extracts the features of that candidate. The features of the target original may already be extracted or may be separately extracted. The resulting data sets for the candidate and the original are then passed through a decision module. The decision module determines a level of similarity between the features of the candidate and the features of the original. The output of the decision module provides an indication of this level of similarity and, depending on this level of similarity, an alert may be generated. A report module may be included to provide an explanation regarding the level of similarity.

Abstract: Systems and methods for use in software module development. A configuration file and a process agent module operate cooperatively in conjunction with a computer system to provision one or more execution environments to implement one or more instances of a user's software module in development. The configuration file contains the hardware and software configuration that defines the limits and capabilities of the execution environment as well as parameters needed by the software module. The process agent launches the execution environment and ensures that the software module executing in the execution environment has access to the resources set out in the configuration file. Once execution of the software module is complete, performance results are then passed to the process agent for collation and analysis. These results can then be used to determine which implementation of the software module performs best.

Abstract: Systems and methods for privacy and sensitive data protection. An image of a document is received at a pre-processing stage and image pre-processing is applied to the image to ensure that the resulting image is sufficient for further processing. Pre-processing may involve processing relating to image quality and image orientation. The image is then passed to an initial processing stage. At the initial processing stage, the relevant data in the document are located and bounding boxes are placed around the data. The resulting image is then passed to a processing stage. At this stage, the type of data within the bounding boxes is determined and suitable replacement data is generated. The replacement data is then inserted into the image to thereby remove and replace the sensitive data in the image.

Abstract: Systems and methods for document analysis. An image containing at least one document is received at a pre-processing stage and the image is analyzed for image quality. If the image quality is insufficient for further processing, this is adjusted until the image is suitable for further processing. After the image quality adjustment, the image is then passed to an initial processing stage. At the initial processing stage, the boundaries of one or more documents within the image are determined. In addition, the orientation of the image may be adjusted and the type of document(s) within the image is determined. From the initial processing stage, the adjusted image is then passed to a data extraction stage. At this stage, clusters of data within the document are determined and bounding boxes are placed around the clusters. Data regarding each of the clusters of data is then gathered.

Abstract: There is disclosed a method and system for executing commands. The method comprises configuring an input event topic subscriber and a command orchestrator process. The input event topic subscriber is invoked. The input event topic subscriber receives an event. The event comprises an event context and associated data. The event is transformed into a command. The command orchestrator is invoked. The command is input to the command orchestrator. The command orchestrator adds contextual information to the command. The command orchestrator schedules execution of the command. The execution of the command is tracked. A returned data object corresponding to the command is received and output.

Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: System and method for producing an adversarial article that may be used to disrupt an automated visual tracking process. An input module receives input related to a specific automated visual tracking process. Based on that input, a pattern-design module generates an adversarial pattern. The adversarial pattern may then be applied to an article, which may be any kind of physical or virtual object. The tracker's normal processing modes are disrupted when the tracker attempts to process an image containing the adversarial article(s). The tracker may be mounted on an autonomous vehicle, a mobile robot, or other mobile or stationary camera surveillance system.

Abstract: There is described a computer-implemented method and system for classifying images, the computer-implemented method comprising: receiving an image to be classified, generating a vector representation of the image to be classified using an image embedding method, comparing the vector representation of the image to predefined vector representations of the predefined image categories, and identifying a relevant category amongst the predefined image categories based on the comparison, the relevant category being associated with the image to be classified and outputting the relevant category.

Abstract: Systems and components for use with neural networks. An execution block and a system architecture using that execution block are disclosed. The execution block uses a fully connected stack of layers and one output is a forecast for a time series while another output is a backcast that can be used to determine a residual from the input to the execution block. The execution block uses a waveform generator sub-unit whose parameters can be judiciously selected to thereby constrain the possible set of waveforms generated. By doing so, the execution block specializes its function. The system using the execution block has been shown to be better than the state of the art in providing solutions to the time series problem.

Abstract: A method for extracting information from a document, comprising: receiving an identification of an entity to be extracted from the document; identifying candidates from the document, each candidate corresponding to a given element contained in the document and having a given location within the document; embedding the candidates, thereby obtaining an embedding vector for each candidate; for each candidate, comparing in a semantic space the respective embedding vector to previous embedding vectors associated with previous entity values previously chosen for the entity, thereby obtaining a first comparison result; for each candidate, comparing in a pixel space the given location within the document of the candidate to a location associated with the previous entity values previously chosen for the entity, thereby obtaining a second comparison result; sorting the candidates using the first and second comparison results obtained for each candidate, thereby obtaining sorted candidates; and outputting the sorted can