Abstract: A device may determine an association between a second set of parameters and a third set of parameters using a pseudoinversion network and a multiple regression procedure. The device may determine semantic embeddings based on a set of semantic descriptions of the second set of parameters. The device may determine a semantic similarity between parameters of the second set of parameters based on the semantic embeddings. The device may determine a consistency error based on the semantic similarity. The device may generate, using a regression-based learning model technique, a matrix representing an association between the second set of parameters and the third set of parameters based on the association and the consistency error. The device may perform an action based on the matrix.

Abstract: There is provided a method and a system for ranking subgraphs as potential explanations for a labelled edge type class. A first graph representing labelled digital items is obtained, where each labelled digital item is represented as an entity node connected via a labelled edge type to a property value node. The first graph is combined with a second graph representing structured relations in the labelled digital items to obtain a combined graph. Unlabelled digital items are received and matched to respective subgraphs in the combined graph. A machine learning model is used to embed the combined graph to generate graph vectors, and an expressivity score between matched subgraphs and respective labelled edge types based on the generated graph vectors. The matched subgraphs are ranked based on the expressivity score to obtain a ranked set of subgraphs as potential explanations for a respective labelled edge type class.

Abstract: Implementations include providing, by the PKG platform, an initial knowledge graph based on user-specific data associated with a user, and a domain-specific knowledge graph, receiving, by the PKG platform, data representative of at least one answer provided from the user to a respective question, providing, by the PKG platform, an expanded knowledge graph based on the initial knowledge graph, the expanded knowledge graph including one or more nodes and respective edges based on the data, generating, by the PKG platform, a weighted knowledge graph based a groundtruth knowledge graph, and a targeted knowledge graph, the groundtruth knowledge graph including one or more true answers, and the targeted knowledge graph including the at least one answer provided from the user, and generating, by the PKG platform, the hyper-personalized knowledge graph (hpKG) based on the weighted knowledge graph, the hpKG being unique to the user within a domain.

Abstract: Implementations include providing, by the PKG platform, an initial knowledge graph based on user-specific data associated with a user, and a domain-specific knowledge graph, receiving, by the PKG platform, data representative of at least one answer provided from the user to a respective question, providing, by the PKG platform, an expanded knowledge graph based on the initial knowledge graph, the expanded knowledge graph including one or more nodes and respective edges based on the data, generating, by the PKG platform, a weighted knowledge graph based a groundtruth knowledge graph, and a targeted knowledge graph, the groundtruth knowledge graph including one or more true answers, and the targeted knowledge graph including the at least one answer provided from the user, and generating, by the PKG platform, the hyper-personalized knowledge graph (hpKG) based on the weighted knowledge graph, the hpKG being unique to the user within a domain.

Abstract: A method of semantic object detection in an image dataset includes extracting semantic links relevant to the image dataset. Objects are detected in the image dataset and confidence scores are assigned to the detected objects. The semantic object detection compares the detected objects with the semantic links and augments the confidence scores based on the semantic links between the detected objects.

Abstract: Implementations are directed to receiving current data, processing the current data using a predictive model to provide a result, the result corresponding to a sub-model of the predictive model, determining a set of syntactically similar sub-models based on other data, providing at least one semantic model based on the sub-model of the predictive model, one or more syntactically similar sub-models of the set of syntactically similar sub-models, a domain ontology (knowledge graph), and constraints, the at least one semantic model being provided by merging nodes of the sub-model of the predictive model, and a previously determined sub-model of the predictive model using the domain ontology, a label of the domain ontology being used to label a merged node, determining an interpretation based on the at least one semantic model, the interpretation providing at least one reason for the result, and providing the interpretation.

Abstract: Implementations of the present disclosure are generally directed to linking entities in dynamic knowledge graphs, and more particularly, to linking entities in knowledge graphs based on contextual evolution in one or more dimensions.

Abstract: Implementations include receiving a predicted value and confidence level from a first ML model, and determining that the confidence level is below a threshold, and in response: providing an encoding based on input data and non-textual information to the first ML model, the encoding representing characteristics of the input data relative to the predicted value, the characteristics including respective gradients of features of the input data, injecting the encoding into a textual knowledge graph that corresponds to a domain of the first ML model to provide an encoded knowledge graph, receiving supplemental data based on the encoded knowledge graph, and providing a supplemental predicted value from a second ML model based on the input data and the supplemental data, the second ML model having a higher number of features than the first ML model, and the supplemental predicted value having a supplemental confidence level that exceeds the threshold.

Abstract: An example method described herein involves receiving a data input; identifying a plurality of topics in the data input; determining an underrepresented set of data for a first set of topics of the plurality of topics based on a plurality of knowledge graphs associated with the first set of topics; calculating a score for each topic of the first set of topics based on a representative learning technique; determining that the score for a first topic of the first set of topics satisfies a threshold score; selecting a topic specific knowledge graph based on the first topic; identifying representative objects that are similar to objects of the data input based on the topic specific knowledge graph; generating representation data that is similar to the data input based on the representative objects to balance the underrepresented set of data with a set of data associated with a second set of topics of the plurality of topics; and performing an action associated with the representation data.

Abstract: A device may generate a product delivery map that includes route information that is to be used by a fleet of delivery vehicles for performing a set of deliveries, and a set of location constraints identifying locations that are to be avoided by the fleet of delivery vehicles when performing the set of deliveries. The device may generate a collaborative interactions map that includes a set of collaborative constraints indicating particular supplier organizations that are candidates to engage in collaborative logistics. The device may determine, based on the set of location constraints and the set of collaborative constraints, a set of delivery schedules that are to be used to perform the set of deliveries. The device may provide the set of delivery schedules to one or more devices associated with the delivery organization to allow the fleet of delivery vehicles to perform the set of deliveries.

Abstract: A device receives a knowledge graph and an ontology for the knowledge graph, and receives a query for information associated with the knowledge graph. The device generates candidate responses to the query, and assigns scores to the candidate responses based on the knowledge graph. The device identifies a particular candidate response, of the candidate responses, based on the scores for the candidate responses, and determines, based on the knowledge graph, a neighborhood of the particular candidate response. The device generates knowledge graph embeddings for the neighborhood of the particular candidate response, and determines a particular neighborhood, with a smallest loss of quality, based on the knowledge graph embeddings. The device generates a reasoning graph based on the ontology and the particular neighborhood, and generates an explanation of the particular candidate response based on the reasoning graph. The device performs an action based the explanation of the particular candidate response.

Abstract: A device may receive data associated with an event. The device may identify a context of the event based on receiving the data. The device may identify a similar event based on performing a comparison of the context of the event and a context of the similar event. The device may determine a set of pre-events associated with the event based on identifying a pre-event that occurred before the similar event. The set of pre-events may include at least one pre-event similar to the pre-event that occurred before the similar event. The device may determine a set of post-events associated with the event based on determining the set of pre-events and identifying a post-event that occurred after the similar event. The set of post-events may include at least one post-event similar to the post-event. The device may perform an action based on the set of post-events.

Abstract: Implementations are directed to providing a semantic sequence based on a sequence associated with the event, and context data provided from a knowledge graph, receiving a set of cases associated with at least one entity included in the event, the set of cases including previous instances of events, and actions performed to resolve the previous instances of events, defining a sub-set of cases from the set of cases based on the context data, for each case of the sub-set of cases, determining a similarity score, each similarity score representing a degree of similarity between the event, and a case of the sub-set of cases, determining an explanation based on features of cases in the sub-set of cases based on the context data, and providing one or more actions based on actions of cases in the sub-set of cases.

Abstract: According to an example, with respect to adverse information based ontology reinforcement, adverse information related to a product or a process may be ascertained and analyzed to further identify and ascertain a relevant ontology of a plurality of ontologies. A determination may be made as to whether the adverse information is present in the ascertained ontology, and if not, the adverse information may be integrated into the ascertained ontology to generate an updated ontology. Similar existing information corresponding to the ascertained adverse information may be identified in the updated ontology to determine an inconsistency between the identified similar existing information and the ascertained adverse information. The determined inconsistency may be used to modify the updated ontology to generate a reinforced ontology.

Abstract: A device may determine an association between a second set of parameters and a third set of parameters using a pseudoinversion network and a multiple regression procedure. The device may determine semantic embeddings based on a set of semantic descriptions of the second set of parameters. The device may determine a semantic similarity between parameters of the second set of parameters based on the semantic embeddings. The device may determine a consistency error based on the semantic similarity. The device may generate, using a regression-based learning model technique, a matrix representing an association between the second set of parameters and the third set of parameters based on the association and the consistency error. The device may perform an action based on the matrix.

Abstract: A device may receive user preference data and company preference data associated with one or more bookable items. The device may obtain external preference data associated with the one or more bookable items. The external preference data may be different from the user preference data and the company preference data. The device may generate a list of schedules based on the user preference data, the company preference data, and the external preference data. The device may generate one or more category scores for a plurality of schedules included in the list of schedules based on the company preference data. The device may rank the list of schedules based on the one or more category scores. The device may select a schedule, from the ranked list of schedules, based on the one or more category scores. The device may perform an action based on selecting the schedule.

Abstract: Complex computer system architectures are described for utilizing a knowledge data graph comprised of elements, and selecting a discovery element to replace an existing element of a formulation depicted in the knowledge data graph. The substitution process takes advantage of the knowledge data graph structure to improve the computing capabilities of a computing device executing a substitution calculation by translating the knowledge data graph into an embedding space, and determining a discovery element from within the embedding space.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for workforce planning.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a conversation monitoring system.

Abstract: Implementations include providing a baseline multi-dimensional model of a cultivar, determining an encoding based on the baseline multi-dimensional model, and a target multi-dimensional model, the encoding defining a string of symbols, and being based on an alphabet and a set of rules, providing an expected multi-dimensional model based on the encoding, and a modified set of rules, the modified set of rules being based on the set of rules, the expected multi-dimensional model representing the cultivar after a period of time, selecting a set of actions by determining multiple predicted multi-dimensional models for each set of actions in a plurality of sets of actions, and, for each predicted multi-dimensional model, providing a predicted yield that can be used to determine impact with respect an expected yield, the set of actions being selected based on a respective impact, and providing the set of actions as output for executing on the cultivar.