Abstract: A content management system may instantiate, from the same super class defined in a database schema, principal objects representing users and groups and content objects representing documents and folders. The principal objects and the content objects share the same social interaction functions. When a content object is modified, the system can create a message in which the content object identifies itself as a first person, update a message table such that any follower of the content object is notified of the message, and update a profile or feed associated with the content object. At least because content objects can “socialize” like principal objects, the system can generate a social graph containing content objects as nodes, map relationships among principal objects and content objects, and make recommendations to perhaps change/enhance such relationships.

Abstract: A method comprising: during a first time period, obtaining one or more first content ratings of a particular content item from one or more first users, each first content rating defining a first user measure of a belief state of the particular content item; and generating a first content score for the particular content item, the first content score defining a crowd-sourced measure of the belief state of the particular content item; during a second time period, obtaining one or more second content ratings from one or more second users for the particular content item, each second content rating defining a second user measure of the belief state of the particular content item; and generating a second content score for the particular content item, the second content score defining a second crowd-sourced measure of the belief state of the particular content item; comparing the second crowd-sourced measure of the belief state of the particular content item against each of the one or more first content ratings of t

Abstract: Provided is a live distribution system including at least one processor configured to: acquire a viewer comment input by a viewer of a live distribution service; estimate whether the viewer comment is appropriate based on a first model that has learned a first training comment; determine whether a first score relating to an estimation accuracy of the first model satisfies a predetermined first criterion; avoid, when the first score is determined to satisfy the first criterion, estimation based on a second model that has learned a second training comment; and estimate, when the first score is determined not to satisfy the first criterion, whether the viewer comment is appropriate based on the second model.

Abstract: An ontology matching system performs operations to refine a natural language processing (NLP) model that encodes terms of a first hierarchical ontology and of a second hierarchical ontology as embeddings in a latent space. The operations include performing at least a first round of triplet loss training to decrease separation between select pairs of the embeddings sampled from the different ontologies that satisfy a first hierarchical relation while increasing separation between other pairs of the embeddings that do not satisfy the first hierarchical relation. The system then determines, from the refined NLP model, a stable matching scheme that matches each term in the first hierarchical ontology with a corresponding term of the second hierarchical ontology. Responsive to receiving terms of the first hierarchical ontology from an application, the system uses the stable matching scheme to map each of the terms to corresponding terms of the second hierarchical ontology.

Abstract: The present disclosure generally relates to selecting and opening applications. An electronic device includes a display and a rotatable input mechanism rotatable around a rotation axis substantially perpendicular to a normal axis that is normal to a face of the display. The device detects a user input, and in response to detecting the user input, displays a first subset of application views of a set of application views. The first subset of application views is displayed along a first dimension of the display substantially perpendicular to both the rotation axis and the normal axis. The device detects a rotation of the rotatable input mechanism, and in response to detecting the rotation, displays a second subset of application views of the set of application views. Displaying the second subset of application views includes moving the set of application views on the display along the first dimension of the display.

Abstract: Methods and systems are disclosed for securely searching for physical resources. Attributes of a plurality of shared physical resources are accessed. An encrypted communication is received and decrypted that provides attributes for a first user. A search is performed, using a first neural network, for physical resources corresponding to attributes of the user to identity a first set of physical resources using decrypted attributes of the user and attributes of the plurality of physical resources. Search match scores are generated for the first set of physical resources. A subset of physical resources that at least one other user has access to is identified. A second neural network identifies users associated with the subset of physical resources that have a temporal usage conflict likelihood with the user. Search match scores may be adjusted. The search results may be ranked using the adjusted search match scores, and the ranked search results may be displayed.

Abstract: A system that enables the efficient identification and/or retrieval of certain timeline content from amongst e.g. a great many options of similar content. Generally, a set of timeline metadata that describes some aspect or aspects of the content of the timeline is produced. This set of timeline metadata includes timing and descriptive information that maps the described aspect or aspects to specific locations within the source timeline. When a user initiates a search of the timeline content, the search criteria is quickly matched against the contents of this separate set of metadata, rather than the raw timeline data itself. When the search criteria is matched, the metadata, original data, or both may be returned.

Abstract: Systems and Methods are disclosed herein for automatically indexing multiple informational fields in digital data records, the method comprising: identifying, based on rules defining target information fields, for each target field of the target information fields, at least one page in a digital data record comprising content related to the target field; extracting, for each target field, from the identified at least one page, at least one portion of text comprising the content; feeding, for each target field, a pre-processed version of the at least one portion of text into a machine learning (ML) model, wherein the ML model is trained on the target field; determining, for each target field, via the ML model trained on the target field, at least one candidate text comprising the content; and extracting, for each target field, the at least one candidate text.

Abstract: A system and method for providing service information on a social network, that can include: receiving, from a first client device, a social media post including a request for a service, where the request for the service includes a set of objectives, service location information, and an identification of a requesting account requesting a service on the social network; applying grouping criteria to a first set of user accounts to generate a group, where: the group is a subset of the first set of user accounts; providing, to one or more user accounts in the group, the social media post for display by the client devices of the one or more user accounts; and receiving, from a servicing user account in the group, an acceptance of the request for service of the social media post.

Abstract: A system for stable and streamlined transaction approval includes a rule management server and an authorizer server. The rule management server is configured to receive a transaction rule that includes a list of named entities specified by a client. The rule management server stores past transaction data and analyzes patterns in the past data to determine a named entity identification rule. The authorizer server receives a transaction data payload related to a pending transaction associated with the client and identifies a noisy data field in the transaction data payload. The noisy data field includes a representation of a particular named entity and one or more irrelevant strings. The authorizer server parses the particular named entity based on the named entity identification rule and determines whether the particular named entity is one of the named entities in the list. The authorizer server conducts a transaction evaluation using the result.

Abstract: Described herein are systems, methods, and non-transitory computer readable media for validating or rejecting automated detections of an entity being tracked within an environment in order to generate a track representative of a travel path of the entity within the environment. The automated detections of the entity may be generated by an artificial intelligence (AI) algorithm. The track may represent a travel path of the tracked entity across a set of image frames. The track may contain one or more tracklets, where each tracklet includes a set of validated detections of the entity across a subset of the set of image frames and excludes any rejected detections of the entity. Each tracklet may also contain one or more user-provided detections in scenarios in which the tracked entity is observed or otherwise known to be present in an image frame but automated detection of the entity did not occur.

Abstract: Embodiments are directed towards a method for creating a relational memory designed for one or more key parameters in at least one memory part configurations library. The method may include identifying one or more high-level parameters (HLPs) within the at least one memory part configurations library, assigning each non-HLP parameter an HLP key, using the assigned HLP keys as a frame of reference to cross-correlate each non-HLP parameter with every other non-HLP parameter in the at least one memory part configurations library. The method may also include extracting a complete relational memory attribute set from the cross-correlated parameters in the at least one memory part configurations library, generating memory configuration metadata equivalent to the at least one memory part configurations library from the complete relational memory attribute set, and providing memory part automation from the generated memory configuration metadata.

Abstract: Aspects identify users as trusted assistant candidates in response to associations to purchases of vehicle repair items. Embodiments further select a one of the trusted assistant candidates that is linked to a vehicle operator as a social network contact and that is located closest to a vehicle location relative to remaining others of the trusted assistant candidates, in response to determining that the vehicle operator needs remote location assistance at the vehicle location; and dispatch the selected one of the trusted assistant candidates to the vehicle location to provide remote location assistance to the vehicle operator.

Abstract: A method for estimating a precise position of a vehicle on a map includes acquiring at least one geolocated position of the vehicle by way of a geolocation system, pre-positioning the vehicle on the map, and particle filtering in which possible positions of the vehicle, called particles are processed. The particle filtering includes distributing particles on the map, and then updating the particles on the map, calculating the likelihood of each particle, selecting a limited set of particles, and, if an indicator relating to the likelihood of the selected particles and to the number of selected particles drops below a threshold, resampling particles on the map.

Abstract: An expert system processes communication data to extract entities and topics. The expert system generates relationship graphs and relationship scores between the entities and topics. The system can identify entities that are expert in a given topic. The expert system uses a knowledge engine to provide different services and applications.

Abstract: A method for determining an energy score for a guest room of a hotel having a plurality of guest rooms includes identifying two or more energy saving conditions associated with the guest room under which there is an opportunity to save energy when controlling the guest room without sacrificing guest comfort. The guest room is controlled in a designated energy savings mode when one or more of the energy savings room conditions are detected, and controlling the guest room in a guest comfort mode when none of the energy savings room conditions are detected. An energy score for the guest room is determined based at least in part on a measure of reliability of detecting the two or more energy savings conditions of the guest room, and thus the ability to take advantage of the opportunities to save energy when controlling the guest room.

Abstract: Financial audits establish trust in the governance and processes in an organization, but they are time-consuming and knowledge intensive. To increase the effectiveness of financial audit, present disclosure provides system and method that address the task of generating audit recommendations that can help auditors to focus their investigations. Adverse remarks, financial variables mentioned in each sentence are extracted/identified from audit reports and category tag is assigned accordingly, thus creating a knowledge base for generating audit recommendations using a trained sentence classifier. In absence of labeled data, the system applies linguistic rule(s) to identify adverse remark sentences, and automatically create labeled training data for training the sentence classifier.

Abstract: The present invention relates to a method for processing a knowledge graph in a data processing apparatus, comprising the steps of: (a) creating a knowledge graph including a taxonomy graph for a classification system of information objects and an entity graph for a relationship between specific information object instances; (b) updating the knowledge graph by reflecting the information objects extracted from a database in the knowledge graph; and (c) inferring the relevance of a random information object by using the updated knowledge graph.

Abstract: A platform dynamically detects a user persona and facilitates a user objective in a user session. The platform obtains user activity of users across multiple historical sessions. The platform clusters similar user activity across the historical sessions to determine personas being used in the historical sessions. The platform mines sequential patterns in a set of user activity data associated with one of the personas and determines at least one predictive rule associated with that persona. Each predictive rule includes an initial activity among the set of user activity data and at least one subsequent activity in the set of user activity data.

Abstract: Disclosed is a system to obtain the data set including multiple variables. The system extracts the multiple variables from the data set. Based on the data set, the system creates an ontology indicating multiple relationships between two or more variables among the multiple variables, where a relationship among multiple relationships indicates a correlation between the two or more variables. The system obtains an intent associated with the user, and a visualization standard, where the visualization standard indicates an attribute associated with the visualization. The system generates a sequence of multiple visualizations to present to the user by ranking the multiple visualizations based on the correlation between the two or more variables, the visualization standard and the intent associated with the user. The system presents the sequence of multiple visualizations based on the ranking.

Abstract: Techniques are disclosed for generating a search index for a hierarchical data set so that a search query of the hierarchical data may return results without searching or analyzing the hierarchical data set itself. The techniques generate a flattened index that includes selected indexed attributes and additional attributes to be displayed with the indexed attributes. The techniques also generate a hierarchy representation of the hierarchical data. Using these generated data structures, query results may be returned without directly traversing the hierarchical data itself while also providing data and hierarchical context for the query results by overlaying the query results with nodes of the hierarchical representation or otherwise concurrently displaying the query results with nodes of the hierarchical representation.

Abstract: Session content is presented during a communication session to the participant devices. The participant devices transmit requests for notes to be generated for the session content. One or more segments of the communication session are determined when a threshold number of participant devices that requested notes to be generated is exceeded. Information associated with the one or more segments is transmitted to a participant device of the participant devices.

Abstract: Examples relate to an evaluation device for re-identification and to a corresponding method, system and computer program. The evaluation device comprises processing circuitry being configured to obtain a plurality of transformed re-identification codes, each transformed re-identification code being associated with a timestamp and location information. Each transformed re-identification code is based on a similarity-preserving transformation of a re-identification code that represents at least a portion of a sample of media data, the media data originating from two or more different sources located in two or more different locations. The processing circuitry is configured to match transformed re-identification codes among the plurality of transformed re-identification codes using a similarity metric to generate one or more tuples of transformed re-identification codes that are similar according to the similarity metric.

Abstract: The disclosure is directed to a document management system having a label management user interface. The document management system may be configured to display document content in either a document view mode or a document edit mode in which document content is displayed in a content panel of the graphical user interface. When in the document view mode and an authenticated user has edit permissions with respect to a current document, the graphical user interface is configured to display a label management user interface including an array of user-selectable label graphical objects and a list of recommended labels selected in accordance with a label score. The label score for each recommended label is determined with respect to the current document based on a set of multiple heuristics including proximity of the document with respect to other labeled documents in a hierarchical element tree.

Abstract: Examples provide a system and method for retraining a machine learning (ML) algorithm associated with a trained model using root cause pattern recognition. The system analyzes the results of parsing unstructured data and identifies a root cause pattern causing the trained model to underperform when parsing data including the identified pattern. Examples of data including the pattern are created for use in retraining the model to correctly detect and parse data following the identified pattern. Once retrained, the model is able to parse unstructured data, including data having the identified pattern, in accordance with expected performance metrics. The system automatically identifies parsing errors, identifies the root cause patterns for these errors and retrains the models to correctly handle those patterns for more accurate and efficient handing of unstructured data by trained models.

Abstract: According to one embodiment, a method, computer system, and computer program product for gathering relevant digital content. The embodiment may include receiving, from an online meeting scheduler, information within an online meeting invite. The embodiment may include analyzing the information using natural language processing (NLP) and machine learning (ML) techniques. Based on results of the analysis of the received information, the embodiment may include locating additional digital content items of the user which are relevant to the information of the online meeting invite. The embodiment may include outputting, to a user, a top-k listing of the additional digital content items for attachment to the online meeting invite before being sent.

Abstract: Methods, systems, and computer programs are presented for generating multimodal content utilizing multimodal templates. One method includes presenting, in a user interface (UI), a template-selection option with one or more templates. Each template comprises a sequence of operations, where each operation comprises a prompt for creating items using generative artificial intelligence (GAI) tools. Further, each operation in the template is multimodal to be configurable to create text and configurable to create one or more images. The method further includes detecting a selection of a template in the UI. For each operation in the selected template, perform operations comprising: presenting, in the UI, the prompt associated with the operation; in response to receiving an input for the prompt, selecting a GAI tool based on a mode of the operation; providing the input to the selected GAI tool to generate the item; and presenting, in the UI, the generated item.

Abstract: In an embodiment, the present disclosure provides computer-implemented systems and methods for automatic management of video content of a plurality of content creators. In an embodiment, the disclosure provides, among other things, computers programmed to implement a networked, online platform for facilitating collaboration between content creators and producers. In an embodiment, the platform is programmatically configured to provide a content creator with a Challenge function that includes a challenge management system with automated messaging and a reward system. In an embodiment, the platform is also programmatically configured to implement a Broadcast function useful to a content creator. In an embodiment, the platform is programmed to implement the foregoing functions using complete, defined workflows that efficiently facilitate collaboration among content creators via the Challenge function or the Broadcast function.

Abstract: Systems, methods, and computer-readable medium storing instructions for identifying low-quality signals of an electronic listing of a listing entity are described herein. The method, system, or instructions may include ingesting text including listing information of the electronic listing and listing entity information of the listing entity; normalizing the text; parsing the text to identify a plurality of phrases; generating a set of category scores for each of at least one of the plurality of phrases; identifying, based on the on the sets of category scores, one or more low-quality signals each including a low-quality phrase and low-quality categories; and presenting an indication of the one or more low-quality signals with the electronic listing.

Abstract: Provided are methods for iteratively refining a training data set which may include training a first predictive model based on a first set of user profiles; determining a classification for each user profile of a second set of user profiles; determining a performance score for the first predictive model; determining to update the first predictive model based on the performance score for the first predictive model; determining a classification for each user profile of the first set of user profiles using the first predictive model; and selecting at least one user profile of the first set of user profiles to include in a removal set of user profiles. In some non-limiting embodiments or aspects, the method may include removing each user profile included in the removal set of user profiles from the first set of user profiles. Systems and computer program products are also provided.

Abstract: A system includes a computing device configured to obtain item attribute data that corresponds to a characteristic of an item ordered by a customer on an e-commerce platform and a common characteristic of a plurality of substitution items. The computing device is also configured to obtain customer attribute data identifying preferences of the customer and to determine a preference score for each substitution item in the plurality of substitution items based on the item attribute data and the customer attribute data. The preference score indicates a likelihood that the customer will accept one of the plurality of substitution items as a replacement for the item ordered by the customer. The computing device is also configured to rank each substitution item in the plurality of substitution items based on the preference scores.

Abstract: A method includes receiving, by a processing device, a definition of a continuous integration and continuous delivery/deployment (CI/CD) pipeline, obtaining, by the processing device in view of the definition, a characterization of the CI/CD pipeline indicative of a use case of the CI/CD pipeline, identifying, by the processing device from a heterogeneous pool of execution platforms, a set of candidate execution platforms in view of the characterization, selecting, by the processing device from the set of candidate execution platforms, a subset of execution platforms having a combination of attributes for executing the CI/CD pipeline, and assigning, by the processing device, the subset of execution platforms to the CI/CD pipeline for execution.

Abstract: A method is provided including presenting a user interface to allow a user of a social networking service to create a new collection for collecting a set of content items for the user, and upon a user request to create the new collection, adding the new collection to a list of collections associated with a user profile of the user, and presenting, in the user interface, the new collection as part of the list of collections associated with the user profile at the social networking service.

Abstract: An artificial intelligence (AI) interaction method, system, and computer program product include selecting an artificial intelligence model to respond to a query to generating a response to the query using the selected artificial intelligence model, and receiving the response to the query from the selected artificial intelligence model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically determining parameter values that control or affect provision of content by a content platform. In one aspect, evaluation points are identified for a parameter. Each evaluation point includes an evaluated parameter value of the parameter and a metric value of a metric corresponding to the provision of digital components by the content platform. A first model is generated using the set of evaluation points. A second model is generated based on the first model and an acquisition function that is based on mean values and confidence intervals of the first model and a configurable exploration weight that controls a priority of exploration for evaluating the parameter. A next parameter value to evaluate is determined from the second model and the content platform is configured to use the next parameter value to provide digital components.

Abstract: Methods and systems are disclosed that include receiving problem information from a user interface at a resolution identification system, receiving product information at the resolution identification system, and performing machine learning analysis of the problem information and the product information. The machine learning analysis produces one or more model outputs, and is performed by a machine learning system of the resolution identification system, using one or more machine learning models. Each of the one or more machine learning models produces a corresponding one of the one or more model outputs. Such a method can further include generating resolution information by performing an action identification operation using the one or more model outputs, and outputting the resolution information from the resolution identification system. The resolution information is output to the user interface.

Abstract: A computer-implemented method for contextually applying audio to an electronic media content, includes the following steps: parsing the electronic media content to determine at least one context of the electronic media content; comparing the at least one context of the electronic media content against a database of context tags corresponding to at least one context of a plurality of audio files; generating a ranked list of audio files corresponding to the comparison of the at least one context of the electronic media content against the database of context tags; selecting at least one audio file from the ranked list; and outputting the electronic media file together with the at least one audio file.

Abstract: An Integrated Circuit (IC) includes one or more functional hardware circuits, one or more processor cores, a cause-tree circuit, a memory buffer, and an analysis circuit. The processor cores are to handle events occurring in the functional hardware circuits. The cause-tree circuit includes leaf nodes, middle nodes and a root node. The leaf nodes are to collect the events from the one or more functional hardware circuits. The middle nodes are to coalesce the collected events and to deliver the events to the root node. The memory buffer is to buffer a plurality of the events delivered to the root node, so as to trigger the processor cores to handle the buffered events. The buffer analysis circuit is to analyze a performance of the cause-tree circuit based on the events buffered in the memory buffer.

Abstract: Systems and methods for improving a search process by providing a visual guided search experience is provided. A networked system determines a location of a user device. A user interface (UI) is presented illustrating a map at a first level view of an area based on the location. The networked system receives, via the UI, a first touch input indicating a zoom selection. In response, the UI shows a second level view of the area that includes a plurality of nodes each representing a point of interest in the area. The second level view is a lower level view than the first level view. The networked system then receives, via the UI, a second touch input selecting a node of the plurality of node. In response to the selecting of the node, navigation information for a selected point of interest corresponding to the selected node is presented.

Abstract: A method for generating digital certificates for anonymous users in blockchain transactions includes: storing a blockchain comprised of a plurality of blocks, each block including a block header and transaction values, where each transaction value includes data related to a blockchain transaction including a sending address, recipient address, and transaction amount; receiving a certificate request from a computing device, the request including a user public key of a cryptographic key pair; identifying a subset of transaction values in the blockchain where the sending address or recipient address was generated using the user public key; determining a confidence level based on the data included in each transaction value included in the subset; generating a digital certificate based on the determined confidence level; and transmitting the generated digital certificate to the computing device.

Abstract: The disclosure relates to systems and methods for real-time detection of a very large number of items in a given constrained volume. Specifically, the disclosure relates to systems and methods for retrieving an optimized set of classifiers from a self-updating classifiers' database, configured to selectively and specifically identify products inserted into a cart in real time, from a database comprising a large number of stock-keeping items, whereby the inserted items' captured images serve simultaneously as training dataset, validation dataset and test dataset for the recognition/identification/re-identification of the product.

Abstract: A method, computer program product, and computing system for sensing a failure within a system within a computing device. The system may include a cache memory system and a vaulted memory comprising a random access memory (RAM) having a plurality of independent persistent areas. A primary node and secondary node may be provided. The primary node may occupy a first independent persistent area of the RAM of the vaulted memory. The secondary node may occupy a second independent persistent area of the RAM of the vaulted memory. Data within the vaulted memory may be written to a persistent media using an iterator. The data may include at least one dirty page. Writing data within the vaulted memory to the persistent media may include flushing the at least one dirty page to the persistent media.

Abstract: In an example, first entities are extracted from user profiles. Second entities are extracted from content information associated with content item. User-associated metrics associated with the first entities are determined based upon the user profiles and/or content events. First vector representations of the first entities and second vector representations of the second entities are processed to generate an attention distribution array. Each value of the attention distribution array represents, for a user interested in an entity of the first entities, a proportion of (i) entity-specific activity, of the user, related to an entity of the second entities relative to (ii) an entirety of activity of the user. An inferred activity distribution array is generated by applying the user-associated metrics to the attention distribution array. A filtered subset of activity distribution values is generated by pruning values from the inferred activity distribution array.

Abstract: An indication of a selection of an entry associated with a machine learning model is received. One or more interpretation views associated with one or more machine learning models are dynamically updated based on the selected entry.

Abstract: The present disclosure provides a method for interconnecting a data lake and a relational database, including the following steps: S1: adding a data source class of a relational database to a data lake; S2: matching and using, by the data lake, a data source class of the relational database; and S3: determining and loading a corresponding driver according to the data source class, so as to connect the corresponding relational database. By cascading a data source registering configuration file, a relational database configuration file and a driver package catalog in a parameter passing method, when the data lake is started, a specific database to be used is designated unnecessarily, but a corresponding database is used directly. The configuration file is also traversed unnecessarily, but the user acquires configuration information as required in the parameter passing method.

Abstract: A device may receive, from a user device, a content selection, and may receive metadata associated with the content. The device may determine viewing options, for viewing the content, based on the metadata associated with the content, and may identify dimensions of the content based on the viewing options. The device may calculate points for each of the dimensions of the content, and may assign the points for each of the dimensions of the content to generate weighted dimensions of the content. The device may associate the weighted dimensions of the content with the viewing options to generate weighted viewing options, and may rank the weighted viewing options to determine a primary viewing option, a secondary viewing option, and remaining viewing options. The device may provide the primary viewing option, the secondary viewing option, and the remaining viewing options to the user device, for display.

Abstract: A computer implemented method includes supplying to a client device prompts for a first individual to provide a vote for a preference of the first individual. The preference relates to an activity during an ephemeral time period. The vote is collected. Matches between the first individual and a pool of individuals are generated based upon common votes and matching criteria. The matches are supplied to the client device. A match acceptance for a second individual is collected from the client device. Network communication is enabled between the first individual and the second individual.

Abstract: A storage device includes a non-volatile memory (NVM) and a storage device controller. The storage device controller includes a NVM interface coupled to the NVM and one or more task queues. The storage device controller is operable to pick a task from one or more queues of the storage device. The task is parsed based upon presence of an extra header segment with an execution condition. The task without the extra header segment is sent to execution. Whether the execution condition of the extra header segment of the task is met is determined. The task with the execution condition met is sent to execution. The task with the execution condition unmet is postponed.

Abstract: Techniques for improving the display of markers on a map include pre-computing cells for multiple locations on the map and associating points of interest with the pre-computed cells. In response to a request from a user device to display points of interest for a particular location, stored data specifying the pre-computed cells for the particular location is accessed and, for each of the cells, a point of interest is selected from the points of interests associated with that cell. The user device is caused to display the map with a marker in each of the cells for the selected point of interest.

Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.