Abstract: A new approach to automatic speech recognition is disclosed. An example method include receiving a first text representing speech recognition of a phrase spoken by a user, isolating a candidate named entity from within the phrase, receiving a first phonetic representation of the candidate named entity, comparing the first phonetic representation to phonetic representations in a mapping database which map the phonetic representations to words to yield a comparison, based on the comparison, identifying a second phonetic representation in the mapping database that matches a second text in the mapping database to the second phonetic representation and replacing the candidate named entity with the second text. The approach can be used for new brands for which automatic speech recognition error rates are high.

Abstract: The technology described herein makes improved use of limited screen space on a search results page by determining whether to present a question-and-answer experience and/or an entity details experience. This determination effects the amount of information presented and the format in which it is presented. In general, the question-and-answer experience provides less information and is more targeted to a question and query terms other than the entity. In contrast, the entity details experience provides more information about the entity that is not tailored to the query beyond the entity being included in the query. In one aspect, the determination of whether to show a question-and-answer experience and/or an entity details experience is based, at least in part, on an entity-details intent classification score (“intent classification score”) generated by a machine classification system. The classification score may be processed in combination with other criteria to make a final determination.

Abstract: A control system for an aircraft system can include a controller configured to connect to one or more subsystems of the aircraft system, the controller having a built-in-test (BIT) module configured to test the one or more subsystems of the aircraft system and output test data. The control system can include a wireless communication module operatively connected to the controller and configured to receive the output data and to output a wireless signal as a function of the test data.

Abstract: Technologies are described herein for denormalizing data instances. Schemas for data instances are embedded with annotations indicating how the denormalization is to be performed. Based on the annotations, one or more sub per object indexes (“sub POIs”) can be generated for each data instance and stored. The sub POIs can include a target sub POI containing data from the data instance, and at least one source sub POI containing data from another data instance, if the data instance depends on the other data instance. Data instance updates can be performed by identifying sub POIs that are related to the updated data instance in storage, and updating the related sub POIs according to the update to the data instance. The sub POIs can be sent to an indexing engine to generate an index for a search engine to facilitate searches on the data instances.

Abstract: Some embodiments provide a method for analyzing database queries performed on a database. The method receives log data associated with queries that were performed on the database, wherein the log data includes multiple sub-tables that each include a set of data entries. Based on the log data, the method assembles a set of queries that were performed on the database, where different queries in the set are assembled by combining different subsets of data entries from the sub-tables. The method performs a query interpretation operation on each query to quantify the impact of performing the assembled set of queries on the database.

Abstract: A data analysis system is provided. Processing resources are configured to at least: identify features within a dataset, identify potential features of interest therefrom, and enable selection of one of the identified potential features of interest. Responsive to an identified potential feature of interest being selected: (a) algorithms are run on the dataset to identify at least one related feature that the selected feature of interest is most likely and/or most heavily influenced by; (b) a display is generated to include a visual representation of each related feature, each including associated data value representations; and (c) a visual representation can be selected. A data value representation is selectable together with the selected visual representation. Responsive selection of the visual representation, (a)-(c) are repeated. Responsive to a data value representation being selected in (c), the dataset is filtered based on it, and the repetition is performed with the filtered dataset.

Abstract: A computer-implemented method for adaptive search refinement is provided. The method may include obtaining an indication of user engagement with an online marketplace and in response to obtaining the indication, providing visually guided search refinement to construct a search query for searching the online marketplace. Providing the visually guided search refinement may include providing search refinement options, obtaining an indication of the approval or disapproval of one or more of the search refinement options, and repeating providing the search refinement options and receiving the indication. For each iteration of providing the plurality of search refinement options, at least some of the search refinement options may be different and determined based on previously received indications of both approval and disapproval. The method for adaptive search refinement may further include providing search results based on the search query.

Abstract: Systems and methods are disclosed herein for providing a recommendation to modify deficient a deficient content item. A plurality of content items associated with a topic is retrieved. Each of the content items includes a plurality of portions each associated with a respective sub-topic. A rating for each sub-topic of the content items is calculated, and a minimum viable subset of the sub-topics is identified based on the calculated ratings. A new content item associated with the topic is accessed. A plurality of portions of the new content item is identified and a sub-topic for each identified portion is determined. An omitted sub-topic of the minimum viable subset of the sub-topics that is not included in the sub-topics of the new content item is identified, and the system interrupts upload of the new content and recommends modifying the new content item to include a portion with the omitted sub-topic.

Abstract: A user interface of an entity-centric knowledge discovery system presents an entity profile including a mix of structured and unstructured data relating to an entity. As a user refines the entity profile based on information gathered from various sources, the changing entity profile can be used as a substantially continuously updating query to search, retrieve, and rank new and pertinent information specifically relevant to the profiled entity. The platform described herein provide an active loop for refining an entity description and searching for additional information in which human input and machine-based algorithms can cooperate to more quickly build a comprehensive description of an entity of interest.

Abstract: One or more systems and/or methods for providing related content associated with a multi-touch gesture to a user are provided. A multi-touch gesture (e.g., a pinch-in gesture, a pinch-out gesture, etc.) may be received through a user interface of a client device (e.g., smartphone, tablet, television, virtual wall, etc.) associated with a user. The multi-touch gesture may be evaluated to identify an area of interest of the user interface (e.g., a portion of user interface containing content of interest to the user). The area of interest may be evaluated to identify context (e.g., keywords, phrases, associated content, etc.) associated with the area of interest. A search of content may be performed based upon the context to identify related content (e.g., news articles, wide-area network search results, local device search results, etc.) associated with the context. The related content may be provided to the user through the client device.

Abstract: A tag-based, user-directed media recommendation scheme is described herein. For example described herein is a recommender system (and method implemented by the recommender system) comprising: a recommendation engine configured to generate a recommendations list which includes a current set of recommendations for a user of a client device; and, a tag engine configured to: (1) receive the recommendations list; (2) obtain information about representative items associated with the user of the client device; (3) correlate the recommendations with tags; (4) correlate the representative items with the tags, (5) sort the tags into a tag list; and (6) provide the recommendations list and the tag list to the client device. The representative items include at least one of following: (1) an item previously purchased by the user; (2) an item previously watched by the user; (3) an item previously placed on a wish-list by the user; and (4) an item recommended by the recommendation engine for the user.

Abstract: Embodiments are directed to interaction with an open-domain question and answer system by recognizing questions that are highly broad or abstract, and generating and processing a batch of questions expressing alternate, concrete instances of the more general, abstract question. Responses to all of the questions in the batch are considered as candidates, and the strongest general answers are returned. A weighted, ranked answer set, based on weighting individual concrete questions and scaling the answers proportional to the weight of the questions, is provided to the user. The approach, according to embodiments herein, addresses the need for responses to broad questions in which a response to any of a set of more concrete question instances may serve to answer the question.

Abstract: Techniques and systems are described for content interest from interaction information. Keywords are extracted from digital content, and relevance values are determined based on the keywords that captures both the statistical and semantic significance of topics in the digital content through use of a network representation. Interest values for an entity are determined based on the relevance values and an interaction dataset, which capture both the statistical and semantic significance of the topics with respect to the entity. The interest values may be utilized to control output of digital content to a client device.

Abstract: Systems and methods of a search engine for interacting with a computer user as a conversation bot at the direction of the computer user. The search engine provides the computer user with the ability to selectively direct the search engine to interact with the computer user as a conversation bot. In interacting as a conversation bot, upon receive a request from the computer user, the search engine/conversation bot identifies an intent of the request, maps the intent to an action, and carries out the action on behalf of the computer user.

Abstract: Training query intents are allocated for multiple training entities into training time intervals in a time series based on a corresponding query intent time for each training query intent. Training performance results for the multiple training entities are allocated into the training time intervals in the time series based on a corresponding performance time of each training performance result. A machine learning model for a training milestone of the time series is trained based on the training query intents allocated to a training time interval prior to the training milestone and the training performance results allocated to a training time interval after the training milestone. Target performance for the target entity for an interval after a target milestone in the time series is predicted by inputting to the trained machine learning model target query intents allocated to the target entity in a target time interval before the target milestone.

Abstract: A search result providing method implemented in a computer includes providing a search result screen including a search result of a first keyword in response to a search request for the first keyword, and additionally providing a search result of a second keyword on the search result screen in response to a search request for at least one second keyword different from the first keyword.

Abstract: System and methods are described for generating query stacks from object relationships. In one implementation, a method comprises receiving user input specifying an initial object and a target object; identifying a plurality of directionality relationships associated with the initial object, the target object, and one or more junction objects that link the initial object to the target object; generating, based on the plurality of directionality relationships, a query stack comprising a plurality of queries linking the initial object to the target object; and executing the query stack to retrieve data stored in the target object.

Abstract: A multimedia dashboard application runs on a computing device that is in networked communication with an inventory database for a particular seller and is also in operative communication with a distribution server. The multimedia dashboard application includes an item selector, a multimedia recording module, multimedia editors, and a distribution controller. Without adding or opening any other application, the multimedia dashboard application is used to record multimedia segments, select segments to be uploaded to and downloaded from the inventory database, and edit the segments to produce multimedia promotions. The multimedia dashboard application also controls the distribution of the promotions. The system can be used collaboratively with multiple sales representative sharing multimedia segments through the inventory database. Marketing partners produce a base video and provide the sales representatives with access to the base segment through the multimedia dashboard application.

Abstract: A method includes loading a software application onto a data capture device of a subject, collecting electronic texts of a subject from a plurality of computer storage devices across the Internet, including electronic text generated by the data capture device, identifying, from the electronic texts, one or more perceptions held by the subject, generating a classification for each of the perceptions, wherein at least one of the perceptions is classified as a negative perception, defining an engagement degree of the subject with a current engagement model using the classifications of the perceptions, analyzing the negative perception, and defining a score for each of a plurality of strategies of engagement, wherein at least one strategy is selected, using the scores, for application to the subject, and the application of a selected strategy includes transmitting configuration data to the data capture device of the subject, the configuration data updates the software application.

Abstract: This invention deals with a computer-implemented method for using predictive analytics to find a second set of entries in a first array that are related to a first set of entries in the first array without directly calculating entry-to-entry similarities between entries in the first array, the method including: (a) identifying a target entry in a second array, wherein the first set of entries in the first array are linked to the target entry in the second array; (b) finding likely entries in the second array that have similarities to a target entry in the second array using a correlation; (c) finding linked entries in the first array that are linked to the likely entries found in the second array; and (d) using the linked entries found in the first array as the second set of entries in the first array.

Abstract: Techniques described modify playback of a narrated analytics playlist in a personalized analytics system. In some implementations, audible input is received during playback of the narrated analytics playlist. The audible input can be used to control the behavior of a playback module playing out the narrated analytics playlist. Alternately or additionally, user input can be received, where the user input corresponds to modifying an original scene included in the narrated analytics playlist. Some implementations generate synchronized audible output that be output with the modified original scene of the narrated analytics playlist. Alternately or additional, implementations can automatically determine to visually apply an auto-pointer to portions of the narrated analytics playlist.

Abstract: In general, the invention relates to a method for servicing query requests. The method includes determining, by a first query node and in response to a first query request, a user data sub-region and a target sub-region associated with the first query request. The further includes identifying a first input sub-region of the target sub-region using a data flow graph, identifying a second query node associated with the first input sub-region, and issuing a second query request to the second query node to obtain data associated with the first input sub-region. The method further includes receiving, in response to the second query request, a second query result from the second query node, generating a first query result for the target sub-region using at least the second query result, and providing the first query result to an entity associated with the issuance of the first query request.

Abstract: A network node associated with a retail store maintains personalized purchasing information identifying one or more products purchased by a customer. Each product is associated with one or more preference tags identifying a respective product category for the product, and indicating the customer's preference for products in that product category. Based on this information, the network node recommends products for the customer to purchase, and indicates those recommendations by controlling the customer's wireless device to visually indicate the location of the recommended products in the store.

Abstract: The method, computer program product and computer system may include computing device which may collect application data from one or more applications and archive the application data into a datastore. The computing device may generate a network graph based on the archived application data. The computing device may detect a user's focus on a piece of content contained within the one or more applications, retrieve data associated with the piece of content and determine the user's skill in relation to the piece of content. The computing device may determine the complexity of the piece of content in relation to the determined skill of the user and generate and present a summary of the piece of content.

Abstract: From a natural language document using a natural language concept analyzer, a set of natural language input concepts is extracted. Using a query generation model, a query corresponding to the set of natural language input concepts is generated. From a set of natural language results using the natural language concept analyzer, a set of natural language output concepts is extracted, a result in the set of natural language results comprising a portion of narrative text within a natural language corpus, the result identified by searching the natural language corpus using the query. Using the set of natural language input concepts and the set of natural language output concepts, a novelty concept is scored, the scored novelty concept comprising a degree to which a natural language input concept in the set of natural language input concepts is external to a boundary defined by the set of natural language output concepts.

Abstract: A system and method for determining the extent of beneficial ownership of a target business by populating a database structure wherein businesses and ownership relationships between the business are represented by nodes and links. Steps include querying the database to establish the related ownership links; analyzing the query to determine ownership loops; de-looping the ownership relationships; and calculating the percentage ownership of each of the beneficial owners of the target business based on de-looped ownership relationships. A computer readable non-transitory storage medium stores instructions of a computer program, which when executed by a computer system results in performance of steps of the method. A system architecture having features uniquely suited to the task is also disclosed.

Abstract: Systems and methods for presenting ranked search results on an interactive graphical user interface based on a semantic matching platform that is configured to apply an ontology are disclosed. In one aspect, a computer system comprising one or more computer readable storage devices configured to store a plurality of computer-executable instructions, a semantic matching platform, one or more network communication systems, and one or more hardware computer processors in communication with the one or more computer readable storage devices to execute the plurality of computer-executable instructions to cause the system to receiving search criteria from a user device, parse the search criteria, determine and rank matched search results, and generating instructions for presentation of a portion of the ranked search results on an interactive graphical user interface configured to be displayed on the user device.

Abstract: Systems and methods are described for a media guidance application (e.g., implemented on a user device) that aggregates related media content, associated with media content selected by a user, by comparing keywords.

Abstract: The invention relates to a method for automatically implementing one or more improved navigation paths between content items provided by a content management system. The content management system comprises a search service with a search monitoring component configured for monitoring search queries issued by a client application and for determining navigation paths used by a user of the client application for navigating between content items searched for by the monitored first search queries. The search service further comprises a navigation optimization component configured for determining improved navigation paths using the navigation paths determined by the search monitoring component. The navigation optimization component creates additional navigations which directly link a start content item and a target content item. The additional navigation path is assigned to be provided to the client application for display as part of a search query result.

Abstract: Instead of processing a query as-is, the query is chunked or broken down into a sequence of smaller chunked queries and the chunked results of those smaller queries are streamed back to the requester. Chunking the query and streaming the chunked results can substantially decrease the user's time to value when running a query by returning some immediate results for display which are refined and eventually converge on the full results as each chunked query runs.

Abstract: A method, device, and computer-readable medium provide for receiving, via a chatbot access channel, a chat message from a user device associated with a customer chat session; determining that the chat message includes a customer intent that corresponds to a chat flow for the customer chat session; generating one or more suggested response messages based on the chat message, wherein at least one of the one or more suggested response messages includes a previously stored chat message response corresponding to the customer intent and approved by a service agent; presenting, via a display, a transcript of a messaging sequence for the customer chat session concurrently with a user interface that enables the service agent to perform an action with respect to the one or more suggested response messages; and sending, via the chatbot access channel, a selected one of the one or more suggested response messages to the user device.

Abstract: Devices, computer-readable media, and methods for encoding a scene in a video program using an encoding strategy that is selected in accordance with a theme that is identified in the scene are disclosed. For example, a method may include a processing system receiving a video program, identifying boundaries of a scene in the video program, identifying a theme in the scene, and selecting an encoding strategy for the scene based upon the theme, where the encoding strategy is associated with the theme. The processing system may further encode the scene using the encoding strategy that is selected.

Abstract: Linguistic expressions for training a chatbot can be generated in an automated system via linguistic expression templates that are associated with intents. The pre-categorized linguistic expressions can then be used for training and validation. Chatbot development can thus be improved by having a large number of expressions for development, leading to a more robust chatbot. In practice, the process can iterate with modifications to the templates until a suitable benchmark is met. The technique can be applied across human languages to generate chatbots conversant in any number of languages and is applicable to a variety of domains.

Abstract: A method of operating a messaging platform, including: obtaining, for a first profile of the messaging platform, a trending entity within a first topic of interest to the first profile; accessing a first plurality of messages classified as the first topic of interest; retrieving a subset of the first plurality of messages corresponding to the trending entity; and sending content associated with the subset for display to a user of the first profile.

Abstract: Techniques for context sensitive illustrated graphical user interface elements, comprising a social networking application. The social networking application may include, among other components, a social networking graphical elements management component to provide a list of recommended graphical element identifier information, in response to a request for the list of recommended graphical element identifier information, a context determination component to determine user context information representative of the at least one user context based at least partially on user communications intent information, user profile information, device location information, calendar event information, and/or external event information, and a graphical elements recommendation component to generate the list of recommended graphical element identifier information based at least partially on the user profile information, graphical elements promotion information, and/or the user context information.

Abstract: The present disclosure provides label data leakage channel detection methods and apparatuses. According to one exemplary label data leakage channel detection method, detection labels are generated based on normal labels of a user. The detection labels can be associated with different data usage channels, so as to indirectly detect usage of the detection labels. Possible data leakage channels can be effectively detected based on massive data indexing and searching. One exemplary apparatus of the present disclosure includes a detection label adding module, a channel association module, an interception module, an intercepted information analysis module, a channel searching module, and an output module. The detection methods and apparatuses provided by the present disclosure have the advantages of high detection efficiency and the capability of processing massive and dynamic user label data.

Abstract: Systems, methods, and articles of manufacture to perform an operation comprising deriving, based on a corpus of electronic text, a machine learning data model that associates words with corresponding usage contexts over a window of time, according to a diffusion process, wherein the machine learning data model comprises a plurality of skip-gram models, wherein each skip-gram model comprises a word embedding vector and a context embedding vector for a respective time step associated with the respective skip-gram model, generating a smoothed model by applying a variational inference operation over the machine learning data model, and identifying, based on the smoothed model and the corpus of electronic text, a change in a semantic use of a word over at least a portion of the window of time.

Abstract: Systems and methods of the disclosure relate to selecting content using beacon identifiers. An indication of a location of a user device and a beacon identifier are received. The beacon identifier can correspond to a beacon at a retail location. A data structure storing attribute data associated with the beacon identifier can be accessed. The attribute data can be associated with a signal having a unique identifier of the user device. The signal can indicate the retail location having the beacon. A request for content for display on the user device can be received. A content item can be selected for display on the user device based on the attribute data. A reward value can be determined based on receiving an indication of user interaction with the content item and the attribute data used to select the content item.

Abstract: A method of recommending a query word using a domain property includes receiving a search keyword from a terminal of a user, the search keyword being input by the user; generating at least one recommendation query word concerned with the search keyword by using a property of an object of a domain when the search keyword belongs to the object of the domain; and providing the recommendation query word to the terminal of the user as an autocomplete query word for the search keyword.

Abstract: A method for generating keywords for searches, comprising the steps of retrieving search metric data comprising a plurality of search strings and interaction data; retrieving a plurality of first product identifiers each having one or more first attributes; generating, a table comprising the plurality of search strings ranked by interaction data; generating relevant lists comprising the plurality of search strings having interaction data above threshold values; retrieving data relating to a second product identifier; extracting one or more second attributes of the second product identifier; performing searches in the relevant lists using the second attribute data; assigning keywords to the data relating to the second identifier.

Abstract: A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for presenting a search result in a search result card, the method includes receiving from a user, an input associated with a search query; fetching one or more search results in accordance with the search query; generating a search result card for each of the one or more search results; and presenting to the user, one or more search result cards as a response to the search query, the one or more search result cards corresponding to the one or more search results, respectively.

Abstract: An apparatus for detecting malicious files includes a memory and a processor communicatively coupled to the memory. The processor receives multiple potentially malicious files. A first potentially malicious file has a first file format, and a second potentially malicious file has a second file format different than the first file format. The processor extracts a first set of strings from the first potentially malicious file, and extracts a second set of strings from the second potentially malicious file. First and second feature vectors are defined based on lengths of each string from the associated set of strings. The processor provides the first feature vector as an input to a machine learning model to produce a maliciousness classification of the first potentially malicious file, and provides the second feature vector as an input to the machine learning model to produce a maliciousness classification of the second potentially malicious file.

Abstract: This application discloses a media content recommendation method. The method includes the steps of receiving historical data of access to media content by a user or media content data followed by the user; determining an interest tag of the user according to the historical data or the followed media content data; and determining a recommended user group for the user according to the interest tag, and sending an identifier of the recommended user group to a client for presentation. The method further includes the steps of receiving an access request that carries the identifier of the recommended user group and that is sent by the client; determining, according to the identifier of the recommended user group, media content recommendation information provided by each user in the recommended user group; and pushing, to the client, the media content recommendation information provided by each user in the recommended user group.

Abstract: A data processing system identifies a first topic for a first table, identifies a second topic for a second table, collects at least one first table attribute comprising at least one row name for the first table, and collects at least one second table attribute comprising at least one row name for the second table. The at least one semantic vector for the first table is compared with the at least one semantic vector for the second table to identify as related at least one row of the first table and at least one row of the second table. The at least one row of the first table and the at least one row of the second table are provided to a communication device with an identification as related.

Abstract: Embodiments use successive refinement to allow a user to systematically explore the result set of an arbitrary query over RDF, such as a SPARQL query. A user inputs an arbitrary base query and modifies this query by replacing selected variables with values to which each selected variable is bound within the result set of the base query. Embodiments present, via a GUI, variable facets that may be substituted for query variables. Embodiments also present, through a GUI, a query history graph that represents query versions that a user has created. A user may navigate this query history graph to return to previously-created query versions. The GUI also provides information about the facets, including a number of results that would be included in the result set of the query version resulting from substitution of the facet for the associated variable.

Abstract: Disclosed is system for extracting tabular data from electronic document, system having data processing arrangement comprising: tabular data detection module that is operable to: (i) receive electronic document; (ii) determine location of tabular data within electronic document; and (iii) extract image of tabular data from electronic document; and tabular data extraction module that receives extracted image of tabular data from tabular data detection module, wherein tabular data extraction module is operable to: (i) convert received image of tabular data into greyscale image; (ii) extract grid structure from greyscale image; (iii) remove grid structure from greyscale image; (iv) determine position for placement of horizontal and vertical lines in greyscale image; (v) generate horizontal and vertical lines on greyscale image; (vi) perform optical character recognition of text associated with tabular data from received image; and (vii) extract tabular data by combining information of grid structure with text, t

Abstract: A server in a cloud-based environment interfaces with storage devices that store shared content. A user retrieves a web-based application from the server. The web-based application comprises a set of native operating system application code, a web content viewer, and a native operating system interface, which are configured to facilitate a transfer of one or more objects between the native operating system application code and the web content viewer. In response to a user upload request, the server generates an object placeholder in an editable document. Using the native operating system application code, objects can be selected for incorporation into the editable document. Shared access to the editable document and shared access to uploaded objects are provided by the server by posting links to locations in the storage devices. The web-based application replaces the object placeholder with a link to the object as stored by the server.

Abstract: A method, system and computer-usable medium for providing cognitive insights comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching to provide enriched data; generating the cognitive session graph, the cognitive session graph being associated with a session, the cognitive session graph comprising at least some enriched data; and, processing the cognitive session graph to provide a cognitive insight, the cognitive insight being related to the session.

Abstract: A location associated with a user of a computing device and a prefix portion of an input string may be received as one or more successive characters of the input string are provided by the user via the computing device. A list of suggested items may be obtained based on a function of respective recommendation indicators and proximities of the items to the location in response to receiving the prefix portion, and based on partially traversing a character string search structure having a plurality of non-terminal nodes augmented with bound indicators associated with spatial regions. The list of suggested items and descriptive information associated with each suggested item may be returned to the user, in response to receiving the prefix portion, for rendering an image illustrating indicators associated with the list in a manner relative to the location, as the user provides each successive character of the input string.

Abstract: The technology disclosed relates to rapidly logging sales activities in a customer relationship management system. It also relates to simplifying logging of sale activities by offering a streamlined data entry path that as immense usability in a mobile environment. The streamlined data entry path can be completed by triple-action, double-action, or single-action. In particular, the technology disclosed relates to automatically identifying and selecting entities that are most likely to be selected by a user. The identification of entities as most likely to be selected is dependent at least upon access recency of records of the entities, imminence of events linked to the entities, and geographic proximities of the entities to the user. It further relates to automatically identifying and selecting sales activities that are most likely to be performed by the user.