Abstract: A method and an apparatus for sequence labeling on an entity text, and a non-transitory computer-readable recording medium are provided. In the method, a start position of an entity text within a target text is determined. Then, a first matrix is generated based on the start position of the entity text. Elements in the first matrix indicates focusable weights of each word with respect to other words in the target text. Then, a named entity recognition model is generated using the first matrix. The named entity recognition model is obtained by training using first training data, the first training data includes word embeddings corresponding to respective texts in a training text set, and the texts are texts whose entity label has been labeled. Then, the target text is input to the named entity recognition model, and probability distribution of the entity label is output.

Abstract: An industrial information identification and retrieval system includes: a crawler; a search engine; a result processor; and a web user interface “web UL” The crawler identifies devices and their associated Open Platform Communication Unified Architecture “OPC UA” servers within a network as identified OPC UA servers. The crawler browses the identified OPC UA servers and extracts and stores data items in a database as extracted data items. The search engine searches the extracted data items and provides search results to the result processor. The result processor determines a score for each search result. The web UI presents the search results according to the scores.

Abstract: Techniques for implementing artificial crowd intelligence via networking of recommendation engines are disclosed. In some example embodiments, a base recommendation engine performs a computer-implemented method comprising: receiving a recommendation request; generating a first plurality of recommendations based on the recommendation request using a base recommendation model; obtaining one or more other recommendations from one or more other recommendation engines, each one of the other recommendation engines being configured to generate the other recommendations based on the recommendation request using a corresponding recommendation model; obtaining a corresponding weight for the other recommendation engine(s); selecting at least one recommendation from the first plurality of recommendations and the other recommendation(s) using the corresponding weight(s); and causing the selected recommendation(s) to be displayed.

Abstract: Systems and methods are described for generating pixel image data, using a lensless camera, based on light that travels through a mask that with pattern masking the lensless camera. The system applies a transformation function to the pixel image data to generate frequency domain image data. The system inputs the frequency domain image data into a machine learning model, wherein the machine learning model does not have access to data that represents the pattern of the mask. The model is trained using a set of images with the feature that are captured by the flat, lensless camera through the mask. The system processes the frequency domain image data using the machine learning model to determine whether the pixel image data depicts the image feature. The system further performs an action based on determining that the pixel image data depicts the image feature.

Abstract: A method for employing a temporal context-aware question routing model (TCQR) in multiple granularities of temporal dynamics in community-based question answering (CQA) systems is presented. The method includes encoding answerers into temporal context-aware representations based on semantic and temporal information of questions, measuring answerers expertise in one or more of the questions as a coherence between the temporal context-aware representations of the answerers and encodings of the questions, modeling the temporal dynamics of answering behaviors of the answerers in different levels of time granularities by using multi-shift and multi-resolution extensions, and outputting answers of select answerers to a visualization device.

Abstract: A system includes a computing platform having processing hardware and a memory storing an asset library and software code including a recommendation engine. The processing hardware executes the software code to receive, from a user, group generation data and a preferences profile of the user, the group generation data identifying a group including the user and another user, and to send, to the other user, an invitation to join the group. The processing hardware also executes the software code to receive, from the other user, one of an acceptance or a refusal of the invitation, obtain, in response to receiving the acceptance, a preferences profile of the other user, generate, using the preferences profiles of the user and the other user, a group preferences profile for the group, and identify, using the recommendation engine and the group preferences profile, one or more assets in the asset library for the group.

Abstract: A server obtains user data for a respective user, including data corresponding to the respective user's consumption of media in a first content domain. Before obtaining, for the respective user, data corresponding to a second content domain, the server uses a neural network to generate a user embedding for the respective user based on the user data. The server generates, for a plurality of content items of the second content domain consumed by users other than the respective user, a respective content item embedding. The respective content item embedding is based on user embeddings of the at least one user other than the respective user. The server system determines, using the user embedding for the respective user and respective content item embeddings, a first content item in the second content domain that meets matching criteria for the respective user and provides the first content item to the respective user.

Abstract: Generating and providing a content feed to a user that surfaces information items that are determined to be interesting or relevant to the user including content that is determined to be “distant” to the user is provided. Explicit user actions are used to discover peers who are not colleagues of the user (e.g., peers with whom the user does not share a close organizational relationship, peers with whom the user does not regularly communicate, etc.), but who the user indicates an interest in via his/her actions. These peers are categorized as elevated peers of the user, and information items associated with and trending around the elevated peers are surfaced to the user in a content feed.

Abstract: The embodiment of the present disclosure discloses a method and device for displaying information. A specific mode of execution for the method comprises the following steps: in response to the detection of a first preset operation performed by a first user on the page of a second user, sending operation prompt information to a terminal device used by the first user, the page of the second user being used for exhibiting contents shared by the second user, the first preset operation being used for requesting to add a user label corresponding to the second user for the first user; in response to the detection of the second preset operation completed by the first user, adding the user label for the first user; generating an initial associated value used for indicating the association degree between the first user and the second user, and displaying the initial associated value on the page.

Abstract: A data server may support segment identification based on a selected user profile. For example, a user may select a user profile as the basis for identifying a segment of additional user profiles. The server may identify attributes associated with the selected user identifier and generate an expression based on the identified subset. The expression may include a normalization function corresponding to at least one attribute. The normalization function may identify correlated attribute values for an attribute associated with the selected user profile. The data server may query a data storage system to identify the additional user profiles based on the expression. The data server may also support user defined Boolean expressions such that the expression is used to identify user identifiers associated with a first attribute and a second attribute.

Abstract: A video recommendation method is provided, including: inputting a video to a first feature extraction network, performing feature extraction on at least one consecutive video frame in the video, and outputting a video feature of the video; inputting user data of a user to a second feature extraction network, performing feature extraction on the discrete user data, and outputting a user feature of the user; performing feature fusion based on the video feature and the user feature, and obtaining a recommendation probability of recommending the video to the user; and determining, according to the recommendation probability, whether to recommend the video to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adapting communications and interactions to enhance monitoring using remote devices. In some implementations, a system communicates with remote devices that are each configured to perform monitoring. The system generates records that specify outcomes or responses obtained after sending the messages. The generated records are used to create or update profiles for different categories of users. Each profile has a set of inclusion criteria defining the category corresponding to the profile, and stores data that characterizes effects of message attributes on outcomes or responses for users in the category corresponding to the profile. The system selects a profile for each member of a group of users involved in a particular monitoring program, then adapts communication for each user based on the profile selected for the user.

Abstract: A method, a device and electronic device for clarification question generation are provided in one or more embodiments of this disclosure. The method includes: extracting entity information from a fuzzy context input by a user; inputting the fuzzy context into a template generating module of a pre-built CQG neural network model so as to obtain a clarification question template; inputting the entity information into an entity rendering module of the CQG neural network model so as to obtain at least one entity phrase; and generating a clarification question for a fuzzy question based on the clarification question template and the at least one entity phrase for presenting to the user.

Abstract: A relationship network generation method and device, electronic apparatus, and a storage medium are provided, which are related to big data processing. In an implementation, at least one historical text data corresponding to N users within a preset duration is acquired, where N is an integer greater than or equal to 1; sampling is performed on at least one historical text data corresponding to the N users to obtain the sampled text data respectively corresponding to the N users; semantic vectors corresponding to the N users respectively are determined based on the sampled text data corresponding to the N users respectively, and a semantic relationship network involving the N users is generated based on the semantic vectors corresponding to the N users respectively.

Abstract: Techniques for implementing artificial crowd intelligence via networking of recommendation engines are disclosed. In some example embodiments, a base recommendation engine performs a computer-implemented method comprising: receiving a recommendation request; generating a first plurality of recommendations based on the recommendation request using a base recommendation model; obtaining one or more other recommendations from one or more other recommendation engines, each one of the other recommendation engines being configured to generate the other recommendations based on the recommendation request using a corresponding recommendation model; obtaining a corresponding weight for the other recommendation engine(s); selecting at least one recommendation from the first plurality of recommendations and the other recommendation(s) using the corresponding weight(s); and causing the selected recommendation(s) to be displayed.

Abstract: A system and method are presented for dialogue tree generation. The dialogue tree may be used for generating a chatbot. Similar phrases from phrases comprising the interactions between a first party and a second party are group together from the first party of a cluster. For each group of similar phrases, percentages are determined and compared against a threshold occurrence rate. Anchors are generated and used in alignment in the determination of dialogue flows. Topic-specific dialogue trees may be determined from the dialogue flows. The topic-specific dialogue trees may be modified to generate a deterministic dialogue tree.

Abstract: A system and method are provided for creating a social-networking community and enabling the social-networking community to interoperate with other social-networking communities within a network of social-networking communities. The method includes creating a core profile that links a user member's identify to plurality of social-networking communities of the network. The system enables user identity information, content, and friend information to be shared across social-networking communities of the network. The system also enables community content to be shared and tracked across social-networking communities of the network.

Abstract: This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Abstract: A method of generating recommendations for a collective profile, the collective profile being linked to a first profile and a second profile. The method may include authenticating a login request from an end user device in association with the collective profile based on credentials associated with the first profile, identifying a query from among a plurality of queries and transmit the query to the end user device, receiving a response to the query, determining that the response is not inconsistent with one or more earlier responses received in association with the second profile and, in response, refining at least one attribute or goal in the collective profile based on the response to generate and store a refined collective profile, and determining whether the refined collective profile results in a new recommendation and, if so, outputting the new recommendation.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a first contextual content item created by a first user. A user input is received from a second user indicating an intent to acquire the first contextual content item. The second user is provided with access to utilize the first contextual content item.

Abstract: A server obtains user data corresponding to a first content domain. The server identifies, from the user data, a plurality of labels. A respective label of the plurality of labels corresponds to a distinct characteristic of content items of the first content domain. The server utilizes a neural network to generate a plurality of user embeddings. A respective user embedding of the plurality of user embeddings includes a plurality of labels that correspond to a respective user. The server determines, using the plurality of user embeddings, a first content item of a plurality of content items of a second type that meets matching criteria for a first user. The server further provides, to a device of the first user, information that corresponds to the first content item of the second content domain.

Abstract: A method and apparatus of a device that performs a search using a deep link index is described. In an exemplary embodiment, the device receives a query on a device. The device additionally determines a plurality of results matching the query. The device further determines a subset of the plurality of results that correspond to at least one native application installed on the device. In addition, the device presents a link for each of the results in the subset of the plurality of results with data that launches the corresponding native application if that link is selected, where the link is a deep link that reference a location in the corresponding native application. Upon detecting one of the links corresponding to the subset of the plurality of results is selected, the device launches the corresponding native application with the data for that link.

Abstract: A method, apparatus and computer program product are provided to index a plurality of records based upon the similarity of the records along a plurality of dimensions. In the context of a method, one or more blocking keys are constructed for each of the plurality of records. A respective blocking key represents a string representation that combines components derived from attributes of a respective record, such as by concatenating components derived from attributes of the respective record. For a respective blocking key, the method determines a locality sensitive hash based upon the string representation of the respective blocking key. The method also includes indexing the respective record based upon the locality sensitive hash.

Abstract: Systems, methods, and computer-readable media for self-monitoring software usage to optimize performance are disclosed. The systems and methods may involve at least one processor configured to: maintain a table; present to an entity a plurality of tools for manipulating data in the table; monitor tool usage by the entity to determine at least one tool historically used by the entity; compare the at least one tool historically used by the entity with information relating to the plurality of tools to thereby identify at least one alternative tool in the plurality of tools whose substituted usage is configured to provide improved performance over the at least one historically used tool; and present to the entity during a table use session a recommendation to use the at least one alternative tool.

Abstract: Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning ranking. An example computing method includes receiving a search query and determining a plurality of machine learning model execution engines based on the search query and a plurality of search result types. The example computing method further includes generating a plurality of subsets of search results based on the search query and the plurality of machine learning model execution engines. The example computing method further includes generating a set of search results comprising at least one search result from each of the plurality of subsets of search results.

Abstract: A device may determine a multi-customer offer, wherein the multi-customer offer identifies a threshold quantity of customers of the multi-customer offer to allow access to the multi-customer offer. The device may receive one or more requests to accept the multi-customer offer, wherein a request, of the one or more requests, is associated with a customer device of the one or more customer devices. The device may determine, based on a quantity of requests of the one or more requests, that the threshold quantity of customers is not satisfied. The device may identify, based on the threshold quantity of customers not being satisfied, one or more candidate customer devices having a likelihood of requesting to accept the multi-customer offer, wherein the one or more candidate customer devices are associated with respective users that are the potential customers, and wherein the likelihood satisfies a threshold.

Abstract: A method for operating an influencer scoring model includes receiving, for a plurality of professionals, professional information and publication information. For each professional, the method also includes generating a professional profile that includes a plurality of attributes. The plurality of attributes are based on (i) professional information and (ii) publication information. The method also includes determining one or more attribute connections among the plurality of attributes of the professional profile. Each attribute connection is based on a common attribute shared between the respective professional and another professional. The method also includes generating a score that includes an authority component and an influence component. A scoring model is configured to receive the plurality of attributes and the attribute connections for the respective professional. The authority component represents at least one attribute corresponding to the received professional information.

Abstract: The present disclosure is directed toward systems and methods for ranking media effects. For example, systems and methods described herein enable a user to select and apply one or more media effects to a media communication such as a digital photograph or video. Systems and methods described herein identify and rank media effects based on characteristics associated with the user and the user's client-computing device. Furthermore, systems and methods described herein automatically present the top-ranked media effects to the user such that the user can easily select and apply one or more media effects that are tailored specifically to the user.

Abstract: Methods and systems for using block chain technology to verify transaction data are described herein. A computing platform may receive data about events related to transactions, personal or corporate information, supply chains, and other relevant information about a person or corporate entity. The event information may be received, aggregated, and processed to determine metadata about the person or corporate entity. The metadata may indicate, for example, a trustworthiness of the person or corporate entity for various purposes. Such event information and/or metadata may be stored as transactions in a block chain that may be accessible by counterparties to a potential transaction involving the person or corporate entity. The automated event processing computing platform may further use automated techniques to implement smart transactions between the person/entity and counterparty based on the trust metadata.

Abstract: A subject-based ranking determining method and system based on an interaction between a writer and a reader. A subject-based ranking determining method may include evaluating a writer that creates content of a corresponding subject for each subject based on the corresponding subject; and providing a search result in which an evaluation result of the writer on a subject corresponding to an input query is applied to a content ranking in response to input of the query.

Abstract: A method and a system for generating an object card are disclosed. The method comprises receiving a request for a digital news article; retrieving the digital news article; and identifying an object contained therein. A set of object features associated with the object is determined, and a score value for the object is generated. The score value is representative of a likelihood of the user executing a web search to locate additional information in respect to the object. In response to the score value being above a predetermined threshold, an object card is generated. The object card and the digital news article are then transmitted to the electronic device for display.

Abstract: One or more computing devices, systems, and/or methods are provided. An informational database may be analyzed based upon an entity to identify an informational article. The informational article may be analyzed to identify one or more first references associated with a first sentiment category and/or one or more second references associated with a second sentiment category. Sentiment tags, indicative of sentiment categories, may be assigned to one or more first reference content items associated with the one or more first references and/or to one or more second reference content items associated with the one or more second references. For each content item of a plurality of content items associated with the entity, a sentiment category associated with the content item may be determined based upon a comparison of the content item with the one or more first reference content items and the one or more second reference content items.

Abstract: A method of pushing information is provided. According to an example, a search server obtains a natural search list including a first threshold number of natural search materials and a first evaluation score of each of the natural search materials by invoking a natural search service to perform a search operation on a search word, obtains a push information list including a second threshold number of push materials and a second evaluation score of each of the push materials by invoking a push information search service to perform a search operation on a search word, integrates the first evaluation score and the second evaluation score of a material existing in the natural search list and the push information list at the same time, re-ranks the natural search materials according to integrated evaluation scores, and pushes re-ranked natural search materials.

Abstract: Embodiments of the present invention provide systems and methods for synchronizing document updates. An end-user subscribes to document updates of interest to the end-user. The contents associated with these updates are contained within one or more document sources, wherein the one or more document sources are used to construct an outputted document. Tags are utilized to monitor these updates and a fragmentation is performed in order to incorporate the modified content, associated with the updates, into a new outputted document.

Abstract: Aspects of the present invention disclose a method for analyzing data from a plurality of data sources. The method includes extracting features of data received from a first source and from a second source by analyzing the data received from the first source of data and from the second source. The method includes processors determining a topic modeling framework, wherein the topic modeling framework detects a semantic structure of the features of the data received from the first data source and the second source. The method includes processors applying the topic modeling framework to the data received from the first source of data the second source of data. The method includes generating a final entity output, wherein the final entity output includes a cluster of entity mentions that the applied topic modeling framework extracts from the first source of data and the second source of data are combined.

Abstract: Embodiments for cognitively identifying a propensity for obtaining white space target entities by a processor. Similarities between one or more potential target entities and current entities may be compared according to structured data and unstructured data. A propensity to engage in a transaction agreement may be determined for the one or more potential target entities according to the similarities and historical transaction agreements.

Abstract: Systems and methods of providing information via a computer network are provided. A data processing system can identify a cluster that includes a plurality of online content items having a semantic or user similarity. The data processing system determines a plurality of cluster placement criteria of the cluster, and receives content configured for display with a web page. The content can be associated with the cluster based on the semantic or user similarity. A cluster placement criterion of the plurality of cluster placement criteria can be selected based on a quality metric of the selected cluster placement criterion, and the selected cluster placement criterion can be provided as a supplemental criterion used to select the content for display with the web page.

Abstract: A method and system for creating secondary copies of data whose contents satisfy searches within data stores is described. In some cases, the system searches for data within a data store, identifies a set of data that satisfies the search, copies the identified set of data, and transfers the copy to secondary or other storage. In some cases, the system utilizes search-based secondary copies of days during restoration processes in order to restore data similar to and/or associated with data requested to be restored.

Abstract: An apparatus, method and associated system is described for the production of search results that are determined to be of interest to the user based on both the search phrase and the level of expertise of the user. Literature is analyzed from a plurality of different domains, and a database, map and/or lexicon is built that categorizes the literature by different levels of expertise. Each item of literature is assigned a particular level of expertise. At least one keyword in a user's search query is analyzed and compared with at least part of the database, and a user's level of expertise is based, at least in part, on the comparison. A set of search results is generated for the search query that is weighted, at least in part, based on a correlation between the user's level of expertise and the particular level of expertise assigned to each item of literature.

Abstract: A method, an apparatus and an electronic device for performing entity linking, and a non-transitory computer-readable recording medium are provided. The method includes constructing training data including a plurality of sets of labeled data using an existing unambiguous entity database where unambiguous entities corresponding to respective entity words are stored, each set of the labeled data including a text having an entity word and an unambiguous entity linked with the entity word; training an unambiguous entity recognition model whose output is a matching probability between an entity word in a text and an unambiguous entity using the training data; and inputting a text having an entity word to be recognized into the unambiguous entity recognition model, and determining an unambiguous entity linked with the entity word to be recognized based on an output result of the unambiguous entity recognition model.

Abstract: Techniques are disclosed for providing recommendations related to digital content. In some embodiments, historical content data may be analyzed to identify abandonments by a plurality of user devices with respect to viewing digital content. The historical content data may indicate viewing behavior associated with the plurality of user devices and the digital content. An index within the digital content may be calculated based at least in part on the abandonments. For example, the index may correspond to a time within the digital content at which a percentage of the plurality of user devices that abandoned the digital content feel below a threshold value. A recommendation related to the digital content may be provided comprising an indication of the index determined for the digital content.

Abstract: A method for extracting structure from networks includes receiving an edge list, where the edge list defines a network including nodes and edges connecting the nodes to each other, where the edges define a strength of a relationship between connected nodes and filtering nodes from the edge list based on a predetermined filter parameter, thereby forming a filtered network. The method further includes identifying distinct connected components within the filtered network, analyzing each of the distinct connected components of the filtered network for the presence of additional structures within the distinct connected components, where the additional structures are decomposed into additional distinct connected components.

Abstract: A digital assistant supported on computing devices such as smartphones, tablet computers, personal computers (PCs), wearable devices, game consoles, connected car devices, virtual and mixed reality devices, and the like is configured to interact with a web browser to open multiple websites within a group responsively to a single voice input at a natural language interface. The user can select websites that are included in a given group through a user interface (UI), or the computing device may be configured to automatically create or recommend groups to the user based on monitored interactions and/or user behaviors (where the monitoring is performed with notice to the user and user consent).

Abstract: A method for generating one or more push notifications to a user device is described. The method comprises: obtaining history data representing a history of online activities of a user and candidate data representing a set of candidate information; generating, based on the history data and the candidate data, user profile vectors representing a user profile associated with the user and content vectors representing a set of content profiles associated with the set of candidate information; generating, based on a machine learning model trained with a history of online activities, embedding user feature vectors and embedding content feature vectors based on the history data and the candidate data; and providing for transmission information for one or more push notifications including first candidate information of to a user device associated with the user, the first candidate information being determined from the set of candidate information based on the aforementioned vectors.

Abstract: Systems, methods, and non-transitory computer readable media configured to determine a degree of separation between a user and a connection within a social network of the user, the connection associated with an interaction from which at least topic is determined. A value of affinity between the user and the connection is determined. A weight reflecting a value of interest similarity between the user and the connection is determined. A term based on the degree of separation, the value of affinity, and the weight reflecting a value of interest similarity is calculated. Terms associated with the at least one topic are combined to generate a composite score associated with the at least one topic to determine whether to present the at least one topic to the user.

Abstract: An application recommending method includes acquiring a first behavior eigenvalue according to behavior data of a first user. It is determined that at least one second user from a user relationship chain of the first user according to the first behavior eigenvalue. The second user is on the user relationship chain of the first user. A degree of similarity between a second behavior eigenvalue and the first behavior eigenvalue is greater than a preset threshold, and the second behavior eigenvalue is a behavior eigenvalue of the second user. A to-be-recommended application for the first user on the basis of behavior data of the at least one second user is determined.

Abstract: A method for performing interaction in a chessboard interface includes: detecting an operation of triggering a chessboard interface to select an interaction area; locating a square in which the operation is located; determining a first movement amount of the square, where the first movement amount is obtained by counting movement operations of a user performed on squares in the chessboard interface; and magnifying the chessboard interface according to the first movement amount.

Abstract: In an example embodiment, one or more sample ideal candidate member profiles in a social networking service are obtained, as well as one or more sample search result member profiles in the social networking service. Then, for each unique pair of sample ideal candidate member profile and sample search result member profile, a label is generated using a score generated from log information of the social networking service, the log information including records of communications between a searcher and members of the social networking service, the score being higher if the searcher communicated with both the member corresponding sample ideal candidate member profile and the member corresponding to the sample search result member profile in a same search session. The generated labels are fed into a machine learning algorithm to train a combined ranking model used to output ranking scores for search result member profiles.

Abstract: An approach for utilizing a motivational effect value for music on a computing device, the approach involves determining a performance indicator for a first segment of distance traveled, retrieving one or more performance factors associated with the first segment, calculating a first motivational effect value for one or more songs associated with the first segment, wherein the calculating is based on the performance indicator and the one or more performance factors, developing a playlist of music based on a plurality of motivational effect values, wherein the developing comprises at least one of generating a new playlist and modifying an existing playlist, and developing a playlist of suggested music based on receiving one or more motivational effect values associated with one or more groups of users.

Abstract: The present disclosure is directed toward systems and methods for ranking media effects. For example, systems and methods described herein enable a user to select and apply one or more media effects to a media communication such as a digital photograph or video. Systems and methods described herein identify and rank media effects based on characteristics associated with the user and the user's client-computing device. Furthermore, systems and methods described herein automatically present the top-ranked media effects to the user such that the user can easily select and apply one or more media effects that are tailored specifically to the user.