Abstract: Herein is a machine learning (ML) explainability (MLX) approach in which a natural language explanation is generated based on analysis of a parse tree such as for a suspicious database query or web browser JavaScript. In an embodiment, a computer selects, based on a respective relevance score for each non-leaf node in a parse tree of a statement, a relevant subset of non-leaf nodes. The non-leaf nodes are grouped in the parse tree into groups that represent respective portions of the statement. Based on a relevant subset of the groups that contain at least one non-leaf node in the relevant subset of non-leaf nodes, a natural language explanation of why the statement is anomalous is generated.

Abstract: Aspects of the disclosure are directed to a system for classifying software as malicious or benign based on predicting the effect the software has on the platform before the software is actually deployed. A system as described herein can operate in close to real-time to receive, isolate, and classify software as benign or malicious. Aspects of the disclosure provide for accurate classification of malicious programs or scripts even if ostensibly the program appears benign, and vice versa, based on the effect predicted by a machine learning model trained as described herein. The system can also be implemented to isolate and verify incoming scripts or software to the platform, to provide a predicted classification while not substantially impacting processing pipelines involving platform resources or the user experience with the platform in general.

Abstract: Techniques are disclosed relating to creating routing connections between graphical elements in a process flow. A computer system may provide process flow information that is executable by a client system to display a graphical user interface (GUI) associated with a process diagram flow. The client system may be able to output, via the GUI, a graphical representation of the process flow. The graphical representation may include graphical elements indicative of process steps and graphical connections between the graphical elements. Via the GUI on the client system, a user may request a graphical connection going from a first graphical element to a second graphical element. The computer system may update the process diagram with the graphical connection where the graphical connection is routed based on a predetermined set of connection rules for the process diagram.

Abstract: Approaches for analyzing an input image and providing one or more outputs related to the input image are provided. In accordance with an exemplary embodiment, an input image may be received and analyzed, using a trained machine learning model, to generate an inference related to the image. Based, at least in part, upon the generated inference, one or more reports related to the inference can be generated and provided for presentation on a user device. A user can interact with the report in a conversational manner with the computer system to generate additional reports or insights related to the input image.

Abstract: Systems and methods for query processing are described. Embodiments of the present disclosure identify an original query; generate a plurality of expanded queries by generating a plurality of additional phrases based on the original query using a causal language model (CLM) and augmenting the original query with each of the plurality of additional phrases, respectively; and provide a plurality of images in response to the original query, wherein the plurality of images are associated with the plurality of expanded queries, respectively.

Abstract: Described herein is a technique for processing a received media content item (e.g., a message), received at a messaging application of a first end-user of a messaging service, to generate a selection of some predetermined number of recommended stickers. The recommended stickers are then presented in a user interface to the first end-user, allowing the first end-user to select a sticker for use in replying to the received media content item. To generate the selection of recommended stickers, in response to receiving the media content item, the messaging application processes the media content item to identify specific attributes and characteristics (e.g., text included with the message, stickers used with the message, and other contextual metadata). The identified attributes and characteristics of the received message are then processed by a scoring model to identify the predetermined number of stickers for presenting in the reply interface as recommended reply stickers.

Abstract: Described are systems and methods for securely distributing computational analysis across analytics nodes. In some embodiments, a system includes a plurality of analytics nodes with each analytics node managing access to its own data sources. The system includes an analytics controller configured to interact with a user to generate an analytic request including a selection of one or more analytics and a selection of one or more data sources determined based on the one or more selected analytics. The generated analytic request is transmitted to one or more analytics nodes corresponding to the one or more selected data sources. Each analytics node that receives the analytic request is configured to execute the analytic request to generate a result. The result from each analytics node of the one or more analytics nodes can be transmitted to the user issuing the analytic request.

Abstract: A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.

Abstract: Implementations of this disclosure provide a search assistant engine that integrates with a data intake and query system and provides an intuitive user interface to assist a user in searching and evaluating indexed event data. Additionally, the search assistant engine provides logic to intelligently provide data to the user through the user interface such as determining fields of events likely to be of interest based on determining a mutual information score for each field and determining groups of related fields based on determining a mutual information score for each field grouping. Some implementations utilize machine learning techniques in certain analyses such as when clustering events and determining an event templates for each cluster. Additionally, the search assistant engine may import terms or characters from user interaction into predetermined search query templates to generate tailored search query for the user.

Abstract: Protecting against a tracking parameter in a web link. In one embodiment, a method may include receiving an input URL during a browser navigation session on a user device, the input URL including parameters, determining that the parameters include a tracking parameter, pausing the browser navigation session on the user device, launching the input URL in a headless browser that operates in an isolated environment that simulates one or more features of the user device, landing on a destination web page in the isolated environment, identifying a URL of the destination web page as a destination URL, and resuming the browser navigation session on the user device by replacing the input URL, which includes the tracking parameter, with the destination URL, which does not include the tracking parameter, in order to protect the user device from the tracking parameter.

Abstract: A computer-implemented method for facilitating the creation of food and/or beverage product concepts, comprising: providing a plurality of content items obtained from one or more sources, each content item comprising structured or unstructured text, at least one of the content items comprising text that pertains, at least in part, to one or more food and/or beverage products, assigning, to each content item, one or more taxonomic labels, wherein each label comprises a term contained in a pre-defined taxonomy of terms and each label assigned to a respective content item is selected based on the particular language used in the respective content item, receiving, from a user, a query specifying a first term; in the event that the first term comprises a taxonomic label from the pre-defined taxonomy of terms; identifying one or more pairs of terms, each pair of terms comprising the first term and a respective other one of the taxonomic labels; determining, for each pair of terms, an association score, wherein the

Abstract: A method of evaluating threats to a network may gather existing threat from a plurality of online sources, collect the existing threats in a database and format the data representing existing threats in the database for review. The method may determine a rating for each existing threat, evaluate attractiveness of honeypots to threats and adjusting the ratings for the threats based on the attractiveness of the honeypots. The method may evaluate applications on network, rank the threats based on the apps and communicate the rankings to a user.

Abstract: Aspects described provide systems and methods that relate generally to image analysis and, more specifically, identifying individual components and elements in an image. The systems and methods include a valuation application executing one or more application program interfaces (APIs) communicating with one or more websites via a network, where the user is prompted to enter information and/or take pictures or videos of their vehicle that they would like to sell. The valuation application utilizes a machine learning model to identify and value the various vehicle components within the images and videos. Based on the machine learning model, the valuation application identifies each component according to the images and videos and performs a search to determine the value of the components identified. The valuation application tabulates and summarizes the vehicle component resale values and resell information for the user to view.

Abstract: Systems and methods for implementing a multi-factor financial ontology framework are disclosed. In exemplary embodiments, a computer-implement method executing on a computer receives a natural language query from a user device and parses the query to determine a set of natural language terms associated with financial product criteria. The computer system maps the natural language terms to data nodes that implement the financial ontology framework and identifies responsive financial products from those data nodes. The computer system transmits the data corresponding to the responsive financial product to the user device.

Abstract: The present disclosure relates generally to systems, methods, and computer-readable media for selectively identifying candidate keywords for a target domain, generating keyword clusters based on the candidate keywords, and implementing the candidate keywords within published online content. In particular, systems disclosed herein generate or otherwise obtain access to a collection of keywords and value metrics descriptive of a profile of the keywords with respect to a target domain. The systems can selectively identify candidate keywords having unique value to a domain and generate keyword clusters including the keywords and associated terms. The systems described herein can further implement the keyword clusters within a structure of published content items that are linked or otherwise associated with the target domain.

Abstract: A method of operating a captioned telephone comprising the steps of dialing a telephone number to a relay gateway, connecting to the gateway over a communication network, performing a test to assess communication network quality, based on the test results, setting up the captioned telephone to operate in at least one of a first mode and a second mode wherein each of the first and second modes is one of (i) a PSTN mode in which data is communicated between the captioned telephone and the relay gateway via analog transmission and (ii) an IP mode in which data is communicated between the captioned telephone and the relay gateway via the Internet.

Abstract: A system and method for creating a menu for an adapted a medical workflow implemented at a computer coupled to a hospital network is disclosed. The disclosed system and method generates a workflow including a list of predicted medical action options for a medical object based, in part, on a determined operating state or vital state of a patient, creates a menu for displaying the list of predicted medical action options, and communicates the menu for display on a graphic interface. Certain menu selections pertaining to predicted medical action options may be disabled based on state values associated with the medical object.

Abstract: The present disclosure relates to a method, device and product for managing a plurality of users of an application system. According to example implementations of the present disclosure, a method is provided for managing a plurality of users of an application system. In the method, a group of users matching a search keyword from a requester user are determined among the plurality of users, the search keyword comprising at least one part of an identifier of a desired user. A requester layer of the requester user is determined in a tree structure comprising hierarchical relations among the plurality of users. A group of layers of the group of users are determined in the tree structure, respectively. The group of users are sorted based on the requester layer and the group of layers. With example implementations of the present disclosure, a user which the requester user is looking for may be sorted at a top place so as to be selected by the requester user.

Abstract: Securing information within a user interface can include mapping, using a processor, an electronic mail address to an avatar, wherein the mapped electronic mail address and the avatar are stored within a data storage device, and generating, using the processor, a user interface including a message correlated with the electronic mail address. The user interface displays the avatar of the electronic mail address in place of at least one of a name for the electronic mail address or the electronic mail address.

Abstract: In some embodiments, an electronic device receives, via one or more input devices, an input corresponding to a request to search content available on the electronic device, wherein the input includes one or more search terms. In some embodiments in response receiving the input corresponding to the request to search content available on the electronic device, an electronic device displays, via a display device, one or more representations of one or more search results including a first representation of a first search result, wherein the first search result is a first content item that is associated with a first transcript of dialog included in the first content item, and the first search result is included in the one or more search results as a result of a relationship between the one or more search terms and the first transcript for the first content item.

Abstract: Protecting against a tracking parameter in a web link. In one embodiment, a method may include receiving an input URL during a browser navigation session on a user device, the input URL including parameters, determining that the parameters include a tracking parameter, pausing the browser navigation session on the user device, launching the input URL in a headless browser that operates in an isolated environment that simulates one or more features of the user device, landing on a destination web page in the isolated environment, identifying a URL of the destination web page as a destination URL, and resuming the browser navigation session on the user device by replacing the input URL, which includes the tracking parameter, with the destination URL, which does not include the tracking parameter, in order to protect the user device from the tracking parameter.

Abstract: A search engine for objects in a corpus of document dynamically evaluates search rank of the objects through Natural Language Processing and machine learning. When a search query is received for a first object, the search engine identifies search results including a plurality of source values that are tied to the first object in the corpus of published documents. A search rank is computed for each identified search result based on content of direct textual references to each of the plurality of source values within the corpus of published documents, as well as a weight assigned to each published document. The identified search results are returned according to the computed search rank.

Abstract: This disclosure is directed to systems and methods for generating correlated load test scripts for use in load testing by receiving an archive of transaction records, each transaction record including a request and a response, organizing the archive of transaction records, determining a collection of transaction records, generating a plain load test script, and correlating the plain load test script to generate a correlated load test script.

Abstract: A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.

Abstract: Systems, methods, and non-transitory computer readable media are configured to train a machine learning model. The training can be based on a training set of embeddings of a first type and a training set of embeddings of a second type. The machine learning model can be trained to receive an embedding of a second type and to output a corresponding embedding of the first type. A given embedding of the second type can be provided as input to the machine learning model. An embedding of the first type can be obtained from the machine learning model. The embedding of the first type can correspond to the given embedding of the second type.

Abstract: Methods for operating a vehicle inspection or measurement system to facilitate selection of specification sets associated with a vehicle undergoing inspection or measurement based on an evaluation of vehicle identifying features and acquired vehicle measurement.

Abstract: Provided is a method of managing a landing page by an electronic apparatus, in which the method includes acquiring first information on a user terminal and second information for the landing page in response to a request for accessing the landing page from the user terminal, generating address information for the landing page based on the first information and the second information, and providing the landing page to the user terminal based on the address information.

Abstract: Providing a recommendation for a specific item of interest using a recommendation system, by obtaining information concerning items of interest offered by multiple business places, receiving a query concerning the specific item of interest from an electronic device, obtaining objective information concerning business places offering the specific item of interest, and outputting one or more business places that offer the specific item of interest based on a function, said function receiving the objective information as input.

Abstract: The present disclosure provides a system and a method for generating an imaging report. The method may include obtaining first imaging information and second imaging information. The first and second imaging information may be acquired from an examination region of a subject using a first imaging device or a second imaging device, respectively. The method may include identifying at least one first target ROI based on the first imaging information, and determining first reporting information corresponding to the at least one first target ROI. The method may include identifying at least one second target ROI with respect to the second imaging information based on the at least one first target ROI, and determining second reporting information corresponding to the at least one second target ROI. The method may further include generating a report based on at least a part of the first reporting information or the second reporting information.

Abstract: An intelligent workspace is disclosed. In example embodiments, methods and systems for operating the intelligent workspace on an application of a computing device are disclosed. The workspace includes various tools utilizing user behavioral analytics and user role information for dynamically operating on applications like procurement applications. The systems and methods reduce operational time of the user and enhance the user experience.

Abstract: A processor may analyze one or more sections of code within a program. The processor may compute a context for each of the one or more sections of code. The processor may generate one or more search terms that are respectively associated with each of the one or more sections of code. The processor may automatically display reference data to a user.

Abstract: A computing system may receive a first user input providing an indication for a search of stored data. The system may generate a list of search criteria in a first graphical user interface. The system may receive a first selection of one or more search criteria from the list of search criteria. The system may generate a selected search criteria interface in a second graphical user interface comprising a graphical Boolean switch between each of adjoining search criteria. The system may receive a second user input for setting the graphical Boolean switch. The system may generate a first logical expression for a search based at least in part on the selected search criteria and positions of a plurality of graphical Boolean switches between the selected search criteria. The system may generate a search result of the stored data based at least in part on the first logical expression.

Abstract: In an approach to detecting the transmission of messages, analyzing said messages, calculating a message risk score and transmitting a warning notification, one or more computer processors detect transmission of a message from a user to a selected recipient. The one or more computer processors extract message information from the detected message. The one or more computer processors retrieve one or more historical conversations between the user and the selected recipient of the detected message. The one or more computer processors determine a risk score corresponding to sending the detected message to the selected recipient based on applying the extracted message information and the retrieved historical conversations to a cognitive model.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for determining a topic. A specific embodiment of the method comprises: determining a to-be-recognized sentence sequence; calculating similarities between the to-be-recognized sentence sequence and each of topic templates in a topic template set in a target area, the each of the topic templates in the topic template set corresponding to a topic in at least one topic in the target area, the topic template including a topic section sequence, and a topic section including a topic sentence sequence; and determining a topic of the to-be-recognized sentence sequence according to an associated parameter, the associated parameter including the similarities between the to-be-recognized sentence sequence and the each of the topic templates in the topic template set. This embodiment reduces labor costs during a topic segmentation.

Abstract: An example method includes obtaining, by a processor on an end user device, from an operating system of the end user device, a permission to access the operating system by a malicious software management application, receiving, by the processor via the malicious software management application from the operating system, a first set of click information indicative of a set of clicks detected by an input-output interface of the end user device and a second set of click information indicative of a set of clicks detected by a web browser of the end user device, identifying, by the processor via the malicious software management application based on the first and second sets of click information, a presence of a click generating application on the end user device, and initiating, by the processor via the malicious software management application based on the presence of the click generating application, a mitigation action.

Abstract: Disclosed herein are techniques related to automated generation of regular expressions. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence.

Abstract: When sharing events between users, the sharing users and the recipient users often have different relationships with details of the events. An event structurer enables sharing users to share events via a single user interface with recipients and tailor what aspects of the events are shared, thus ensuring the relevant portions of the events are properly presented to new recipients based on their new relationship with the event's details.

Abstract: A computer-implemented method is provided for comparing the security profile of a particular entity to peer entities. The method can include receiving, for a particular entity, (i) a value for at least one feature and (ii) a number of security records of one or more security risk types. The method can include determining peer entities based on the value of the features; obtaining, for each peer entity, a number of security records; and adjusting the number of peer security records based on the number of entity security records. The method can further include comparing, for one or more security risk types, the received number of security records for the particular entity to the respective adjusted number of security records for each peer entity; and comparing a security profile of the particular entity to security profiles of the population of peer entities based on the comparison for the security risk types.

Abstract: Embodiments may process search input for different users based on classifications of information and based on emotional content of search commands from the users. For example, a method may comprise receiving, at a computer system, speech data from a client device, the speech data representing a voice command from a user, obtaining, at the computer system, a plurality of items of content responsive to the voice command by searching for content, determining, at the computer system, at least one class related to the voice command, classifying, at the computer system, each obtained item of content into at least one class, identifying, at the computer system, at least one item of content classified into at least one class related to the voice command, and transmitting, at the computer system, the at least one identified item of content.

Abstract: Embodiments can include an information pushing method and device. An embodiment of the method can include: receiving an information stream data acquisition request sent by a terminal, wherein the information stream data acquisition request comprises query information; performing a query according to the query information to obtain first information stream data; acquiring at least one of a search record or a browsing record of an account associated with the terminal with respect to a predetermined time period; determining, based on the at least one of the search record or the browsing record, a keyword; determining second information stream data located in a preset information stream data set and matching the key word; generating, based on the first information stream data and the determined second information stream data, data to be pushed; and pushing to the terminal the data to be pushed. The embodiment can achieve targeted information pushing.

Abstract: A search engine determines a number of pages to present to a user based on one or more of a variety of factors. The search engine may send the search results to a client machine, which may present a subset of the results along with a pagination control in a scrollable interface. The pagination control may present the number of pages determined by the search engine. The search engine may also determine a number of search results to present prior to the presentation of non-scrollable user interface (UI) elements based on the same or different factors. After the amount of scrolling exceeds a threshold, a non-scrollable UI element may be displayed. Additional thresholds may exist, such that additional non-scrollable UI elements are added as the user continues to scroll.

Abstract: Functionality is disclosed herein for using a framework for a VR/AR application to utilize different services. In some configurations, a VR/AR application can utilize different services, such as an animation service, a multi-modal disambiguation service, a virtual platform service, a recognition service, an automatic speech recognition (ASR) service, a text-to-speech (TTS) service, a search service, as well as one or more other services. Instead of a developer of the VR/AR application having to develop programming code to implement features provided by one or more of services, the developer may utilize functionality of existing services that are available from a service provider network.

Abstract: A system includes a processor and a memory accessible to the processor. The memory stores instructions that, when executed, cause the processor to provide a graphical user interface (GUI) including a plurality of user-selectable elements accessible by a user to select a patent strength calculator from a plurality of patent strength calculators, to edit a patent strength calculator, or to create a new patent strength calculator. The memory further stores instructions that, when executed, cause the processor to apply a selected patent strength calculator to a list of documents to determine a patent strength score for each patent of the list of documents.

Abstract: A system and method for creating a menu for an adapted a medical workflow implemented at a computer coupled to a hospital network is disclosed. The disclosed system and method generates a workflow including a list of predicted medical action options based on an identified healthcare worker and based on a determined operating state or vital state of a patient, creates a menu for displaying the list of predicted medical action options, disables one or more of the predicted medical action options in the menu based on the determined one or more state values associated with an identified medical object, and communicates for display on a graphic interface the menu comprising the disabled one or more predicted medical action options, wherein the disabled one or more predicted medical action options is visible in the menu but unselectable by the healthcare worker.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for pushing information. A specific embodiment of the method includes: acquiring, in response to a user selecting historical search data, a webpage content corresponding to the historical search data; dividing the webpage content into at least one webpage content segment, and extracting a topic of the at least one webpage content segment; and pushing information to the user based on the topic of the at least one webpage content segment. This embodiment can quickly push core information of a webpage to the user when the user browses the webpage again.

Abstract: An electronic device includes a touchscreen display, a microphone, at least one speaker, a processor and a memory which stores instructions that cause the processor to receive a user utterance including a request for performing a task with the electronic device, to transmit data associated with the user utterance to an external server, to receive a response from the external server including sample utterances representative of an intent of the user utterance and the sample utterances being selected by the external server based on the user utterance, to display the sample utterances on the touchscreen display, to receive a user input to select one of the sample utterances, and to perform the task by causing the electronic device to follow a sequence of states associated with the selected one of the sample utterances.

Abstract: A method and system. A first interest value is determined. The first interest value is associated with a first combination of one or more concepts derived from one or more word objects extracted from a message on which an action is to be performed. The first interest value is determined to be at least a specified first threshold value and in response, a concept interest dataset is updated. The concept interest dataset prior to being updated includes combinations of at least one concept. Each concept of the at least one concept has been derived from a previous processing of messages. The updated concept interest dataset includes the first combination and a cumulative interest value that encompasses the first interest value.

Abstract: First and second data catalogs each indicate sensing data attributes. The first and second data catalogs each include a first word indicating an observation object of a sensor that generated sensing data and a second word indicating an observation characteristic of the sensor. A score calculation unit includes a first weight determination part, a second weight determination part, and a score calculation part. The first weight determination part determines a first weight value relating to the observation object, based on the relationship between the first words included in the first and second data catalogs. The second weight determination part determines a second weight value relating to the observation characteristic, based on the relationship between the second words included in the first and second data catalogs. The score calculation part calculates a score relating to the coincidence of the first and second data catalogs, using the first and second weight values.

Abstract: Aspects of the subject disclosure may include, for example, detecting, by a processing system including a processor, access to a search engine by a user; obtaining a user model associated with the user; generating, by the processing system, a search query according to the user model; and presenting an overlay on a graphical user interface of the search engine, wherein the graphical user interface includes the search query field, and wherein the overlay includes the search query. Other embodiments are disclosed.

Abstract: Disclosed herein are system, method, and computer program product embodiments for mitigating similar and/or duplicate data. An embodiment operates by a computing device receiving a first and second code segment and parsing the first and second code segments into a first and second abstract syntax tree (AST), respectively. Thereafter, the computing device generates a first and a second normalized. AST corresponding to the first and second ASTs, respectively, based on a normalization rule such that the first and second normalized ASTs correspond to a first and second normalized code segment. The computing device then derives analytical information of the first and second normalized ASTs based on the first and second normalized code segments.