A natural language dialog method and a natural language dialog system are provided. In the method, a first speech input is received and parsed to generate at least one keyword included in the first speech input, so that a candidate list including at least one report answer is obtained. According to a properties database, one report answer is selected from the candidate list, and a first speech response is output according to the report answer. Other speech inputs are received, and a user's preference data is captured from the speech inputs. The user's preference data is stored in the properties database.

Systems, methods, and tangible, non-transitory, computer readable media is described herein. For example, a system includes a portable non-destructive testing (NDT) device. The NDT device includes a display, a user interface, a memory storing an operations object having a first text in a first language, and a processor. The processor is configured to present the first text on the operations object via the display during an operation of the portable NDT device, and wherein the processor is configured to create a second text in a second language via the user interface of the NDT device, and to present the second text on the operations object as an alternative to the first text via the display during the operation of the NDT device.

Embodiments of the present application relate to a system for implementing screen capture, a method for implementing screen capture, and a computer program product for implementing screen capture. A method for implementing screen capture is provided. The method includes providing multiple types of screen capture adapters, selecting a screen capture adapter that is of a type corresponding to a preset mobile terminal application type as a target type screen capture adapter, the screen capture adapters being selected from among the provided multiple types of screen capture adapters, registering the target type screen capture adapter, providing screen capture implementing techniques that correspond to the multiple types of screen capture adapters, and performing screen capture by invoking a screen capture implementing technique that corresponds to the registered target type screen capture adapter, the screen capture implementing technique being selected from among the provided screen capture implementing techniques.

Natural language understanding (NLU) engines perform better when they are trained with large amounts of data. However, a large amount of data is not always available. Embodiments of the present invention overcome this problem by generating annotated data for use in a NLU system. An example embodiment generates annotated data by parsing an input annotated phrase, generating a syntactic tree reflecting a grammatical structure of the parsed phrase, and generating one or more alternative versions of the input annotated phrase based on the syntactic tree. Alignment between expressions and corresponding annotations in the annotated phrase are preserved in the one or more alternative versions generated to ensure intention of the input annotated phrase is maintained.

Herein is described a data-parallel and sparse algorithm for topic modeling. This algorithm is based on a highly parallel algorithm for a Greedy Gibbs sampler. The Greedy Gibbs sampler is a Markov-Chain Monte Carlo algorithm that estimates topics, in an unsupervised fashion, by estimating the parameters of the topic model Latent Dirichlet Allocation (LDA). The Greedy Gibbs sampler is a data-parallel algorithm for topic modeling, and is configured to be implemented on a highly-parallel architecture, such as a GPU. The Greedy Gibbs sampler is modified to take advantage of data sparsity while maintaining the parallelism. Furthermore, in an embodiment, implementation of the Greedy Gibbs sampler uses both densely-represented and sparsely-represented matrices to reduce the amount of computation while maintaining fast accesses to memory for implementation on a GPU.

In some cases, a handheld device that includes a microphone and a scanner may be used for voice-assisted scanning. For example, a user may provide a voice input via the microphone and may activate the scanner to scan an item identifier (e.g., a barcode). The handheld device may communicate voice data and item identifier information to a remote system for voice-assisted scanning. The remote system may perform automatic speech recognition (ASR) operations on the voice data and may perform item identification operations based on the scanned identifier. Natural language understanding (NLU) processing may be improved by combining ASR information with item information obtained based on the scanned identifier. An action may be executed based on the likely user intent.

In one aspect, a method includes (a) accessing, by a computing system, a social media (SM) platform, (b) selecting a SM content item published on the SM platform, (c) responsive to the selection, accessing a webpage of the SM platform, (d) detecting that the webpage contains a nested link object, (e) selecting the nested link object to display the hidden SM content item(s) on the webpage, (f) responsive to selecting the nested link object, evaluating the displayed hidden SM content item(s) on the webpage to determine whether the selected SM content item is displayed on the webpage, (g) repeating acts (d)-(f) until the computing system determines that the selected SM content item is displayed on the webpage, and (h) responsive to determining that the selected SM content item is displayed on the webpage, retrieving the selected SM content item via the webpage.

This disclosure generally covers systems and methods that, in some embodiments, provide an electronic survey template for creating a user customizable electronic survey including authentication features. Those authentication features include, in some embodiments, authenticating questions with elements that capture a digitally drawn signature, digital image, fingerprint, or voiceprint. Certain embodiments of the disclosed systems and methods provide a graphical user interface comprising an electronic survey template with a menu of survey question types, including an option to create authenticating questions within the electronic survey template. Some embodiments of the disclosed systems and methods also provide functions and features that allow users to preview a customized electronic survey template as an interactive electronic survey or to preview individual electronic survey questions as interactive electronic survey questions.

The present disclosure is directed toward systems and methods for maintaining semantic information in a document from a web page. For example, one or more embodiments described herein encode unique colors into an HTML DOM associated with a web page prior to passing the HTML DOM through an existing rendering engine. In response to receiving a color-coded graphical objects representative of the HTML DOM, systems and method described herein apply the original semantic attributes of the web page into the graphical objects based on the unique color encoding.

A system for rapid deployment and configuration of a virtual agent to a hosted cloud platform is provided. A virtual agent builder may convert a dialog corpus into a dialog model that includes parameters that cause a cognitive service engine to provide natural language processing for the virtual agent according to the dialog corpus. Depending on the natural language processing capabilities of the cognitive engine service, the dialog model may be included in the virtual agent or communicated to the cognitive service engine. The virtual agent, or individual components of the virtual agent, may be generated and/or reconfigured in real time using predetermined logic that is selected based on virtual agent configuration parameters. The virtual agent configuration parameters may be received from a graphical user interface that reduces the complexity of deploying and/or managing the virtual agent.