23 results about "Language processor" patented technology

Visual language processors that include an image encoder configured to convert an image into a low-resolution feature map, a feature refinement network configured to upsample the low-resolution feature map into a high-resolution feature map, and a visual-language connector configured to map an image-level feature map and a region-level feature map both derived from the high-resolution feature map into an embedding space of a language encoder.

There are provided systems and methods for named entity recognition in chat dialogues for customer relationship management systems. A service provider, such as an electronic transaction processor for digital transactions, may provide live chat service channels for assistance through live agents and chatbot services. When interacting with these channels, a user may engage in a chat dialogue with live agents. This may include lines of texts corresponding to the exchanged messages and may include named entities for particular types or categories of words that refer to a particular object or thing. To identify these named entities, a natural language processor may utilize machine learning and other engines for named entity recognition in customer relationship management systems to highlight the named entities in live service chats. Agents of the systems may view content that identify the named entities and interact with the named entities to view descriptions.

Examples of the present disclosure describe systems and methods for intelligent contract analysis and data organization. In example aspects, input data may be received into the system in the form of a legal document, such as a contract. The contract may be processed by a natural-language processor, and a summarized version of the contract and / or particular contract provisions may be provided. In other aspects, a machine-learning engine may process the input data in combination with a user's decisions to accept or reject particular contract provisions. The ML engine may provide an intelligent recommendation to a user regarding whether the user should consent or not consent to a particular contract provision. In other example aspects, a data dashboard displaying how a user's personally identifiable information (PII) is shared with third parties may be displayed. Aggregated PII may further be displayed in a dashboard.

Systems and methods provide a cloud-based intelligent and interactive customer service platform that includes a communication manager, customer app, agent app, a virtual container (e.g. room) for communication, a natural language processor, voice processor, image processor, video processor, and an inference processor exposed by application programming interfaces; and executing an agent picker functionality within the automation infrastructure that performs operations comprising: receiving a communication from a customer; immediately analyzing the communication to determine the right agent; automatically understanding the state of the room parsing a knowledgebase for some of the conversation to the subject associated with the customer's communication; providing the state of the room to agent within a unified interface during the communication with the customer, capability to rate other party and add and drop multimedia to all containers.

A method and system are disclosed for enabling payment of a good or service by means of voice commands. The method and system comprise a voice assistant, an electronic human language processor connected to the voice assistant, an application for delivering services to be paid connected to the electronic human language processor, an operative server device connected to the application for delivering services to be paid, a first authentication server device connected to the operative server device, a second authentication server device connected to the operative server device, a payment server device connected to the operative server device and an electronic device.

Methods, apparatuses, and computer program products are described for presenting an interactive audio-visual presentation of transaction documents. A method can include receiving a bill associated with a payor and payee, using a textual language processor or the like to identify content fields from the bill and assign markups and / or metadata to content fields, and using the content fields, markups, and / or metadata to generate an audio-visual presentation associated with the bill. This audio-visual presentation can be presented to the payor. The payee may then interact with the audio-visual presentation, for instance by verbal, visual, manual, or textual response. A verbal language processing engine, natural language processing engine, audio-visual language processing engine, or visual-manual language processing engine can be initiated to facilitate interpretation of the payee response and generate a further audio-visual presentation.

A system and method for processing operations involving dependent sequences. A natural language processor component is capable of parsing an input audio signal to identify a request and a triggering keyword. A prediction component is capable of determining a thread based on the triggering keyword and the request, which includes a first action, a second action following the first action, and a third action following the second action. A content selector component is capable of selecting a content item based on the third action and the triggering keyword. An audio signal generator component is capable of generating an output signal including the content item. Before at least one of the first and second actions occurs, the interface is capable of transmitting the output signal to cause a client computing device to drive a speaker to generate a sound wave corresponding to the output signal.

An apparatus for reducing occurrences of out-of-domain utterances resulting from static intervals within an utterance that is made by a user within a vehicle includes an automotive assistant for receiving an utterance from a user. The automotive assistant includes a streaming-language processor to process the utterance in real time as it is being received from the user via a microphone in the vehicle. The utterance includes a growth interval, a static interval, and a transition from the growth interval to the static interval. A hesitation model is configured to interact with the streaming-language processor to determine whether a static interval represents either an intent to end the utterance or an intent to begin a new growth interval after the static interval. The streaming-language processor is configured to respond to detection of the latter intent by promoting resolution of the utterance based on information from the hesitation model and intent-prediction model.

Disclosed are various embodiments for compliance detection using natural language processing. Various embodiments include a computing device that can transcribe a sound recording of a transcript, where the sound recording can be representative of a telephonic call occurring between an agent and a client. The computing device can determine that the telephonic call included a discussion related to a regulated subject based on an analysis by a natural language processor of the transcript. The computing device can obtain a compliance rule based at least in part on the regulated subject of the telephonic call. The computing device can determine that the compliance rule has been violated using a natural language processor of the transcript. The computing device can also store various information related to the compliance violation.

Disclosed herein are system, method, and computer program product aspects for an insight-based research synthesis platform. An aspect operates by partitioning a piece of content into a plurality of content segments. An aspect also operates by contextualizing and / or enriching a content segment to form an insight. An aspect further operates by generating a vector embedding for the insight. An aspect further operates by determining that the vector embedding is relevant to a task associated with the piece of content. An aspect further operates by querying a language processor to perform the task using the insight. As such, the insight-based research synthesis platform may provide more efficient and higher quality results compared to conventional systems.

Methods, apparatuses, and computer program products are described for presenting an interactive audio-visual presentation of transaction documents. A method can include receiving a bill associated with a payor and payee, using a textual language processor or the like to identify content fields from the bill and assign markups and / or metadata to content fields, and using the content fields, markups, and / or metadata to generate an audio-visual presentation associated with the bill. This audio-visual presentation can be presented to the payor. The payee may then interact with the audio-visual presentation, for instance by verbal, visual, manual, or textual response. A verbal language processing engine, natural language processing engine, audio-visual language processing engine, or visual-manual language processing engine can be initiated to facilitate interpretation of the payee response and generate a further audio-visual presentation.

Systems and methods for authoring and modifying presentation conversation files are disclosed. Exemplary implementations may: receive, at a renderer module, voice files, visual effect files, facial expression files, and / or mobility files; analyze, by the language processor module, the voice files, the visual effect files, the facial expression files, and / or mobility files follow guidelines of a multimodal authoring system; generate, by the renderer module, one or more presentation conversation files based at least in part on the received voice files, visual effect files, facial expression files, and / or mobility files; test, at an automatic testing system, the one or more presentation conversation files to verify correct operation of a computing device that receives the one or more presentation conversation files as an input; and identify, by a multimodal review module, changes to be made to the voice input files, the visual effect files, the facial expression files, and / or the mobility files.

Identifier dependent operation processing of packet based data communication is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. A content selector component can select, based on the request or trigger keyword, a content item. A link generation component can determine whether the client computing device has an account or a record in a database associated with the service provider device. In the absence of the record or account, the link generation device generates and sends a virtual identifier to the service provider device with instructions to generate an account in the database using the virtual identifier. Once the account is created, the service provider device can communicate with the client computing device.

The utility model discloses an artificial cochlea protective sleeve, and belongs to the technical field of artificial cochlea. The artificial cochlea protection sleeve comprises a first protection sleeve arranged on the language processor in a sleeving mode, a second protection sleeve arranged on the coil in a sleeving mode and a wire sleeve arranged on the wire in a sleeving mode, a hanging rope is connected to the wire sleeve, and the free end of the hanging rope is detachably connected with a fixing piece. The first protective sleeve is connected with a first wire section, and the top of the first wire section is provided with a first opening part; the second protective sleeve is connected with a second wire section, and the top of the second wire section is provided with a second opening part; the design of the first opening part and the second opening part can facilitate the connection of the wire with the language processor and the coil. The artificial cochlea can be connected with clothes of a user through the fixing piece, so that loss is avoided; the fixing piece adopts a pin structure, and the pin is provided with the protection assembly for limiting and protecting the tip of the pin, so that the tip of the pin is prevented from popping up to puncture a user.

Provided are a computer program product, system, and method for processing participant input in a virtual meeting to determine effects to render in the virtual meeting. A natural language processor (NLP) processes a sentence to determine a structural representation of the sentence comprising a subject and object, which is processed to determine whether the object of the sentence comprises an object of recognition and the subject of the sentence is a participant in the virtual meeting. The structural representation of the sentence is processed to determine an attention level in response to determining that the structural representation of the sentence includes the object of recognition and the subject comprises a participant in the virtual meeting. In response to the attention level exceeding a threshold, a recognition attention effect is rendered in the virtual meeting associated with the attention level, observable by the participants of the virtual meeting.

A feedback control system (100) for data transmissions over a computer network, comprising: a natural language processor component (112) executed by a data processing system (102) for receiving, via an interface (110) of the data processing system (102), data packets comprising an input audio signal detected by a sensor (134) of a client device (104); the natural language processor component (112) for parsing the input audio signal to identify a request, a content provider, and a trigger keyword corresponding to the request; a content selection component (118) executed by the data processing system (102) for receiving the trigger keyword identified by the natural language processor component (112) and, based on the trigger keyword, selecting a content item via a real-time content selection process;A feedback monitor component (120) for:receiving data packets carrying acoustic signals between the client device (104) and a conversational application programming interface (116) that has established a communication session (206) with the client device (104) in response to interaction with the content item;measuring a characteristic of the communication session (206) based on the acoustic signals; andgenerating a quality signal based on the measured characteristic; andadjusting the real-time content selection process, by the content selection component (118), based on the quality signal.

Provided are a computer program product, system, and method for processing participant input in a virtual meeting to determine effects to render in the virtual meeting. A natural language processor (NLP) processes a sentence to determine a structural representation of the sentence comprising a subject and object, which is processed to determine whether the object of the sentence comprises an object of recognition and the subject of the sentence is a participant in the virtual meeting. The structural representation of the sentence is processed to determine an attention level in response to determining that the structural representation of the sentence includes the object of recognition and the subject comprises a participant in the virtual meeting. In response to the attention level exceeding a threshold, a recognition attention effect is rendered in the virtual meeting associated with the attention level, observable by the participants of the virtual meeting.

A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

Embodiments of a system and a method for classifying blocks of text at varying, possibly simultaneous, and possibly interacting levels of scope (e.g., sentence, paragraph, section, document) are disclosed. A system includes a processor coupled to: a data reader to receive an input comprising of a data stream, and convert the data stream into one or more logical data blocks of varying scopes. The system includes a dependency tree generator to create a dependency tree to define the scope and dependencies of each of a plurality of natural language processors (NL Processors) with respect to each other such that the dependency tree identifies when an input of a NL Processor (depender) depends on an output of another NL Processor (dependee). Each NL Processor is configured based on a type of at least one logical data block of the one or more logical blocks to which it applies. The system includes a pipeline generator, which automatically generates a pipeline of natural language processors from the dependency tree such that all dependee classifiers are executed and completed on all of their text blocks before all of their depender classifiers.

The utility model provides an adapter for monitoring current of a speech processor of an artificial cochlea, which comprises a single chip microcomputer master controller, the single chip microcomputer master controller is connected with a current acquisition circuit through an IIC (inter-integrated circuit) communication circuit to acquire current and power consumption information of the speech processor, and the single chip microcomputer master controller transmits the current and power consumption information to a display screen for display through an SPI (serial peripheral interface) communication circuit; the TYPE-C port provides 5V power supply voltage for the LDO, the DC-DC, the level conversion circuit and the display screen and serves as a USB signal interface at the same time. And the DC-DC outputs 3.7 V voltage and provides the 3.7 V voltage to an external voice processor. The communication between the external language processor and the debugging software can be realized, the current and power consumption of the language processor can be monitored in real time, and convenience is provided for the test and verification of the language processor.

A computerized method enhances chat interaction through 2-way user interface (UI) communication. Data associated with an element, selected by a user from a UI of a web application, is received in a chat box. A query corresponding to the selected element is received in the chat box. A request is sent to a language processor for a list of application programming interfaces (APIs) relevant to the query and the data. For each API, the query and the data are sent to the API, and an answer including a data text and a data object is received from the API. A request including the data texts for a cohesive answer is sent to the language processor that returns the cohesive answer. If the web application can render the data object, the data object and the cohesive answer are presented on the UI of the web application.

Computer system security is improved by implementing zero-trust principles for management of source codes in a software development lifecycle. In some embodiments, a source code may be processed with a natural language processor to attribute the source code to its particular developer. Further, a machine learning algorithm may be applied to data related to the coding behavior of the code developer to identify any behavioral anomalies of the code developer in developing the source code. In addition, the interaction, of applications executing in an execution environment of an organization's network of managed compute facilities, with the various components of the network may be analyzed with a machine learning algorithm to identify code execution anomalies.

A system includes an input interface receiving conversation input from at least one system participant. A natural language processor operates on the conversational input. A sentiment processor operates on the pre-processed input using a sentiment classification model to predict sentiment, the sentiment processor predicting positive, neutral, and negative sentiment for the pre-processed input. An emotion processor receiving the pre-processed input from the natural language processor and a corresponding sentiment from the sentiment processor and operates to predict an emotion class and a strength of the emotion based on the corresponding sentiment. An output mechanism generates sentiment strength for the conversation input based on the emotion class and strength of the emotion.