Abstract: A computer implemented messaging and management system for organizing and extracting information sent between users, and for automatically generating and updating management data based on information extracted from messages. One or more processors are configured to receive posts and post relational data and configured to generate a set of P-tags from the received posts and post relational data, wherein each P-tag has a value associated therewith, wherein some of the values are derived from users' input and wherein some of the values are generated by a tag management engine and a statistics engine. A logic engine having logic gates groups the P-tags or P-tags and keywords into a plurality of logic expressions; and, a compilation engine for creates and displays one or more management views in dependence upon at least some of the plurality of logic expressions.

Abstract: A processor may receive a plurality of text samples generated by a user and identify at least one variable text element in at least one of the plurality of text samples. The processor may tokenize the at least one variable text element, thereby producing a plurality of tokenized text samples including at least one token. The processor may build a longest common substring from the plurality of tokenized text samples and add the longest common substring and the at least one token to a set of selectable user interface options specific to the user. The processor may generate a user interface comprising the set of selectable user interface options. This can include detecting a user interface context and automatically replacing the at least one token with information specific to the user interface context within the set of selectable user interface options.

Abstract: Methods and systems for performing contact resolution are described herein. When initiating a communications session using a voice activated electronic device, a contact name may be resolved to determine an appropriate contact with which the communications session may be directed to. Contacts from an individual's contact list may be queried to determine a listing of probable contacts associated with the contact name, and contact identifiers associated with the contact may be determined. Using one or more rules for disambiguating between similar contact names, a single contact may be identified, and a communications session with that contact may be initiated.

Abstract: A method and apparatus with natural language processing is disclosed. The method includes determining a first similarity between an input sentence of a user and a select first database query sentence and dependent on a determination that the first similarity fails to meet a first threshold, determining a second similarity between a portion of the input sentence, less than all of the input sentence, and a select second database query sentence, and in response to the second similarity meeting a second threshold, outputting a response sentence corresponding to the second database query sentence as a response to the input sentence.

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.

Abstract: According to embodiments of the present disclosure, a method and an apparatus for responding to a question, and a storage medium are provided. The method includes: determining a question characteristic representation corresponding to a question for an object; determining a comment characteristic representation corresponding to a first comment for the object; generating a first target characteristic representation by utilizing the question characteristic representation and the comment characteristic representation; and determining an answer for the question based on the first target characteristic representation.

Abstract: A device may receive a command associated with identifying a merchant for a virtual card swap procedure wherein the virtual card swap procedure is to replace a credit card of a user with a virtual card corresponding to the credit card. The device may identify the merchant for the virtual card swap procedure based on the command. The device may obtain the virtual card for the user. The device may determine a virtual card swap procedure template for the merchant. The device may perform the virtual card swap procedure based on the virtual card swap procedure template.

Abstract: Exemplary embodiments relate to methods, mediums, and systems for moving language models from a server to the client device. Such embodiments may be deployed in an environment where the server is not able to provide modeling services to the clients, such as an end-to-end encrypted (E2EE) environment. Several different techniques are described to address issues of size and complexity reduction, model architecture optimization, model training, battery power reduction, and latency reduction.

Abstract: An encoding system encodes an N-channel audio signal (X), wherein N?3, as a single-channel downmix signal (Y) together with dry and wet upmix parameters ({tilde over (C)}, {tilde over (P)}). In a decoding system, a decorrelating section outputs, based on the downmix signal, an (N?1)-channel decorrelated signal (Z); a dry upmix section maps the downmix signal linearly in accordance with dry upmix coefficients (C) determined based on the dry upmix parameters; a wet upmix section populates an intermediate matrix based on the wet upmix parameters and knowing that the intermediate matrix belongs to a predefined matrix class, obtains wet upmix coefficients (P) by multiplying the intermediate matrix by a predefined matrix, and maps the decorrelated signal linearly in accordance with the wet upmix coefficients; and a combining section combines outputs from the upmix sections to obtain a reconstructed signal ({circumflex over (X)}) corresponding to the signal to be reconstructed.

Abstract: Disclosed herein is an artificial intelligence apparatus for recognizing speech of a user including a microphone and a processor configured to obtain, via the microphone, speech data including speech of a user, determine a frequency weight for each word using a speech recognition log, generate a speech recognition result corresponding to the speech data using the frequency weight, and perform control corresponding to the speech recognition result.

Abstract: A method for collaborative conversational artificial intelligence (CCAI). The invention discloses an architecture wherein members of the disclosed system participate in collaborative conversations with one or more AI and human “subminds” connected via a forum, including conversing in natural language and facilitated by one or more “facilitators”. CCAI Applications include the creation of widely extensible evolving modular polylogical groups that are capable of collaboration with sentient beings, collaborative control of devices, service worker interfaces, hybrid representations of sentient beings (including via “reconveyance” of conversation segments), in collaborations that may include, exclude or require human or AI participation.

Abstract: The current invention describes a method and system for imposing a dynamic sentiment vector to an electronic message. In one embodiment of the invention, the method comprises of receiving a text input comprising message content from an electronic computing device associated with a user. The message content is further parsed and comprised in the text input for emotionally-charged language, assigned a sentiment value, based on the emotionally-charged language, from a dynamic sentiment value spectrum to the text input. Additionally, based on the sentiment value, imposing a sentiment vector, corresponding to the assigned sentiment value, to the text input, the imposed sentiment vector rendering a sensory effect on the message content designed to convey a corresponding sentiment.

Abstract: In some examples, natural language dialogue system perturbation testing may include identifying semantic segments for conversation data for a natural dialogue system. For each semantic segment, a perturbed variant that includes a perturbation may be generated, and forwarded to the natural dialogue system. An updated response to the perturbed variant may be obtained from the natural dialogue system. A semantic similarity may be determined between an original response to a semantic segment and the updated response, and based on the semantic similarity between the original response and the updated response, a perturbability of the natural dialogue system may be determined. A determination may be made as to whether the perturbability of the natural dialogue system is greater than a specified perturbability threshold, and if so, a training corpus that includes a failed response to a perturbed variant may be utilized to train the natural dialogue system.

Abstract: Embodiments of the present disclosure provide a method and apparatus for recognizing speech. An embodiment of the method includes: in response to detecting a speech frame, converting the speech frame into a current text in real time; in response to there being no previously saved historical text, inputting the current text into a semantic parsing model to obtain a parsing result; in response to the parsing result including a valid intention slot, ending a speech endpoint detection to complete the recognition; and outputting an instruction corresponding to the valid intention slot.

Abstract: The present invention relates to a method for receiving data transmitted acoustically. The method includes receiving an acoustically transmitted signal encoding data; processing the received signal to minimise environmental interference within the received signal; and decoding the processed signal to extract the data. The data encoded within the signal using a sequence of tones. A method for encoding data for acoustic transmission is also disclosed. This method includes encoding data into an audio signal using a sequence of tones. The audio signal in this method is configured to minimise environmental interference. A system and software are also disclosed.

Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second subset.

Abstract: A computerized method is disclosed including operations of receiving one or more request texts, including at least a first request text, automatically performing processing on the first request text to determine a most similar request text in a knowledge base, determining a degree of similarity between the first request text and the most similar request text, and in response to a comparison between the degree of similarity and a similarity threshold, retrieving, from the knowledge base, an answer corresponding to the most similar request text. Performing processing may include (i) removing stop words and punctuation and creating tokenized text, (ii) converting the tokenized text into a vector using a trained neural network, and (iii) performing an analysis of the vector with the entries of the knowledge base using one or more of a Word Mover's Distance (WMD) algorithm, or a Soft Cosine Measure (SCM) algorithm.

Abstract: The present disclosure discloses a voice interaction method, system, terminal device and medium. The method comprises the following operations performed by a terminal device: performing voice recognition on collected voice signals to acquire an input sentence; semantically matching the input sentence with cached sample sentences to determine whether there is a sample sentence having the same or similar semantics as the input sentence among the cached sample sentences; if yes, acquiring cached response content corresponding to the sample sentence having the same or similar semantics as the input sentence as response content of the input sentence; if not, sending the input sentence to a server; receiving from the server response content acquired by the server through semantic understanding according to a knowledge base stored on the server; and responding to the input sentence according to the response content.

Abstract: A technique for managing real-time communications includes generating, during a communication session between at least a first computing device and a second computing device over a computer network, multiple audio factors of the communication session, each of the audio factors being susceptible to degradation in a way that affects audio quality of the communication session. The technique further includes combining the audio factors to produce an overall measure of audio quality and taking remedial action to improve the overall measure of audio quality by adjusting a setting on the first computing device.

Abstract: A semantic messaging collaboration (SMC) system using simultaneous post, user and user-post interaction tagging. The system includes a natural language processing (NLP) engine, statistics engine, tag management engine and a story engine. The NLP engine is configured to: a) identify topics that appear in a select conversation b) analyze user expertise from available sources, and c) analyze posts with respect to sentiment. The statistics engine is configured to generate descriptive statistics from available system information on user-post interactions, as well as select outputs from NLP engine. The tag management engine generates and collates system tags.