Abstract: A process of a voice control method with a cloud server and a terminal device. The voice control method includes: a terminal device receiving voice information; the terminal device querying a control instruction corresponding to the voice information from a local voice database; when the control instruction corresponding to the voice information is not queried in the local voice database, the terminal device uploading the voice information to a cloud server; the cloud server parsing the control instruction corresponding to the voice information; when the control instruction corresponding to the voice information is parsed, the cloud server sending the control instruction to the terminal device; and the terminal device receiving the control instruction, and performing a corresponding operation on the basis of control instruction.

Abstract: A user using a messaging application may be in conversations with multiple people and may inadvertently send a message intended for a first person to a second person. The user may be warned before making such mistakes by processing the text of an entered message and/or the text of the conversations with a mathematical model. A match score may be computed that indicates the match between the entered message and the conversation in which it was entered. Where the match score indicates a possible mistake, a warning may be presented to the user. In some implementations, a match score may be computed using a conversation encoding vector and a message encoding vector. In some implementations, a match score may be computed by processing a sequence of tokens for the conversation and the entered message that includes special token separators.

Abstract: An audio encoder for encoding segments of coefficients, the segments of coefficients representing different time or frequency resolutions of a sampled audio signal, the audio encoder including a processor for deriving a coding context for a currently encoded coefficient of a current segment based on a previously encoded coefficient of a previous segment, the previously encoded coefficient representing a different time or frequency resolution than the currently encoded coefficient. The audio encoder further includes an entropy encoder for entropy encoding the current coefficient based on the coding context to obtain an encoded audio stream.

Abstract: A system and method for algorithmically orchestrating conversational dialogue transitions within an automated conversational system may include extracting a set of slots defined within a plurality of utterances and converting the plurality of utterances to a plurality of skeleton utterances. The method may also include grouping the plurality of skeleton utterances into a plurality of skeleton utterance groups, identifying a plurality of valid slot transition pairs based on an assessment of the plurality of skeleton utterance groups, and deriving a plurality of slot ontology groups based on the plurality of valid slot transition pairs. The system and method may use the plurality of distinct slot ontology groups and the plurality of skeleton utterances to facilitate contextually relevant dialogue transitions in the automated conversational system.

Abstract: Methods, systems, and apparatus for receiving, by a voice action system, data specifying trigger terms that trigger an application to perform a voice action and a context that specifies a status of the application when the voice action can be triggered. The voice action system receives data defining a discoverability example for the voice action that comprises one or more of the trigger terms that trigger the application to perform the voice action when a status of the application satisfies the specified context. The voice action system receives a request for discoverability examples for the application from a user device having the application installed, and provides the data defining the discoverability examples to the user device in response to the request. The user device is configured to provide a notification of the one or more of the trigger terms when a status of the application satisfies the specified context.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. In some instances, the speech recognition platform engages in a back-and-forth dialog with the user in order to properly fulfill the user's request.

Abstract: Provided is an information processing device including a presence/absence prediction unit that performs prediction of presence/absence of a user at a visit destination on a basis of sensed data, and a providing unit that provides a result of the prediction to an external device.

Abstract: Systems and methods for detecting and using semantic relatedness to classify segments of digital text are disclosed. More particularly, embodiments determine the semantic relatedness of segments of text to abstract categories where the abstract categories are not defined by a single word or semantic concept. Detecting semantic relatedness includes analyzing text, embedding the text, and determining semantic relatedness to a set of concepts for a category where each concept may include a set of words/phrases embedded in a similar fashion. The text embedding can be projected onto each concept embedding and reduced to a score representing semantic relatedness. The text is classified based on the semantic relatedness.

Abstract: Systems and methods for user-agent anomaly detection are disclosed. In one embodiment, a user-agent string may be embedded into a numerical data vector representation using a sentence embedding algorithm (e.g., FastText). A predictive score may be calculated based on the numerical data vector representation and using a probability distribution function model that models a likelihood of occurrence of the observed user-agent based on patterns learned from historic payload data (e.g., a Gaussian Mixture Model). The predictive score may be compared to a threshold and, based on the comparison, it may be determined whether the user-agent is fraudulent.

Abstract: A voice dialogue system includes a voice input unit which acquires a user utterance, an intention understanding unit which interprets an intention of utterance of a voice acquired by the voice input unit, a dialogue text creator which creates a text of a system utterance, and a voice output unit which outputs the system utterance as voice data. When creating a text of a system utterance, the dialogue text creator creates the text by inserting a tag in a position in the system utterance, and the intention understanding unit interprets an utterance intention of a user in accordance with whether a timing at which the user utterance is made is before or after an output of a system utterance at a position corresponding to the tag from the voice output unit.

Abstract: Computer implemented methods and systems are provided for generating diverse key phrases while maintaining competitive output quality. A system for training a sequence to sequence (S2S) machine learning model is proposed where neural unlikelihood objective approaches are used at (1) a target token level to discourage the generation of repeating tokens, and (2) a copy token level to avoid copying repetitive tokens from the source text. K-step ahead token prediction approaches are also proposed as an additional mechanism to augment the approach to further enhance the overall diversity of key phrase outputs.

Abstract: A classification code parser and method can include: reading a classification code having a description; reading a required keyword, and a total number of keywords associated with the classification code; reading text of a note; tokenizing the text of the note to create a note token stream, the note token stream having a note token and a position of the note token within the note token stream; creating a keyword map including a total number of matched keywords; determining a match ratio from the total number of the matched keywords and the total number of the keywords; determining a proximity factor based on a shortest span of tokens within the note token stream containing all the matched keywords; and determining a strength of a match between the classification code and the note based on the match ratio being multiplied by the proximity factor.

Abstract: Embodiments are disclosed for performing fact correction of natural language sentences using data tables. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input sentence, tokenizing elements of the input sentence, and identifying, by a first machine learning model, a data table associated with the input sentence. The systems and methods further comprise a second machine learning model identifying a tokenized element of the input sentence that renders the input sentence false based on the data table and masking the tokenized element of the tokenized input sentence that renders the input sentence false. The systems and method further includes a third machine learning model predicting a new value for the masked tokenized element based on the input sentence with the masked tokenized element and the identified data table and providing an output including a modified input sentence with the new value.

Abstract: Technologies relating to model interpretation are described herein. A text classifier is provided with input text and assigns a class to the input text from amongst several possible classes. Based upon the class assigned to the input text by the text classifier, a class profile of a centroidal classifier is selected, where the class profile is constructed based upon numerous input texts to which the text classifier has previously assigned the class. Based upon the selection of the class profile, information that is indicative of operation of the text classifier with respect to the text classifier assigning the class to the input text is output, where the information includes an exemplar text sequence.

Abstract: A method, computer system, and a computer program product for semantic matching is provided. The present invention may include pre-processing and normalizing a job title. The present invention may include deconstructing the job title based on at least one semantic element. The present invention may include training a machine learning model. The present invention may include creating a contextual word representation of the job title using the at least one semantic element of the job title. The present invention may include computing a similarity score for each of the at least one semantic element of the job title. The present invention may lastly include applying a weight to the computed similarity score before making a final match assessment.

Abstract: Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.

Abstract: Systems and processes for proactive assistance based on dialog communication between devices are provided. In one example process, while voice communication between an electronic device and a second electronic device is established, a stream of audio data associated with the second electronic device can be received. In response to detecting a user input, a text representation of speech contained in a portion of the stream of audio data can be generated. The process can determine whether the text representation contains information corresponding to one of a plurality of types of information In response to determining that the text representation contains information corresponding to one of a plurality of types of information, one or more tasks based on the information can be performed.

Abstract: Enforcing data ownership may include receiving a request to register an application programming interface (API) endpoint. A plurality of elements of the API endpoint and a target API endpoint may be preprocessed. A distance may be computed for each of element of the API endpoint relative to at least one of the elements of the target API endpoint. A distance score for the API endpoint may be computed based on the distance scores. A term frequency-inverse document frequency (TF-IDF) value may be computed for a plurality of metadata terms of the API endpoint and the target API endpoint. A similarity score between the TF-IDF values of the metadata terms may be computed. An adjusted score may be computed for the API endpoint based on the distance score and the similarity scores. The API endpoint may be registered based on the adjusted score being below a permissions threshold.

Abstract: A patent evaluation method and system thereof are provided. The method includes collecting patent documents, and further includes the following steps: generating technical points and patent-affiliated technical points; generating technical clusters and patent-affiliated cluster; performing a patent evaluation in each of the technical clusters. The patent evaluation method and system proposed in the present invention aggregates the patents in a technical cluster mode through natural language processing and complex network algorithms, gives patents scientific and technological attributes, and places the patents in a global same industry for evaluation.

Abstract: An example system includes a processor to receive an image containing an object to be detected. The processor is to detect the object in the image via a binary object detector trained via a self-supervised training on raw and unlabeled videos.