21 results about "Data language" patented technology

Systems, methods, and computer-readable media for presenting one or more bets to a user based on a natural language query received from the user. In some embodiments, a natural language query from a user may be received. The natural language query may be translated into computer-readable data by a language processing engine. The language processing engine may use a large language model to translate the natural language query into computer-readable data. The computer-readable data may be in the form of an embedding. A bet engine may match the computer-readable data to a bet when the bet and the computer-readable data exceed a predetermined threshold with regard to similarity. The bet engine may generate a new bet corresponding to the computer-readable data. The system may then present the bet to the user.

An expressive speech translation system may process source speech in a source language and output synthesized speech in a target language while retaining vocal performance characteristics such as intonation, emphasis, rhythm, style, and / or emotion. The system may receive a transcript of the source speech, translate it, and generate transcript data. To generate the synthesized speech, the system may process the transcript data with a language embedding representing language-dependent speech characteristics of the target language, a speaker embedding representing speaker-dependent voice identity characteristics of a speaker, and a performance embedding representing the vocal performance characteristics of the source speech. The system may control the duration of segments of the synthesized speech to better align with corresponding segments of the source speech for the purpose of dubbing multimedia content with synthesized speech in a language different from that of the original audio.

An online system uses a voice augmented language model to create a personalized online order using voice commands from a user of the online system. The online system generates a prompt for input into the language model, the prompt including user's voice content, user's sentiment data, other user data, and source data. The language model uses the prompt to generate a list of components and metadata for each component. Upon receiving an acknowledgement signal indicating an acknowledgement of the list of components by the user, the online system converts the list of components into a list of items and generates one or more options for servicing an order including the list of items. The online system then generates a user interface signal that causes a device associated with the user to display a user interface with the list of items and the one or more options for servicing the order.

The present disclosure is directed to a universal data language (UDL) translator. Specifically, the systems and methods disclosed enable input data from a variety of sources to be translated into a UDL that can be consistently analyzed and compared against other sources of data. For example, an entity may upload input data that has a plurality of data terms and definitions (e.g., header column in a spreadsheet). These terms may be duplicative and / or inaccurate with respect to the underlying data. If the entity wishes to compare and transact data within a data marketplace, the entity may not fully comprehend what data it is missing and / or what data another entity may have to offer for trade. To remedy this problem of business semantic management, the present invention discloses steps for creating a UDL and a UDL translator so that any input data can be translated to UDL.

The invention relates to a multi-modal generation type pre-training method and system and an image question and answer generation method. Visual modal data, language modal data and multi-modal data are obtained; training a visual base model on the visual modal data through a self-supervised comparative learning normal form, and storing a prediction layer weight as a visual prototype; a language base model is trained on the language modal data through a self-supervised lexical element prediction normal form, and word embedding weights are saved to serve as language prototypes; bridging the trained visual base model and language base model, and obtaining lexical element prediction loss through a multi-modal lexical element prediction normal form; cross-modal knowledge distillation and self-modal knowledge distillation are carried out on multi-modal data, and supervised pre-training is carried out. Compared with the prior art, the method has the advantages that the prior information of the visual modality and the language modality can be effectively utilized, and high-precision understanding and reasoning in a cross-modal scene are realized through unified multi-modal generation type pre-training.

The present disclosure is directed to a universal data language (UDL) translator. Specifically, the systems and methods disclosed enable input data from a variety of sources to be translated into a UDL that can be consistently analyzed and compared against other sources of data. For example, an entity may upload input data that has a plurality of data terms and definitions (e.g., header column in a spreadsheet). These terms may be duplicative and / or inaccurate with respect to the underlying data. If the entity wishes to compare and transact data within a data marketplace, the entity may not fully comprehend what data it is missing and / or what data another entity may have to offer for trade. To remedy this problem of business semantic management, the present invention discloses steps for creating a UDL and a UDL translator so that any input data can be translated to UDL.

We provide the system. [Solution] A means for receiving natural language data entered by a user and automatically identifying the language of the data, A means of translating from an identified language to another language, Means for presenting translated data to the user visually or aurally, A means of acquiring and displaying information about surrounding facilities based on the user's current location, A system that includes this.

Techniques are described for recognizing a spoken wake word (WW) or a spoken command for a human-machine interface using a speech recognition system that does not require WW or command-matching speech data for training. The system uses the text or grapheme representation of the WW or commands for pre-deployment training. The technique involves the system receiving a text representation of a target phrase in a target language. It includes training an acoustic model based on a speech database to distinguish speech signals according to the acoustic units of the target language. The training of the acoustic model is independent of the target phrase.It involves creating a recognition model based on the textual representation of the target phrase and the acoustic model to recognize the target phrase in speech, and processing speech from a speaker based on the acoustic model and the recognition model to detect the presence of the target phrase.

A method for constructing a unified business and technology data language includes the following steps: Step 1, specifying independent variables based on the business model and the indicator meta-model; Step 2, performing the specified independent variables as follows to ensure they conform to the domain language model of the asset management data domain: whether the independent variable corresponds to a concept or class in the asset management domain and whether it corresponds to metadata, whether the independent variable forms parent and child nodes and thus performs association calculations; Step 3, determining whether to use the independent variable or return to Step 1.

An embodiment for improved computer-implemented methods of recommending emotion icons. The embodiment may detect text associated with user activity within a connected messaging environment. The embodiment may, in response to detecting the text associated with user activity within the connected messaging environment, determine a context for the detected text based on at least location data, environment data, language context data, and historical data. The embodiment may generate a filtered series of emotion icons based on the context. The embodiment may display the filtered series of emotion icons to a user for selection.

Systems and methods in the present disclosure relate to technology for automated and personalized message generation. A user interface on a user device presents instructions for performing a therapeutic activity. During a session, one or more sensors capture activity data for a user while the user performs the therapeutic activity. The activity data is processed to track performance of the therapeutic activity and generate session data. A prompt for a language model is automatically generated using a prompt data structure that is updated in real-time based on at least one of the session data or historical data associated with the user. A personalized message, as generated in real-time by the language model, is presented to the user via the user interface or via audio hardware associated with the user device.

Searches based on an incoming ticket identify quality ticket enrichment data using a vector database. Language model prompts target particular kinds of quality ticket data. The incoming quality ticket, or a search result ticket, or both, are enriched using enrichment data, such as a user intent identification, a workaround suggestion, a resolution description, a target audience description, a relevance description, an impact description, a description of missing resolution facilitation information, an association between the incoming quality ticket and the search result ticket, a user sentiment identification, a tag suggestion, or a feedback utility estimate. The enrichment reduces engineering and support burdens, and facilitates faster more effective resolution of the problem or the request that is stated or implied in the incoming quality ticket. Duplicate tickets are merged or removed. Tickets are prioritized. Missing problem resolution information is identified and requested sooner.

The invention discloses a method and device for testing a voice analysis system based on a large model, and relates to the technical field of software testing, and the method comprises the steps: generating a voice for testing through a testing model, the training module is obtained by training a machine learning model according to the voice data and text data, language data, speech speed data, accent data and noise data corresponding to the voice data; inputting the voice for testing into the voice analysis system to obtain an analysis text; and obtaining a test result according to the analysis text. According to the embodiment of the invention, various test voices with various characteristics are generated by using the test model, so that the coverage of the test voices is wide, the acquisition difficulty of the voice data set is reduced, the voice analysis system can be comprehensively evaluated, and the accuracy, reliability and automation degree of the test are improved.

The present disclosure belongs to the technical field of Internet software development, and relates to a low-code development method and device, a readable storage medium and an electronic device. The method comprises the following steps: determining a target metadata language template, identifying a target metadata language corresponding to the target metadata language template; analyzing the target metadata language to obtain action information, identifying the action information to obtain a type identification result; and distributing the action information to a front-end page or a back-end system according to the type identification result, so as to execute an action corresponding to the action information in the front-end page or the back-end system. In the present disclosure, the target metadata language is obtained, the target metadata language is analyzed to obtain the action information, and the action information is distributed according to the type identification result obtained by identifying the action information. Compared with the prior art, the target metadata language can be developed by mixing the front end and the back end, the situation that the front end and the back end are developed separately is avoided, the development cycle is shortened, and the development efficiency is improved.

The application relates to the technical field of artificial intelligence, can be applied to a financial technology, medical health and other business system platform, and discloses a multi-modal action model strategy optimization method, device, equipment and medium, the method comprises the following steps: relationship analysis is carried out among acquired image data, language instructions and the behavior action sequence of a target user, relationship dependency is obtained, an initial multi-modal action model is constructed in combination with initial training parameters, the initial multi-modal action model is fine-tuned by using acquired task-specific data, a fine-tuned multi-modal action model is obtained, environment interaction data sets of a target environment are acquired, the environment interaction data sets are sampled one by one by using the fine-tuned multi-modal action model, a plurality of target interaction trajectories are generated, and the selection strategy in the fine-tuned multi-modal action model is optimized, and a target selection strategy is obtained. The application improves the selection strategy accuracy of the multi-modal action model when the model faces new situations or insufficient data.

The invention discloses a data processing method, system and device and a computer readable storage medium, and relates to the technical field of neural networks, in the process of processing to-be-processed data, target data to be subjected to softmax operation is acquired, and the to-be-processed data comprises one or more of image data, text data and language data; determining a maximum value in the target data; generating a target difference value between each datum in the target data and the maximum value, and performing exponential operation on the target difference value to obtain a normalized exponential value corresponding to each datum; generating a sum value of all normalized index values; determining a target fitting model corresponding to the sum value, wherein the target fitting model comprises a model obtained by fitting a reciprocal of the sum value; processing the sum value according to a target fitting model to obtain an initial value; performing Newton iteration on the initial value to obtain a reciprocal of the sum value; and generating a softmax operation result of the target data based on the reciprocal of the sum value. And the operation precision can be improved.

The invention relates to a multi-modal data-based intelligent VLA data pre-labeling method and device, and the method comprises the steps: obtaining a multi-modal data stream containing visual modal data, language modal data and action modal data, and carrying out the time sequence segmentation of the multi-modal data stream according to a time sequence, and obtaining a plurality of time period data units; for each time period data unit, identifying a current task execution state based on the visual modal data and the language modal data, and generating at least one candidate labeling hierarchy set corresponding to the state according to the task execution state; performing multi-modal semantic representation on each level label in the candidate label level set, and constructing a multi-modal consistency relation graph containing visual nodes, language nodes and action nodes; and executing a consistency propagation operation in the multi-modal consistency relation graph to obtain a multi-modal consistency constraint relation among the nodes. According to the scheme, the stability and reliability of multi-modal labeling in a complex scene can be improved.

An expressive speech translation system may process source speech in a source language and output synthesized speech in a target language while retaining vocal performance characteristics such as intonation, emphasis, rhythm, style, and / or emotion. The system may receive a transcript of the source speech, translate it, and generate transcript data. To generate the synthesized speech, the system may process the transcript data with a language embedding representing language-dependent speech characteristics of the target language, a speaker embedding representing speaker-dependent voice identity characteristics of a speaker, and a performance embedding representing the vocal performance characteristics of the source speech. The system may control the duration of segments of the synthesized speech to better align with corresponding segments of the source speech for the purpose of dubbing multimedia content with synthesized speech in a language different from that of the original audio.

Methods and apparatuses for improving the speed, quality, and relevance of automated responses provided by a question answering system for security data are described. The question answering system may generate and utilize a large language model that is trained to combine the language of security data, such as the language found in security logs and alerts, with natural language text. Given an input prompt (or a search query) from an end user of the question answering system, the question answering system may identify relevant content from the security data and display a response based on the relevant content. The question answering system may allow the end user of the question answering system to query security logs using natural language text without requiring the end user to provide a structured query and without requiring the security data be parsed and ingested into a database system.

The application relates to a multimodal generative pre-training method and system and an image question and answer generation method, visual modality data, language modality data and multimodal data are acquired; a visual base model is trained on the visual modality data through a self-supervised contrast learning paradigm, and a prediction layer weight is saved as a visual prototype; a language base model is trained on the language modality data through a self-supervised word element prediction paradigm, and word embedding weight is saved as a language prototype; the trained visual base model and the language base model are bridged, word element prediction loss is acquired through a multimodal word element prediction paradigm; cross-modal knowledge distillation and self-modal knowledge distillation are carried out on the multimodal data, and supervised pre-training is carried out. Compared with the prior art, the application can effectively utilize prior information of the visual modality and the language modality, and through unified multimodal generative pre-training, high-precision understanding and reasoning under a cross-modal scene are realized.

We provide the system. [Solution] A means for acquiring voice data from the user, A means of sending the acquired audio data to the server, A means by which the server converts audio data into text data, A means for the server to detect the language of the text data, A means for the server to translate text data into the target language, A means by which the server converts translated text data into audio data, A means of sending translated audio data to the user's device, A system that includes means for a device to play translated audio data.