7 results about "Word language" patented technology

The invention discloses a vehicle-mounted scene hot word recognition method and related equipment, and relates to the technical field of Internet, and the method comprises the steps: obtaining voice data inputted by a user, extracting a hot word text from the voice data, and obtaining fusion features of the voice data and the hot word text; analyzing the hot word text to generate a plurality of mapping paths, and constructing a hot word language model based on the plurality of mapping paths; decoding the fusion feature based on the hot word language model to obtain a hot word decoding result; decoding the fusion feature based on the universal language model to obtain a universal decoding result; and determining a target recognition result based on the hot word decoding result and the general decoding result.

This application discloses a method and related equipment for identifying hot words in a vehicle-mounted scene, relating to the field of Internet technology. The method includes: acquiring user-input voice data; extracting hot word text from the voice data; and acquiring fusion features between the voice data and the hot word text; parsing the hot word text to generate multiple mapping paths; constructing a hot word language model based on the multiple mapping paths; decoding the fusion features based on the hot word language model to obtain a hot word decoding result; decoding the fusion features based on the general language model to obtain a general decoding result; and determining a target recognition result based on the hot word decoding result and the general decoding result.

The application discloses a natural source search method based on an SVM improved convolutional neural network, and comprises the following steps: S1, collecting different formats of languages, and importing the languages into a conversion program in a plaintext mode; S2, importing mark information in a newly generated language database into a language generation program, analyzing feature data imported into the language generation program by using a pre-constructed deep neural network model, and automatically generating a general functional description language; S3, randomly selecting two literal languages from the general functional description language, learning a common occurrence property between words of each source language, converting the property into a low-dimensional real value distributed representation, and forming a resource dictionary vector; and S4, identifying the resource dictionary vector based on the SVM improved convolutional neural network. The natural source search method based on the SVM improved convolutional neural network increases spatial relation judgment capability and improves search efficiency.

The present invention belongs to the field of speech recognition technology, and particularly relates to a speech recognition method and system based on domain classification and hot word prefix tree beam search, which uses a hot word list in a known domain to construct a hot word prefix tree of a corresponding domain type, and trains a corresponding hot word language model; for target speech data, a trained end-to-end model is used for one decoding, and a trained domain classification model is used to obtain the domain type to which the target speech data belongs; the target speech data is decoded twice using the end-to-end model, and a beam search algorithm is used and the trained hot word language model is used to output the text corresponding to the target speech data, wherein, in each time step search of the beam search algorithm, the hot word prefix tree of the domain type to which the target speech data belongs is combined to enhance the hot word probability. The present invention uses a domain hot word prefix tree to appropriately enhance the hot words in the speech data, improve the speech recognition effect, and facilitate application in actual scenarios.

The invention discloses a log query method and device, a medium and a program product, and relates to the field of log analysis. The log query method comprises the steps of obtaining a current log query statement; when the current log query statement has the hot word query attribute, determining a hot word query bit vector according to the current log query statement and the target hot word language unit dictionary; generating a log index bit vector according to the to-be-queried log and the target hot word language unit dictionary; and based on the hot word query bit vector and the log index bit vector, determining a hit log in the to-be-queried log. According to the technical scheme provided by the embodiment of the invention, the log required to be queried can be accurately and quickly hit on the premise of low resource consumption.

The invention discloses a text content detection method and device in a game interface, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of obtaining a game interface image, determining a text content area in the game interface image, and performing character detection on the text content area to obtain first text content; determining a target text language corresponding to the first text content, and obtaining a plurality of second text contents corresponding to the target text language; and determining a second target text content closest to the first text content in the plurality of second text contents, and detecting the first text content based on the second target text content to obtain a detection result. According to the method, the text detection efficiency and the detection accuracy are improved.

The application discloses a kind of speech assistance dialogue management method, device, equipment and storage medium, by responding to the wake-up word language monitored, record audio data to form voice file, and obtain vehicle state information;According to the vehicle state information, the voice file is carried out voice recognition using natural language understanding component, and system cognitive information is extracted;According to the system cognitive information, the corresponding logic element set is matched in pre-built logic database;The logic element set is sent to finite state machine, generates the finite state machine state set, event set and action set, and executes logic engine;Through logic engine, the function corresponding to the pre-built signal source set is called, and the execution result is output. It can solve the problem that the existing speech assistance function logic function is complex, improve development efficiency, reduce development cycle.