Abstract: This application provides an interface control method. The method includes: obtaining a speech instruction of a user and a sound source location of the user; obtaining line-of-sight information of the user; determining a target window on an interface based on the sound source location and the line-of-sight information; and controlling the target window based on the speech instruction. According to the interface control method in this application, collaborative decision-making is performed with reference to multimode information such as sound source information, line-of-sight tracking information, speech semantic information, and priorities thereof, so that page content in a plurality of windows on the interface is quickly and accurately controlled, to improve user experience.

Abstract: A voice interaction method, where a service type set on which a user has a voice interaction intention is predicted based on a target event that can trigger voice interaction, and when a service type of a first service expressed by a voice instruction is a target service type in the service type set, the first service is executed.

Abstract: This application provides a voice interaction method and apparatus. A first apparatus obtains, by using a voice sensor, first voice information including a voice instruction of a user. The first apparatus may determine, based on the first voice information, to perform a target operation indicated by the first voice information. The first apparatus may also send the first voice information to a second apparatus. The first apparatus may determine, based on a first preset condition, to perform a first operation determined by the first apparatus based on the first voice information. The first apparatus may alternatively determine, based on a first preset condition, to perform a second operation indicated by the second apparatus. The solution provided in this application helps balance accuracy and efficiency of voice recognition, and further helps enable the apparatus to appropriately and quickly respond to the user.

Abstract: An in-vehicle speech interaction method and a device are provided. The method includes: obtaining user speech information; determining a user instruction based on the user speech information; determining, based on the user instruction, whether response content to the user instruction is privacy-related; and determining, based on whether the response content is privacy-related, whether to output the response content in a privacy protection mode, to protect privacy from being leaked.

Abstract: Example vehicle unlocking methods and apparatus are described. In one example method, wakeup keyword detection is performed on an obtained voice signal. If the voice signal includes a wakeup keyword, an acoustic source direction is determined, and a target camera is indicated to collect image data. The target camera is a target camera that is installed on the vehicle and whose angle of view can ensure that the acoustic source direction is captured. Then, the vehicle is unlocked based on the image data collected by the target camera.

Abstract: A speech detection method includes performing recognition on a photographed face image using a model to predict whether a user intends to continue speaking, and to determine whether a collected audio signal is a speech end point with reference to a prediction result.

Abstract: A speech recognition method, apparatus, and device, and a computer-readable storage medium provided pertain to the field of artificial intelligence technologies. The method includes: obtaining or generating a dynamic target language model based on reply information of a first intent, where the dynamic target language model includes a front-end part and a core part; obtaining a speech signal, parsing the speech signal to generate a key word; and invoking the dynamic target language model to determine a second intent and a service content. The front-end part of the dynamic target language model parses out the second intent based on the key word, and the core part of the dynamic target language model parses out the service content based on the key word. The speech recognition method prevents a provided service content from deviating from a user requirement and achieves a good recognition effect.

Abstract: A filtering model training method includes obtaining N original syllables, obtaining N recognized syllables, and obtaining N syllable distances based on the N original syllables and the N recognized syllables, where the N syllable distances are in a one-to-one correspondence with N syllable pairs, the N original syllables and the N recognized syllables form the N syllable pairs, each syllable pair includes an original syllable and a recognized syllable that correspond to each other, and each syllable distance is used to indicate a similarity between an original syllable and a recognized syllable that are included in a corresponding syllable pair.

Abstract: A voice interaction method, where a service type set on which a user has a voice interaction intention is predicted based on a target event that can trigger voice interaction, and when a service type of a first service expressed by a voice instruction is a target service type in the service type set, the first service is executed.

Abstract: A system and method for maintaining a system configuration to provide desired system performance is disclosed. The system comprises a processing unit receiving sensor data associated with environmental conditions within an area, generating a map of the area based on the received sensor data, determining a change in the map of the area and determining at least one system commissioning parameter associated with the determined change in the map to compensate for or correct the change in the map. In one aspect of the invention, the sensor data is provided through a plurality of mobile devices.

Abstract: A filtering model training method includes obtaining N original syllables, obtaining N recognized syllables, and obtaining N syllable distances based on the N original syllables and the N recognized syllables, where the N syllable distances are in a one-to-one correspondence with N syllable pairs, the N original syllables and the N recognized syllables form the N syllable pairs, each syllable pair includes an original syllable and a recognized syllable that correspond to each other, and each syllable distance is used to indicate a similarity between an original syllable and a recognized syllable that are included in a corresponding syllable pair.

Abstract: A system for managing provided services is disclosed. The system receiving information regarding measureable events, determining a distribution pattern of the measureable events, determining an identity of a user based on the distribution pattern and providing instruction to controllable devices to alter surrounding conditions based at least on the identity of the user. In another aspect of the invention, the controllable devices may represent a second set of sensors that are used to collect data of a second type. The information collected from the second set of sensors may be used to determine a health status of a user.

Abstract: The invention relates to an eye condition determination system (1) for determining an eye condition of a person, especially of a child, during a viewing activity during which the person views an object (3). A spatial characteristics capturing unit (2) captures a spatial dimension of the object and/or a spatial position of the object relative to the person during the viewing activity, and an eye condition determination unit (4) determines an eye condition like myopia or strabismus based on the captured spatial dimension of the object and/or the captured spatial position of the object relative to the person. This allows for a determination of the eye condition during a normal viewing activity like reading a text without any assistance by, for instance, parents, especially without any user interaction.

Abstract: A system and method for maintaining a system configuration to provide desired system performance is disclosed. The system comprises a processing unit receiving sensor data associated with environmental conditions within an area, generating a map of the area based on the received sensor data, determining a change in the map of the area and determining at least one system commissioning parameter associated with the determined change in the map to compensate for or correct the change in the map. In one aspect of the invention, the sensor data is provided through a plurality of mobile devices.