Abstract: This application provides a human-machine interaction method and the like. In one aspect, gesture action information of the user is detected by using an optical sensor of the object device; motion track information of the mobile terminal is detected by using a motion sensor of the mobile terminal. When the gesture action information matches the terminal motion track information, corresponding first control is executed.

Abstract: A vehicle summoning method may be applied to an intelligent vehicle. The vehicle summoning method includes obtaining, when a vehicle is in a parking state, identifier information of a person in a first range around the vehicle, and determining, when the identifier information of the person in the first range meets a preset condition, that the person who meets the preset condition is a target person. The method further includes obtaining a body movement of the target person and, when a first distance is less than a first threshold, controlling, based on the body movement, the vehicle to travel to a first location. The first distance is used to indicate a distance between the target person and the vehicle. According to the vehicle summoning method, a user can summon a vehicle by using a body movement, which improves user experience of the vehicle.

Abstract: This disclosure provides an in-vehicle mid-air gesture-based interaction method, an electronic apparatus, and a system, and relates to the field of intelligent vehicle technologies. The method includes: obtaining a first mid-air gesture detected by a camera; and starting, when a preset response operation corresponding to the first mid-air gesture matches a first user who initiates the first mid-air gesture, the preset response operation corresponding to the first mid-air gesture in response to the first mid-air gesture. The method can be used in an in-vehicle mid-air gesture-based interaction scenario, reduce a mid-air gesture operation rate, and improve driving safety and interaction experience.

Abstract: A system includes obtaining a plurality of automobile part sets through classification based on at least one of the following factors an interface type of an interface of an automobile part, a transmission type used by the automobile part to transmit data, a manufacturer of the automobile part, a type of the automobile part, a safety level of the automobile part, a service type of a service to which data transmitted by the automobile part belongs, or a service level of the service to which the data transmitted by the automobile part in the automobile belongs.

Abstract: Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.

Abstract: A system includes obtaining a plurality of automobile part sets through classification based on at least one of the following factors an interface type of an interface of an automobile part, a transmission type used by the automobile part to transmit data, a manufacturer of the automobile part, a type of the automobile part, a safety level of the automobile part, a service type of a service to which data transmitted by the automobile part belongs, or a service level of the service to which the data transmitted by the automobile part in the automobile belongs.

Abstract: This application provides an image recognition method and device. The image recognition method includes: setting a presentation time sequence corresponding to an image sequence includes N images, the presentation time sequence includes unequal presentation times, a difference between any two presentation times of the unequal presentation times is k×?, k is a positive integer, and ? is a preset time period value; processing the image sequence by using a computer vision algorithm, to obtain a computer vision signal corresponding to each image in the image sequence; obtaining a feedback signal that is corresponding to each image in the image sequence generated when an observation object watches the image sequence displayed in the presentation time sequence; and fusing, for each image in the image sequence, a corresponding computer vision signal and a corresponding feedback signal to obtain a target recognition signal of each image in the image sequence.

Abstract: A system includes obtaining a plurality of automobile part sets through classification based on at least one of the following factors an interface type of an interface of an automobile part, a transmission type used by the automobile part to transmit data, a manufacturer of the automobile part, a type of the automobile part, a safety level of the automobile part, a service type of a service to which data transmitted by the automobile part belongs, or a service level of the service to which the data transmitted by the automobile part in the automobile belongs.

Abstract: This application provides an image recognition method and device. The image recognition method includes: setting a presentation time sequence corresponding to an image sequence includes N images, the presentation time sequence includes unequal presentation times, a difference between any two presentation times of the unequal presentation times is k×?, k is a positive integer, and ? is a preset time period value; processing the image sequence by using a computer vision algorithm, to obtain a computer vision signal corresponding to each image in the image sequence; obtaining a feedback signal that is corresponding to each image in the image sequence generated when an observation object watches the image sequence displayed in the presentation time sequence; and fusing, for each image in the image sequence, a corresponding computer vision signal and a corresponding feedback signal to obtain a target recognition signal of each image in the image sequence.

Abstract: Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.