CN-122002122-A - Shooting control method, device, equipment, medium and program product

CN122002122ACN 122002122 ACN122002122 ACN 122002122ACN-122002122-A

Abstract

The application discloses a shooting control method, a shooting control device, shooting control equipment, shooting control media and shooting control program products, and relates to the technical field of computers. The method comprises the steps of obtaining target voice information of a user, inputting the target voice information into an instruction analysis model to obtain a target voice command corresponding to the target voice information, training the instruction analysis model to obtain a model to be trained based on at least one voice sample to be trained, wherein the voice sample to be trained comprises voice information, a first instruction label and a second instruction label corresponding to the voice information, the first instruction label is used for indicating whether an image needs to be shot or not, the second instruction label is used for indicating an image shooting type, responding to the target voice command to indicate the image needs to be shot, sending an image shooting instruction corresponding to the target voice command to a TWS earphone to enable the TWS earphone to shoot a scene image, and receiving the scene image sent by the TWS earphone. The application can meet the shooting requirement of the convenience of the user and improve the use experience of the user on shooting functions.

Inventors

ZHANG ZHONGHAI
WU HAIQUAN
JIANG DEJUN
CHI XIN
CAO LEI
HE GUIXIAO

Assignees

深圳市飞科笛系统开发有限公司

Dates

Publication Date: 20260508
Application Date: 20251226

Claims (10)

1. A photographing control method, the method being applied to a mobile terminal, comprising: Acquiring target voice information of a user; The target voice information is input into an instruction analysis model to obtain a target voice command corresponding to the target voice information, the instruction analysis model is obtained by training a model to be trained based on at least one voice sample to be trained, the voice sample to be trained comprises voice information, a first instruction label and a second instruction label corresponding to the voice information, the first instruction label is used for indicating whether an image needs to be shot or not, and the second instruction label is used for indicating the image shooting type; Responding to the target voice command to indicate that an image needs to be shot, and sending an image shooting instruction corresponding to the target voice command to a TWS earphone so that the TWS earphone shoots a scene image; and receiving the scene image sent by the TWS earphone.
2. The method of claim 1, wherein the TWS headset comprises a first side headset and a second side headset, the scene images comprising a first side scene image transmitted by the first side headset and a second side scene image transmitted by the second side headset; After the receiving the scene image sent by the TWS headset, the method further includes: Receiving target inertial sensor data sent by the TWS earphone, wherein the target inertial sensor data is the inertial sensor data of the TWS earphone when the first side scene image and the second side scene image are shot; Determining a relative pose between the first side scene image and the second side scene image based on the target inertial sensor data; and based on the relative pose, splicing the first side scene image and the second side scene image to obtain a target scene image.
3. The method of claim 1, wherein before inputting the target voice information into the command parsing model to obtain the target voice command corresponding to the target voice information, the method further comprises: the method comprises the steps of obtaining at least one voice sample to be trained and a model to be trained, wherein the model to be trained is constructed by a target self-distillation model, a first classification head and a second classification head, the target self-distillation model is a model with semantic feature extraction capability, the model is obtained by self-distillation pre-training by adopting a non-labeling voice sample, the first classification head is used for outputting the probability that whether the voice sample to be trained indicates that an image needs to be shot or not, and the second classification head is used for outputting the probability that the voice sample to be trained indicates various image shooting types; And updating the model parameters of the target self-distillation model, the first classification head parameters of the first classification head and the second classification head parameters of the second classification head based on the voice sample to be trained to obtain the instruction analysis model.
4. The method of claim 1, wherein after the receiving the scene image transmitted by the TWS headset, the method further comprises: inputting the scene image into an image recognition model, and extracting a flag element in the scene image; Searching element introduction information associated with the significative element from a background knowledge base; and sending the element introduction information to the TWS headset so as to introduce the logo element to the user.
5. The method of claim 1, wherein after the receiving the scene image transmitted by the TWS headset, the method further comprises: acquiring a historical image preference style of the user; Based on the historical image preference style, determining a personalized optimization strategy corresponding to the historical image preference style; and optimizing the scene image based on the personalized optimization strategy to obtain an optimized scene image.
6. A photographing control method, wherein the method is applied to a TWS headset, comprising: acquiring an image shooting instruction; Responding to the image shooting instruction, executing image shooting behaviors corresponding to the image shooting instruction, and obtaining a scene image; and sending the scene image to the mobile terminal.
7. The method of claim 6, wherein the acquiring the image capturing instruction includes any one of: responding to interaction actions between a user and a target key of the TWS earphone, and acquiring the image shooting instruction corresponding to the interaction actions; Responding to target voice information of a user, matching the target voice information with a preset voice command template, and determining an image shooting instruction corresponding to the target voice information; and receiving the image shooting instruction sent by the mobile terminal.
8. The method of claim 6, wherein the performing, in response to the image capturing instruction, an image capturing action corresponding to the image capturing instruction to obtain a scene image comprises: Responding to the image shooting instruction, and adjusting the camera parameters of the TWS earphone until the camera parameters meet preset shooting conditions; and responding to the camera parameters meeting preset shooting conditions, and executing image shooting behaviors corresponding to the image shooting instructions to obtain the scene images.
9. A photographing control apparatus, the apparatus being applied to a mobile terminal, comprising: The information acquisition module is used for acquiring target voice information of a user; The command determining module is used for inputting the target voice information into the command analyzing model to obtain a target voice command corresponding to the target voice information, wherein the command analyzing model is obtained by training a model to be trained based on at least one voice sample to be trained, the voice sample to be trained comprises voice information, a first command label and a second command label corresponding to the voice information, the first command label is used for indicating whether an image needs to be shot or not, and the second command label is used for indicating the image shooting type; The instruction sending module is used for responding to the target voice command to indicate that the image needs to be shot, and sending an image shooting instruction corresponding to the target voice command to the TWS earphone so that the TWS earphone shoots a scene image; and the image receiving module is used for receiving the scene image sent by the TWS earphone.
10. A photographing control apparatus, the apparatus being applied to a TWS headset, comprising: the instruction acquisition module is used for acquiring an image shooting instruction; The image shooting module is used for responding to the image shooting instruction and executing image shooting behaviors corresponding to the image shooting instruction to obtain a scene image; And the image sending module is used for sending the scene image to the mobile terminal.

Description

Shooting control method, device, equipment, medium and program product Technical Field The present application relates to the field of computer technologies, and in particular, to a shooting control method, device, apparatus, medium, and program product. Background In recent years, computer technology has rapidly developed, and mobile terminals such as mobile phones and tablet computers have become indispensable electronic products in people's life. In the use scenarios of these mobile terminals, the image capturing function is receiving a great deal of attention, and users have a strong demand for a convenient capturing operation mode. Currently, mobile terminals are often equipped with camera shooting functionality, and a user may trigger shooting through physical keys or screen virtual keys on the mobile terminal. However, in the existing method, the camera shooting operation mode of the mobile terminal is complex, so that shooting requirements of convenience of a user cannot be met, and the use experience of the user on shooting functions is affected. Disclosure of Invention The embodiment of the application provides a shooting control method, a shooting control device, shooting control equipment, shooting control media and a shooting control program product, which can meet shooting requirements of convenience of users and improve user experience of shooting functions. In a first aspect of an embodiment of the present application, a photographing control method is provided, which is applied to a mobile terminal, and includes: Acquiring target voice information of a user; The method comprises the steps of inputting target voice information into an instruction analysis model to obtain a target voice command corresponding to the target voice information, wherein the instruction analysis model is obtained by training a model to be trained based on at least one voice sample to be trained, the voice sample to be trained comprises voice information, a first instruction label and a second instruction label corresponding to the voice information, the first instruction label is used for indicating whether an image needs to be shot or not, and the second instruction label is used for indicating the image shooting type; Responding to the target voice command to indicate that the image needs to be shot, and sending an image shooting command corresponding to the target voice command to the TWS earphone so that the TWS earphone shoots the scene image; and receiving the scene image sent by the TWS earphone. In a second aspect of the embodiment of the present application, a shooting control method is provided, which is applied to a TWS earphone, and includes: acquiring an image shooting instruction; responding to the image shooting instruction, executing image shooting behaviors corresponding to the image shooting instruction, and obtaining a scene image; And sending the scene image to the mobile terminal. In a third aspect of an embodiment of the present application, there is provided a photographing control apparatus applied to a mobile terminal, including: The information acquisition module is used for acquiring target voice information of a user; The command determining module is used for inputting the target voice information into the command analyzing model to obtain a target voice command corresponding to the target voice information, wherein the command analyzing model is obtained by training the model to be trained based on at least one voice sample to be trained, the voice sample to be trained comprises voice information, a first command label and a second command label corresponding to the voice information, the first command label is used for indicating whether an image needs to be shot or not, and the second command label is used for indicating the image shooting type; the instruction sending module is used for responding to the target voice command to indicate that the image needs to be shot, and sending an image shooting instruction corresponding to the target voice command to the TWS earphone so as to enable the TWS earphone to shoot the scene image; And the image receiving module is used for receiving the scene image sent by the TWS earphone. In a fourth aspect of an embodiment of the present application, there is provided a photographing control apparatus applied to a TWS headset, including: the instruction acquisition module is used for acquiring an image shooting instruction; the image shooting module is used for responding to the image shooting instruction, executing image shooting actions corresponding to the image shooting instruction and obtaining a scene image; and the image sending module is used for sending the scene image to the mobile terminal. In a fifth aspect of the embodiments of the present application, there is provided an electronic device including a memory and a program or instructions stored on the memory and executable on a processor, the program or instructions implementing the p