CN-122018703-A - Display equipment non-sensing control method and system based on visual sector access event

CN122018703ACN 122018703 ACN122018703 ACN 122018703ACN-122018703-A

Abstract

The invention relates to the technical field of man-machine interaction, in particular to a method and a system for non-inductive control of display equipment based on an access event of a visual sector, which are used for acquiring position information of the wearable equipment worn by a user based on a deployed remote control base station, constructing a coordinate system by taking the remote control base station as an origin and taking the normal direction of a screen of the display equipment as an X axis, identifying a viewing area of the display equipment in the coordinate system, determining a first motion mode and a second motion mode based on the position information of the wearable equipment and the visual sector for identification and analysis, determining an impending state of the position information of the wearable equipment for the first motion mode, constructing a state feature vector containing space coordinates and a proper viewing index for the second motion mode, identifying based on the state feature vector, and analyzing to obtain an behavior state in the sector.

Inventors

CUI ZHENG
WANG LEI
ZHENG WEIFEI

Assignees

杭州华数智屏信息技术有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (9)

1. The method for controlling the display equipment to be noninductive based on the visual sector access event is characterized by comprising the following steps: Based on the deployed remote control base station, acquiring the position information of the wearable equipment worn by the user, wherein the position information of the wearable equipment comprises real-time angle information and real-time distance information; the remote control base station is used as an origin, and the normal direction of the screen of the display equipment is used as an X axis to construct a coordinate system, wherein in the coordinate system, the viewing area of the display equipment is identified and is determined as a visible sector; Based on the wearable device position information and the visual sector, performing recognition analysis to determine a first motion mode and a second motion mode; judging the impending state of the position information of the wearable equipment for the first movement mode; For the second motion mode, constructing a state feature vector comprising a space coordinate and a proper viewing index, identifying based on the state feature vector, and analyzing to obtain a sector inner behavior state in the second motion mode, wherein the sector inner behavior state comprises a viewing maintaining state, a dynamic adjusting state and an impending exit state; And performing noninductive control of the display equipment based on the identified impending state and the sector behavior state.
2. The visual sector access event-based display device noninductive control method as claimed in claim 1, wherein: The process of acquiring the wearable device location information includes: A wireless space sensing unit arranged in the remote control base station is used for receiving wireless signals sent by the wearable equipment, a signal arrival angle algorithm is adopted for analyzing the phase difference of the wireless signals, a horizontal azimuth angle and a vertical pitch angle of the wearable equipment relative to the remote control base station are calculated, and the real-time angle information is generated by combining; Measuring physical transmission characteristics of wireless signals by utilizing a wireless signal ranging technology, calculating a linear distance between the wearable equipment and a remote control base station, and generating real-time distance information; And carrying out time synchronization and coordinate conversion on the real-time angle information and the real-time distance information to synthesize the position information of the wearable equipment.
3. The visual sector access event-based display device noninductive control method as claimed in claim 1, wherein: the specific process of identifying the visual sector of the display device comprises the following steps: Acquiring installation height data of a remote control base station relative to a physical ground plane, and establishing space mapping of the ground plane in a coordinate system taking the remote control base station as an origin; On a horizontal projection plane parallel to the ground plane, a horizontal sector coverage area which is bilaterally symmetrical is defined according to a preset horizontal opening angle parameter by taking the normal direction of a screen of display equipment as a central axis; defining an effective distance ring belt according to a preset minimum monitoring radius and a preset maximum viewing distance in a radial dimension taking a screen of the display device as a center; in the height dimension vertical to the ground plane, setting a proper viewing height interval based on the human body posture and the sight line, and converting the proper viewing height interval into a vertical effective coordinate range in a coordinate system by combining the installation height data; And determining an intersection area of the horizontal sector coverage area, the effective distance annular belt and the vertical effective coordinate range in the three-dimensional space as the visible sector, so as to form a three-dimensional monitoring space limited by the ground height and the viewing angle.
4. The visual sector access event-based display device noninductive control method as claimed in claim 1, wherein: the identifying and judging process of the first motion mode and the second motion mode comprises the following steps: The method comprises the steps of presetting a hysteresis double-threshold strategy for judging the space of a visible sector, wherein the hysteresis double-threshold strategy comprises an inner ring threshold group and an outer ring threshold group, and the space range of the outer ring threshold group is larger than that of the inner ring threshold group; Acquiring the position of the wearable device at the starting moment of the remote control base station, and judging a first movement mode if the position of the wearable device is outside an outer ring threshold group; When the wearable equipment position information falls within the range limited by the inner ring threshold value group, the state is judged to be turned over to a second movement mode; and triggering the pre-judgment of turning to the first movement mode only when the position information of the wearable equipment exceeds the range limited by the outer ring threshold group.
5. The visual sector access event based display device noninductive control method as in claim 4, wherein: In the first motion mode, the process of identifying the impending state specifically comprises the following steps: Establishing a sliding time window, extracting a position coordinate sequence of the wearable equipment in the sliding time window, and constructing a first motion track vector; The method comprises the steps of inputting a first motion track vector and a speed component into a pre-trained track prediction model, constructing the track prediction model based on a long-short-period memory network, outputting a predicted position sequence in a preset time period in the future, and judging that a state is about to enter when the end point of the predicted position sequence falls into the visible sector and the speed component shows a decreasing trend to accord with a seating deceleration characteristic.
6. The visual sector access event-based display device noninductive control method as in claim 5, wherein: in the second motion mode, the process of analyzing and obtaining the behavior state in the sector specifically comprises the following steps: synchronously acquiring triaxial acceleration data, triaxial angular velocity data and space position coordinates of the wearable equipment, calculating a proper viewing index according to the position information of the wearable equipment, and performing time alignment and normalization processing to obtain a state feature vector; The state characteristic vector is input into a preset behavior recognition neural network model, the behavior recognition neural network model adopts a convolution neural network to extract space displacement characteristics, attitude frequency characteristics, energy attenuation characteristics and proper viewing index change rate, and performs weighted analysis on time position change by combining an attention mechanism, and classification results including a viewing maintaining state, a dynamic adjusting state and a state to be withdrawn are output.
7. The visual sector access event based display device noninductive control method as claimed in claim 6, wherein: The acquisition process of the suitable viewing index specifically comprises the following steps: Calculating the position suitability, the attitude suitability and the light suitability in real time by adopting a weighted scoring model, and fusing to obtain a suitable viewing index; the calculation of the position suitability comprises the steps of carrying out cluster learning on historical position data of a user in a viewing state based on a Gaussian mixture model, generating a probability distribution cluster suitable for furniture positions, and calculating probability values belonging to the probability distribution cluster according to current position coordinates to obtain the position suitability; The method comprises the steps of calculating the posture fitness, namely decomposing the position information into vertical heights, and judging the user posture by combining the height data of the user and the inertial sensor data of the wearable equipment; and calculating the light suitability, namely detecting the ambient light intensity through an ambient light sensor integrated with the remote control base station, and carrying out combination analysis based on the time sequence change of the ambient light intensity and the pre-identified suitable light intensity to obtain the light suitability.
8. The method for sensorless control of a display device based on visual sector access events of claim 6, Based on the identified state, the non-sensing control of the display device comprises triggering the display device to execute pre-wake-up and volume fade-up operations when the state is about to enter, maintaining current playing parameters of the display device when the state is about to keep watching, shielding false triggering instructions generated by position jitter when the state is about to be dynamically adjusted, and triggering the display device to execute pause and mute operations when the state is about to exit.
9. A visual sector access event based display device sensorless control system comprising: The system comprises a position acquisition module, a remote control base station, a position acquisition module and a control module, wherein the position acquisition module is used for acquiring position information of wearable equipment worn by a user based on a deployed remote control base station, and the position information of the wearable equipment comprises real-time angle information and real-time distance information; The sector determining module takes the remote control base station as an origin and takes the normal direction of the screen of the display equipment as an X axis to construct a coordinate system, wherein in the coordinate system, a viewing area of the display equipment is identified and is determined as a visible sector; The mode identification module is used for carrying out identification analysis on the wearable equipment position information and the visible sector and judging a first motion mode and a second motion mode; judging the impending state of the position information of the wearable equipment for the first movement mode; For the second motion mode, constructing a state feature vector comprising a space coordinate and a proper viewing index, identifying based on the state feature vector, and analyzing to obtain a sector inner behavior state in the second motion mode, wherein the sector inner behavior state comprises a viewing maintaining state, a dynamic adjusting state and an impending exit state; And the noninductive control module is used for noninductive control of the display equipment based on the identified impending entering state and the identified behavior state in the sector.

Description

Display equipment non-sensing control method and system based on visual sector access event Technical Field The invention relates to the technical field of man-machine interaction, in particular to a display equipment noninductive control method and a system based on visual sector access events. Background With the deep integration of computer technology and intelligent hardware, man-machine interaction approaches are undergoing evolution from traditional physical contact input to non-contact natural space interaction. In the intelligent home and multimedia interaction scene, a non-inductive control technology based on the space state of a user gradually becomes a research hot spot. Such techniques aim to automatically trigger wake-up, suspension, or multimedia state switching of a computing device by sensing the presence and behavior of a user to promote the level of fluency and intelligence of interactions. The current noninductive interaction scheme mainly depends on two technical paths, namely an image recognition technology based on computer vision, a proximity detection technology based on infrared or simple wireless signal intensity and used for capturing bones or faces of a user to judge the presence state. However, the above prior art has significant limitations in practical applications. Firstly, although the recognition accuracy is higher in the vision-based scheme, serious user privacy concerns are raised in private spaces such as families, and the input data is easily interrupted due to the influence of ambient light and shielding. Secondly, schemes based on infrared or simple signal strength, which essentially belong to threshold triggering mechanisms, lack deep understanding of user behavior semantics. Such techniques have difficulty in constructing accurate three-dimensional interaction space and are susceptible to boundary jitter due to the effects of signal multipath. More importantly, the prior art does not effectively distinguish between non-interactive physical adjustments and substantial interaction intents of the user. For example, when a user adjusts the sitting posture only to cause a small fluctuation of the signal, the user often misjudges that the user leaves to trigger the device to lock or pause, and the continuity of the user experience is seriously damaged. Therefore, on the premise of not depending on image acquisition, how to accurately define the interaction area by processing the spatial perception data and intelligently identify the deep behavioral intention of the user becomes a breakthrough difficulty in the field. Therefore, a method and a system for controlling the noninductive display equipment based on the visual sector access event are provided. Disclosure of Invention The invention aims to provide a method and a system for controlling the display equipment without sense based on a visual sector access event, which are used for controlling the display equipment without sense through the identified impending entering state and the identified behavior state in a sector. In order to achieve the above purpose, the present invention provides the following technical solutions: The method for controlling the display equipment to be noninductive based on the visual sector access event comprises the following steps: Based on the deployed remote control base station, acquiring the position information of the wearable equipment worn by the user, wherein the position information of the wearable equipment comprises real-time angle information and real-time distance information; the remote control base station is used as an origin, and the normal direction of the screen of the display equipment is used as an X axis to construct a coordinate system, wherein in the coordinate system, the viewing area of the display equipment is identified and is determined as a visible sector; Based on the wearable device position information and the visual sector, performing recognition analysis to determine a first motion mode and a second motion mode; judging the impending state of the position information of the wearable equipment for the first movement mode; For the second motion mode, constructing a state feature vector comprising a space coordinate and a proper viewing index, identifying based on the state feature vector, and analyzing to obtain a sector inner behavior state in the second motion mode, wherein the sector inner behavior state comprises a viewing maintaining state, a dynamic adjusting state and an impending exit state; And performing noninductive control of the display equipment based on the identified impending state and the sector behavior state. The process of acquiring the wearable device location information includes: A wireless space sensing unit arranged in the remote control base station is used for receiving wireless signals sent by the wearable equipment, a signal arrival angle algorithm is adopted for analyzing the phase difference of the wireless signals, a horizo