New media promotion method and system based on Internet

Abstract

The invention discloses a new media promotion method and system based on the Internet, and belongs to the technical field of new media promotion, and the method specifically comprises the steps that the distribution density and the stop position of people in a waiting area are monitored in real time, load distribution data in a lift car are collected, and the vibration frequency and the start-stop state in the elevator running process are recorded; when it is detected that the density of people in the waiting area exceeds a set threshold value, switching to duration compressed advertisement content, and when the load distribution of the lift car displays that one side is crowded, displaying interactive advertisements in the free area; capturing a user eyeball movement track, calculating an advertisement interface fixation thermodynamic diagram, identifying a user gesture operation by using a millimeter wave radar, mapping a specific gesture into an advertisement content switching instruction, and generating a personalized advertisement recommendation scheme; and the advertisement interaction data is converted into a pushing strategy adjustment basis of adjacent elevators, a propagation path is established according to the flow rule of people in the elevator room, and when the advertisement click rate of a certain elevator exceeds a set value, a content recommendation signal is sent to the associated elevator.

Description

Technical Field

[0001] The present invention relates to the technical field of new media promotion, and in particular to a new media promotion method and system based on the Internet. Background Art

[0002] When it comes to new media promotion in elevators, the current mainstream technology relies on fixed advertising displays inside elevator cars and waiting areas. These displays typically display uniform advertising content using conventional delivery methods, with a predetermined schedule and format. Whether during the busy morning rush hour in office buildings or during normal hours in residential communities, these displays remain largely unchanged, making it difficult to flexibly and accurately adapt to the ever-changing real-world scenarios in elevator waiting areas and cars, as well as the diverse needs of different user groups. Traditional elevator advertising models have exposed a series of significant drawbacks. From a scene perception perspective, existing technologies are unable to effectively and accurately grasp the density of people in waiting areas, nor can they accurately understand the actual conditions within the elevator car, such as load distribution and crowding, in real time. As a result, in high-density waiting areas or when one side of the elevator car is crowded, advertising content remains unchanged, failing to optimize its display for these specific scenarios. Consequently, a large number of ads fail to achieve the desired results, resulting in a significant waste of advertising resources. Summary of the Invention

[0003] The purpose of the present invention is to provide a new media promotion method and system based on the Internet to solve the following technical problems: In waiting areas with high population density or when one side of the elevator is crowded, advertising cannot achieve the desired effect.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A new media promotion method based on the Internet, comprising the following steps: Infrared thermal imaging technology is used to monitor the density and location of people in the waiting area in real time. Pressure sensing floors are used to collect load distribution data in the elevator car. Accelerometers are used to record the vibration frequency and start and stop status of the elevator during operation. When the density of people in the waiting area exceeds the set threshold, the system automatically switches to a compressed version of the advertisement. When the load distribution of the elevator car shows congestion on one side, interactive advertising elements are displayed in the idle area. Capture user eye movement trajectories, calculate gaze heat maps on ad interfaces, use millimeter-wave radar to identify user gestures, map specific gestures to ad content switching instructions, and generate personalized ad recommendations based on user interaction behavior data. The advertising interaction data is converted into a basis for adjusting the push strategy of adjacent elevators. The communication path is established by analyzing the flow of people between elevators. When the click-through rate of an elevator advertisement exceeds the set value, a content recommendation signal is sent to the associated elevators.

[0005] As a further solution of the present invention: the distribution of people in the waiting area is identified by an infrared thermal imaging device, the load distribution of the car is detected using a pressure sensing floor, the operating status is recorded by an acceleration sensor, and the environmental noise characteristics are analyzed in combination with a sound collection device. The above data are fused and processed to generate an environmental status description.

[0006] As a further solution of the present invention: when the elevator door is open, a floating advertising interface is projected on the inner wall of the car, and the advertising content is adjusted according to real-time environmental data. When the number of waiting people exceeds a set value, it is switched to a short-duration advertisement. When the load distribution in the car is uneven, interactive elements are added in the idle area. When the running acceleration exceeds a set value, the brightness of the advertising interface is reduced.

[0007] As a further solution of the present invention: the user behavior data collection process includes: The user's eye movement trajectory is captured through a micro-camera array, the gaze heat map of the advertising interface is calculated, the palm movement trajectory is identified using millimeter-wave radar, specific gestures are mapped into advertising content switching instructions, and the advertising preference description is generated by combining the gaze duration and interaction frequency.

[0008] As a further solution of the present invention: the interactive behavior recording process includes: An invisible watermark is embedded in the advertising interface. When users scan the advertising content through their mobile devices, the association data between the device identifier and the advertising identifier is recorded to establish frequency statistics of users being exposed to the same advertising content across elevators. At the same time, voice keywords in the elevator are collected to extract advertising content recall indicators.

[0009] As a further solution of the present invention: the push strategy adjustment process includes: Each elevator is abstracted as a network node, and the connection strength between nodes is dynamically adjusted according to the frequency of personnel flow. When the click-through rate of an advertisement at a node exceeds a threshold, a content recommendation signal is sent to adjacent nodes with high connection strength. The receiving node then makes adaptive adjustments to the recommended advertisement based on local environmental data. The adjustments include compressing the playback time period, enhancing visual elements, and grading the interaction difficulty.

[0010] As a further solution of the present invention: the group behavior-driven advertising optimization process includes: Advertising elements are decomposed into three types of feature segments: visual theme, interaction mode, and duration configuration. The fitness score of each feature segment is calculated based on the elevator network communication data. New advertising plans are generated through feature recombination. After testing on designated elevator nodes, the best ones are promoted to the entire network.

[0011] The present invention also includes an Internet-based new media promotion system for implementing the above-mentioned Internet-based new media promotion method, comprising: The elevator environment monitoring module uses infrared thermal imaging technology to monitor the density and location of people in the waiting area in real time. It uses a pressure sensing floor to collect load distribution data within the elevator car and uses an acceleration sensor to record the vibration frequency and start and stop status of the elevator during operation. A dynamic advertising display module automatically switches to a compressed version of the ad when it detects that the density of people in the waiting area exceeds a set threshold. It also displays interactive advertising elements in the idle area when the load distribution of the elevator car indicates congestion on one side. The advertising effect feedback module is used to capture user eye movement trajectories, calculate gaze heat maps on the advertising interface, use millimeter-wave radar to identify user gestures, map specific gestures to advertising content switching instructions, and generate personalized advertising recommendations based on user interaction behavior data; The elevator network communication module is used to convert advertising interaction data into a basis for adjusting the push strategy of adjacent elevators. It establishes a communication path by analyzing the flow of people between elevators. When the click-through rate of an elevator advertisement exceeds a set value, a content recommendation signal is sent to the associated elevators.

[0012] Beneficial effects of the present invention: The present invention uses infrared thermal imaging, pressure-sensing floors, and acceleration sensors to accurately monitor the distribution of people in the waiting area and the load conditions in the car in real time. When it is detected that the density of people in the waiting area exceeds the set threshold, the advertisement will automatically switch to a compressed version, effectively adapting to scenarios where users have a shorter waiting time and preventing users from feeling bored due to long advertisements. When the load distribution of the car shows congestion on one side, the system will display interactive advertising elements in the vacant area of the car, making full use of the space while attracting user attention, increasing the exposure and dissemination effect of the advertisement, and greatly improving the scene adaptability of the advertisement. In addition, with the help of micro-camera arrays and millimeter-wave radars, user eye movements and gestures are captured to generate personalized advertising recommendations and enhance interactivity. The elevator is abstracted as a network node, and the connection strength is adjusted according to the frequency of personnel flow. High-click-rate advertisements can be recommended to adjacent nodes to expand their influence. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below with reference to the accompanying drawings.

[0014] Figure 1 This is a flow chart of a new media promotion method based on the Internet according to the present invention; Figure 2 This is a module diagram of a new media promotion system based on the Internet according to the present invention. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0016] See also Figure 1-Figure 2 As shown, the present invention is a new media promotion method based on the Internet, comprising the following steps: In the critical data collection process, this invention utilizes infrared thermal imaging technology. Based on Planck's law, this technology uses infrared detectors to capture infrared radiation energy emitted by the human body. The detectors convert the received infrared signals into electrical signals, which are then processed through complex algorithms to generate a visual thermal image. Intelligent analysis of thermal images accurately displays the density of people in waiting areas and their specific standing positions. For example, in elevator waiting areas of large shopping malls, infrared thermal imaging can clearly distinguish the density of people in different areas, providing a key and intuitive basis for adjusting subsequent advertising strategies. Furthermore, pressure sensing floors, a key tool for data collection within the elevator cabin, utilize advanced piezoresistive sensors installed on the floor of the cabin. These sensors are highly sensitive to subtle pressure changes in different areas and convert these pressure changes into electrical signals using a Wheatstone bridge circuit. The data processing system can accurately determine the distribution of people within the cabin, accurately identifying both uniform distribution and unusual situations such as one-sided crowding. Accelerometers utilize piezoelectric effects or microelectromechanical systems (MEMS) technology to record the vibration frequency and start / stop status of the elevator during operation. During smooth elevator operation, sensors can detect subtle vibrations caused by the elevator's mechanical structure. During elevator starts and stops, they can quickly and accurately record changes in acceleration. This data provides an essential reference for comprehensively assessing the elevator's operating environment and, in turn, optimizing the timing and methods of advertising.

[0017] After conducting in-depth analysis of the collected data, the system demonstrates robust adaptive capabilities. Once it detects that the waiting area's density exceeds a pre-set threshold, indicating high traffic and relatively short wait times, the system quickly responds during the morning rush hour in an office building. For example, the system automatically switches the currently playing ad to a compressed version. For example, consider a 60-second car brand ad. The system uses intelligent video editing algorithms to precisely extract key highlights, such as the car's exterior and unique features, and intelligently edits it into a 15-second, condensed version. This condensed version quickly conveys the core message within a limited timeframe, effectively preventing users from becoming bored during a rushed wait due to lengthy ads. This ensures that the ad reaches users precisely within the limited timeframe, increasing its effective exposure. Furthermore, when the elevator car's load distribution indicates congestion on one side, the system, relying on data from the pressure-sensing floor, can detect this situation. Interactive advertising elements are then displayed in the unoccupied area of the car. For example, when the right side of the elevator car is crowded and the left side is relatively empty, the system uses projection technology to display touchable and clickable interactive ads on the left side of the car wall. Users can click on product images to enlarge and view detailed configuration information, or participate in simple and fun games such as guessing the car model to win coupons. This approach fully utilizes the available space, greatly attracts user attention, and significantly improves the exposure and dissemination of ads.

[0018] To gain deep insights into user behavior, this invention has built a comprehensive and sophisticated data collection system. By meticulously installing arrays of micro-cameras at specific locations within the elevator car, these cameras utilize advanced deep learning-based image recognition technology to accurately capture the user's eye movements. As the user views an ad, the cameras meticulously record key information such as the direction of eye movement, the location of the gaze, and the duration of gaze. Using a specialized eye movement analysis algorithm, a gaze heat map of the ad interface is calculated. This heat map clearly and intuitively reveals the user's attention to different areas of the ad, clearly identifying which color combinations or content attract attention and which areas are easily overlooked due to bland design. Furthermore, millimeter-wave radar is used to identify the user's hand movements. Based on the Doppler effect, millimeter-wave radar emits millimeter-wave signals and detects changes in the frequency of the reflected signals to identify user gestures. Whether it's a common gesture like waving, clicking, or swiping, or even more complex gesture combinations, it can be accurately recognized. The system pre-sets a mapping relationship between specific gestures and instructions for switching between ad content. For example, a wave of the hand switches to the next page of ad details, while a click plays an ad video. Based on this, the system uses big data analysis models to generate accurate descriptions of ad preferences, taking into account the length of time users look at ads and the frequency of their interactions. For example, if a user frequently clicks on ads for a certain type of electronic product and their gaze lasts for a long time, the system can determine through data analysis that the user has a high interest in this type of product, laying a solid foundation for subsequent personalized ad recommendations.

[0019] This invention also places great emphasis on the in-depth mining and utilization of advertising interaction data. An invisible watermark is embedded in the ad interface. This watermark utilizes advanced digital watermarking technology and is invisible to the naked eye. However, when a user scans the ad content with a mobile device, recognition software in the mobile device can read the invisible watermark information based on a specific decoding algorithm. This process enables the system to accurately record the association between the device identifier and the ad identifier. For example, if a user scans a car ad for the same brand in both Elevator 1 in Building A and Elevator 3 in Building B, the system can accurately record this association data and gain a deeper understanding of the user's continued interest in this ad. Furthermore, the system utilizes advanced speech recognition technology to capture key words in the elevator car's speech. A high-sensitivity microphone array is installed in the elevator car to collect speech signals in real time. After pre-processing such as noise reduction and filtering, a deep learning speech recognition model is used to extract key words mentioned by users during discussions about the ad content. These key words are analyzed to assess ad recall. If users frequently mention keywords such as the product name and unique selling points in the advertisement, it means that the advertisement has left a deep impression on users and has a high recall rate. On the contrary, if keywords are mentioned less frequently, it indicates that the advertisement content may need to be optimized and adjusted.

[0020] In terms of push strategy adjustment, this invention abstracts each elevator into a network node, building a dynamic and intelligent advertising dissemination network. The connection strength between nodes is not fixed but dynamically adjusted in real time based on the frequency of personnel movement. For example, during rush hour in an office building, there is frequent movement between elevators on different floors. By analyzing multi-source data such as elevator card swipe records and surveillance videos, the paths and frequencies of personnel movement between different elevators can be determined, resulting in a corresponding increase in the connection strength between nodes. During late night hours, personnel movement decreases significantly, and the connection strength decreases accordingly. When the click-through rate of an ad at a node (i.e., a specific elevator) exceeds a preset threshold, it indicates that the ad has high appeal among the audience in that elevator. At this point, the system sends a content recommendation signal to neighboring nodes with strong connection strength. Upon receiving the signal, the receiving node does not directly copy the recommended ad but instead adapts it based on local environmental data. The adjustments are rich and varied, including compression of playback time. If the local waiting area is densely populated and the waiting time is short, the system will further shorten the advertising playback time based on the analysis of local historical data; visual element enhancement. By mining the local user group's past advertising click behavior data, the user's preferred colors, image styles, etc. are analyzed, and the visual elements such as advertising colors and images are optimized to make them more attractive; interaction difficulty grading. If the local user group is more familiar with interactive operations, by analyzing the user's historical interaction depth data in local elevator advertisements, the interaction difficulty can be appropriately increased, and more complex and interesting interactive links can be set. Otherwise, the difficulty can be reduced to ensure that different user groups can easily participate and improve the overall communication effect of the advertisement.

[0021] Finally, the present invention features a group behavior-driven advertising optimization mechanism. Ad elements are meticulously broken down into three characteristic segments: visual theme, interaction mode, and duration configuration. Visual theme encompasses the ad's color scheme, image style, and product presentation. Different color combinations and image styles create different visual impacts and emotional resonances for users. Interaction mode encompasses the user's interaction with the ad, such as touch, voice commands, and gestures. Each interaction mode offers a unique user experience. Duration configuration involves the overall ad duration and the time allocation for each component. A reasonable duration configuration effectively directs user attention. Based on elevator network communication data, a big data analysis algorithm is used to calculate the fitness score of each characteristic segment. For example, if a visual theme with bright colors, simple imagery, and highlighting the core features of a product consistently receives high click-through rates across multiple elevator nodes, its fitness score is high. If a touch interaction mode experiences low user engagement across multiple areas, its score is low. By recombining these characteristic segments, a new advertising plan is generated. The new plan is first tested on a small scale at designated elevator nodes to collect user feedback and various metrics, such as click-through rate, interaction frequency, and dwell time. By comparing and analyzing data from different new plans, we use a multi-indicator comprehensive evaluation model to select the most effective advertising plan, which is then promoted to the entire elevator network to ensure that the advertising always maintains a high level of appeal and communication effectiveness, thereby maximizing the use of advertising resources.

[0022] The present invention also includes an Internet-based new media promotion system for implementing the above-mentioned Internet-based new media promotion method, comprising: The elevator environment monitoring module uses infrared thermal imaging technology to monitor the density and location of people in the waiting area in real time. It uses a pressure sensing floor to collect load distribution data within the elevator car and uses an acceleration sensor to record the vibration frequency and start and stop status of the elevator during operation. A dynamic advertising display module automatically switches to a compressed version of the ad when it detects that the density of people in the waiting area exceeds a set threshold. It also displays interactive advertising elements in the idle area when the load distribution of the elevator car indicates congestion on one side. The advertising effect feedback module is used to capture user eye movement trajectories, calculate gaze heat maps on the advertising interface, use millimeter-wave radar to identify user gestures, map specific gestures to advertising content switching instructions, and generate personalized advertising recommendations based on user interaction behavior data; The elevator network communication module is used to convert advertising interaction data into a basis for adjusting the push strategy of adjacent elevators. It establishes a communication path by analyzing the flow of people between elevators. When the click-through rate of an elevator advertisement exceeds a set value, a content recommendation signal is sent to the associated elevators.

[0023] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A new media promotion method based on the Internet, characterized in that: The following steps are involved: Infrared thermal imaging technology is used to monitor the density and location of people in the waiting area in real time. Pressure sensing floors are used to collect load distribution data in the elevator car. Accelerometers are used to record the vibration frequency and start and stop status of the elevator during operation. When the density of people in the waiting area exceeds the set threshold, the system automatically switches to a compressed version of the advertisement. When the load distribution of the elevator car shows congestion on one side, interactive advertising elements are displayed in the idle area. Capture user eye movement trajectories, calculate gaze heat maps on ad interfaces, use millimeter-wave radar to identify user gestures, map specific gestures to ad content switching instructions, and generate personalized ad recommendations based on user interaction behavior data. The advertising interaction data is converted into a basis for adjusting the push strategy of adjacent elevators. The communication path is established by analyzing the flow of people between elevators. When the click-through rate of an elevator advertisement exceeds the set value, a content recommendation signal is sent to the associated elevators.

2. The new media promotion method based on the Internet according to claim 1, characterized in that: The distribution of people in the waiting area is identified through infrared thermal imaging devices, the load distribution of the car is detected using a pressure sensing floor, the operating status is recorded using an acceleration sensor, and the environmental noise characteristics are analyzed using a sound collection device. The above data are fused and processed to generate an environmental status description.

3. The new media promotion method based on the Internet according to claim 1, characterized in that: When the elevator door opens, a floating advertising interface is projected on the inner wall of the car. The advertising content is adjusted according to real-time environmental data. When the number of waiting people exceeds the set value, it switches to a short-duration advertisement. When the load distribution in the car is uneven, interactive elements are added in the idle area. When the running acceleration exceeds the set value, the brightness of the advertising interface is reduced.

4. The new media promotion method based on the Internet according to claim 1, characterized in that: The user behavior data collection process includes: The user's eye movement trajectory is captured through a micro-camera array, the gaze heat map of the advertising interface is calculated, the palm movement trajectory is identified using millimeter-wave radar, specific gestures are mapped into advertising content switching instructions, and the advertising preference description is generated by combining the gaze duration and interaction frequency.

5. The new media promotion method based on the Internet according to claim 1, characterized in that: The interactive behavior recording process includes: An invisible watermark is embedded in the advertising interface. When users scan the advertising content through their mobile devices, the association data between the device identifier and the advertising identifier is recorded to establish frequency statistics of users being exposed to the same advertising content across elevators. At the same time, voice keywords in the elevator are collected to extract advertising content recall indicators.

6. The new media promotion method based on the Internet according to claim 1, characterized in that: The push strategy adjustment process includes: Each elevator is abstracted as a network node, and the connection strength between nodes is dynamically adjusted according to the frequency of personnel flow. When the click-through rate of an advertisement at a node exceeds a threshold, a content recommendation signal is sent to adjacent nodes with high connection strength. The receiving node then makes adaptive adjustments to the recommended advertisement based on local environmental data. The adjustments include compressing the playback time period, enhancing visual elements, and grading the interaction difficulty.

7. The new media promotion method based on the Internet according to claim 1, characterized in that: The advertising optimization process driven by group behavior includes: Advertising elements are decomposed into three types of feature segments: visual theme, interaction mode, and duration configuration. The fitness score of each feature segment is calculated based on the elevator network communication data. New advertising plans are generated through feature recombination. After testing on designated elevator nodes, the best ones are promoted to the entire network.

8. An Internet-based new media promotion system, used to implement the Internet-based new media promotion method according to any one of claims 1 to 7, characterized in that: include: The elevator environment monitoring module uses infrared thermal imaging technology to monitor the density and location of people in the waiting area in real time. It uses a pressure sensing floor to collect load distribution data within the elevator car and uses an acceleration sensor to record the vibration frequency and start and stop status of the elevator during operation. A dynamic advertising display module automatically switches to a compressed version of the ad when it detects that the density of people in the waiting area exceeds a set threshold. It also displays interactive advertising elements in the idle area when the load distribution of the elevator car indicates congestion on one side. The advertising effect feedback module is used to capture user eye movement trajectories, calculate gaze heat maps on the advertising interface, use millimeter-wave radar to identify user gestures, map specific gestures to advertising content switching instructions, and generate personalized advertising recommendations based on user interaction behavior data; The elevator network communication module is used to convert advertising interaction data into a basis for adjusting the push strategy of adjacent elevators. It establishes a communication path by analyzing the flow of people between elevators. When the click-through rate of an elevator advertisement exceeds a set value, a content recommendation signal is sent to the associated elevators.

Images