Advertising sign playing method based on pedestrian vision and advertising sign

Abstract

An advertising sign playing method and an advertising sign based on passers-by vision, which relate to the field of image processing. The method is applied to an edge server, and the edge server is communicatively connected to one or more advertising signs within a target area. The method includes: obtaining a target image of passers-by within the range of the advertising sign area; obtaining the visual features and group features of the passers-by in the target image, and determining one or more target advertisements based on the visual features and the group features; obtaining the movement trajectories of the passers-by in the target image; and controlling one or more of the advertising signs to play each of the target advertisements based on the movement trajectories. Implementing the technical solution provided by this application can improve the advertising placement effect.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to an advertising signboard playback method based on passerby vision and an advertising signboard. Background Art

[0002] With the advancement of smart city construction, various types of advertising signs are widely used in public places such as commercial centers and transportation hubs. These advertising signs usually use a fixed playback method to display advertising content to different groups of passers-by. However, different groups of passers-by often show different behavior patterns and visual characteristics when watching advertisements, such as viewing angles, dwelling time, group density, etc. How to improve the pertinence and effectiveness of advertising sign placement has become an important issue that needs to be solved in the field of advertising placement.

[0003] At present, the main way of playing advertising signs is to loop different advertising content in a preset time period, or switch advertising content based on basic characteristics of passers-by such as age and gender based on face recognition technology. For example, some advertising sign systems will play workplace-related advertising content during rush hour and parent-child activities-related advertising content on weekends.

[0004] However, existing technologies only deliver advertising content based on time periods or single demographic characteristics, and fail to accurately grasp the variability of passerby groups. This results in a mismatch between advertising content and actual viewers, and inappropriate advertising timing, resulting in low advertising delivery effects. Summary of the invention

[0005] The present application provides an advertising signboard playback method and an advertising signboard based on passerby vision, which can improve the effect of advertising delivery.

[0006] In a first aspect of the present application, a method for playing an advertising sign based on passerby vision is provided, which is applied to an edge server, wherein the edge server is communicatively connected to one or more advertising signs in a target area, and the method for playing an advertising sign based on passerby vision includes:

[0007] Acquire a target image of a passerby within the area of ​​the advertising signboard;

[0008] Acquire visual features and group features of passers-by in the target image, and determine one or more target advertisements based on the visual features and the group features;

[0009] Obtaining the trajectory of the passerby in the target image;

[0010] Based on the travel trajectory, one or more of the advertising signs are controlled to play the target advertisements.

[0011] In a second aspect of the present application, an edge server is provided, including:

[0012] Obtain a target image of passers-by within the area range of an advertising signboard;

[0013] Obtain the visual features and group features of the passers-by in the target image, and determine one or more target advertisements based on the visual features and the group features;

[0014] Obtain the movement trajectories of the passers-by in the target image;

[0015] Control one or more of the advertising signboards to play the respective target advertisements based on the movement trajectories.

[0016] In a third aspect of the present application, an advertising signboard is provided, characterized by including:

[0017] Obtain a target image of passers-by within the area range;

[0018] Obtain the visual features and group features of the passers-by in the target image, and determine one or more target advertisements based on the visual features and the group features;

[0019] Obtain the movement trajectories of the passers-by in the target image;

[0020] Control one or more of the other advertising signboards to play the respective target advertisements based on the movement trajectories.

[0021] In a fourth aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are adapted to be loaded and executed by a processor to perform the above method steps.

[0022] In the present application of In a fifth aspect, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the above method steps.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] By obtaining the target images of passers-by within the area of the advertising signboard, extracting the visual features and group features of the passers-by from the target images, determining the target advertisement based on these features, and obtaining the movement trajectories of the passers-by to control the playback of the advertising signboard, the real-time perception and response to the changes of the passer-by group are realized. Since the edge server is communicatively connected to the advertising signboards within the target area, the system can quickly process the target images and timely adjust the advertising playback strategy. By analyzing the visual features and group features of the passers-by to determine the target advertisement and combining the movement trajectories to control the playback timing, the limitations of advertising placement relying only on preset time periods or single population features are avoided, and the matching degree between the advertising content and the actual viewers is improved. This solution can not only accurately grasp the variability of the passer-by group, but also select the appropriate playback timing, which can improve the advertising placement effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 FIG. is a schematic flowchart of a method for playing an advertising signboard based on the vision of passers-by provided by an embodiment of the present application;

[0026] Figure 2 FIG. is a schematic flowchart of another method for playing an advertising signboard based on the vision of passers-by provided by an embodiment of the present application;

[0027] Figure 3 FIG. is a schematic structural diagram of an edge server provided by an embodiment of the present application;

[0028] Figure 4 FIG. is a schematic structural diagram of an advertising signboard provided by an embodiment of the present application;

[0029] Figure 5 FIG. is a schematic structural diagram of an electronic device disclosed by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0031] In the description of the embodiments of the present application, words such as "for example" or "for instance" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for instance" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for instance" is intended to present relevant concepts in a specific manner.

[0032] In the description of the embodiments of the present application, the term "a plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] The present application provides an advertising sign playing method based on passers-by's vision. Referring to Figure 1 , Figure 1 is a schematic flowchart of an advertising sign playing method based on passers-by's vision disclosed in the embodiments of the present application. This method is applied to an edge server, and the edge server is communicatively connected to one or more advertising signs in a target area. The specific steps are as follows:

[0034] Step 101: Obtain the target images of passers-by within the area range of the advertising sign.

[0035] Among them, the target area refers to a specific spatial area formed by the effective coverage ranges of one or more advertising signs. Specifically, the target area can be an open area inside public places such as shopping malls, airports, and subway stations. At least one advertising sign is set in this area, and passers-by can move freely and view advertising content in this area.

[0036] In the embodiments of the present application, the target area can be understood as a set of spatial ranges extending outward a specific distance centered on each advertising sign. Among them, the effective coverage range of each advertising sign can be a circular area, and the radius of this circular area can be determined according to factors such as the size of the advertising sign, the installation height, and the clarity of the played content. For example, for a standard LED advertising screen of 2 meters × 3 meters, its effective coverage range can be set as a circular area with the center point of the advertising screen as the center and a radius of 10 meters. When the effective coverage ranges of multiple advertising signs overlap, these overlapping areas also belong to a part of the target area.

[0037] The division of the target area is used to determine the spatial range that the edge server needs to monitor and analyze, facilitating the system to accurately obtain the passers-by's visual behavior and group characteristic information within this range. By reasonably dividing the target area, it can ensure that the system can effectively capture the interaction behavior between passers-by and advertising signs, and at the same time avoid processing area information unrelated to advertising placement, improving the operating efficiency of the system.

[0038] Correspondingly, the area range of an advertising sign refers to the effective playing coverage range of a single advertising sign, which is the spatial area where passers-by can clearly view the advertising content and have effective visual interaction. This area is different from the aforementioned target area. The target area is the set of the coverage ranges of multiple advertising signs, while the area range of an advertising sign is the specific effective range defined for a single advertising sign.

[0039] In the embodiments of the present application, the area range of an advertising sign can be understood as a fan-shaped space centered on the advertising sign. The size and shape of this fan-shaped space are jointly determined by multiple parameters: its radial distance is determined by the size, installation height, and display resolution of the advertising sign, and is generally set to the maximum distance that allows passers-by to clearly recognize the advertising content; its opening angle is determined by the viewing angle of the display screen of the advertising sign and the environmental occlusion situation, usually being 120 - 160 degrees; its height range takes into account the line-of-sight height of general passers-by, approximately ranging from 1.2 meters to 2 meters above the ground. For example, for a 55-inch high-definition LED advertising screen, its area range may be a fan-shaped area with the advertising screen as the vertex, a radius of 8 meters, and an opening angle of 140 degrees.

[0040] Specifically, three high-definition cameras can be deployed within the area range of each advertising sign, and are respectively set at different positions to achieve omnidirectional monitoring. Among them, the first camera is installed directly above the advertising sign and is used to take a top-down photo of the crowd distribution within the entire fan-shaped area; the second and third cameras are respectively installed on the left and right sides of the advertising sign, forming a 45-degree angle with the surface of the sign, and are used to collect the side images of passers-by. This three-point layout method can effectively avoid viewing blind spots and ensure that the system can accurately capture the complete behavioral characteristics of passers-by within the area range of the advertising sign. The installation height of all cameras is uniformly 3 meters from the ground. This height can not only ensure a large monitoring range but also cause no obvious interference to passers-by.

[0041] After the edge server receives the original images transmitted by multiple cameras, it first performs image preprocessing. The preprocessing process includes operations such as denoising, illumination equalization, and geometric correction to eliminate the influence of environmental factors on the image quality. Then, the system synchronizes the image data from different cameras in time and registers them in space. Time synchronization ensures that the images collected by different cameras correspond to the same moment, and spatial registration establishes the corresponding relationship between images from different perspectives. Through feature point matching and image stitching algorithms, the system fuses the image data from three perspectives into a set of complete target images.

[0042] To meet the requirements of different scenarios, the system adopts an adaptive image acquisition strategy. In the standard mode, each camera captures images at a frame rate of 25 frames per second, and the system processes a set of target images every 200 milliseconds. When it detects a sudden increase in the number of people or a crowd gathering, the system will automatically increase the sampling frequency to one set every 100 milliseconds to ensure that important behavioral features are not missed. Conversely, during periods with sparse pedestrian flow, the system will appropriately reduce the sampling frequency to save computing resources.

[0043] Step 102: Obtain the visual features and group features of pedestrians in the target image, and determine one or more target advertisements based on the visual features and group features.

[0044] Among them, the visual features refer to the behavioral features related to visual perception shown by pedestrians within the range of the advertisement sign area, mainly including two core indicators: the line-of-sight range and the fixation duration. Among them, the line-of-sight range is used to characterize the angular difference between the direction of the pedestrian's line of sight and the center of the advertisement sign, reflecting whether the pedestrian focuses on the advertisement content; the fixation duration represents the length of time the pedestrian continuously pays attention to the advertisement content, reflecting the degree of interest of the pedestrian in the advertisement content. In the embodiments of the present application, the line-of-sight range can be understood as an angular value. When this angular value is less than a preset threshold, it means that the pedestrian's line of sight falls within the effective viewing range of the advertisement; the fixation duration can be understood as a time accumulation value, and the system will record the continuous stay time of the pedestrian within the line-of-sight range. The acquisition of visual features is used to identify potential target objects interested in the advertisement content, providing a behavioral basis for subsequent advertisement content optimization.

[0045] Correspondingly, the group features refer to the attribute features shown by the pedestrian group in terms of demographics and spatial distribution, mainly including the number of pedestrians, age groups, gender ratio, and group density. Among them, the number of pedestrians reflects the size of the pedestrian flow in the current area; the age group is used to distinguish the audience groups of different age levels; the gender ratio represents the composition ratio of men and women in the current group; the group density is used to characterize the ratio of the number of target objects to the total number of pedestrians. In the embodiments of the present application, the above group features can be understood as a set of statistical indicators, and the system describes the overall characteristics of the current audience group by calculating the values of these indicators in real time. The acquisition of group features is used to analyze the portrait of the audience, guiding the system to select the most suitable advertisement content for the current group attributes, and realizing the precision and personalization of advertisement delivery.

[0046] Based on the above embodiments, as an optional embodiment, in step 102: the step of determining one or more target advertisements based on the visual features and the group features may specifically further include the following steps:

[0047] Step 201: Based on the visual features, determine the target objects interested in the advertisement sign.

[0048] Among them, the target object refers to an individual passerby who shows continuous attention and relatively high interest in the advertisement content within the area of the advertisement sign. In the embodiments of the present application, the target object can be understood as a specific passerby who simultaneously meets the requirements of line-of-sight range matching and fixation duration. Determining the target object is mainly used to provide an effective audience basis for the intelligent adjustment of advertisement content. By continuously tracking and analyzing the behavioral characteristics of the target object, the system can accurately evaluate the attractiveness of the currently played content and provide data support for the optimization of subsequent advertisement placement strategies.

[0049] Based on the above embodiments, as an optional embodiment, the visual features include the line-of-sight range and the fixation duration. The line-of-sight range is used to characterize the angular difference between the line-of-sight direction of the passerby and the center of the advertisement sign. For step 201: Based on the visual features, determining the target object interested in the advertisement sign, this step can specifically include the following steps:

[0050] Step 301: Based on the line-of-sight range, determine the matching degree between the advertisement sign and the passerby's line-of-sight range.

[0051] Among them, the line-of-sight range refers to the spatial relationship parameter between the line-of-sight direction of the passerby and the center position of the advertisement sign, which mainly reflects the visual focusing state of the passerby when watching the advertisement content. In the embodiments of the present application, the line-of-sight range can be understood as the included angle θ formed between the line-of-sight direction vector of the passerby and the connection vector of the center of the advertisement sign. The smaller this included angle, the closer the passerby's line of sight is to the center position of the advertisement content. For example, when the passerby looks directly at the advertisement sign, the included angle θ is close to 0 degrees; when the passerby looks at the advertisement sign at a 45-degree angle, the line-of-sight range significantly deviates from the optimal viewing angle. The line-of-sight range is used to evaluate the quality of visual interaction between the passerby and the advertisement sign and is a basic parameter for judging whether the passerby actually pays attention to the advertisement content.

[0052] Exemplarily, the line-of-sight range matching degree can be calculated by a first preset formula, expressed as:

[0053] ;

[0054] In the formula, represents the line-of-sight range matching degree, represents the angular difference between the line-of-sight direction of the passerby and the center of the advertisement sign, represents the maximum allowable line-of-sight deviation angle, that is, the maximum allowable included angle between the passerby's line-of-sight range and the center of the advertisement sign.

[0055] Among them, ;

[0056] In the formula, represents obtaining the line-of-sight vector of the passerby, represents obtaining the normal vector of the advertisement sign.

[0057] Specifically, the system first needs to obtain the line-of-sight vector of passersby and the normal vector of the advertising sign. The system collects the facial images of passersby through high-definition cameras deployed around the advertising sign, and uses computer vision algorithms to extract the eye positions and pupil orientations of passersby, thereby determining the spatial direction of the line-of-sight vector. At the same time, based on the installation position and orientation information of the advertising sign, the system can obtain the normal vector perpendicular to the advertising display plane. After determining these two vectors, the angle between the line-of-sight direction of the passerby and the center of the advertising sign can be calculated through the dot product operation of the vectors and the ratio of the vector magnitudes.

[0058] After obtaining the line-of-sight angle, the system introduces a preset maximum line-of-sight deviation angle as a standardization reference value, which is usually set to 30 degrees, and this is determined based on the physiological characteristics of the comfortable viewing range of the human eye. The line-of-sight range matching degree of a single passerby is calculated through a first preset formula. When the passerby looks directly at the advertising content, the matching degree reaches the maximum value; as the line-of-sight deviation angle increases, the matching degree decreases linearly; when the deviation angle exceeds the maximum allowable value, the matching degree drops to zero. The above calculation method not only conforms to the gradual change characteristics of visual perception but also can effectively filter out invalid samples with significantly deviated lines of sight.

[0059] Exemplarily, for multiple passersby within the range of the advertising sign, the line-of-sight range matching degree can be expressed as:

[0060] ;

[0061] In the formula, N represents the number of passersby within the range of the advertising sign, represents the line-of-sight angle of the i-th passerby.

[0062] Specifically, considering that there are usually multiple passersby watching the advertisement simultaneously in the actual scenario, the system designs a calculation method for the group line-of-sight range matching degree. For multiple passersby within the range of the advertising sign, the system obtains the overall line-of-sight range matching degree by calculating the arithmetic mean of all individual matching degrees. This calculation method not only retains the influence of individual line-of-sight characteristics but also can reflect the overall viewing state of the group, providing more comprehensive data support for evaluating the advertising placement effect.

[0063] Step 302: Based on the fixation duration, determine the matching degree between the advertisement currently broadcast on the advertising sign and the fixation duration of the passerby.

[0064] Among them, the fixation duration refers to the duration that the passerby keeps their line of sight within the effective viewing range of the advertising sign within a specific time period. In the embodiments of the present application, the fixation duration can be understood as the cumulative time when the system detects that the line-of-sight range matching degree of the passerby continuously maintains at a relatively high level.

[0065] Specifically, when the line-of-sight range of passersby continuously meets the matching conditions, the system will record and accumulate their effective viewing time; once it detects that the line of sight significantly deviates or is interrupted, the time accumulation will stop and the current value will be recorded. The fixation duration is used to quantify the continuous attention of passersby to the advertisement content and is an important indicator for evaluating the attractiveness of the advertisement and the effectiveness of the content.

[0066] Step 303: Based on the line-of-sight range matching degree and the fixation duration matching degree, determine the degree of interest value of passersby in the advertisement sign, and identify passersby with an interest degree value greater than the threshold as target objects.

[0067] Specifically, in the advertisement placement system, a single visual feature is difficult to comprehensively reflect the true degree of interest of passersby in the advertisement content. To accurately identify target objects, the embodiments of this application propose a comprehensive evaluation method based on the line-of-sight range matching degree and the fixation duration matching degree, and achieve precise quantification of the interest degree of passersby through multi-dimensional feature fusion.

[0068] Specifically, the system first needs to obtain two basic indicators: the line-of-sight range matching degree and the fixation duration matching degree of passersby. The line-of-sight range matching degree reflects the spatial correspondence between the line of sight of passersby and the advertisement content, while the fixation duration matching degree characterizes the continuous attention degree of passersby to the advertisement content. By setting different weight coefficients, the system performs weighted fusion calculation on these two matching degree indicators to obtain the degree of interest value of passersby in the advertisement sign.

[0069] After obtaining the degree of interest value, the system compares it with a preset interest threshold. When the degree of interest value of a passerby exceeds this threshold, the system marks it as a target object, indicating that the passerby shows an obvious willingness to pay attention to the advertisement content.

[0070] Exemplarily, the degree of interest value can be calculated by a second preset formula, expressed as:

[0071] ;

[0072] In the formula, represents the degree of interest value, represents the line-of-sight range matching degree, represents the fixation duration matching degree, represents the fixation duration, represents the maximum fixation duration, which is used for normalization.

[0073] Among them, in different application scenarios, the importance of the line-of-sight range and the fixation duration will vary, and it is necessary to adjust the weight coefficients α and β to adapt to specific requirements. The embodiments of this application provide two typical application scenarios and their corresponding weight configuration schemes.

[0074] In a fast-response scenario, such as the real-time push of mall promotion information, the system pays more attention to capturing the immediate attention behavior of passersby. At this time, the advertisement content usually consists of short texts and eye-catching price information, requiring the system to quickly identify potential customers interested in the promotion information. In this scenario, the system sets the weight coefficient α of the line-of-sight range to 0.6 and the weight coefficient β of the fixation duration to 0.4. The above configuration emphasizes the immediate response characteristics of the line-of-sight range matching degree. As long as the passerby's line of sight turns to the advertisement content, the system can promptly capture this attention behavior, thereby achieving the precise push of promotion information.

[0075] In a deep-content scenario, such as brand image promotion, the system pays more attention to the continuous attention degree of passersby. At this time, the advertisement content often contains relatively rich brand stories or product details, and it takes a longer time to fully convey the information. In this scenario, the system sets the weight coefficient α of the line-of-sight range to 0.3 and the weight coefficient β of the fixation duration to 0.7. This configuration emphasizes the importance of the fixation duration matching degree, requiring passersby not only to direct their line of sight at the advertisement content but also to maintain a sufficient viewing time to be recognized as a truly interested target object.

[0076] Step 202: Determine one or more target advertisements based on the group characteristics of the target object.

[0077] Specifically, in the advertisement placement system, merely identifying the target object is not sufficient to achieve precise advertisement placement. It is also necessary to deeply analyze the group characteristics of the target object to select the advertisement content most suitable for the current audience group. The embodiment of the present application proposes an intelligent matching method for advertisement content based on group characteristics, which realizes the dynamic optimization of advertisement content by analyzing characteristics such as the number, age group, gender ratio, and group density of the target object.

[0078] Based on the above embodiments, as an optional embodiment, the group characteristics include the number of passersby, age group, gender ratio, and group density. In step 202, the step of determining one or more target advertisements based on the group characteristics of the target object may specifically further include the following steps:

[0079] Among them, the number of passersby refers to the total statistical number of all pedestrian individuals simultaneously present within the range of the advertisement sign area. In the embodiment of the present application, the number of passersby can be understood as the number of valid human targets recognized by the system through the target detection algorithm within a preset time window, and this value will be dynamically updated over time.

[0080] The age range refers to the characteristic of the age distribution interval of passers-by. In the embodiments of the present application, the age range can be understood as the age estimation result obtained by the system through analyzing the facial features of passers-by, and is usually divided into three main intervals: young (18 - 35 years old), middle-aged (36 - 55 years old), and elderly (over 56 years old). For example, the system may detect that among the current target objects, the young account for 60%, the middle-aged account for 30%, and the elderly account for 10%. The age range is used to guide the system to select advertising content suitable for specific age groups.

[0081] The gender ratio refers to the distribution relationship between the number of males and females in the passer-by group. In the embodiments of the present application, the gender ratio can be understood as the ratio of the number of males and females calculated by the system after identifying the gender characteristics of passers-by. The gender ratio is used to help the system select advertising content more suitable for the current gender composition.

[0082] Step 301: Obtain the group density of the target object, where the group density is used to characterize the ratio of the number of target objects to the number of passers-by.

[0083] Among them, the group density refers to the ratio value of the number of target objects to the total number of passers-by. In the embodiments of the present application, the group density can be understood as the ratio of the number of target objects that show continuous attention to the advertising content identified by the system within a specific time window to the current total number of passers-by. The group density is used to evaluate the attractiveness level of the current advertising content and is an important basis for the system to judge whether to adjust the advertising placement strategy.

[0084] Exemplarily, the group density can be calculated by a third preset formula, which is expressed as follows:

[0085] ;

[0086] In the formula, represents the group density of the target objects in front of the billboard at time t, represents the number of target objects, represents the number of passers-by.

[0087] Step 302: If the group density is greater than the threshold, determine one or more target advertisements based on the age range and the gender ratio.

[0088] Specifically, when the advertising content obtains a high group density, it indicates that the current content has successfully attracted the attention of passers-by. In order to maximize the advertising placement effect, the most suitable subsequent advertising content can be selected by analyzing the population portrait characteristics of the target objects.

[0089] Specifically, the system first determines whether the current group density exceeds a preset threshold. When the group density is greater than the threshold, the system immediately starts to analyze the age distribution and gender ratio characteristics of the target objects. Through deep learning algorithms, the system can extract age and gender information from the facial features of the target objects and generate group portrait data.

[0090] After obtaining these group characteristic data, the system will perform matching and screening in the advertisement content library. Each advertisement in the advertisement content library is pre-labeled with the applicable target population characteristics, including age group preferences and gender inclinations. The system uses a weighted scoring method to calculate the matching degree scores for each candidate advertisement based on the group characteristics of the current target objects. For example, when it is detected that the target objects are mainly young women, the system will preferentially select advertisement content related to fashion and beauty; when the target objects show the characteristics of a middle-aged group with a balanced male-female ratio, the system may tend to select advertisement content related to home and automobiles.

[0091] To ensure the coherence of advertisement placement, the system also considers the correlation degree between advertisement contents. On the basis of ensuring group characteristic matching, it preferentially selects advertisements with similar themes or content forms to the current advertisement to avoid overly abrupt content switching. The system will finally select one or more from the candidate advertisements with the highest scores as target advertisements and sequentially place them according to the preset playback strategy.

[0092] Step 302: If the group density is less than or equal to the threshold, determine the group density change rate within a preset duration, and determine one or more target advertisements based on the group density change rate.

[0093] The group density change rate refers to the change trend of the proportion of target objects within the range of the advertisement sign area within a preset duration. The group density change rate is used to evaluate the attraction trend of advertisement content and guide the real-time adjustment of the placement strategy. A positive change rate indicates that the advertisement content is gradually attracting more attention, and the system may choose to maintain the current placement strategy; a negative change rate prompts the system to adjust the advertisement content in a timely manner to avoid continuous loss of the viewing population.

[0094] Exemplarily, the group density change rate can be calculated by the fourth preset formula, which is expressed as follows:

[0095] ;

[0096] In practical applications, discrete time intervals can be used to approximately calculate the density change rate:

[0097] ;

[0098] In the formula, represents the time interval.

[0099] When When it is [a certain value], it indicates that the group density is increasing, that is, the number of target objects is increasing relative to the total number of passers-by; when it is [another value], it indicates that the group density is decreasing, that is, the number of target objects is decreasing relative to the total number of passers-by.

[0100] Specifically, the system uses an approximate calculation method with discrete time intervals to obtain the change rate of group density. In practical applications, the system will set a fixed sampling time interval and record the current group density D(t) at each sampling moment. By calculating the difference in group density between two adjacent sampling moments and dividing it by the sampling time interval, the change rate of group density ΔD(t) at the current moment can be obtained. For example, if the group density at time t is 0.25 and the group density 10 seconds ago (at time t - Δt) was 0.2, the current change rate of group density is approximately 0.005 per second, indicating that the advertising content is steadily attracting more attention.

[0101] The system evaluates the changing trend of the attractiveness of advertising content by judging the positive or negative of the change rate of group density. When the calculated change rate is greater than 0, it indicates that the number of target objects shows an increasing trend relative to the total number of passers-by, indicating that the current advertising content is continuously attracting new audiences; when the change rate is less than or equal to 0, it indicates that the proportion of target objects is decreasing or remaining stable, and it may be necessary to consider adjusting the advertising content. To avoid interference caused by instantaneous fluctuations, the system usually combines data from multiple sampling points for smoothing processing to obtain a more stable judgment of the changing trend.

[0102] When the group density is less than or equal to the threshold, the effect of advertising playback can be measured by an objective function that depends on the change rate of group density and the type of advertising playback . Assuming there are several advertisements available for selection, each advertisement has its popularity , and a matching function suitable for different change rates of group density .

[0103] Then the objective function can be expressed as:

[0104] ;

[0105] Correspondingly, when it is [a certain situation], it is suitable to play long-duration, static advertisements to attract fewer but potentially interested passers-by. The matching function can be reflected as the absolute value of the density change rate and can be expressed as:

[0106] ;

[0107] In the formula, and are advertisements A specific parameter that indicates the sensitivity of the advertisement to density changes.

[0108] At , medium-length advertisements can be selected, with advertisement content suitable for the current population, such as product introductions or brand promotions. The matching degree can be set as a constant:

[0109] ;

[0110] Specifically, the system first establishes a feature attribute profile for each candidate advertisement, including its popularity and the sensitivity parameter to group density changes. Popularity reflects the basic attractiveness of the advertisement content and can be determined through historical playback data and user feedback; the sensitivity parameter characterizes the adaptability of the advertisement content to different viewing environments and needs to be set according to the advertisement type and display form. For example, a well-produced brand story advertisement may have a high popularity, and its sensitivity parameter reflects the performance characteristics of the advertisement under different crowd densities.

[0111] The system evaluates the real-time playback effect of each advertisement through an objective function. When the detected group density change rate is negative, indicating that the current viewing population is decreasing, the system tends to select long-duration and static-type advertisement content. The effect of this type of advertisement is evaluated through a specific matching degree function, where a higher basic parameter value indicates that the advertisement has a stronger basic attractiveness, and the sensitivity parameter controls the response degree of the advertisement to group density changes. When the group density change rate is close to zero, the system selects medium-length advertisement content, such as product introductions or brand promotional videos. At this time, the matching degree is evaluated using a fixed value to ensure the selection of the most suitable advertisement content for the current stable viewing environment.

[0112] To select the best advertisement, with the main goal being to maximize the objective function, the optimization problem can be defined as:

[0113] ;

[0114] To address the problem of dependencies between advertisement plays, especially in the scenario of advertisement sequence optimization. The cumulative effect of advertisement plays over a period of time can be optimized by constructing a state transition equation and considering the group density changes at different future time points. Over T time periods, the group density change rate varies with time , and the state transition equation is:

[0115] ;

[0116] In the formula, represents selecting advertisement The optimal cumulative objective function value after that, j represents the advertisement played at the previous time point t−1, and finally traces back the optimal advertisement sequence selected at each time period t.

[0117] Specifically, the matching degree of the current population density change is used as an evaluation index. This optimization model not only considers the immediate effect of a single advertisement but also needs to consider the coherence between advertisement sequences. For example, playing a relevant product introduction immediately after playing a brand story advertisement may achieve better communication effects.

[0118] To solve the problem of dependency relationships between advertisement plays, the system uses a dynamic programming algorithm to construct a state transition equation. At each time period, the system needs to select the optimal advertisement content based on the play state at the previous moment and the current population density change. By recording the cumulative effects after selecting different advertisements at each moment, the system can find the optimal advertisement play sequence throughout the planning time period. For example, if it is detected that the previous advertisement attracted a large number of young viewers, the system will give priority to relevant advertisement content suitable for the young group in subsequent time periods.

[0119] The system determines the final advertisement play sequence through a backtracking algorithm. Starting from the last time point, according to the optimal choices recorded in the state transition equation, it gradually derives the advertisement content that should be played at each time period. This method ensures that not only the choices at each time point are locally optimal, but also the cumulative effect of the entire advertisement sequence reaches the global optimum.

[0120] Step 103: Obtain the movement trajectories of passers-by in the target image.

[0121] Among them, the movement trajectory refers to the sequence of spatial positions of passers-by changing over time in the target area. In the embodiments of the present application, the movement trajectory can be understood as the movement trajectory of passers-by represented in a two-dimensional coordinate system, including information such as the position coordinates, moving speed, and direction of passers-by at specific time points. The movement trajectory is used to characterize the relative position relationship between the displacement of passers-by and each advertisement sign.

[0122] Specifically, the system first needs to calculate the real-time distance between passers-by and advertisement signs. Each advertisement sign has its fixed position coordinates in the two-dimensional plane, while the position coordinates of passers-by change continuously over time. By calculating the Euclidean distance between the current position of passers-by and the position of the advertisement sign, the system can obtain the spatial distance between the two in real time. This distance calculation method is intuitive and efficient, providing reliable data support for the system to monitor the position relationship between passers-by and advertisement signs.

[0123] Based on the acquired location data, the system further analyzes the movement characteristics of passers-by. The movement trajectory of a passer-by is essentially a trajectory curve of their position changing over time. By performing a time differentiation on the location data, the instantaneous speed of the passer-by can be obtained. The system continuously collects the location data of passers-by through the deployed camera network, and after processing, obtains the complete movement trajectory information.

[0124] Step 104: Control one or more advertising signs to play each target advertisement based on the movement trajectory.

[0125] After determining the target advertisement, the system needs to control the advertisement playback strategy according to the movement trajectory characteristics of the passers-by to achieve the optimal advertisement display effect. As the passers-by move, the positional relationship between them and different advertising signs is constantly changing, and the above dynamic changes directly affect the viewing effect of the advertisement content. Therefore, the playback order and duration of the advertisement can be optimized by analyzing the movement characteristics of the passers-by.

[0126] Based on the above embodiments, as an alternative embodiment, in step 104: The step of controlling one or more advertising signs to play each target advertisement based on the movement trajectory may specifically further include the following steps:

[0127] Step 401: Obtain the relative distances between each passer-by and each advertising sign based on the movement trajectory.

[0128] Exemplarily, assuming that the area where the advertising sign is located is a two-dimensional plane, the movement trajectory of the passer-by can be represented by the change of their displacement over time:

[0129] ;

[0130] In the formula, The position of the j-th advertising sign, represented as a two-dimensional coordinate ( ), Represents the distance between the passer-by and the advertising sign at time t. The spatial position of the passer-by at time t, represented as a two-dimensional coordinate ( ).

[0131] The movement trajectory of the passer-by can be represented as the change trajectory of their position over time t. The position change data of the passer-by can be obtained, and the change speed of the trajectory is represented as: .

[0132] Step 402: Determine the distance weight based on the relative distances of each advertising sign. The distance weight is used to characterize the possibility that a passer-by sees the corresponding advertising sign based on their corresponding movement trajectory.

[0133] Among them, the distance weight refers to a quantitative index of the possibility that passers-by view the content of the advertising sign. This index comprehensively considers the spatial distance and the characteristics of the traveling direction between the passers-by and the advertising sign. In the embodiments of the present application, the distance weight can be understood as the product of the basic spatial weight and the direction adjustment factor. Among them, the basic spatial weight adopts the form of the reciprocal of the distance to reflect the influence of the distance on the viewing possibility, and the direction adjustment factor characterizes the matching degree between the line of sight of the passers-by and the advertising content through the cosine value of the included angle between the traveling direction of the passers-by and the direction of the advertising sign.

[0134] Exemplarily, for each advertising sign calculate a weight related to the distance of the passers-by , and the calculation of the weight can be based on the reciprocal of the distance. The closer the distance, the greater the weight, which is expressed as:

[0135] ;

[0136] In the formula, is used to prevent the denominator from being 0.

[0137] Furthermore, the playback order can be adjusted by the included angle between the traveling angle of the passers-by and the advertising sign. The traveling direction of the passers-by can be determined by the position change between the current position and the next moment, which is expressed as:

[0138] ;

[0139] Then the angle between the advertising sign and the current position of the passers-by is expressed as:

[0140] ;

[0141] The included angle between the traveling direction of the passers-by and the advertising sign is expressed as:

[0142] ;

[0143] Specifically, the above calculation method ensures that the advertising sign closer to the passers-by obtains a higher weight value. To avoid calculation anomalies when the passers-by are too close to the advertising sign, the system introduces a small smoothing factor in the denominator. For example, when the passers-by are 2 meters away from a certain advertising sign, its basic weight value may be 0.4; when the distance increases to 10 meters, the weight value may decrease to 0.09. The weight calculation method based on the reciprocal of the distance intuitively reflects the influence law of the spatial distance on the advertising viewing possibility.

[0144] After obtaining the basic distance weights, the system further considers the movement direction characteristics of passers-by. By analyzing the position changes of passers-by at adjacent moments, the system can calculate the real-time moving direction of passers-by. Specifically, the system uses the position coordinates of passers-by at the current moment and the next moment, and calculates the moving angle through the arctangent function. At the same time, the system also calculates the azimuth angle of the advertising sign relative to the current position of the passer-by, which reflects the position of the advertising sign in the passer-by's field of vision. By calculating the difference between these two angles, the system obtains the included angle between the moving direction of the passer-by and the direction of the advertising sign.

[0145] The calculation of the included angle enables the system to more accurately evaluate the possibility of passers-by viewing the advertising content. For example, when a passer-by moves directly towards the advertising sign, the included angle is close to 0 degrees, indicating that the passer-by is more likely to notice the advertising content; when a passer-by approaches the advertising sign at a 45-degree angle, even if the distance is the same, the possibility of viewing will be correspondingly reduced; if a passer-by moves away from the advertising sign, that is, the included angle is close to 180 degrees, even if the distance is relatively close, the possibility of viewing is extremely low.

[0146] Furthermore, the smaller the included angle, the more likely it is that a passer-by can see the advertising sign. Therefore, the weight can be adjusted as follows:

[0147] ;

[0148] Step 403: Determine the playback order of one or more advertising signs based on the distance weights, and play one or more target advertisements on each advertising sign based on the playback order.

[0149] Specifically, the playback order of the advertising signs can be sorted based on the weights. The advertising sign with a higher weight is played earlier, which can be expressed as:

[0150] ;

[0151] Specifically, after obtaining the adjusted weight values of each advertising sign, the system needs to set the advertising playback order to achieve the optimal allocation of advertising resources. Since the attention and viewing time of passers-by are limited, a reasonable playback order is crucial for improving the advertising delivery effect. Therefore, the embodiment of this application proposes a method for determining the playback order based on weight maximization to enhance the dissemination effect of advertising content by dynamically optimizing the playback order.

[0152] Specifically, the system first sorts all advertising signboards based on the adjusted distance weights. Through the principle of maximizing the weights, the system selects the advertising signboard with the highest weight value as the primary playback position. This selection mechanism ensures that the advertising content is preferentially played on the signboard that passers-by are most likely to notice. For example, when it is detected that a passer-by is approaching an advertising signboard and the walking direction is basically the same as the direction of the signboard, the signboard may obtain the highest adjusted weight value, and the system will preferentially play the advertisement on this signboard.

[0153] After determining the playback order, the system starts to play the target advertisement on each advertising signboard in sequence according to the priority. This playback process is dynamic, and the system continuously monitors the position changes and walking directions of passers-by, and updates the weight values and playback order of each signboard in real time. For example, when the movement of a passer-by causes the viewing conditions of an advertising signboard to improve, the system may increase the playback priority of this signboard; conversely, if the viewing conditions deteriorate, the priority may be reduced or the playback may be paused.

[0154] When there are multiple target advertisements to be played, the system will perform intelligent matching according to the characteristics of the advertisement content and the viewing behavior characteristics of passers-by. For advertising signboards with higher weight values, the system tends to play more important or more suitable advertisement content for immediate viewing; while for signboards with lower weight values, it may choose to play secondary information or cyclic content. The above differential content distribution strategy ensures that important advertising information can be delivered to the target audience at the best time and location.

[0155] Based on the above embodiments, as an optional embodiment, after determining the playback order of the advertising signboards, the following steps may further be included:

[0156] Step 501: Determine the residence time of the passer-by at the next advertising signboard based on the relative distances of the passer-by to each advertising signboard.

[0157] Exemplarily, the residence time of the passer-by near the advertising signboard can be calculated by the distance between the passer-by and the advertising signboard being less than a threshold, which can be expressed as:

[0158] ;

[0159] In the formula, the {1} indicator function takes 1 when the condition is satisfied and 0 otherwise; and are the time ranges of the passer-by near the advertising signboard.

[0160] Specifically, the system first defines a distance threshold to determine whether a passerby is within the effective viewing range of the advertising sign. The setting of this threshold comprehensively considers factors such as the size of the advertising sign, the installation height, and the clarity of the displayed content. For example, for a standard-sized LED advertising screen, the system may set the distance threshold to 5 meters. Passersby within this range can clearly see the advertising content and generate effective visual interaction.

[0161] After determining the distance threshold, the system starts to monitor the relative distance between the passerby and the advertising sign in real time. When it detects that a passerby enters the effective viewing range, the system starts time accumulation counting; when the passerby leaves this range, the system stops counting and records the accumulated time. This accumulation process takes into account the situation where a passerby may enter and leave the effective range multiple times. Through continuous distance monitoring and time accumulation, the system can obtain the total residence time of the passerby in front of a specific advertising sign.

[0162] The system uses an indicator function to mark whether a passerby is within the effective viewing range. When the distance between the passerby and the advertising sign is less than the preset threshold, the indicator function takes a value of 1, indicating that the passerby is within the effective range at this time; when the distance is greater than the threshold, the indicator function takes a value of 0, indicating that the passerby has left the effective range. By integrating the indicator function over a specific time interval, the system can accurately calculate the actual residence time of the passerby.

[0163] Step 502: Adjust the playback duration of one or more target advertisements based on the residence time.

[0164] Exemplarily, the advertisement playback duration can be associated with the passerby's residence time. Therefore, a minimum playback duration can be set and extended according to the residence time. This process can be expressed as:

[0165] ;

[0166] In the formula, k is a proportionality coefficient used to adjust the extensibility of the playback duration.

[0167] Specifically, the system can set a minimum playback duration, which ensures that the advertising content can fully convey the core information. The setting of the minimum playback duration considers the complexity and amount of information of the advertising content. For example, for simple promotional information, it may be set to 10 seconds, while brand image advertisements may require a benchmark duration of more than 20 seconds. This benchmark setting provides a basic guarantee for advertisement playback, ensuring that even when passersby pass by quickly, the necessary advertising information can be conveyed.

[0168] Based on the benchmark duration, the system introduces a proportionality coefficient to achieve dynamic extension of the playback duration. This proportionality coefficient determines the system's response to the behavior of passersby staying. A larger proportionality coefficient means that the playback duration is more sensitive to the staying time. For example, when the proportionality coefficient is set to 0.5, if it is detected that a passerby stays in front of the advertising sign for an additional 20 seconds, the system will correspondingly extend the playback duration by 10 seconds. This linear extension mechanism not only maintains the simplicity of playback control but also realizes dynamic adaptation to viewing behavior.

[0169] The system will also dynamically adjust the proportionality coefficient according to different scenarios and advertising types. In high-traffic places such as shopping malls, the system may adopt a smaller proportionality coefficient to avoid the influence of a single passerby's long viewing time on other potential viewers; in low-traffic places such as airport waiting areas, a larger proportionality coefficient can be used to allow more complete advertising content to be provided to interested passersby. This scenario-based parameter adjustment ensures the flexibility and adaptability of playback control.

[0170] Please refer to Figure 2 , Figure 2 Another advertising sign playback method based on the vision of passersby provided by the embodiments of this application is applied to the advertising sign. The advertising sign is communicatively connected to one or more other advertising signs in the target area. Specifically, this method may further include the following steps:

[0171] Step 601: Obtain the target images of passersby within the regional scope;

[0172] Step 602: Obtain the visual features and group features of passersby in the target images, and determine one or more target advertisements based on the visual features and group features;

[0173] Step 603: Obtain the movement trajectories of passersby in the target images;

[0174] Step 604: Control one or more other advertising signs to play each target advertisement based on the movement trajectories.

[0175] It should be noted that the two methods in the embodiments of this application have different execution entities. Figure 1 The execution entity of the illustrated embodiment is the edge server, and the edge server uniformly manages and controls multiple advertising signs in the target area; while Figure 2 The execution entity of the illustrated embodiment is the advertising sign, and a single advertising sign is used as the main control device to coordinate and control the playback behavior of other advertising signs.

[0176] Specifically, when the edge server is the execution entity, it directly obtains the passerby information within the coverage of all advertising billboards in the target area, realizing global monitoring and unified management of the entire target area. The edge server can process the data of multiple advertising billboards simultaneously and make playback decisions based on the global information, which is conducive to achieving a larger range of advertising placement coordination.

[0177] When the advertising billboard is the execution entity, it mainly analyzes and makes decisions based on the passerby information within its own area range, and coordinates the playback behavior through the communication connection with other advertising billboards. This distributed control method reduces the dependence on the central server and improves the flexibility and scalability of the system. Even if a certain advertising billboard fails, it will not affect the operation of the entire system.

[0178] The above two execution entities each have their own advantages, and the appropriate implementation method can be selected according to the requirements of the actual application scenario. For example, in relatively concentrated spaces such as shopping malls, the edge server can be used as the execution entity; while in decentralized scenarios such as blocks, the implementation method with the advertising billboard as the execution entity can be selected.

[0179] It should be noted that the specific implementation process of the above method can refer to the relevant descriptions of steps 101 to 104 in the above embodiments, and will not be elaborated here.

[0180] Please refer to Figure 3 , Figure 3 FIG.

[0181] The first target image acquisition module is used to acquire the target images of passersby within the area range of the advertising billboard;

[0182] The first target advertisement determination module is used to acquire the visual features and group features of the passersby in the target images, and determine one or more target advertisements based on the visual features and the group features;

[0183] The first trajectory acquisition module is used to acquire the trajectories of the passersby in the target images;

[0184] The first target advertisement playback module is used to control one or more of the advertising billboards to play each of the target advertisements based on the trajectories.

[0185] Based on the above embodiments, as an optional embodiment, the first target advertisement determination module is further used to determine the target objects interested in the advertising billboard based on the visual features; and determine one or more target advertisements based on the group features of the target objects.

[0186] Based on the above embodiments, as an alternative embodiment, the first target advertisement determination module is further configured to determine the matching degree between the advertisement sign and the line of sight of passers-by based on the line of sight range; determine the matching degree between the advertisement currently played on the advertisement sign and the fixation duration of passers-by based on the fixation duration; determine the degree of interest value of the passers-by in the advertisement sign based on the line of sight range matching degree and the fixation duration matching degree, and determine the passers-by with the degree of interest value greater than the threshold as target objects.

[0187] Based on the above embodiments, as an alternative embodiment, the first target advertisement determination module is further configured to obtain the group density of the target objects, where the group density is used to represent the ratio of the number of target objects to the number of passers-by; if the group density is greater than the threshold, determine one or more target advertisements based on the age group and the gender ratio; if the group density is less than or equal to the threshold, determine the change rate of the group density within a preset duration, and determine one or more target advertisements based on the change rate of the group density.

[0188] Based on the above embodiments, as an alternative embodiment, the first trajectory acquisition module is further configured to obtain the relative distance between each passer-by and each advertisement sign based on the trajectory; determine a distance weight based on the relative distance of each advertisement sign, where the distance weight is used to represent the possibility that a passer-by sees a corresponding advertisement sign when moving based on the corresponding trajectory; determine the playing order of one or more of the advertisement signs based on the distance weight, and play the one or more target advertisements on each advertisement sign based on the playing order.

[0189] Based on the above embodiments, as an alternative embodiment, the first trajectory acquisition module is further configured to determine the residence time of a passer-by at the next advertisement sign based on the relative distance of the passer-by to each advertisement sign; adjust the playing duration of one or more of the target advertisements based on the residence time.

[0190] Please refer to Figure 4 , Figure 4 , which is a schematic structural diagram of an advertisement sign provided by an embodiment of the present application. The advertisement sign includes:

[0191] A second target image acquisition module, configured to acquire a target image of passers-by within a regional range;

[0192] A second target advertisement determination module, configured to acquire the visual features and group features of passers-by in the target image, and determine one or more target advertisements based on the visual features and the group features;

[0193] A second trace trajectory acquisition module, configured to acquire the trace trajectory of passers-by in the target image;

[0194] A second target advertisement playing module, configured to control one or more of the other advertisement signs to play each of the target advertisements based on the trace trajectory.

[0195] It should be noted that: when the device provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0196] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform the advertisement sign playing method based on the vision of passers-by as described in the above embodiment. The specific execution process can refer to the specific description of the shown embodiment and will not be elaborated here.

[0197] The present application also discloses an electronic device. Refer to Figure 5 , Figure 5 which is a schematic structural diagram of an electronic device disclosed in the embodiment of the present application. The electronic device 500 may include: at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502.

[0198] Among them, the communication bus 502 is used to realize the connection and communication between these components.

[0199] Among them, the user interface 503 may include a display interface and a camera interface. Optionally, the user interface 503 may further include a standard wired interface and a wireless interface.

[0200] Among them, the network interface 504 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0201] Among them, the processor 501 may include one or more processing cores. The processor 501 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 505, and by calling the data stored in the memory 505. Optionally, the processor 501 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 501 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface graphics, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501 and may be implemented separately by a single chip.

[0202] Among them, the memory 505 may include random access memory (RAM), and may also include read-only memory. Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 505 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 505 may further be at least one storage device located far from the aforementioned processor 501. Refer to Figure 5 , as a computer storage medium, the memory 505 may include an operating system, a network communication module, a user interface module, and an application program for an advertising sign playback method based on pedestrian vision.

[0203] In Figure 5In the electronic device 500 shown, the user interface 503 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 501 can be used to call an application program stored in the memory 505 for a method of playing an advertising sign based on passers-by vision. When executed by one or more processors 501, the electronic device 500 is caused to execute one or more of the methods as described in the above embodiments. It should be noted that for the foregoing method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0204] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0205] In several implementation manners provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0206] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0207] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0208] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0209] The foregoing are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the disclosure of the practical truth, those skilled in the art will readily think of other implementation manners of the present disclosure.

[0210] This application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for playing advertising signs based on passerby vision, characterized in that: Applied to an edge server, the edge server is connected to one or more advertising signs in a target area, and the advertising sign playing method based on passerby vision includes: Acquire target images of passers-by within the advertising sign area; Obtain visual features and group features of passers-by in the target image. Visual features include sight range and gaze duration. The sight range is used to represent the angle difference between the sight direction of passers-by and the center of the advertising sign. Based on the sight range, determine the matching degree between the advertising sign and the sight range of passers-by; Based on the gaze duration, determine the matching degree between the advertisement currently broadcasted by the billboard and the gaze duration of the passerby; Based on the sight range matching degree and the gaze duration matching degree, the passerby's interest level in the advertising signboard is determined, and the passerby whose interest level value is greater than a threshold is determined as a target object; Determine one or more targeted advertisements based on the group characteristics of the target objects; Obtain the trajectory of the pedestrian in the target image, which is used to characterize the relative position relationship between the displacement of the pedestrian and each advertising sign; Obtain the relative distance between each passerby and each advertising sign based on the movement trajectory; Based on the relative distance of each advertising sign, the distance weight is determined. The distance weight is used to characterize the possibility of a passerby seeing the corresponding advertising sign based on the corresponding movement trajectory. The distance weight is the product of the basic space weight and the direction adjustment factor. The basic space weight is the inverse of the relative distance. The direction adjustment factor characterizes the degree of match between the passerby's sight and the advertising content through the cosine value of the angle between the passerby's moving direction and the advertising sign direction. The play order of the one or more advertising signs is determined based on the distance weights, and one or more target advertisements are played on each advertising sign based on the play order.

2. The method for playing advertising signs based on passerby vision according to claim 1, characterized in that: Group characteristics include the number of passersby, age group, gender ratio, and group density; Determine one or more targeted advertisements based on the group characteristics of the target audience, including: Obtaining the group density of the target object, where the group density is used to represent the ratio of the number of target objects to the number of passers-by; If the group density is greater than a threshold, one or more targeted advertisements are determined based on the age group and gender ratio; If the group density is less than or equal to the threshold, the group density change rate within a preset time period is determined, and one or more target advertisements are determined based on the group density change rate.

3. The method for playing advertising signs based on passerby vision according to claim 1, characterized in that: After determining the order of playing one or more advertising signs based on the distance weight, the method further includes: Determine the dwell time of the passerby at the next advertising sign based on the relative distance of the passerby to each advertising sign; Adjust the playing duration of one or more target ads based on the dwell time.

4. A method for playing advertising signs based on passerby vision, characterized in that: Applied to an advertising sign, the advertising sign is connected to one or more other advertising signs in a target area, and the advertising sign playing method based on passerby vision includes: Acquire target images of passers-by within the area; Obtain visual features and group features of passers-by in the target image. Visual features include sight range and gaze duration. The sight range is used to represent the angle difference between the sight direction of passers-by and the center of the advertising sign. Based on the sight range, determine the matching degree between the advertising sign and the sight range of passers-by; Based on the gaze duration, determine the matching degree between the advertisement currently broadcasted by the billboard and the gaze duration of the passerby; Based on the sight range matching degree and the gaze duration matching degree, the passerby's interest level in the advertising signboard is determined, and the passerby whose interest level value is greater than a threshold is determined as a target object; Determine one or more targeted advertisements based on the group characteristics of the target objects; Obtain the trajectory of the pedestrian in the target image, which is used to characterize the relative position relationship between the displacement of the pedestrian and each advertising sign; Obtain the relative distance between each passerby and each other advertising sign based on the movement trajectory; Based on the relative distances of other advertising signs, a distance weight is determined. The distance weight is used to characterize the possibility of a passerby seeing the corresponding other advertising signs based on the corresponding movement trajectory. The distance weight is the product of the basic spatial weight and the direction adjustment factor. The basic spatial weight is the inverse of the relative distance. The direction adjustment factor characterizes the degree of match between the passerby's sight and the advertising content through the cosine value of the angle between the passerby's moving direction and the advertising sign direction. A playback order of the one or more other advertising signs is determined based on the distance weights, and one or more target advertisements are played on each of the other advertising signs based on the playback order.

5. An edge server, characterized in that: include: A first target image acquisition module is used to acquire a target image of a passerby within the advertising sign area; The first target advertisement determination module is used to obtain visual features and group features of passers-by in the target image, wherein the visual features include sight range and gaze duration, wherein the sight range is used to characterize the angle difference between the sight direction of the passer-by and the center of the advertising sign, and based on the sight range, determine the matching degree between the advertising sign and the sight range of the passer-by, and based on the gaze duration, determine the matching degree between the advertisement currently broadcasted by the advertising sign and the gaze duration of the passer-by, and determine the interest level of the passer-by in the advertising sign based on the sight range matching degree and the gaze duration matching degree, and determine the passer-by whose interest level value is greater than a threshold as the target object, and determine one or more target advertisements based on the group features of the target object; A first track acquisition module is used to acquire the track of the pedestrian in the target image, and the track is used to characterize the relative position relationship between the displacement of the pedestrian and each advertising sign; The first target advertisement playing module is used to obtain the relative distance between each passerby and each advertisement sign based on the movement trajectory; determine the distance weight based on the relative distance of each advertisement sign, and the distance weight is used to characterize the possibility of the passerby seeing the corresponding advertisement sign based on the corresponding movement trajectory, wherein the distance weight is the product of the basic space weight and the direction adjustment factor, the basic space weight is the inverse of the relative distance, and the direction adjustment factor characterizes the degree of match between the passerby's line of sight and the advertisement content through the cosine value of the angle between the passerby's moving direction and the advertisement sign direction; determine the playback order of one or more advertisement signs based on the distance weight, and play one or more target advertisements on each advertisement sign based on the playback order.

6. An advertising sign, characterized in that: include: The second target image acquisition module is used to acquire target images of passers-by within the area; The second target advertisement determination module is used to obtain visual features and group features of passers-by in the target image, wherein the visual features include sight range and gaze duration, wherein the sight range is used to characterize the angle difference between the sight direction of the passer-by and the center of the advertising sign, and based on the sight range, determine the matching degree between the advertising sign and the sight range of the passer-by, and based on the gaze duration, determine the matching degree between the advertisement currently broadcasted by the advertising sign and the gaze duration of the passer-by, and determine the interest level of the passer-by in the advertising sign based on the sight range matching degree and the gaze duration matching degree, and determine the passer-by whose interest level value is greater than a threshold as the target object, and determine one or more target advertisements based on the group features of the target object; A second trajectory acquisition module is used to acquire the trajectory of the passerby in the target image, and the trajectory is used to characterize the relative position relationship between the displacement of the passerby and each advertising sign; The second target advertisement playing module is used to obtain the relative distance between each passerby and each other advertisement sign based on the movement trajectory; determine the distance weight based on the relative distance of each other advertisement sign, and the distance weight is used to characterize the possibility of the passerby seeing the corresponding other advertisement sign based on the corresponding movement trajectory, wherein the distance weight is the product of the basic space weight and the direction adjustment factor, the basic space weight is the inverse of the relative distance, and the direction adjustment factor characterizes the degree of match between the passerby's line of sight and the advertisement content through the cosine value of the angle between the passerby's moving direction and the advertisement sign direction; determine the playback order of one or more other advertisement signs based on the distance weight, and play one or more target advertisements on each other advertisement sign based on the playback order.

7. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as claimed in any one of claims 1 to 4.

8. A computer storage medium, characterized in that The computer storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.

Images