Remote control method and system for information playing of LED display screen

Abstract

The invention relates to a remote control method for information playing of an LED display screen, and the method improves the accuracy and effect of advertisement putting through intelligent analysis and optimization of a playing strategy, and comprises the steps: constructing a media playing database, generating an initial playing strategy, and analyzing audience feedback data to evaluate the attraction of media information. A media portrait is constructed to identify a target audience, historical audience flow data is recorded, future audience flow is predicted by using a machine self-learning algorithm, an optimized playing strategy is generated based on the predicted data and the media portrait, and remote intelligent control of the content of the LED display screen is realized. According to the method, the playing content can be dynamically adjusted to meet the requirements of different time periods and audience groups, so that the effective reach rate and the watching experience of the advertisement are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of LED information delivery, and in particular to a remote control method and system for LED display screen information playback. Background Art

[0002] LED displays are widely used in outdoor billboards, including street billboards, gas stations, community media, and building curtain walls, due to their high brightness and good weather resistance. These displays can attract the attention of a large number of pedestrians and vehicles and are an important medium for advertisers to promote their products.

[0003] Currently, LED screens are used for information dissemination, public announcements, and art exhibitions in public places, city centers, landmarks, and other places. Traditional LED screens generally use a preset loop playback sequence when playing information, and the preset loop playback sequence is difficult to adapt to the actual needs of the audience, resulting in a mismatch between content playback and the actual needs and preferences of the audience. This limits the attractiveness and audience stickiness of LED screens in advertising and information delivery, and reduces the effectiveness of LED screens in information playback. Summary of the invention

[0004] In order to improve the effectiveness of an LED display screen when playing information, the present application provides a remote control method and system for playing information on an LED display screen.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] A remote control method for playing information on an LED display screen, the method comprising the steps of:

[0007] Acquire media information data for LED display screen playback, and build an information playback database based on the media information data;

[0008] Acquire playback demand data, and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0009] Acquire audience viewing feedback data corresponding to each piece of media information, and generate an attractiveness level corresponding to each piece of media information according to the audience viewing feedback data;

[0010] Marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0011] Acquire historical audience flow data, and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0012] The preset traffic analysis model analyzes the audience traffic data set based on a machine self-learning algorithm to generate predicted audience traffic data;

[0013] An optimized playback strategy is generated based on the predicted audience flow data and the media portrait, and information playback on the LED display screen is remotely controlled according to the optimized playback strategy.

[0014] By adopting the above technical solution, media information is marked according to the audience viewing feedback data to help build a media portrait, so as to analyze which types of advertisements are more popular with specific audiences, analyze the audience flow pattern in a specific time period, and provide a basis for subsequent flow prediction and playback strategy optimization. Combined with the predicted audience flow data and media portraits, an optimized playback strategy is generated. The optimized playback strategy automatically adjusts the playback content of the LED display through the remote control system to improve the effective reach of the advertisement and the audience's participation, thereby improving the effectiveness of the LED display when playing information.

[0015] In a preferred example, the present application may be further configured as follows: in the step of obtaining audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data includes the dwell time, including the following steps:

[0016] Obtaining the dwell time of each viewer, where the dwell time is the time the viewer spends watching the LED display screen within the visual range of the LED display screen;

[0017] The dwell time is compared with a preset basic duration to calculate an initial first attraction degree, and the calculation formula of the initial first attraction degree is: P1=(T1 / T0)*100%, where P1 is the initial first attraction degree, T1 is the audience's dwell time, and T0 is the preset basic duration;

[0018] Obtaining the initial movement speed of the audience before watching and the viewing movement speed after watching, and calculating the speed correction factor;

[0019] The corrected first attraction degree is calculated based on the speed correction factor and the initial first attraction degree, and the calculation formula for the corrected first attraction degree is P2=P1*p; p=v1 / v2; wherein P2 is the corrected first attraction degree, v1 is the initial moving speed, v2 is the viewing moving speed, and p is the speed correction factor.

[0020] By adopting the above technical solution, by measuring the audience's dwell time, we can more accurately understand which advertising content is more likely to attract the audience's attention, thereby providing data support for advertising delivery, and introducing a speed correction factor to quantify the audience's interest in the advertising content, because the audience's interest may affect their movement speed, thereby achieving a quantitative evaluation of the advertising effect; according to the audience's dwell time and movement speed, adjust the order, frequency and duration of advertising playback to maximize the advertising effect, thereby optimizing the display strategy of advertising content, and by optimizing the advertising content and display strategy, improve the attractiveness of the advertisement and the audience's participation, thereby improving the return on investment of advertising delivery.

[0021] In a preferred example, the present application may be further configured as follows: in the step of obtaining the audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data also includes emotion change data, including the following steps:

[0022] The emotion change data is judged according to a preset emotion judgment standard to judge whether the audience's emotion is positive, negative or neutral;

[0023] The number of times the judgment result is positive is recorded, and the initial second attraction degree is calculated according to the emotion change data, and the initial second attraction degree is used to generate the attraction degree corresponding to each media information; the calculation formula of the initial second attraction degree is: E1=(N1 / N0)*100%, wherein E1 is the initial second attraction degree, N1 is the number of times the emotion change is positive, and N0 is the total number of all emotion change events.

[0024] By adopting the above technical solution, combined with the emotion recognition technology of facial expressions, the accuracy and reliability of emotion analysis are improved. By real-time monitoring and analysis of the audience's emotional changes, real-time emotional feedback is provided to advertisers, so that the advertising content can be adjusted instantly, and personalized advertising recommendations are provided according to the audience's emotional state, thereby improving the relevance and attractiveness of the advertisements.

[0025] In a preferred example, the present application can be further configured as follows: after recording the number of times the judgment result is positive and calculating the initial second attraction degree according to the emotion change data, the following steps are included:

[0026] The preset emotion intensity analysis model analyzes the emotion change data to generate emotion intensity data;

[0027] Analyzing the emotion intensity data based on a preset emotion intensity reference value to generate an emotion intensity correction factor;

[0028] The initial second attraction degree is modified based on the emotion intensity modification factor to generate a modified second attraction degree, and the modified second attraction degree is used to generate an attraction degree corresponding to each media information.

[0029] By adopting the above technical solution and introducing the emotion intensity correction factor, the evaluation of advertisement attractiveness becomes more detailed and precise, which helps to more accurately measure the attractiveness of advertisement content.

[0030] In a preferred example, the present application may be further configured as follows: in the step of obtaining the audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data also includes behavior data, including the following steps:

[0031] Analyze the specific behavior characteristics of the behavior data and mark the behavior, wherein the behavior characteristics include clapping, talking, and covering the face;

[0032] Classifying all the behavior markers and calculating the number of each behavior marker, and constructing a behavior database;

[0033] Analyzing the behavior database based on a machine self-learning algorithm to generate emotion intensity weights corresponding to different behavior markers;

[0034] The behavioral attraction degree is calculated based on the emotion intensity weight and the behavioral data, and the behavioral attraction degree is used to generate the attraction degree corresponding to each media information.

[0035] By adopting the above technical solution, the weight coefficient is adjusted according to the actual application scenario and data analysis results, and the emotional intensity weight makes it more realistic when conducting popularity analysis and more accurately measures the attractiveness of advertising content.

[0036] In a preferred example, the present application can be further configured as follows: in the step of generating an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely controlling the information playback of the LED display screen according to the optimized playback strategy, the steps are as follows:

[0037] Generating audience population data corresponding to different time periods based on the predicted audience flow data;

[0038] Matching the media information data corresponding to the media portrait based on the audience population data in different time periods to generate the media information playing frequency and switching order in different time periods;

[0039] Generate an optimized playback strategy based on the playback frequency and switching order of media information in different time periods.

[0040] By adopting the above technical solutions, combined with the predicted audience flow data and media portraits, an optimized playback strategy is generated so that the information content of the LED display meets the needs of the audience.

[0041] In a preferred example, the present application can be further configured as follows: after the step of generating an optimized playback strategy based on the playback frequency and switching order of media information in different time periods, the score of the optimized playback strategy is calculated, and the score formula is as follows: S=ω F *F+ω R *R+ω A *A;

[0042] Among them: S is the score of the optimized broadcast strategy; F is the predicted audience traffic data; R is the relevance of media information and audience population; A is audience feedback data, such as attractiveness; ω F ,ω R and ω A is the weight coefficient, which is used to adjust the relative importance of different factors in the optimization strategy.

[0043] By adopting the above technical solution, a score is assigned to each advertisement, and the frequency and order of advertisement playback are determined based on the score. For example, if an advertisement is highly correlated with predicted high-traffic time periods and is expected to receive positive audience feedback, it may receive a higher score and be prioritized in the playback strategy. This optimization method makes advertising playback more flexible and dynamic, and can be adjusted based on real-time data and predictive models, thereby improving the effectiveness of advertising and audience engagement.

[0044] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0045] A remote control device for information playback on an LED display screen, the device comprising: an information playback database construction unit, used to obtain media information data for LED display screen playback, and to construct an information playback database based on the media information data;

[0046] An initial playback strategy generating unit, used to obtain playback demand data, and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0047] An attraction level generating unit, used for acquiring audience viewing feedback data corresponding to each media information, and generating an attraction level corresponding to each media information according to the audience viewing feedback data;

[0048] A media portrait construction unit, used for marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0049] An audience flow data set construction unit is used to obtain historical audience flow data and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0050] A predicted audience flow data generating unit, configured to be pre-set with a flow analysis model to analyze the audience flow data set based on a machine self-learning algorithm to generate predicted audience flow data;

[0051] The optimized playback strategy generating unit is used to generate an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely control the information playback of the LED display screen according to the optimized playback strategy.

[0052] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0053] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the remote control method for playing information on an LED display screen are implemented.

[0054] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions:

[0055] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the remote control method for playing information on an LED display screen are implemented.

[0056] In summary, the present application includes at least one of the following beneficial technical effects:

[0057] 1. According to the audience viewing feedback data, media information is marked to help build media portraits, so as to analyze which types of advertisements are more popular with specific audience groups, analyze the audience flow pattern in a specific time period, and provide a basis for subsequent flow prediction and playback strategy optimization. Combined with the predicted audience flow data and media portraits, an optimized playback strategy is generated. The optimized playback strategy automatically adjusts the playback content of the LED display through the remote control system to improve the effective reach of the advertisement and the audience's participation, thereby improving the effectiveness of the LED display when playing information;

[0058] 2. By measuring the audience's dwell time, we can more accurately understand which advertising content is more likely to attract the audience's attention, thereby providing data support for advertising delivery, and introducing a speed correction factor to quantify the audience's interest in the advertising content, because the audience's interest may affect their movement speed, thereby achieving a quantitative evaluation of the advertising effect; according to the audience's dwell time and movement speed, adjust the order, frequency and duration of advertising playback to maximize the advertising effect, thereby optimizing the display strategy of advertising content. By optimizing advertising content and display strategy, the attractiveness of advertising and the audience's participation can be improved, thereby improving the return on investment of advertising delivery;

[0059] 3. Emotion recognition technology combined with facial expressions improves the accuracy and reliability of emotion analysis. By real-time monitoring and analyzing the emotional changes of viewers, it provides advertisers with real-time emotional feedback, allowing the advertising content to be adjusted instantly. It also provides personalized advertising recommendations based on the emotional state of the audience, improving the relevance and appeal of the advertising.

[0060] 4. Assign a score to each ad and determine the frequency and order of ad playback based on the score. For example, if an ad is highly relevant to predicted high-traffic time periods and is expected to receive positive viewer feedback, it may receive a higher score and be prioritized in the playback strategy. This optimization method makes ad playback more flexible and dynamic, and can be adjusted based on real-time data and predictive models, thereby improving advertising effectiveness and viewer engagement. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a remote control method for playing information on an LED display screen in one embodiment of the present application;

[0062] Figure 2 This is a principle block diagram of a remote control device for playing information on an LED display screen in one embodiment of the present application;

[0063] Figure 3 It is a schematic diagram of an electronic device in an embodiment of the present application.

[0064] Figure Number:

[0065] 1. Information playback database construction unit; 2. Initial playback strategy generation unit; 3. Attraction level generation unit; 4. Media portrait construction unit; 5. Audience flow data set construction unit; 6. Prediction of audience flow data generation unit; 7. Optimization playback strategy generation unit. DETAILED DESCRIPTION

[0066] The present application is further described in detail below in conjunction with the accompanying drawings.

[0067] In one embodiment, if Figure 1 As shown, the present application discloses a remote control method for playing information on an LED display screen, which specifically includes the following steps:

[0068] S10: Acquire media information data for LED display screen playback, and build an information playback database based on the media information data;

[0069] Specifically, in this embodiment, the media information data includes advertising content such as videos, images, and texts, which are obtained through cooperation with advertisers or downloaded through public advertising platforms. The media information data is classified and stored according to attributes such as format, resolution, and playback duration, and a unique identifier is assigned to each media file in the database. After the database is built, the media information can be effectively managed and retrieved to facilitate the subsequent generation of playback strategies.

[0070] S20: Acquire playback demand data, and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0071] Specifically, the broadcast demand data may include the demand for advertising in a specific time period, the advertising preferences of a specific audience group, etc. By analyzing this data, the system can generate an initial broadcast strategy. For example, if the demand data shows that there are more family viewers during the weekend, the system may arrange to broadcast advertising content suitable for family viewing.

[0072] S30: Obtaining audience viewing feedback data corresponding to each piece of media information, and generating an attractiveness level corresponding to each piece of media information according to the audience viewing feedback data;

[0073] Specifically, audience viewing feedback data is collected through cameras and sensors installed on the LED display. The feedback data includes the audience's stay time, emotional response when watching (such as smiles, surprised expressions), and audience interaction (such as using mobile phones to scan the QR code on the screen). By analyzing this data, the system evaluates the attractiveness of each media information and scores each advertising content.

[0074] S40: marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0075] Specifically, the system labels media information based on audience feedback data, such as "suitable for young women" and "attracting technology enthusiasts". These labels help build media portraits, thereby analyzing which types of advertisements are more popular with specific audiences.

[0076] S50: Acquire historical audience flow data, and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0077] Specifically, historical audience flow data is collected through monitoring systems in public places, and the data set records audience flow at different time periods every day according to the time axis. These data help analyze audience flow patterns in specific time periods and provide a basis for subsequent flow prediction and playback strategy optimization.

[0078] S60: The preset traffic analysis model analyzes the audience traffic data set based on a machine self-learning algorithm to generate predicted audience traffic data;

[0079] Specifically, the traffic analysis model uses machine learning algorithms, such as random forests or neural networks, to train historical audience traffic data to identify patterns and trends in traffic changes. The traffic analysis model can predict audience traffic in a specific time period in the future and provide scientific predictive data for advertising and information delivery.

[0080] S70: generating an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely controlling the information playback on the LED display screen according to the optimized playback strategy;

[0081] Specifically, an optimized playback strategy is generated by combining the predicted audience traffic data and media portraits. In an embodiment of the present application, when it is predicted that a large number of young audiences will pass by during peak hours, the system will choose to play advertising content targeting young groups. When a large number of families will travel during weekends, advertising content targeting family groups will be selected. The optimized playback strategy automatically adjusts the playback content of the LED display screen through the remote control system to increase the effective reach of the advertisement and the audience's participation.

[0082] In the step of S30: obtaining audience viewing feedback data corresponding to each media information, and generating the attractiveness corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data includes the stay time, emotion change data and behavior data, including the following steps:

[0083] S301: Acquire the stay time of each viewer, where the stay time is the time the viewer spends watching the LED display screen within the visible range of the LED display screen;

[0084] Specifically, in public places such as shopping malls or bus stations, LED screens are installed to display advertisements. Through cameras installed around the screens, the system automatically tracks and records the time each viewer stays in front of the screen. For example, a viewer stays in front of the screen and watches the content on the LED screen for 40 seconds.

[0085] S302: Compare the stay time with a preset basic duration to calculate an initial first attraction degree, the calculation formula of the initial first attraction degree is: P1=(T1 / T0)*100%, where P1 is the initial first attraction degree, T1 is the audience's stay time, and T0 is the preset basic duration;

[0086] Specifically, in the embodiment of the present application, the preset basic duration T0 is 30 seconds, which is used to define the audience's basic attention threshold for the advertising content. In other embodiments, the preset duration can be other, which is determined according to the actual content. If a viewer's stay time T1 is 40 seconds, according to the formula P1 = (T1 / T0) × 100% P1 = (T0T1) × 100%, the calculated initial first attraction level P1 = (40 / 30) × 100% ≈ 133.33%, and 133.33% exceeds the basic attention threshold, it is judged that the delivery information is more attractive to the audience.

[0087] S303: Obtaining the initial movement speed of the viewer before watching and the viewing movement speed after watching, and calculating the speed correction factor;

[0088] Before the audience watches the ad, the system captures their moving speed v1 as 1.0 m / s through the camera. After watching the ad, the audience's moving speed is reduced to v2, which is 0.5 m / s. The speed correction factor is calculated as p = v2 / v1 = 0.5 / 1.0 = 2, where p is the speed correction factor.

[0089] S304: Calculating a corrected first attraction degree based on the speed correction factor and the initial first attraction degree, the calculation formula of the corrected first attraction degree is P2=P1*p; p=v1 / v2; wherein P2 is the corrected first attraction degree, v1 is the initial moving speed, and v2 is the viewing moving speed;

[0090] Specifically, combining the speed correction factor and the initial first attraction level, the modified first attraction level P2 can be optimized as P2 = P1 × p = 133.33% × 2 = 266.67%. This modified attraction level reflects the actual slowdown of the audience due to the advertising content, thereby more accurately measuring the attractiveness of the advertising content.

[0091] For steps S301-S304, by measuring the audience's dwell time, we can more accurately understand which advertising content is more likely to attract the audience's attention, thereby providing data support for advertising delivery, and introducing a speed correction factor to quantify the audience's interest in the advertising content, because the audience's interest may affect their movement speed, thereby achieving a quantitative evaluation of the advertising effect; according to the audience's dwell time and movement speed, adjust the order, frequency and duration of advertising playback to maximize the advertising effect, thereby optimizing the display strategy of the advertising content, and by optimizing the advertising content and display strategy, improve the attractiveness of the advertisement and the audience's participation, thereby improving the return on investment of advertising delivery.

[0092] S305: judging the emotion change data according to a preset emotion judgment standard to determine whether the audience's emotion is positive, negative or neutral;

[0093] Specifically, when advertisements are displayed on large LED screens in public places, installed cameras acquire the facial features of the audience, and use emotion recognition software to identify and calculate changes in facial features, and judge emotions by analyzing the audience's facial expressions, for example, identifying expressions such as smiles and frowns, and classifying them as positive, negative, or neutral emotions.

[0094] S306: Record the number of times the judgment result is positive, and calculate the initial second attraction degree according to the emotion change data, the initial second attraction degree is used to generate the attraction degree corresponding to each media information; the calculation formula of the initial second attraction degree is: E1=(N1 / N0)*100%, where E1 is the initial second attraction degree, N1 is the number of times the emotion change is positive, and N0 is the total number of all emotion change events;

[0095] Specifically, in the embodiment of the present application, for example, during a day of advertising, 500 emotion change events were recorded when an advertisement was played. Among them, 350 were judged as positive emotions. According to the formula E1 = (N1 / N0)*100%, if N1 is the number of positive emotions 350, and N0 is the total number of emotion change events 500, then the initial second attraction degree E1 = (350 / 500) × 100% = 70%.

[0096] S307: Analyzing the emotion change data using a preset emotion intensity analysis model to generate emotion intensity data;

[0097] Specifically, the emotion intensity analysis model further analyzes the intensity of positive emotions. In the embodiment of the present application, the intensity of emotions is quantified by the width and duration of a smile, and an emotion intensity value is assigned to each positive emotion event.

[0098] S308: Analyze the emotion intensity data based on a preset emotion intensity reference value to generate an emotion intensity correction factor;

[0099] Specifically, a baseline value of emotion intensity is preset for comparing the actual emotion intensity value. If the intensity of most positive emotions is higher than the baseline value, the system may generate a correction factor greater than 1 to reflect a stronger audience response.

[0100] S309: modifying the initial second attraction degree based on the emotion intensity modification factor to generate a modified second attraction degree, wherein the modified second attraction degree is used to generate an attraction degree corresponding to each media information;

[0101] Specifically, assuming that the emotion intensity correction factor is 1.2, based on the emotion intensity correction factor and the initial second attraction degree, the corrected second attraction degree E2 is optimized to E2 = E1 × emotion intensity correction factor = 70% × 1.2 = 84%.

[0102] For steps S305-S309, emotion recognition technology combined with facial expressions improves the accuracy and reliability of emotion analysis. By real-time monitoring and analyzing the emotional changes of the audience, real-time emotional feedback is provided to advertisers, so that the advertising content can be adjusted instantly. Personalized advertising recommendations are provided based on the emotional state of the audience, which improves the relevance and attractiveness of the advertisements. The introduction of an emotion intensity correction factor makes the evaluation of the attractiveness of the advertisement more detailed and precise, which helps to more accurately measure the attractiveness of the advertising content.

[0103] S310: Analyze specific behavior characteristics of the behavior data and mark the behavior, wherein the behavior characteristics include clapping, talking, and covering the face;

[0104] Specifically, in this application, the behavior recognition software (this application uses the action recognition capability provided by the visual intelligence open platform) can identify and mark the specific behavior characteristics of the audience, such as clapping, talking, and covering the face. The software classifies and marks these behavior characteristics by analyzing the audience's body movements and facial expressions.

[0105] S311: Classifying all the behavior markers and calculating the number of each behavior marker, and constructing a behavior database;

[0106] Specifically, the identified behavioral features are classified and the number of each behavioral feature is calculated. For example, during a day of advertising, the system recorded 100 clapping, 150 conversations, and 80 face-covering behaviors. These data are used to build a behavioral database, in which each behavioral marker is associated with its number of occurrences.

[0107] S312: Analyze the behavior database based on a machine self-learning algorithm to generate emotion intensity weights corresponding to different behavior markers;

[0108] Specifically, the system uses a machine self-learning algorithm, which in the embodiment of the present application includes a support vector machine (SVM) and a stochastic gradient descent classifier (SGD) to analyze the behavior database and generate an emotional intensity weight for each behavior marker. These weights reflect the contribution of each behavior to the attractiveness of the advertisement. For example, if applause is usually associated with high emotional intensity, the system may assign a higher weight to the applause behavior, such as 2.0; while covering the face may be associated with low emotional intensity and may be assigned a lower weight, such as 0.5.

[0109] It should be further explained that the weight calculation formula includes entropy method, factor analysis method and CRITIC weight method. The optimized weight calculation method helps to improve the accuracy and objectivity of advertising effectiveness evaluation.

[0110] S313: Calculating a behavior attraction degree based on the emotion intensity weight and the behavior data, wherein the behavior attraction degree is used to generate an attraction degree corresponding to each media information;

[0111] Specifically, the degree of attraction of each behavior is calculated by combining the emotion intensity weight and behavior data. For example, if the weight of applause is 2, the weight of conversation is 1.5, and the weight of covering the face is 1, then the degree of attraction of each behavior can be calculated by the following formula: Behavior attraction degree = (number of applause times × applause weight) + (number of conversations × conversation weight) + (number of face covering times × face covering weight). Assuming that during the broadcast of a certain advertisement, the number of applause times is 100, the number of conversations is 150, and the number of face covering times is 80, then the behavior attraction degree is: Behavior attraction degree = (100×2)+(150×1.5)+(80×1).

[0112] To calculate the overall attraction, we can combine the modified first attraction (P2), the modified second attraction (E2), and the behavioral attraction (B). The overall attraction (A) can be calculated using the following formula:

[0113] A=α*P2+β*E2+γ*B; where: A is the overall attraction level, P2 is the modified first attraction level, calculated based on the audience's residence time and movement speed; E2 is the modified second attraction level, calculated based on the audience's emotional change data; B is the behavioral attraction level, calculated based on the audience's specific behavioral characteristics; α, β and γ are corresponding weight coefficients, which are used to adjust the relative importance of different attraction levels in the overall evaluation.

[0114] These weight coefficients can be adjusted according to the actual application scenario and data analysis results. For example, if behavioral data is considered more important for the evaluation of advertising attractiveness, a higher value of γ can be given.

[0115] In the step of S70: generating an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely controlling the information playback of the LED display screen according to the optimized playback strategy, the following steps are included:

[0116] S701: generating audience population data corresponding to different time periods based on the predicted audience flow data;

[0117] Specifically, by analyzing historical audience traffic data, the system predicts the number of viewers at different time periods every day in the next week. For example, the system predicts that there will be 1,000 viewers during the morning peak (7:00-9:00) and 2,000 viewers during the afternoon (17:00-19:00). These data will be used to formulate subsequent broadcast strategies.

[0118] S702: Matching the media information data corresponding to the media portrait based on the audience group data in different time periods to generate the media information playing frequency and switching order in different time periods;

[0119] Specifically, based on the audience data during the morning rush hour, the system analyzed the media portrait and found that the audience during this time period was mainly commuters. Therefore, the system matched media information related to office workers, such as coffee brand ads and transportation ads. The system also determined the frequency of these ads, such as once every 5 minutes, and the switching order to ensure the diversity and attractiveness of the advertising content.

[0120] S703: Generate an optimized playback strategy based on the playback frequency and switching order of media information in different time periods;

[0121] Specifically, the system generates an optimized broadcast strategy by combining predicted audience flow data and media portraits. For example, during the morning rush hour, the system arranges a high frequency of coffee brand ads and transportation ads, while in the afternoon, considering the increase in audience flow and possible family audiences, the system arranges the broadcast of household goods ads and leisure activities ads.

[0122] It should be noted that in order to further optimize the playback strategy, an optimization formula is introduced, which combines the audience flow prediction (F), the relevance of media information (R) and the audience feedback (U):

[0123] S=ω F *F+ω R *R+ω A *A;

[0124] Among them: S is the score of the optimized broadcast strategy; F is the predicted audience traffic data; R is the relevance of media information and audience population; A is audience feedback data, such as attractiveness; ω F ,ω R and ω A is the weight coefficient, which is used to adjust the relative importance of different factors in the optimization strategy.

[0125] Through this formula, a score is assigned to each ad, and the frequency and order of ad playback are determined based on the score. For example, if an ad is highly relevant to predicted high-traffic time periods and is expected to receive positive viewer feedback, it may receive a higher score and be prioritized in the playback strategy. This optimization method makes ad playback more flexible and dynamic, and can be adjusted based on real-time data and predictive models, thereby improving advertising effectiveness and audience engagement.

[0126] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0127] In one embodiment, a remote control device for playing information on an LED display screen is provided, and the remote control device for playing information on an LED display screen corresponds one-to-one with the remote control method for playing information on an LED display screen in the above embodiment. Figure 2 As shown, the remote control device for playing information on an LED display screen includes:

[0128] An information playing database building unit 1 is used to obtain media information data for playing on the LED display screen, and build an information playing database based on the media information data;

[0129] An initial playback strategy generating unit 2 is used to obtain playback demand data and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0130] The attraction level generating unit 3 is used to obtain the audience viewing feedback data corresponding to each media information, and generate the attraction level corresponding to each media information according to the audience viewing feedback data;

[0131] A media portrait construction unit 4 is used to mark the media information data based on the audience viewing feedback data to construct a media portrait, and the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0132] The audience flow data set construction unit 5 is used to obtain historical audience flow data and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0133] A predicted audience flow data generating unit 6, which is configured to be pre-set with a flow analysis model to analyze the audience flow data set based on a machine self-learning algorithm to generate predicted audience flow data;

[0134] The optimized playback strategy generating unit 7 is used to generate an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely control the information playback of the LED display screen according to the optimized playback strategy.

[0135] The specific definition of the remote control device for playing information on the LED display screen can be found in the definition of the remote control method for playing information on the LED display screen mentioned above, which will not be repeated here. Each module in the above remote control device for playing information on the LED display screen can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory in the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0136] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a database. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a remote control method for playing information on an LED display screen is implemented.

[0137] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0138] Acquire media information data for LED display screen playback, and build an information playback database based on the media information data;

[0139] Acquire playback demand data, and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0140] Acquire audience viewing feedback data corresponding to each piece of media information, and generate an attractiveness level corresponding to each piece of media information according to the audience viewing feedback data;

[0141] Marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0142] Acquire historical audience flow data, and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0143] The preset traffic analysis model analyzes the audience traffic data set based on a machine self-learning algorithm to generate predicted audience traffic data;

[0144] An optimized playback strategy is generated based on the predicted audience flow data and the media portrait, and information playback on the LED display screen is remotely controlled according to the optimized playback strategy.

[0145] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0146] Acquire media information data for LED display screen playback, and build an information playback database based on the media information data;

[0147] Acquire playback demand data, and generate an initial playback strategy according to the playback demand data based on a preset demand analysis logic;

[0148] Acquire audience viewing feedback data corresponding to each piece of media information, and generate an attractiveness level corresponding to each piece of media information according to the audience viewing feedback data;

[0149] Marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data;

[0150] Acquire historical audience flow data, and record the historical audience flow data based on a preset public time axis to construct an audience flow data set;

[0151] The preset traffic analysis model analyzes the audience traffic data set based on a machine self-learning algorithm to generate predicted audience traffic data;

[0152] An optimized playback strategy is generated based on the predicted audience flow data and the media portrait, and information playback on the LED display screen is remotely controlled according to the optimized playback strategy.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0154] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0155] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A remote control method for LED display screen information playback, characterized in that: The method comprises the steps of: acquiring media information data for playing on the LED display screen, and constructing an information playing database based on the media information data; Acquire playback demand data, and generate an initial playback strategy based on the playback demand data based on a preset demand analysis logic; Acquire audience viewing feedback data corresponding to each piece of media information, and generate an attractiveness level corresponding to each piece of media information according to the audience viewing feedback data; Marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data; Acquire historical audience flow data, and record the historical audience flow data based on a preset public time axis to construct an audience flow data set; The preset traffic analysis model analyzes the audience traffic data set based on a machine self-learning algorithm to generate predicted audience traffic data; An optimized playback strategy is generated based on the predicted audience flow data and the media portrait, and information playback on the LED display screen is remotely controlled according to the optimized playback strategy.

2. A remote control method for LED display screen information playback according to claim 1, characterized in that: In the step of obtaining audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data includes the dwell time, including the following steps: Obtaining the dwell time of each viewer, where the dwell time is the time the viewer spends watching the LED display screen within the visual range of the LED display screen; The dwell time is compared with a preset basic duration to calculate an initial first attraction degree, and the calculation formula of the initial first attraction degree is: P1=(T1 / T0)*100%, where P1 is the initial first attraction degree, T1 is the audience's dwell time, and T0 is the preset basic duration; Obtaining the initial movement speed of the audience before watching and the viewing movement speed after watching, and calculating the speed correction factor; The modified first attraction degree is calculated based on the speed correction factor and the initial first attraction degree, and the calculation formula of the modified first attraction degree is: ; v1 / v2; wherein P2 is the modified first attraction degree, v1 is the initial moving speed, v2 is the viewing moving speed, and p is the speed correction factor.

3. A remote control method for LED display screen information playback according to claim 2, characterized in that: In the step of obtaining audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data also includes emotion change data, including the following steps: The emotion change data is judged according to a preset emotion judgment standard to judge whether the audience's emotion is positive, negative or neutral; Recording the number of times the judgment result is positive, and calculating the initial second attraction degree according to the emotion change data, wherein the initial second attraction degree is used to generate the attraction degree corresponding to each media information; The calculation formula of the initial second attraction degree is: E1=(N1 / N0)*100%, wherein E1 is the initial second attraction degree, N1 is the number of times the emotion changes to be positive, and N0 is the total number of all emotion change events.

4. A remote control method for LED display screen information playback according to claim 3, characterized in that: After recording the number of times the judgment result is positive and calculating the initial second attraction degree according to the emotion change data, the following steps are included: The preset emotion intensity analysis model analyzes the emotion change data to generate emotion intensity data; Analyzing the emotion intensity data based on a preset emotion intensity reference value to generate an emotion intensity correction factor; The initial second attraction degree is modified based on the emotion intensity modification factor to generate a modified second attraction degree, and the modified second attraction degree is used to generate an attraction degree corresponding to each media information.

5. A remote control method for LED display screen information playback according to claim 1, characterized in that: In the step of obtaining audience viewing feedback data corresponding to each media information and generating the attractiveness level corresponding to each media information according to the audience viewing feedback data, the audience viewing feedback data also includes behavior data, including the following steps: Analyze the specific behavior characteristics of the behavior data and mark the behavior, wherein the behavior characteristics include clapping, talking, and covering the face; Classifying all the behavior markers and calculating the number of each behavior marker, and constructing a behavior database; Analyzing the behavior database based on a machine self-learning algorithm to generate emotion intensity weights corresponding to different behavior markers; The behavioral attraction degree is calculated based on the emotion intensity weight and the behavioral data, and the behavioral attraction degree is used to generate the attraction degree corresponding to each media information.

6. A remote control method for LED display screen information playback according to claim 1, characterized in that: In the step of generating an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely controlling the information playback of the LED display screen according to the optimized playback strategy, the following steps are included: Generating audience population data corresponding to different time periods based on the predicted audience flow data; Matching the media information data corresponding to the media portrait based on the audience population data in different time periods to generate the media information playing frequency and switching order in different time periods; Generate an optimized playback strategy based on the playback frequency and switching order of media information in different time periods.

7. A remote control method for LED display screen information playback according to claim 6, characterized in that: After the step of generating an optimized playback strategy based on the playback frequency and switching order of media information in different time periods, the score of the optimized playback strategy is calculated. The score formula is as follows: S = *F+ R+ *A; Among them: S is the score of the optimized broadcast strategy; F is the predicted audience traffic data; R is the relevance of media information to the audience population; A is audience feedback data, such as the degree of attraction; , and is the weight coefficient, which is used to adjust the relative importance of different factors in the optimization strategy.

8. A remote control device for playing information on an LED display screen, applied to a remote control method for playing information on an LED display screen as claimed in any one of claims 1 to 7, characterized in that: The device comprises: an information playing database construction unit (1), which is used to obtain media information data for playing on the LED display screen, and to construct an information playing database based on the media information data; An initial playback test strategy generating unit (2) is used to obtain playback demand data and generate an initial playback test strategy according to the playback demand data based on a preset demand analysis logic; An attraction level generating unit (3) is used to obtain audience viewing feedback data corresponding to each piece of media information, and generate an attraction level corresponding to each piece of media information according to the audience viewing feedback data; A media portrait construction unit (4), used for marking the media information data based on the audience viewing feedback data to construct a media portrait, wherein the media portrait is used to analyze the preferred audience corresponding to the media information data; An audience flow data set construction unit (5) is used to obtain historical audience flow data and record the historical audience flow data based on a preset common time axis to construct an audience flow data set; A predicted audience flow data generating unit (6), which is configured to be pre-set with a flow analysis model to analyze the audience flow data set based on a machine self-learning algorithm to generate predicted audience flow data; An optimized playback strategy generating unit (7) is used to generate an optimized playback strategy based on the predicted audience flow data and the media portrait, and remotely control the information playback of the LED display screen according to the optimized playback strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a remote control method for LED display screen information playback as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of a remote control method for LED display screen information playback as described in any one of claims 1 to 7 are implemented.

Images