A video carousel control system for IPTV

Abstract

The present invention relates to the technical field of video carousel control, and in particular to a video carousel control system applied to IPTV, comprising a range delimitation analysis module, a primary carousel control module, a bias analysis module, a secondary carousel control module and a carousel display analysis module; the present invention identifies a user face image within a monitoring range, extracts face features and inputs them into an age prediction model to obtain the user age, generates primary video carousel content according to the age and a preset age range matching, and when the user browses the primary video carousel content for a time period exceeding a set threshold, analyzes the user bias information, determines the target main theme, content category and region as key conditions for screening programs, generates secondary video carousel content, and then analyzes the carousel display parameters of the current monitoring time point of the display terminal to obtain the carousel display parameters, thereby realizing intelligent control and personalized recommendation of video carousel content, and greatly improving the user viewing experience and satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of video carousel control, in particular to a video carousel control system applied to IPTV. Background Art

[0002] With the rapid development of information technology and multimedia technology, Internet Protocol Television (IPTV), as an emerging digital television service, is gradually becoming an important form of entertainment in modern families. The carousel function provides users with a simple video on demand experience similar to forward and backward by playing the same set of programs in multiple channels at a certain time interval, and the interface design is continuously optimized with the evolution of technology. However, the current IPTV carousel system has obvious shortcomings in the following two aspects: On the one hand, the content of existing video carousel interfaces is usually designed based on fixed templates and lacks a dynamic adjustment mechanism, making it difficult to make personalized recommendations based on the user's real-time situation. This inflexible design cannot fully adapt to the diverse changes in user needs, resulting in a relatively simple user experience and an inability to provide carousel content that better suits the user's interests. On the other hand, the display settings of existing video carousel interfaces usually adopt fixed parameters and fail to make dynamic adjustments based on the user's actual viewing status. This static display mode may affect the user's visual comfort and even cause visual fatigue after long-term viewing, thereby reducing the user's overall viewing experience.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] The present invention is used to solve the problem that the existing IPTV carousel interface content and display settings are fixed and single and cannot be dynamically adjusted according to the real-time needs and viewing status of users, and proposes a video carousel control system applied to IPTV.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A video carousel control system applied to IPTV, comprising: A scope demarcation and analysis module is used to perform monitoring scope demarcation and analysis based on the semicircular area of ​​the IPTV display terminal to obtain a monitoring scope; The first video carousel control module is used to identify the face image of the user within the monitoring range, extract the face features from the face image and input them into the age prediction model to obtain the user's age, match the age with the set age range, and generate the user's first video carousel content; The bias analysis module is used to obtain and analyze the user's bias information set to obtain the bias value of each topic, the bias value of each content category, and the bias value of each region; The re-carousel control module is used to monitor the duration of the user browsing the initial video carousel content on the IPTV display terminal interface. If the duration is greater than the set duration threshold, a re-carousel control analysis is performed to determine the target main theme, target main content category and target main region as screening conditions to generate the user's re-carousel video content; The carousel display analysis module is used to monitor the user's glasses wearing status at the current monitoring time point, thereby analyzing the carousel display parameters of the IPTV display terminal at the current monitoring time point to obtain the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point.

[0006] Furthermore, the monitoring scope is defined and the specific analysis process is as follows: With the center point of the IPTV display terminal as the center Q1, a semicircle is drawn with a radius R to obtain a semicircular area; Set each IPTV display terminal to correspond to an identification angle, take the midpoints Q2 and Q3 of the left and right ends of the IPTV display terminal as the starting point, and draw a ray respectively. These two rays intersect the arc edges of the semicircle at points Q2′ and Q3′ to obtain line segments Q2Q2′ and Q3Q3′, thereby obtaining the monitoring range of the shaded part Q3-Q3′-Q1′-Q2′-Q2-Q1-Q3, that is, starting from Q1, the area between the two boundary rays and the semicircular arc segment is the monitoring range.

[0007] Furthermore, the specific analysis process of selecting the user's first video carousel content is as follows: According to the age range to which the user belongs, the playback volume of each program in a unit time period within the range is counted, and the programs are sorted from high to low according to the playback volume to generate a playback volume list, and the top T programs in the playback volume list are selected as the user's initial video carousel content.

[0008] Furthermore, the user's preference information set is obtained and analyzed. The specific analysis process is as follows: The number of views, viewing time, number of favorites, and number of recharges for each theme of the program watched by the user are marked as Zviews t , Zduras t 、Zcolle t and Zcharg t , t represents the number of each topic, according to the formula: , get the bias value ZTP of each topic t , where Zviews θ t , Zduras θ t 、Zcolle θ t and Zchargθ t They are respectively represented as the reference viewing times, reference viewing time, reference collection times, and reference recharge times of each topic, and b1, b2, b3, and b4 are respectively represented as the set weight coefficients; Similarly, the bias values ​​of each content category and each region are analyzed and recorded as NRP r and DYP y , where r represents the number of each content category and y represents the number of each region.

[0009] Furthermore, determine the target main theme. The specific analysis process is as follows: Get the bias value ZTP of each topic during the historical monitoring period t , set the conversion factor of the bias value of each topic to Z t , according to the formula: , and obtain the conversion bias value δ1 of each topic t , u is a natural constant; Among them, the conversion factor of the bias value of each topic indicates that the bias value of each topic can be converted into the conversion bias value of each topic; Get the bias value of each topic in the current monitoring period, marked as ZTP t* ; According to the formula: , get the comprehensive bias value SZ of each topic t ; The comprehensive bias value of each topic is compared and analyzed with the preset topic bias threshold. When the comprehensive bias value of a topic is greater than or equal to the preset topic bias threshold, the topic is determined to be the target main promotion topic.

[0010] Furthermore, the target promotion content category is determined. The specific analysis process is as follows: Get the bias value NRP of each content category during the historical monitoring period r , set the conversion factor of the bias value of each content category to N r , according to the formula: , and obtain the conversion bias value δ2 of each content category r ; The conversion factor of the bias value of each content category indicates that the bias value of each content category can be converted into a conversion bias value of each content category; Get the bias value of each content category in the current monitoring period, marked as NRP r* ; According to the formula: , get the comprehensive bias value SN of each content category r ; The comprehensive bias value of each content category is compared and analyzed with the preset content category bias threshold. When the comprehensive bias value of a content category is greater than or equal to the preset content category bias threshold, the content category is determined to be the target main content category.

[0011] Furthermore, we determine the target promotion area. The specific analysis process is as follows: Get the bias value DYP of each region during the historical monitoring period y , set the conversion factor of the bias value of each region to D y , according to the formula: , and obtain the conversion bias value δ3 of each region y ; Among them, the conversion factor of the bias value of each region indicates that the bias value of each region can be converted into the conversion bias value of each region; Get the deviation value of each region in the current monitoring period, marked as DYP y* ; According to the formula: , get the comprehensive bias value SD of each region y ; The comprehensive bias value of each region is compared and analyzed with the preset regional bias threshold. When the comprehensive bias value of a region is greater than or equal to the preset regional bias threshold, the region is determined to be the target main promotion region.

[0012] Furthermore, the carousel display parameters are analyzed, and the specific analysis process is as follows: By collecting the eye image of the user at the current monitoring time point and matching it with the eye images of various glasses wearing states, the glasses wearing state of the user at the current monitoring time point is obtained, and the glasses wearing state includes the wearing state and the not wearing state; The distance of the user at the current monitoring time point is recorded as JL, and the corresponding myopia degree of the user is extracted from the system repository; If the user's glasses wearing state at the current monitoring time point is in the wearing state, the user's corresponding myopia degree is matched with the reference distance corresponding to each myopia degree of the glasses, and the reference distance corresponding to the user's glasses is obtained, which is recorded as JP * ; According to the formula: , get the display impact ratio value Y of the wearing status at the current monitoring time point 佩戴 , where e represents the natural constant, and ΔJP represents the allowable distance difference corresponding to the set wearing glasses; Match the display impact ratio value of the wearing state at the current monitoring time point with the display impact ratio threshold value of each display impact level corresponding to the set wearing state, obtain the display impact level of the wearing state at the current monitoring time point, and match it with the carousel display parameters of each display impact level corresponding to the set wearing state, obtain the carousel display parameters of the wearing state at the current monitoring time point, and use them as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point; If the user is not wearing glasses at the current monitoring time point, the user's corresponding myopia degree is matched with the set reference distances for each myopia degree when not wearing glasses to obtain the user's reference distance when not wearing glasses, which is recorded as JW * ; According to the formula: , get the display impact ratio value Y of the non-wearing state at the current monitoring time point 未戴 , where ΔJW represents the allowable distance difference corresponding to not wearing glasses; The display impact ratio value of the not-wearing state at the current monitoring time point is matched with the display impact ratio threshold value of each display impact level corresponding to the not-wearing state, and the display impact level of the not-wearing state at the current monitoring time point is obtained, and it is matched with the carousel display parameters of each display impact level corresponding to the set not-wearing state to obtain the carousel display parameters of the not-wearing state at the current monitoring time point, which are used as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point.

[0013] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: 1. The present invention generates the user's first video carousel content by accurately identifying the user within the monitoring range and matching the program with the current high playback volume according to the age range to which the user belongs. At the same time, the duration of the user browsing the first video carousel content on the IPTV display terminal is monitored. If the duration exceeds a preset threshold, it is considered that the first content fails to fully attract the user's interest. On this basis, the user's preferences are deeply explored, and the bias values ​​of various topics, content categories and regions in the user's historical monitoring period are analyzed, and the bias values ​​are converted in combination with conversion factors to obtain conversion bias values. The bias values ​​in the current monitoring period are captured in real time, and are comprehensively analyzed with the conversion bias values ​​to generate a comprehensive bias value. The comprehensive bias value integrates the user's historical preferences and the latest interest dynamics, and can intelligently identify the target main theme, content category and region as the key condition for screening programs, and screen qualified programs from the program library to generate the user's second video carousel content, thereby realizing content personalization and accurate push, which not only significantly improves the user's viewing experience, but also enhances the attractiveness and competitiveness of IPTV services.

[0014] 2. By analyzing the user's glasses wearing status, myopia degree and the distance between the user and the display terminal, intelligent display control of the carousel content of the IPTV display terminal is achieved, ensuring that users can get the best viewing experience in different glasses wearing states. This not only improves the user's viewing comfort, but also helps to reduce viewing obstacles caused by vision problems, further enhancing the practicality and attractiveness of IPTV services. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 It is the overall module block diagram of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, a video carousel control system applied to IPTV includes: a range demarcation analysis module, a primary carousel control module, a bias analysis module, a secondary carousel control module and a carousel display analysis module; The scope demarcation analysis module is used to draw a semicircle with a radius R and the center point of the IPTV display terminal as the center Q1 to obtain a semicircular area, and perform monitoring scope demarcation analysis based on the semicircular area. The specific analysis process is as follows: Set each IPTV display terminal to correspond to an identification angle, and record it as ∠1. Take the midpoints Q2 and Q3 of the left and right ends of the IPTV display terminal as the starting point, and make a ray respectively. These two rays intersect with the arc edge of the semicircle at points Q2′ and Q3′ to obtain line segments Q2Q2′ and Q3Q3′, respectively. The angles between line segments Q2Q2′ and Q3Q3′ and the radii of the two sides are ∠1, thereby obtaining the monitoring range of the shaded part Q3-Q3′-Q1′-Q2′-Q2-Q1-Q3, that is, starting from Q1, the area between the two boundary rays and the semicircular arc segment is the monitoring range; It should be noted that the center Q1 is the geometric center of the IPTV display terminal (the midpoint of the line connecting the midpoints of the left and right ends), and the radius R is a ray extending outward from the center Q1. Its length depends on the scene setting. For example, the effective distance range of the IPTV display terminal. The semicircular area usually faces the front of the IPTV display terminal (consistent with the normal direction of the screen), covering the space area when the user is standing or sitting to watch; The initial carousel control module is used to identify the face image of the user within the monitoring range, extract the face features from the face image and input them into the age prediction model (such as a model built based on CNN or PyTorch), obtain the user's age, and match the user's age with the set age range, and each age range corresponds to a specific video carousel content, thereby obtaining the user's initial video carousel content; The process of selecting the content for the initial video carousel is as follows: According to the age range of the user, the number of plays of each program in a unit time period within the age range is counted, and the programs are sorted from high to low according to the number of plays to generate a play list, and the top T programs in the play list are selected as the user's first video rotation content; It should be noted that when multiple users are identified within the monitoring range, the deviation angle PC1, viewing distance PC2 and historical viewing times PC3 of each user are obtained according to the formula: , get the recognition value PCZ, a1, a2 and a3 represent the set weight coefficients respectively, and take the user corresponding to the maximum recognition value as the recognized user, where the deviation angle refers to the angle between the user's face direction and the central axis of the IPTV display terminal screen, the viewing distance refers to the distance between the user and the IPTV display terminal, and the historical viewing number refers to the cumulative number of times the user has used the IPTV display terminal to watch programs in the past period of time; In a specific embodiment, the present invention accurately identifies users within the monitoring range and matches programs with a high current playback volume as the user's first video carousel content according to the user's age range. This method not only improves the relevance of recommended content to user interests and user satisfaction, but also greatly enhances the intelligence level and personalized experience of IPTV services. The bias analysis module is used to obtain and analyze the user's bias information set. The specific process of obtaining and analyzing is as follows: Statistics are collected on the number of times, viewing time, favorites, and top-ups of programs watched by users for each theme, and statistics are collected on the number of times, viewing time, favorites, and top-ups of programs watched by users for each content category, and the number of times, viewing time, favorites, and top-ups of programs watched by users for each region, thereby forming a user preference information set; It should be noted that the theme refers to movies, variety shows, animations, documentaries, sports, etc., and the content category refers to action, suspense, comedy, etc.; The number of views, viewing time, number of favorites, and number of recharges for each theme of the program watched by the user are marked as Zviews t , Zduras t 、Zcolle t and Zcharg t , t represents the number of each topic, according to the formula: , get the bias value ZTP of each topic t , where Zviews θ t , Zduras θ t 、Zcolle θ t and Zcharg θ t They are respectively represented as the reference viewing times, reference viewing time, reference collection times, and reference recharge times of each topic, and b1, b2, b3, and b4 are respectively represented as the set weight coefficients; The number of views, viewing time, number of favorites, and number of top-ups for each content category of the program watched by the user are marked as Nviews r , Nduras r 、Ncolle r and Ncharg r , r represents the number of each content category, according to the formula: , get the bias value NRP of each content category r , where Nviews θ r , Nduras θ r 、Ncolle θ r and Ncharg θ r They are respectively represented as the reference viewing times, reference viewing duration, reference collection times, and reference recharge times of each content category, and b5, b6, b7, and b8 are respectively represented as the set weight coefficients; The number of views, viewing time, number of favorites, and number of recharges corresponding to the user's viewing of the program in each region are marked as Dviews y , Dduras y 、Dcolle y and Dcharg y , y represents the number of each region, according to the formula: , get the bias value DYP of each regiony , where Dviews θ y , Dduras θ y 、Dcolle θ y and Dcharg θ y They are respectively represented by the reference viewing times, reference viewing duration, reference collection times, and reference recharge times of each region, and b9, b10, b11, and b12 are respectively represented by the set weight coefficients; The re-carousel control module is used to monitor the time that the user browses the initial video carousel content on the IPTV display terminal interface, and compares and analyzes the time of browsing the initial video carousel content with the set time threshold. If the time of browsing the initial video carousel content is longer than the set time threshold, a re-carousel control analysis is performed. The specific analysis process is as follows: Get the bias value ZTP of each topic during the historical monitoring period t , the bias value NRP of each content category r And the bias value DYP of each region y , set the conversion factor of the bias value of each topic to Z t , set the conversion factor of the bias value of each content category to N r , set the conversion factor of the bias value of each region to D y , according to the formula: , and obtain the conversion bias value δ1 of each topic respectively t , the conversion bias value of each content category δ2 r and the conversion bias value δ3 for each region y , u is a natural constant; Among them, the conversion factor of the bias value of each topic means that the bias value of each topic can be converted into the conversion bias value of each topic, the conversion factor of the bias value of each content category means that the bias value of each content category can be converted into the conversion bias value of each content category, and the conversion factor of the bias value of each region means that the bias value of each region can be converted into the conversion bias value of each region. The specific setting of the conversion factor is reasonably set by those skilled in the art according to actual conditions; Get the bias value of each topic, each content category, and each region in the current monitoring period, and mark them as ZTP t* 、NRP r* and DYP y* , according to the formula: , and obtain the comprehensive bias value SZ of each topic t , the comprehensive bias value SN of each content category r and the comprehensive bias value SD of each region y; Compare and analyze the comprehensive bias value of each topic with the preset topic bias threshold. When the comprehensive bias value of a topic is greater than or equal to the preset topic bias threshold, the topic is determined to be the target main promotion topic. Otherwise, the topic is determined to be a non-promotion topic. Compare and analyze the comprehensive bias value of each content category with the preset content category bias threshold. When the comprehensive bias value of a content category is greater than or equal to the preset content category bias threshold, the content category is determined as the target main promotion content category. Otherwise, the content category is determined as the non-promotion content category. Compare and analyze the comprehensive bias value of each region with the preset regional bias threshold. When the comprehensive bias value of a region is greater than or equal to the preset regional bias threshold, the region is determined as the target main promotion region. Otherwise, the region is determined as a non-promotion region. Using the target main promotion theme, target main promotion content category and target main promotion region as screening conditions, screen out programs that meet these conditions from the program library, and synthesize these programs into the user's video carousel content; In a specific embodiment, the present invention monitors the duration of the user's first browsing of the video carousel content on the IPTV display terminal. If the duration exceeds a preset duration threshold, it is considered that the first video carousel content fails to fully attract the user's interest. On this basis, the user's preferences are further explored by obtaining the bias values ​​of the user for each theme, content category and region in the historical monitoring period, and converting these bias values ​​according to the conversion factor to obtain the conversion bias value. Subsequently, the user's bias values ​​for each theme, content category and region in the current monitoring period are captured in real time, and a comprehensive analysis is performed with the previously obtained conversion bias value to obtain a comprehensive bias value. These comprehensive bias values ​​not only integrate the user's historical preferences, but also take into account their latest interest dynamics. Based on these comprehensive bias values, the target main push theme, content category and region are intelligently identified, thereby forming the key conditions for screening programs, and programs that meet these conditions are screened from the program library, and these programs are synthesized into the user's second video carousel content, thereby realizing personalized customization of content and precise push control, which can not only significantly improve the user's viewing experience, but also help to enhance the attractiveness and competitiveness of IPTV services. The carousel display analysis module is used to monitor the glasses wearing state of the user corresponding to the IPTV display terminal at the current monitoring time point, thereby analyzing the carousel display parameters of the IPTV display terminal at the current monitoring time point. The specific analysis process is as follows: The user's eye image at the current monitoring time point is collected by the smart camera on the IPTV display terminal, and matched with the eye images of various glasses wearing states, to obtain the user's glasses wearing state at the current monitoring time point; It should be noted that the glasses wearing state includes a wearing state and a not wearing state, wherein the glasses are plain glasses; The distance of the user at the current monitoring time point (the actual distance between the user and the IPTV display terminal) is recorded as JL, and the corresponding myopia degree of the user is extracted from the system repository; It should be noted that the myopia degree corresponding to the user is specifically the average degree of myopia of the user's two eyes; If the user's glasses wearing state at the current monitoring time point is in the wearing state, the user's corresponding myopia degree is matched with the reference distance corresponding to each myopia degree of the glasses, and the reference distance corresponding to the user's glasses is obtained, which is recorded as JP * ; According to the formula: , get the display impact ratio value Y of the wearing status at the current monitoring time point 佩戴 , where e represents the natural constant, and ΔJP represents the allowable distance difference corresponding to the set wearing glasses; Match the display impact ratio value of the wearing state at the current monitoring time point with the display impact ratio threshold value of each display impact level corresponding to the set wearing state, obtain the display impact level of the wearing state at the current monitoring time point, and match it with the carousel display parameters of each display impact level corresponding to the set wearing state, obtain the carousel display parameters of the wearing state at the current monitoring time point, and use them as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point; Among them, the carousel display parameters include but are not limited to display brightness, font size, video screen display area, and playback speed; If the user is not wearing glasses at the current monitoring time point, the user's corresponding myopia degree is matched with the set reference distances for each myopia degree when not wearing glasses to obtain the user's reference distance when not wearing glasses, which is recorded as JW * ; According to the formula: , get the display impact ratio value Y of the non-wearing state at the current monitoring time point 未戴 , where ΔJW represents the allowable distance difference corresponding to not wearing glasses; Match the display impact ratio value of the non-wearing state at the current monitoring time point with the set display impact ratio threshold value of each display impact level corresponding to the non-wearing state, obtain the display impact level of the non-wearing state at the current monitoring time point, and match it with the set carousel display parameters of each display impact level corresponding to the non-wearing state, obtain the carousel display parameters of the non-wearing state at the current monitoring time point, and use them as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point; In a specific embodiment, the present invention realizes intelligent display control of the carousel content of the IPTV display terminal by analyzing the user's glasses wearing state, myopia degree and the distance between the user and the display terminal, ensuring that the user can obtain the best viewing experience in different glasses wearing states, which not only improves the user's viewing comfort, but also helps to reduce viewing obstacles caused by vision problems, further enhancing the practicality and attractiveness of IPTV services; The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A video carousel control system applied to IPTV, characterized in that: include: A scope demarcation and analysis module is used to perform monitoring scope demarcation and analysis based on the semicircular area of ​​the IPTV display terminal to obtain a monitoring scope; The first video carousel control module is used to identify the face image of the user within the monitoring range, extract the face features from the face image and input them into the age prediction model to obtain the user's age, match the age with the set age range, and generate the user's first video carousel content; The bias analysis module is used to obtain and analyze the user's bias information set to obtain the bias value of each topic, the bias value of each content category, and the bias value of each region; The re-carousel control module is used to monitor the duration of the user browsing the initial video carousel content on the IPTV display terminal interface. If the duration is greater than the set duration threshold, a re-carousel control analysis is performed to determine the target main theme, target main content category and target main region as screening conditions to generate the user's re-carousel video content; The carousel display analysis module is used to monitor the user's glasses wearing status at the current monitoring time point, thereby analyzing the carousel display parameters of the IPTV display terminal at the current monitoring time point to obtain the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point.

2. A video carousel control system for IPTV according to claim 1, characterized in that: The specific analysis process for delineating the monitoring scope is as follows: With the center point of the IPTV display terminal as the center Q1, a semicircle is drawn with a radius R to obtain a semicircular area; Set each IPTV display terminal to correspond to an identification angle, take the midpoints Q2 and Q3 of the left and right ends of the IPTV display terminal as the starting point, and draw a ray respectively. These two rays intersect the arc edges of the semicircle at points Q2′ and Q3′ to obtain line segments Q2Q2′ and Q3Q3′, thereby obtaining the monitoring range of the shaded part Q3-Q3′-Q1′-Q2′-Q2-Q1-Q3, that is, starting from Q1, the area between the two boundary rays and the semicircular arc segment is the monitoring range.

3. The video carousel control system applied to IPTV according to claim 1, characterized in that: The specific analysis process for the user's first video carousel content selection is as follows: According to the age range to which the user belongs, the playback volume of each program in a unit time period within the range is counted, and the programs are sorted from high to low according to the playback volume to generate a playback volume list, and the top T programs in the playback volume list are selected as the user's initial video carousel content.

4. The video carousel control system applied to IPTV according to claim 1, characterized in that: The user's preference information set is obtained and analyzed. The specific analysis process is as follows: The number of views, viewing time, number of favorites, and number of recharges for each theme of the program watched by the user are marked as Zviews t , Zduras t 、Zcolle t and Zcharg t , t represents the number of each topic, according to the formula: , get the bias value ZTP of each topic t , where Zviews θ t , Zduras θ t 、Zcolle θ t and Zcharg θ t They are respectively represented as the reference viewing times, reference viewing time, reference collection times, and reference recharge times of each topic, and b1, b2, b3, and b4 are respectively represented as the set weight coefficients; Similarly, the bias values ​​of each content category and each region are analyzed and recorded as NRP r and DYP y , where r represents the number of each content category and y represents the number of each region.

5. The video carousel control system applied to IPTV according to claim 1, characterized in that: Determine the target theme. The specific analysis process is as follows: Get the bias value ZTP of each topic during the historical monitoring period t , set the conversion factor of the bias value of each topic to Z t , according to the formula: , and obtain the conversion bias value δ1 of each topic t , u is a natural constant; Among them, the conversion factor of the bias value of each topic indicates that the bias value of each topic can be converted into the conversion bias value of each topic; Get the bias value of each topic in the current monitoring period, marked as ZTP t* ; According to the formula: , get the comprehensive bias value SZ of each topic t ; The comprehensive bias value of each topic is compared and analyzed with the preset topic bias threshold. When the comprehensive bias value of a topic is greater than or equal to the preset topic bias threshold, the topic is determined to be the target main promotion topic.

6. The video carousel control system applied to IPTV according to claim 1, characterized in that: Determine the target content category. The specific analysis process is as follows: Get the bias value NRP of each content category during the historical monitoring period r , set the conversion factor of the bias value of each content category to N r , according to the formula: , and obtain the conversion bias value δ2 of each content category r ; The conversion factor of the bias value of each content category indicates that the bias value of each content category can be converted into a conversion bias value of each content category; Get the bias value of each content category in the current monitoring period, marked as NRP r* ; According to the formula: , get the comprehensive bias value SN of each content category r ; The comprehensive bias value of each content category is compared and analyzed with the preset content category bias threshold. When the comprehensive bias value of a content category is greater than or equal to the preset content category bias threshold, the content category is determined to be the target main content category.

7. A video carousel control system for IPTV according to claim 1, characterized in that: Determine the target promotion area. The specific analysis process is as follows: Get the bias value DYP of each region during the historical monitoring period y , set the conversion factor of the bias value of each region to D y , according to the formula: , and obtain the conversion bias value δ3 of each region y ; Among them, the conversion factor of the bias value of each region indicates that the bias value of each region can be converted into the conversion bias value of each region; Get the deviation value of each region in the current monitoring period, marked as DYP y* ; According to the formula: , get the comprehensive bias value SD of each region y ; The comprehensive bias value of each region is compared and analyzed with the preset regional bias threshold. When the comprehensive bias value of a region is greater than or equal to the preset regional bias threshold, the region is determined to be the target main promotion region.

8. The video carousel control system applied to IPTV according to claim 1, characterized in that: Analyze the carousel display parameters. The specific analysis process is as follows: By collecting the eye image of the user at the current monitoring time point and matching it with the eye images of various glasses wearing states, the glasses wearing state of the user at the current monitoring time point is obtained, and the glasses wearing state includes the wearing state and the not wearing state; The distance of the user at the current monitoring time point is recorded as JL, and the corresponding myopia degree of the user is extracted from the system repository; If the user's glasses wearing state at the current monitoring time point is in the wearing state, the user's corresponding myopia degree is matched with the reference distance corresponding to each myopia degree of the glasses, and the reference distance corresponding to the user's glasses is obtained, which is recorded as JP * ; According to the formula: , get the display impact ratio value Y of the wearing status at the current monitoring time point 佩戴 , where e represents the natural constant, and ΔJP represents the allowable distance difference corresponding to the set wearing glasses; Match the display impact ratio value of the wearing state at the current monitoring time point with the display impact ratio threshold value of each display impact level corresponding to the set wearing state, obtain the display impact level of the wearing state at the current monitoring time point, and match it with the carousel display parameters of each display impact level corresponding to the set wearing state, obtain the carousel display parameters of the wearing state at the current monitoring time point, and use them as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point; If the user is not wearing glasses at the current monitoring time point, the user's corresponding myopia degree is matched with the set reference distances for each myopia degree when not wearing glasses to obtain the user's reference distance when not wearing glasses, which is recorded as JW * ; According to the formula: , get the display impact ratio value Y of the non-wearing state at the current monitoring time point 未戴 , where ΔJW represents the allowable distance difference corresponding to not wearing glasses; The display impact ratio value of the not-wearing state at the current monitoring time point is matched with the display impact ratio threshold value of each display impact level corresponding to the not-wearing state, and the display impact level of the not-wearing state at the current monitoring time point is obtained, and it is matched with the carousel display parameters of each display impact level corresponding to the set not-wearing state to obtain the carousel display parameters of the not-wearing state at the current monitoring time point, which are used as the carousel display parameters of the IPTV display terminal corresponding to the current monitoring time point.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the system according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the system according to any one of claims 1 to 8 is implemented.

Images