Real-time interaction enhancement system of electronic publication

Abstract

The invention is applicable to the technical field of interactive video processing and information updating scheduling, and provides a real-time interactive enhancement system for electronic publications, which comprises a data acquisition module used for acquiring a user interactive historical record of a target unmanned vending machine and an initial updating period value of a target interactive video. Aiming at the interactive video updating problem in the unmanned vending scene, the method does not depend on an updating mode purely based on a commodity data change period in the prior art, but introduces user interaction feedback as a core decision basis. A correction factor is dynamically generated to adjust an initial updating period value by obtaining and analyzing user interaction historical records, recognizing wrong clicks, repeated switching of branch paths or interruption after interaction steps are not completed, and combining the occurrence frequency in a newest preset time window, so that the updating rhythm can truly reflect understanding and trust requirements of users.

Description

Real-time interactive enhancement system for electronic publications Technical Field

[0001] This invention belongs to the field of interactive video processing and information update scheduling technology, and particularly relates to a real-time interactive enhancement system for electronic publications. Background Technology

[0002] Interactive video, as a novel information display method, has been gradually applied in various fields such as e-commerce, education, and retail. Especially in unmanned vending scenarios, interactive videos are typically used for product introductions, displaying test data, or presenting traceability information. Their update methods largely rely on a fixed-period scheduling mechanism in the backend; that is, after a set update cycle, the video content is comprehensively retrieved and replaced. This model can ensure the timeliness of product information to a certain extent, but the update logic is mainly based on the periodic changes in product data generation, failing to fully utilize the inherent user-interactive characteristics of interactive video.

[0003] However, in practical applications, users exhibit various interactive behaviors when watching interactive videos, such as clicking, branch selection, repeated rewinding, or quick exiting. These behaviors essentially reflect the user's level of understanding, trust, or points of doubt regarding the video content. Current technology fails to incorporate user feedback into update strategies, causing video content updates to be solely related to the natural rhythm of product data changes, rather than reflecting actual user perception. This results in the following problems: when users collectively generate abnormal interactions, the system still delays updates until a fixed period, easily causing user dissatisfaction with the timeliness and accuracy of information. Summary of the Invention

[0004] The purpose of this invention is to provide a real-time interactive enhancement system for electronic publications, aiming to solve the problems mentioned in the background art.

[0005] This invention is implemented as follows: a real-time interactive enhancement system for electronic publications, comprising: a data acquisition module for acquiring the user interaction history of a target unmanned vending machine and the initial update cycle value of the target interactive video; an interaction behavior analysis module for analyzing the history and identifying interaction anomalies generated by historical users of a specified user profile while watching the target interactive video; a local content labeling module for locating local segments of the target interactive video based on the interaction anomalies, and identifying the local segments as anomaly-triggered video segments when they contain preset updatable marker information; a trend analysis module for statistically analyzing the historical frequency of occurrence of the anomaly-triggered video segments within each preset time window, and determining whether the frequency is trending upwards; if so, determining the frequency of occurrence of the anomaly-triggered video segments of historical users of a specified user profile within a preset time window after the completion of the update of a similar interactive video as a reference frequency; and an update correction module for acquiring the current frequency of occurrence of the target interactive video within the latest preset time window, and generating a correction factor based on the deviation between the current frequency and the reference frequency to correct the initial update cycle value.

[0006] As a further limitation of the technical solution of the embodiments of the present invention, the abnormal interaction situations include situations such as quick exit, repeated back operations, or facial expression recognition as a negative state, or abnormal interactive behaviors generated by the user in the interactive video, including incorrect clicks, repeated switching of branch paths, or interruption before completing the interactive steps.

[0007] As a further limitation of the technical solution of this embodiment of the invention, the designated user profile refers to the user group that best matches the characteristics of the target interactive video content.

[0008] As a further limitation of the technical solution of the present invention, the preset updatable marker information is used to characterize that the content contained in a local segment of the target interactive video belongs to a replaceable or dynamically adjustable content area, and the content area can be replaced with new information in subsequent data updates or version iterations.

[0009] As a further limitation of the technical solution of this embodiment of the invention, the trend analysis module specifically includes: a frequency statistics unit, used to perform statistics on several preset time windows based on the time process, calculate the number of interaction anomalies generated by historical users and the number of corresponding anomaly triggering video segments in each preset time window, and thereby obtain the historical occurrence frequency of the anomaly triggering video segments in each preset time window; a trend determination unit, used to analyze the change of the historical occurrence frequency of the anomaly triggering video segments over time, and determine whether it is on an upward trend; when it is determined to be on an upward trend, a comparison interaction video of the same type as the target interaction video is selected based on the historical records; and a baseline extraction unit, used to obtain the occurrence frequency of the anomaly triggering video segments generated by historical users in the preset time window after the update of the comparison interaction video, and use the occurrence frequency as a reference occurrence frequency.

[0010] As a further limitation of the technical solution of this embodiment of the invention, the update correction module specifically includes: a frequency calculation unit, used to calculate the current occurrence frequency of the target interactive video within the latest preset time window based on historical user interaction records; a correction factor generation unit, used to generate a correction factor according to the deviation between the current occurrence frequency and the reference occurrence frequency, and use the correction factor to correct the initial update cycle value to obtain an optimized update cycle value; and an application execution unit, used to apply the optimized update cycle value to the content update scheduling of the target interactive video to control the update triggering timing or the calculation of the remaining update duration of the target interactive video.

[0011] As a further limitation of the technical solution of this embodiment of the invention, in the application execution unit, when the interval between the content of the target interactive video and the last update is within the optimized update cycle value, the remaining update time is calculated and an update waiting instruction is output; when the interval exceeds the optimized update cycle value, a content update instruction is generated to trigger the update of the target interactive video.

[0012] As a further limitation of the technical solution of this embodiment of the invention, in the correction factor generation unit, a preset correction function is used to calculate the optimization update cycle value; the correction function is: ;in This refers to optimizing the update cycle value. This refers to the initial update cycle value. This refers to the minimum allowed update cycle. This refers to the maximum allowed update cycle. This refers to the current frequency of occurrence. This refers to the frequency of occurrence of the reference. This refers to the correction factor, which is the deviation between the current frequency of occurrence and the reference frequency of occurrence. This refers to the correction amplitude control coefficient, and .

[0013] Compared with existing technologies, this invention has the following advantages: Addressing the issue of interactive video updates in unmanned vending scenarios, it no longer relies on the existing update model based solely on the product data change cycle. Instead, it introduces user interaction feedback as the core decision-making basis. By acquiring and analyzing user interaction history records, it identifies erroneous clicks, repeated switching of branch paths, or interruptions before completing interaction steps. Combined with the frequency of occurrence within the latest preset time window, it dynamically generates a correction factor to adjust the initial update cycle value, ensuring that the update rhythm truly reflects the user's understanding and trust needs. This invention particularly emphasizes the role of specifying user profiles, ensuring that corrections are based on the most suitable user group's interactive behavior, avoiding redundant updates or update delays.

[0014] Its core innovation lies in leveraging the characteristics of interactive video to establish a correlation between abnormal reactions expressed by users during viewing and updatable content segments, and then achieving precise scheduling through trend analysis and correction functions. This significantly improves the real-time nature and credibility of information display in vending machines, enhances the user experience, and possesses good potential for widespread application. Attached Figure Description

[0015] Figure 1 is an application architecture diagram of the system provided in an embodiment of the present invention; Figure 2 is a structural block diagram of the trend analysis module in the system provided in an embodiment of the present invention; Figure 3 is a structural block diagram of the update and correction module in the system provided in an embodiment of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] Figure 1 shows the application architecture diagram of the system provided in an embodiment of the present invention.

[0018] In another preferred embodiment of the present invention, a real-time interactive enhancement system for electronic publications includes: a data acquisition module 100, used to acquire the user interaction history of the target unmanned vending machine and the initial update cycle value of the target interactive video.

[0019] In this embodiment of the invention, the data acquisition module 100 is used in vending machines. Vending machines are typically located in public areas such as shopping malls, campuses, office buildings, or transportation hubs, enabling unmanned and self-service sales of goods. Unlike traditional vending machines, the vending machine involved in this invention is equipped with an interactive video interface in the form of an electronic publication, through which users can obtain relevant product information before purchasing. This interactive video differs from a simple static advertising video; it is dynamic content with interactive features, allowing users to click, swipe, or select during playback to view details of specific information within the video. This type of interactive video does not require frequent updates to the entire content; instead, some segments carry dynamic information such as product testing values, production batches, and supply chain details. These segments can be selectively updated based on changes in background data, thereby ensuring the timeliness and relevance of the video's information interaction.

[0020] The user interaction history is derived from the user's interactions with videos on the vending machine's interface, primarily generated through front-end touch data collection and back-end behavior log recording. Specifically, this history includes the number and location of user clicks, the duration of time spent on a particular video segment, the frequency of repeated back actions, instances of rapid exits, user browsing paths, and user facial expressions identified by cameras or sensors. It also includes different user profiles identified during the interaction, such as age group, gender characteristics, consumption preferences, or interest tags. This data reflects user behavior habits, potential questions, and the degree of adaptation to the video content during viewing, thus providing a more comprehensive foundation for subsequent interaction behavior analysis and trend analysis.

[0021] The initial update cycle value refers to the video content update cycle of the target interactive video before any corrections are made. This update cycle value is typically set by the backend management system during the video generation or configuration phase and can be obtained based on mature update scheduling strategies in existing technologies. In existing technologies, the determination of the update cycle value often considers multiple factors, such as the frequency of changes in product information, the cycle of generating detection data, the timeliness of updates to inventory and supply chain information, and the overall fluctuation of user interaction data. By weighting or empirically setting the above factors, the backend system generates the initial update cycle value.

[0022] In existing technologies, the process typically involves a comprehensive search of the entire content of the target interactive video after the initial update cycle value is reached, identifying the parts that need to be updated and replacing them, and then re-uploading the updated video to replace the original version.

[0023] Furthermore, the real-time interactive enhancement system for electronic publications also includes an interactive behavior analysis module 200, used to analyze historical records and identify abnormal interactive situations generated by historical users of a specified user profile while watching target interactive videos.

[0024] The abnormal interaction situations include situations such as quickly exiting, repeatedly performing back operations, or having facial expressions recognized as negative, or abnormal interactive behaviors generated by the user in the interactive video, including incorrect clicks, repeated switching of branch paths, or interruption before completing the interactive steps.

[0025] The specified user profile refers to the user group that best matches the characteristics of the target interactive video content.

[0026] The local content identification module 300 is used to locate local segments of the target interactive video based on abnormal interaction conditions, and to identify the local segment as an abnormal trigger video segment when it contains preset updatable tag information.

[0027] The preset updatable tagging information is used to characterize that the content contained in a local segment of the target interactive video belongs to a replaceable or dynamically adjustable content area, which can be replaced with new information during subsequent data updates or version iterations.

[0028] In this embodiment of the invention, the designated user profile refers to the user group that best matches the characteristics of the target interactive video content, i.e., the set of users who show a higher degree of fit or attention to the target interactive video in historical interaction data. For example, for an interactive video displaying information on the testing of a certain type of food, the designated user profile may include users who have repeatedly viewed relevant food testing content, frequently clicked to view product traceability information, or have a higher sensitivity to health indicators in their consumption habits. The reason for selecting the designated user profile is that the interactive behavior of this type of user better reflects the actual effectiveness and attention level of local content in the video, thereby providing more representative data support for subsequent updates and optimizations.

[0029] Interactive anomalies refer to unusual user interactions during the viewing of a target interactive video. These behaviors can be acquired and identified through various technical means. For example, rapid exits can be identified by monitoring user dwell time below a preset threshold in front-end logs; repeated back actions can be identified by analyzing user action sequences to determine if the same segment is repeatedly revisited; negative facial expressions can be determined by capturing user expressions with the front-end camera and combining this with an expression recognition model for sentiment analysis. In addition, abnormal interactive behaviors specific to interactive videos are also included. For instance, erroneous clicks can be identified by detecting mismatches between user actions and preset interactive areas; repeated switching between branch paths can be determined by statistically analyzing the frequency of user switching between different interactive branches; and interruptions before completing interactive steps can be identified by monitoring user exits or abandonments midway through mandatory interactive steps. Through these methods, user actions and emotional reactions during viewing can be transformed into structured data, thereby enabling effective identification of interactive anomalies.

[0030] In the local content identification module 300, when a local segment located by an interaction anomaly also contains preset updatable marker information, it indicates that the user's doubts or negative experiences are concentrated in the dynamic content area carried by that segment. This reflects that the dynamic data contained in that segment may be inaccurate, outdated, or not in line with user expectations in the current version. Therefore, it is necessary to set this local segment as an anomaly trigger video segment so that it can be prioritized for correction or replacement in subsequent updates.

[0031] The pre-defined updatable tagging information is metadata embedded in local segments of the target interactive video, used to characterize replaceable or dynamically adjustable content areas within those segments. It can take the form of video node identifiers configured in the backend, embedded tags, timestamp location information, or product-related data placeholders, such as production dates, test values, batch numbers, or supply chain traceability information. By pre-implanting such tagging information during the video content generation or editing stage, the system can quickly identify updatable areas during subsequent data updates and dynamically replace local information without altering the overall video structure, thereby improving the timeliness and flexibility of interactive videos.

[0032] Furthermore, the real-time interactive enhancement system for electronic publications also includes a trend analysis module 400, which is used to statistically analyze the historical frequency of abnormally triggered video segments within each preset time window in the time dimension, and determine whether the frequency of occurrence is on the rise. If so, the frequency of occurrence of abnormally triggered video segments of historical users of a specified user profile within the preset time window after the completion of the same type of interactive video update is determined as the reference frequency of occurrence.

[0033] Specifically, Figure 2 shows a structural block diagram of the trend analysis module 400 in the system provided in this embodiment of the invention.

[0034] In a preferred embodiment of the present invention, the trend analysis module 400 specifically includes: a frequency statistics unit 401, used to perform statistics on several preset time windows based on the time process, calculate the number of interactive anomalies generated by historical users and the number of corresponding anomaly-triggered video segments within each preset time window, and thereby obtain the historical occurrence frequency of the anomaly-triggered video segments in each preset time window; a trend determination unit 402, used to analyze the change in the historical occurrence frequency of the anomaly-triggered video segments over time, and determine whether it shows an upward trend; when it is determined to show an upward trend, a comparison interactive video of the same type as the target interactive video is selected based on historical records; and a baseline extraction unit 403, used to obtain the occurrence frequency of the anomaly-triggered video segments generated by historical users within the preset time window after the update of the comparison interactive video, and use the occurrence frequency as a reference occurrence frequency.

[0035] In this embodiment of the invention, the frequency statistics unit 401 is implemented as follows: First, the interactive data of the target interactive video is divided into several preset time windows according to the time process, such as by day, week, or month as window intervals; then, within each time window, the number of all historical user-generated interaction anomalies is counted, and these anomalies are mapped to specific local segments, thereby obtaining the total number of abnormally triggered video segments within the window. By comparing the number of abnormally triggered video segments with the total number of times users watch the video within the window, the historical frequency of occurrence within the time window is obtained. This process can be implemented using log analysis tools, database aggregation operations, or statistical methods based on big data processing frameworks, thereby ensuring the accuracy and scalability of the calculation results.

[0036] The specific implementation process of the trend determination unit 402 is as follows: After obtaining the historical occurrence frequencies of multiple preset time windows, time series analysis or regression analysis methods are used to identify the frequency change trend over time. When the overall frequency shows an upward trend, it is determined that the concentration of abnormally triggered video segments intensifies over time. It should be noted that the upward trend here does not require each window to show a strict increase, but rather refers to an overall increasing trend, such as determined by moving average, linear fitting with a positive slope, or statistically significant growth of moving windows.

[0037] Interactive videos differ from traditional one-way videos in that they not only present information to users but also allow for real-time interaction through clicking, swiping, and rewinding. This interactivity allows users' actions and emotional reactions to directly reflect their understanding and acceptance of the video content. When users quickly exit, frequently rewind, or display negative expressions in certain segments, these behaviors become direct signals of user confusion or dissatisfaction. In contrast, existing technologies often determine video update timing solely based on the periodicity of product information updates, failing to leverage the inherent user reactions within interactive videos. This invention, based on this characteristic of interactive videos, captures and analyzes abnormal feedback trends of core user profiles during interaction to determine which parts of the video require priority updates, thereby more accurately meeting users' needs for real-time and reliable information.

[0038] In the baseline extraction unit 403, the selection method for the reference interactive video is as follows: Content similar to the target interactive video is retrieved from the historical database; that is, videos that are consistent with the target video in terms of theme, information type, or product category. Furthermore, the reference interactive video must be within a preset time window immediately after an update, thus ensuring that its interaction data represents a reference standard of "normal state after update." After selecting this type of reference interactive video, the frequency of occurrence of abnormal trigger video segments generated by historical users within the preset time window after the update is statistically analyzed, and this frequency is used as the reference occurrence frequency. The significance of setting this reference occurrence frequency is that it provides a benchmark for the update effect of the target interactive video, used to measure whether the current video's performance in user interaction deviates from a reasonable range. If the current frequency of the target video is significantly higher than the reference frequency, it indicates that an update is urgently needed. Further, to reduce the randomness of a single update effect, the reference occurrence frequency is preferably the average of the frequency results after multiple updates of similar videos, to ensure that the reference value is more stable and representative.

[0039] Furthermore, the real-time interactive enhancement system for the electronic publication also includes an update correction module 500, which is used to obtain the current occurrence frequency of the target interactive video within the latest preset time window, and generate a correction factor based on the deviation between the current occurrence frequency and the reference occurrence frequency, so as to correct the initial update cycle value.

[0040] Specifically, Figure 3 shows a structural block diagram of the update and correction module 500 in the system provided in an embodiment of the present invention.

[0041] In a preferred embodiment of the present invention, the update correction module 500 specifically includes: a frequency calculation unit 501, used to calculate the current occurrence frequency of the target interactive video within the latest preset time window based on historical user interaction records; a correction factor generation unit 502, used to generate a correction factor based on the deviation between the current occurrence frequency and the reference occurrence frequency, and use the correction factor to correct the initial update cycle value to obtain an optimized update cycle value; and an application execution unit 503, used to apply the optimized update cycle value to the content update scheduling of the target interactive video to control the update triggering timing or the calculation of the remaining update duration of the target interactive video.

[0042] In the application execution unit 503, when the interval between the content of the target interactive video and the last update is within the optimized update cycle value, the remaining update time is calculated and an update waiting instruction is output; when the interval exceeds the optimized update cycle value, a content update instruction is generated to trigger the update of the target interactive video.

[0043] In the correction factor generation unit, the optimization update cycle value is calculated using a preset correction function; the correction function is: ;in This refers to optimizing the update cycle value. This refers to the initial update cycle value. This refers to the minimum allowed update cycle. This refers to the maximum allowed update cycle. This refers to the current frequency of occurrence. This refers to the frequency of occurrence of the reference. This refers to the correction factor, which is the deviation between the current frequency of occurrence and the reference frequency of occurrence. This refers to the correction amplitude control coefficient, and .

[0044] In this embodiment of the invention, the latest preset time window refers to the closest statistical window before the current time. For example, if the system divides time windows by day, then when the current time is 10:00 AM, the latest preset time window could be from 00:00 to 24:00 of the previous day. This ensures that frequency calculations are based on the latest complete data range, avoiding fluctuations caused by real-time data. If the amount of data within this time window is insufficient to support effective statistics, the system can recursively select earlier time windows until the cumulative amount reaches a preset minimum data threshold, thereby ensuring the reliability and representativeness of the frequency calculation results.

[0045] In the frequency calculation unit 501, the calculation process is the same as that used in the aforementioned trend analysis module. It still involves statistically analyzing user interaction logs, mapping abnormal interaction situations to local segments, and statistically analyzing the ratio of the number of times the abnormal trigger video segment appears to the number of times the user watches it within the latest preset time window, thereby obtaining the current frequency of occurrence.

[0046] In the correction factor generation unit 502, the deviation between the current frequency of occurrence and the reference frequency of occurrence is calculated, and this deviation is used as a correction factor to correct the initial update cycle value. The significance of this design is that the deviation essentially reflects the difference between the user's current abnormal reaction and the "ideal normal state." When the deviation increases, it indicates that the user's doubts or dissatisfaction are more concentrated. The system shortens the update cycle through the correction factor, triggering updates in a timely manner, thereby increasing the user's trust and acceptance of the interactive video content. This process solves the problem of existing technologies not considering user interaction feedback, making the video update strategy no longer solely dependent on the natural cycle of product data, but combined with the user's actual interaction state. This is precisely the core technical problem that this invention aims to solve.

[0047] In the application execution unit 503, the system compares the interval between the target interactive video and the last update with the optimized update cycle value. When the interval is still within the optimized update cycle value, the system calculates the remaining update time and generates an update waiting instruction to keep the background on standby; when the interval exceeds the optimized update cycle value, a content update instruction is generated to directly trigger the update of the corresponding segment in the video, thereby ensuring accurate and efficient update scheduling.

[0048] The correction function provided by this invention is an intuitive and effective way to quickly reflect the correspondence between user interaction status and update cycle through proportional relationships. Of course, other calculation methods can also be used, such as training and predicting the relationship between historical interaction behavior and update requirements based on machine learning models, or using fuzzy logic reasoning methods to classify different degrees of deviation to achieve more flexible update scheduling.

[0049] Here is a specific implementation example: In the data acquisition module 100, the system collects interaction data from the vending machine, obtaining an initial update cycle of 7 days for a target interactive video. User interaction history shows that the video was played 1000 times in the past week, with 200 instances of abnormal interaction. The interaction behavior analysis module 200 identifies these abnormalities as mainly concentrated in segments of the video involving detection values. The local content labeling module 300 further confirms that the segment carries preset updatable marker information, identifying it as an abnormal trigger video segment. The trend analysis module 400 statistically analyzes data from the past four weeks, finding that the proportion of abnormal trigger video segments gradually increased from 10% to 20%, and after updating similar comparison videos, a reference frequency of 12% was obtained. The update correction module 500 statistically analyzes the current frequency of the video within the latest time window as 18%, and generates a correction factor based on the deviation magnitude, correcting the original 7-day initial update cycle value to obtain a new optimized update cycle value of 5 days. The application execution unit 503 detected that the video had been updated for 6 days, exceeding the optimized update cycle value. Therefore, it immediately generated an update instruction to replace the segments in the video containing the detected values, thereby ensuring that the information obtained by the user is up-to-date.

[0050] The overall beneficial effects of this invention are as follows: Firstly, by combining the characteristics of unmanned vending scenarios with interactive videos, the system can automatically adapt to user interaction feedback in unmanned retail environments and dynamically adjust the update rhythm of video content, achieving timeliness and personalization of information. Secondly, by focusing on the interactive behavior of core user groups, it can enhance users' understanding and trust in product information, reducing confusion and dissatisfaction caused by outdated data or inappropriate expression. This method is not only applicable to product introductions and detection data display in unmanned vending machines, but can also be extended to other real-time information transmission scenarios based on interactive videos, such as self-service medical consultations, education and training, or government services, showing broad application prospects.

[0051] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0052] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, 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. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0053] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0054] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A real-time interactive enhancement system for electronic publications, characterized in that, The system includes: a data acquisition module for acquiring the user interaction history of the target unmanned vending machine and the initial update cycle value of the target interactive video; an interaction behavior analysis module for analyzing the history and identifying interaction anomalies generated by historical users of a specified user profile while watching the target interactive video; a local content labeling module for locating local segments of the target interactive video based on interaction anomalies, and identifying the local segment as an anomaly-triggered video segment when it contains preset updatable marker information; a trend analysis module for statistically analyzing the historical occurrence frequency of the anomaly-triggered video segment within each preset time window, and determining whether the occurrence frequency is on the rise. If so, the occurrence frequency of the anomaly-triggered video segment of historical users of a specified user profile within the preset time window after the completion of the update of the similar comparison interactive video is determined as the reference occurrence frequency; and an update correction module for acquiring the current occurrence frequency of the target interactive video within the latest preset time window, and generating a correction factor based on the deviation between the current occurrence frequency and the reference occurrence frequency to correct the initial update cycle value.

2. The real-time interactive enhancement system for electronic publications according to claim 1, characterized in that, The abnormal interaction situations include situations such as quickly exiting, repeatedly performing back operations, or having facial expressions recognized as negative, or abnormal interactive behaviors generated by the user in the interactive video, including incorrect clicks, repeated switching of branch paths, or interruption before completing the interactive steps.

3. The real-time interactive enhancement system for electronic publications according to claim 1, characterized in that, The specified user profile refers to the user group that best matches the characteristics of the target interactive video content.

4. The real-time interactive enhancement system for electronic publications according to claim 1, characterized in that, The preset updatable tagging information is used to characterize that the content contained in a local segment of the target interactive video belongs to a replaceable or dynamically adjustable content area, which can be replaced with new information during subsequent data updates or version iterations.

5. The real-time interactive enhancement system for electronic publications according to claim 1, characterized in that, The trend analysis module specifically includes: a frequency statistics unit, used to perform statistics on several preset time windows based on the time process, calculate the number of interaction anomalies generated by historical users and the number of corresponding anomaly-triggered video segments within each preset time window, and thereby obtain the historical occurrence frequency of the anomaly-triggered video segments in each preset time window; a trend determination unit, used to analyze the change in the historical occurrence frequency of the anomaly-triggered video segments over time, and determine whether it shows an upward trend; when it is determined to show an upward trend, a comparison interaction video of the same type as the target interaction video is selected based on historical records; and a baseline extraction unit, used to obtain the occurrence frequency of the anomaly-triggered video segments generated by historical users within the preset time window after the update of the comparison interaction video, and use this occurrence frequency as a reference occurrence frequency.

6. The real-time interactive enhancement system for electronic publications according to claim 5, characterized in that, The update correction module specifically includes: a frequency calculation unit, used to calculate the current occurrence frequency of the target interactive video within the latest preset time window based on historical user interaction records; a correction factor generation unit, used to generate a correction factor based on the deviation between the current occurrence frequency and the reference occurrence frequency, and use the correction factor to correct the initial update cycle value to obtain an optimized update cycle value; and an application execution unit, used to apply the optimized update cycle value to the content update scheduling of the target interactive video to control the update triggering timing or the calculation of the remaining update duration of the target interactive video.

7. The real-time interactive enhancement system for electronic publications according to claim 6, characterized in that, In the application execution unit, when the interval between the content of the target interactive video and the last update is within the optimized update cycle value, the remaining update time is calculated and an update waiting instruction is output; when the interval exceeds the optimized update cycle value, a content update instruction is generated to trigger the update of the target interactive video.

8. The real-time interactive enhancement system for electronic publications according to claim 6, characterized in that, In the correction factor generation unit, the optimization update cycle value is calculated using a preset correction function; the correction function is: ;in This refers to optimizing the update cycle value. This refers to the initial update cycle value. This refers to the minimum allowed update cycle. This refers to the maximum allowed update cycle. This refers to the current frequency of occurrence. This refers to the frequency of occurrence of the reference. This refers to the correction factor, which is the deviation between the current frequency of occurrence and the reference frequency of occurrence. This refers to the correction amplitude control coefficient, and 。

Images