Exhibition activity picture and image online management system

Abstract

The invention discloses an exhibition activity picture and image online management system, which belongs to the technical field of data management and comprises a user behavior analysis module, a commercial value analysis module, a propagation state analysis module, a performance analysis module and a picture increment optimization module. By constructing a user participation state model, a commercial conversion state model, a growth and propagation state model, an upload-response adaptation model and a picture increment optimization model, quantitative analysis of each dimension state coefficient is realized, and the number of daily newly added pictures is dynamically optimized based on the growth and propagation state coefficient and the upload-response adaptation coefficient. The method can effectively solve the problems that in the prior art, system performance is not matched with service requirements, and resource allocation is unreasonable, dynamic balance of system resources and the service requirements is achieved, and system operation efficiency and user experience are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of data management, and particularly relates to an online management system for pictures and videos of exhibition activities. BACKGROUND

[0002] With the rapid development of digital exhibition industry, the number of picture, video and other image data generated during the exhibition activities has shown explosive growth. These image data, as an important carrier for recording exhibition content and showing enterprise image, need to be effectively collected, stored, managed and distributed. Traditional picture management systems often only provide basic storage and sharing functions, and are difficult to meet the needs of modern exhibition for intelligent management of image data.

[0003] Most of the existing exhibition image management systems adopt a static resource configuration method, which supports system operation through pre-set storage space and bandwidth. Such systems usually lack multi-dimensional perception ability of user behavior, commercial value and system performance, and cannot dynamically adjust according to actual business status. Although some systems have basic performance monitoring functions, they are limited to CPU, memory and other hardware indicators monitoring, and fail to establish a correlation model between business demand and system performance.

[0004] The existing technology mainly has the following defects: first, the system resource configuration is out of touch with the real-time business demand, which is easy to cause resource idling or performance bottleneck; second, it lacks a comprehensive evaluation mechanism for multi-dimensional states such as user participation, commercial value and dissemination effect; third, the picture incremental management adopts a fixed strategy, which cannot dynamically adjust according to system load and business growth, affecting system stability and user experience.

[0005] Therefore, there is an urgent need for an exhibition activity picture image online management system that can intelligently perceive business status and adaptively adjust resource configuration. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides an exhibition activity picture image online management system, which solves the above problems.

[0007] To achieve the above purpose, the present application is implemented by the following technical scheme: an exhibition activity picture image online management system, comprising:

[0008] A user behavior analysis module constructs a user participation state model based on the number of daily active users, average session duration and average page views per user to output a user participation state coefficient;

[0009] The business value analysis module constructs a business conversion status model based on monthly recurring revenue (stable monthly revenue obtained through subscription services), paid user conversion rate (the proportion of free users who become paid users), and average revenue per user (the average revenue obtained from each user within a specific period (such as a month)) and outputs business conversion status coefficients.

[0010] The propagation status analysis module constructs a growth and propagation status model based on the number of new user registrations (the number of unique users who register new each week), the number of new activities created (the number of new activities created by the organizer each month), and the number of social media shares (the number of times users share pictures to social media through the system each day), and outputs growth and propagation status coefficients.

[0011] The performance analysis module constructs an upload-response adaptation model and outputs upload-response adaptation coefficients based on user participation status coefficients, business conversion status coefficients, and total image storage (the total size of all images and videos currently stored in the system), average image upload time (the average time from user selection to completion of upload), and average system response time (the average time for the system to return results after user operations (such as searching and filtering)).

[0012] The image incremental optimization module constructs an image incremental optimization model based on the growth and propagation state coefficient, upload-response adaptation coefficient, and the current daily number of newly added images, and outputs the target daily number of newly added images.

[0013] Based on the above technical solutions, the present invention also provides the following optional technical solutions:

[0014] Further technical solution: The image incremental optimization model is represented as follows:

[0015]

[0016] in, This indicates the target number of newly added images per day. This indicates the number of newly added images per day. Represents the growth and propagation state coefficients. This represents the upload-response adaptation coefficient. Indicates the adjustment rate. This represents the fit threshold.

[0017] Further technical solution: The work content of the performance analysis module includes:

[0018] Get user engagement status coefficient, business conversion status coefficient, total image storage (the total size of all images and videos currently stored in the system), average image upload time (the average time from when a user selects an image to when the upload is completed), and average system response time (the average time it takes for the system to return results after a user operation (such as searching or filtering).

[0019] The image storage index is obtained by comparing the total image storage size with the maximum allowed image storage size.

[0020] The average image upload time and the average system response time are subjected to max-min normalization to obtain the image upload time index and the response time index.

[0021] A business requirement model is constructed based on user engagement status coefficients and business conversion status coefficients to obtain business requirement coefficients. The business requirement model is expressed as follows:

[0022]

[0023] in, Indicates the business demand coefficient. Indicates the user participation status coefficient. Indicates the business conversion status coefficient. Indicates the elasticity coefficient of user participation and , Indicates the elasticity coefficient of business conversion and The The Furthermore, the larger the value, the greater the business demand;

[0024] An upload-response adaptation model is constructed based on the business demand coefficient, image upload time index, and response time index under the image storage index, and the upload-response adaptation degree is obtained. The upload-response adaptation model is expressed as follows:

[0025]

[0026] in, Indicates upload-response adaptation. Indicates the business demand coefficient. This indicates the storage load impact factor. This indicates the image upload time index. This represents the response time index. Represents the weight coefficient and The Furthermore, the larger the value, the better the system performance matches business needs.

[0027] Further technical solutions: The work content of the propagation state analysis module includes:

[0028] Acquire new user registrations (the number of unique new users registering each week), new event creations (the number of new events created by the organizer each month), and social media shares (the number of times users share images to social media through the system each day).

[0029] The number of new user registrations, the number of new event creations, and the number of social media shares are processed by max-min normalization to obtain the new user registration index, the new event creation index, and the number of shares index.

[0030] A growth and propagation state model is constructed based on the new user registration index, new activity creation index, and sharing frequency index to obtain growth and propagation state coefficients. The growth and propagation state model is expressed as follows:

[0031]

[0032] in, Represents the growth and propagation state coefficients. This indicates the new user registration index. Indicates the index of new activity creation. The index represents the number of times a message is shared. Furthermore, the higher the value, the better the transmissibility.

[0033] Further technical solution: The business value analysis module's functions include:

[0034] Acquire monthly recurring revenue (stable monthly revenue earned through subscription services), paid user conversion rate (the percentage of free users who become paid users), and average revenue per user (the average revenue earned from each user over a specific period, such as a month).

[0035] The monthly recurring revenue, paid user conversion rate, and average revenue per user are subjected to maximum-min normalization to obtain the monthly recurring revenue index, average revenue per user index, and paid user conversion rate index.

[0036] A business conversion status model is constructed based on the monthly recurring revenue index, average revenue per user index, and paying user conversion rate index to obtain business conversion status coefficients. The business conversion status model is expressed as follows:

[0037]

[0038] in, Indicates the business conversion status coefficient. This represents the monthly recurring income index. This represents the average revenue per user index. This represents the paid user conversion rate index. Represents the weight coefficient and The Furthermore, the higher the value, the better the business performance.

[0039] Further technical solution: The user behavior analysis module's work includes:

[0040] Get daily active users, average session duration, and average page views per user;

[0041] The daily active users, average session duration, and average page views per user are subjected to max-min normalization to obtain the active user index, session duration index, and page view index.

[0042] A user engagement state model is constructed based on the active user index, session duration index, and page view index to obtain the user engagement state coefficient. The user engagement state model is represented as follows:

[0043]

[0044] in, Indicates the user participation status coefficient. Indicates the active user index. Indicates the session duration index. This represents the page view count index. Represents the weight coefficient and The Furthermore, the higher the value, the better the user participation.

[0045] Further technical solutions: The number of new user registrations refers to the number of unique users who register new each week, which can be achieved by using user registration log statistics to quantify the scale of user growth. The number of new activity creations refers to the number of new activities created by the organizer each month, which can be statistically analyzed through the creation records in the activity management backend to reflect business expansion capabilities. The number of social media shares refers to the number of times users share images to social media through the system each day, which can be achieved by capturing sharing data from third-party platforms through API interfaces to measure the effectiveness of content dissemination.

[0046] Further technical solutions: Monthly recurring revenue refers to the stable monthly revenue obtained through subscription services. Specifically, it can be realized using periodic subscription revenue data recorded by the financial system, which is used to reflect the sustainability of the system's business model. Paid user conversion rate refers to the proportion of free users who become paid users. Specifically, it can be calculated by using user account status change records and the total number of registered users, which is used to measure users' willingness to pay and business conversion efficiency. Average revenue per user refers to the average revenue obtained from each user in a specific period. Specifically, it can be calculated by dividing the total revenue by the number of active users, which is used to evaluate the value contribution of a single user.

[0047] Further technical solutions: Daily active users refer to the number of users who log in to the system and perform effective operations each day. This can be achieved through the user login log statistics module and is used to reflect the basic activity scale of the user group. Average session duration refers to the average duration of a user's operation during a single login session. This can be calculated through user behavior tracking data and is used to characterize the depth of user engagement with the system. Average page views per user refers to the average number of pages viewed by a single user in a single session. This can be achieved through the page access log analysis module and is used to measure the intensity of user interaction with content.

[0048] This invention provides an online management system for exhibition event images and videos, which has the following advantages compared with the prior art:

[0049] 1. This invention achieves precise matching between system performance and business needs through a multi-state collaborative analysis model. It can intelligently perceive user participation status, business conversion status, and dissemination status, establish a dynamic correlation between business needs and system performance, and evaluate system load capacity in real time through an upload-response adaptation model. Based on growth potential and system adaptability, it automatically optimizes the image increment strategy. This dynamic adjustment mechanism ensures stable operation of the system under high load and can fully leverage business growth potential when resources are abundant. This invention significantly improves system resource utilization, enhances user experience, and provides a more intelligent and efficient image management solution for exhibition activities. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0051] 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 of the invention and are not intended to limit the invention.

[0052] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0053] Please see Figure 1 An online image management system for exhibition activities, provided as an embodiment of the present invention, includes:

[0054] The user behavior analysis module builds a user engagement status model based on the number of daily active users, average session duration, and average page views per user, and outputs user engagement status coefficients.

[0055] The business value analysis module constructs a business conversion status model based on monthly recurring revenue (stable monthly revenue obtained through subscription services), paid user conversion rate (the proportion of free users who become paid users), and average revenue per user (the average revenue obtained from each user within a specific period (such as a month)) and outputs business conversion status coefficients.

[0056] The propagation status analysis module constructs a growth and propagation status model based on the number of new user registrations (the number of unique users who register new each week), the number of new activities created (the number of new activities created by the organizer each month), and the number of social media shares (the number of times users share pictures to social media through the system each day), and outputs growth and propagation status coefficients.

[0057] The performance analysis module constructs an upload-response adaptation model and outputs upload-response adaptation coefficients based on user participation status coefficients, business conversion status coefficients, and total image storage (the total size of all images and videos currently stored in the system), average image upload time (the average time from user selection to completion of upload), and average system response time (the average time for the system to return results after user operations (such as searching and filtering)).

[0058] The image incremental optimization module constructs an image incremental optimization model based on the growth and propagation state coefficient, upload-response adaptation coefficient, and the current daily number of newly added images, and outputs the target daily number of newly added images.

[0059] Through the above technical solutions, this application achieves dynamic matching of resource allocation with business needs, solving the problems of idle resources or insufficient performance in traditional systems. It establishes a comprehensive evaluation system for user engagement, monetization capabilities, and dissemination effects, overcoming the limitations of single-dimensional monitoring. By adaptively adjusting the incremental image target, it meets business growth needs while ensuring system stability, avoiding storage overload or service degradation caused by fixed strategies.

[0060] Preferably, the user behavior analysis module's functions include:

[0061] Get daily active users, average session duration, and average page views per user;

[0062] The daily active users, average session duration, and average page views per user are subjected to max-min normalization to obtain the active user index, session duration index, and page view index.

[0063] A user engagement state model is constructed based on the active user index, session duration index, and page view index to obtain the user engagement state coefficient. The user engagement state model is represented as follows:

[0064]

[0065] in, Indicates the user participation status coefficient. Indicates the active user index. Indicates the session duration index. This represents the page view count index. Represents the weight coefficient and The Furthermore, the higher the value, the better the user participation.

[0066] Among them, Daily Active Users (DAU) refers to the number of users who log in to the system and perform effective operations each day. This can be achieved through the user login log statistics module and reflects the basic active scale of the user group. Average Session Duration refers to the average duration of a user's operation during a single login session. This can be calculated using user behavior tracking data and represents the depth of user engagement with the system. Average Page Views per User (APPS) refers to the average number of pages viewed by a single user in a single session. This can be achieved through the page access log analysis module and measures the intensity of user interaction with content. Max-Min Normalization is a method of linearly transforming the original data to the 0-1 range. This can be achieved by using the maximum and minimum values ​​of the indicator within a set period as benchmark values ​​to eliminate the incomparability of indicators with different dimensions. Logical Function refers to the Sigmoid function form, specifically implemented using the mathematical expression 1 / (1+exp(-x)), used to convert the linear combination result into a probabilistic evaluation value.

[0067] Specifically, this technical solution acquires three core user behavior metrics in real time through a data acquisition module. After normalization to eliminate dimensional differences, a standardized index is formed. During model building, a weighted summation method is used to fuse the three-dimensional index. The weight coefficients are dynamically adjusted according to the business scenario to reflect the contribution of different metrics; either preset fixed values ​​or dynamic adjustments based on historical data can be used. The introduction of a logistic function ensures the output results have clear boundary ranges, forming interpretable quantitative values ​​of user engagement. When the system detects a significant increase in the active user index, the model adjusts the weight allocation to enhance the influence of this dimension on the final coefficient, thereby accurately reflecting the changes in engagement brought about by user scale expansion. In content operation scenarios, if the pageview index continues to decline, the model can automatically reduce the weight of this metric to avoid excessive interference with the overall evaluation.

[0068] Through the above technical solutions, this application achieves dynamic quantitative evaluation of user participation status, solving the problem that traditional systems cannot accurately reflect the actual usage status of users. Normalization eliminates the dimensional differences between multi-source data, enabling the effective integration of different behavioral indicators. The logical function mapping mechanism generates intuitive participation coefficients, providing a quantifiable basis for system resource scheduling decisions. The dynamic weight allocation function enhances the model's adaptability to different business scenarios; for example, it automatically increases the weight of the active user index during peak exhibition periods to accurately reflect changes in participation caused by traffic surges.

[0069] Preferably, the business value analysis module includes the following functions:

[0070] Acquire monthly recurring revenue (stable monthly revenue earned through subscription services), paid user conversion rate (the percentage of free users who become paid users), and average revenue per user (the average revenue earned from each user over a specific period, such as a month).

[0071] The monthly recurring revenue, paid user conversion rate, and average revenue per user are subjected to maximum-min normalization to obtain the monthly recurring revenue index, average revenue per user index, and paid user conversion rate index.

[0072] A business conversion status model is constructed based on the monthly recurring revenue index, average revenue per user index, and paying user conversion rate index to obtain business conversion status coefficients. The business conversion status model is expressed as follows:

[0073]

[0074] in, Indicates the business conversion status coefficient. This represents the monthly recurring income index. This represents the average revenue per user index. This represents the paid user conversion rate index. Represents the weight coefficient and The Furthermore, the higher the value, the better the business performance.

[0075] Among them, monthly recurring revenue refers to the stable monthly revenue obtained through subscription services, which can be realized by using periodic subscription revenue data recorded by the financial system, and is used to reflect the sustainability of the system's business model. Paid user conversion rate refers to the proportion of free users who become paying users, which can be calculated by using user account status change records and the total number of registered users, and is used to measure user willingness to pay and business conversion efficiency. Average revenue per user refers to the average revenue obtained from each user within a specific period, which can be calculated by dividing total revenue by the number of active users, and is used to assess the value contribution of a single user. Max-min normalization refers to linearly mapping the original data to the 0-1 interval, used to eliminate the incomparability of indicators with different dimensions. Weighted summation model refers to linearly combining the normalized indicators according to preset weights, which can be implemented using... The formula is implemented in which the weight coefficients can be dynamically adjusted according to the business strategy to determine the importance of each indicator. Specifically, a preset fixed value can be used or the value can be dynamically adjusted based on historical data.

[0076] Specifically, this method constructs a multi-dimensional evaluation system through three core indicators: monthly recurring revenue reflects revenue stability, paying user conversion rate reflects user willingness to pay, and average revenue per user represents the value contribution of a single user. First, normalization eliminates the dimensional differences among revenue scale, conversion rate, and user value, making them comparable. Then, a weighted summation model integrates the processed indicators into a unified coefficient, with the weighting coefficient dynamically adjusted according to different business stages. For example, during the user growth stage, the weight of paying user conversion rate can be increased, while during the revenue optimization stage, the focus can be on average revenue per user. This coefficient dynamically reflects the system's business performance, providing a quantitative basis for subsequent resource allocation, thereby solving the problem of the single and static dimensions of traditional system business value assessment.

[0077] Through the above technical solution, this application achieves dynamic quantitative evaluation of business conversion status, solving the problem of mismatch between traditional system resource allocation and business value growth needs. By monitoring core business indicators in real time and generating dynamic coefficients, the system can automatically adjust storage resource allocation strategies based on current business performance. For example, when the business conversion status coefficient is high, priority is given to ensuring the resource needs of high-value users, and when the coefficient is low, cost control strategies are optimized, thereby improving resource utilization efficiency and business value conversion effectiveness.

[0078] Preferably, the propagation state analysis module includes the following functions:

[0079] Acquire new user registrations (the number of unique new users registering each week), new event creations (the number of new events created by the organizer each month), and social media shares (the number of times users share images to social media through the system each day).

[0080] The number of new user registrations, the number of new event creations, and the number of social media shares are processed by max-min normalization to obtain the new user registration index, the new event creation index, and the number of shares index.

[0081] A growth and propagation state model is constructed based on the new user registration index, new activity creation index, and sharing frequency index to obtain growth and propagation state coefficients. The growth and propagation state model is expressed as follows:

[0082]

[0083] in, Represents the growth and propagation state coefficients. This indicates the new user registration index. Indicates the index of new activity creation. The index represents the number of times a message is shared. Furthermore, the higher the value, the better the transmissibility.

[0084] Among these metrics, new user registrations refer to the number of unique users registering each week, which can be achieved using user registration log statistics to quantify user growth. New activity creations refer to the number of new activities created by the organizer each month, which can be statistically analyzed through the activity management backend to reflect business expansion capabilities. Social media sharing counts refer to the daily number of times users share images to social media platforms through the system, which can be obtained by scraping sharing data from third-party platforms via API interfaces to measure content dissemination effectiveness. Max-min normalization maps the original data to the 0-1 range, which can be achieved using linear transformation formulas to eliminate the influence of different dimensions, making cross-period data comparable. The exponential decay function in the growth and propagation state model refers to the fusion of multi-dimensional indices through nonlinear operations, which can be achieved using natural exponential functions to realize the saturation effect after data superposition, strengthening the abrupt response of key indicators.

[0085] Specifically, the process begins by collecting raw data across three dimensions: user growth, business expansion, and dissemination effectiveness. This includes metrics such as weekly new user registrations, monthly new activity creations, and daily social media shares. Further, the raw data from different periods is converted into standardized indices using max-min normalization. For example, dividing the weekly registration count by the historical highest weekly registration count yields the new user registration index. These three indices are then fed into an exponential decay function for fusion calculation. When any index increases significantly, the function's output value rapidly approaches 1. For instance, when the share count index surges, the G value exhibits non-linear growth. The resulting growth and dissemination state coefficients can sensitively reflect changes in the dissemination trend, providing a quantitative basis for subsequent resource optimization.

[0086] Through the above technical solution, this application achieves dynamic quantitative evaluation of business dissemination status, solving the problem that existing systems cannot comprehensively perceive user growth and dissemination effects. Specifically, it can promptly detect sudden changes in the dissemination trend; for example, when the number of social media shares surges, the system can quickly identify and trigger incremental image optimization strategies. Simultaneously, by eliminating the influence of different units of measurement and statistical periods, the objectivity and comparability of the evaluation results are ensured, providing a reliable basis for resource allocation decisions.

[0087] Preferably, the performance analysis module's functions include:

[0088] Get user engagement status coefficient, business conversion status coefficient, total image storage (the total size of all images and videos currently stored in the system), average image upload time (the average time from when a user selects an image to when the upload is completed), and average system response time (the average time it takes for the system to return results after a user operation (such as searching or filtering).

[0089] The image storage index is obtained by comparing the total image storage size with the maximum allowed image storage size.

[0090] The average image upload time and the average system response time are subjected to max-min normalization to obtain the image upload time index and the response time index.

[0091] A business requirement model is constructed based on user engagement status coefficients and business conversion status coefficients to obtain business requirement coefficients. The business requirement model is expressed as follows:

[0092]

[0093] in, Indicates the business demand coefficient. Indicates the user participation status coefficient. Indicates the business conversion status coefficient. Indicates the elasticity coefficient of user participation and , Indicates the elasticity coefficient of business conversion and The The Furthermore, the larger the value, the greater the business demand;

[0094] An upload-response adaptation model is constructed based on the business demand coefficient, image upload time index, and response time index under the image storage index, and the upload-response adaptation degree is obtained. The upload-response adaptation model is expressed as follows:

[0095]

[0096] in, Indicates upload-response adaptation. Indicates the business demand coefficient. This indicates the storage load impact factor. This indicates the image upload time index. This represents the response time index. Represents the weight coefficient and The Furthermore, the larger the value, the better the system performance matches business needs.

[0097] Among them, the business demand coefficient refers to the weighted combination of user participation status and business conversion status, which can be implemented using an exponential weighted model. The user participation elasticity coefficient and business conversion elasticity coefficient are used to balance the contribution weights of user activity and business value. These coefficients can be preset fixed values ​​or dynamically adjusted based on historical data. The image storage index is a quantitative indicator of current storage resource occupancy, calculated as the ratio of total storage to maximum allowed storage, reflecting the impact of storage pressure on system performance. Maximum-minimum normalization is a standardization method that linearly maps raw data to the 0-1 range, implemented using the range method to eliminate interference from different units on upload and response time metrics. Upload-response adaptability refers to the degree of matching between system performance and business needs, calculated using a combination formula of the business demand coefficient, storage load, and performance index. A dynamic evaluation mechanism is formed by strengthening business demand-driven metrics at the numerator and suppressing the impact of storage load at the denominator. The weighting coefficients can be preset fixed values ​​or dynamically adjusted based on historical data.

[0098] Specifically, user engagement and business conversion coefficients are input into the business demand model for fusion calculation. The contribution ratio of these two coefficients is dynamically adjusted using elasticity coefficient constraints to generate a demand coefficient reflecting real-time business intensity. Total image storage is converted into a storage index to quantify storage resource utilization. Average upload time and response time are normalized to form standardized performance evaluation parameters. The business demand coefficient, storage index, and performance index are input into the upload-response adaptation model. This model, through a synergistic mechanism between the numerator and denominator, positively increases adaptation when business demand increases and negatively suppresses adaptation when storage load or performance deteriorates. Finally, it outputs a quantified adaptation coefficient as a basis for system optimization.

[0099] Through the above technical solution, this application solves the problem of rigid resource allocation caused by the lack of a business demand and performance correlation model in existing systems. It can dynamically adjust the system resource allocation strategy according to changes in user participation and fluctuations in business value, avoid upload delays or slow response caused by a surge in business demand, and prevent resource redundancy and waste during low business cycles, effectively maintaining a dynamic balance between system performance and business development.

[0100] Preferably, the image incremental optimization model is expressed as:

[0101]

[0102] in, This indicates the target number of newly added images per day. This indicates the number of newly added images per day. Represents the growth and propagation state coefficients. This represents the upload-response adaptation coefficient. Indicates the adjustment rate. This represents the fit threshold.

[0103] The target daily new image count refers to the expected increase in images calculated by the model, which can be implemented using a dynamic feedback algorithm to adjust resource allocation based on the real-time system status. The current daily new image count refers to the actual increase in images processed by the system, which can be obtained in real-time through the data acquisition module and used as an adjustment benchmark. The growth and propagation status coefficient is a quantitative indicator reflecting the user growth rate and content propagation efficiency, used to measure business expansion potential. The upload-response adaptation coefficient is a parameter characterizing the degree of matching between system performance and business needs, used to assess system capacity. The adjustment rate is a factor controlling the magnitude of incremental changes, which can be a preset fixed value or dynamically adjusted based on historical data to balance adjustment sensitivity and stability. The adaptation threshold is the critical value for determining whether system performance meets business needs, which can be set according to the system's maximum load capacity and used to trigger the incremental adjustment mechanism.

[0104] Specifically, this model uses the current daily number of newly added images as a benchmark, combines growth and propagation state coefficients to reflect business expansion trends, and evaluates the matching degree between the system's current performance and business needs through the upload-response adaptation coefficient. When the upload-response adaptation coefficient is higher than the adaptation threshold, it indicates that the system has redundant performance, and the model positively expands the target incremental scale by adjusting the rate; when the adaptation coefficient is lower than the threshold, it negatively inhibits incremental expansion to prevent system overload. The adjustment rate is used to control the magnitude of incremental changes, avoiding drastic fluctuations in the target value due to coefficient fluctuations. This model achieves closed-loop control between business needs and system performance through dynamic adjustment factors, ensuring that resource allocation matches real-time status.

[0105] Through the above technical solution, this application solves the problems of resource waste or performance overload caused by traditional fixed strategies. By dynamically balancing business expansion needs and system performance limitations, it achieves intelligent adjustment of the incremental scale of images, ensuring that the system maintains a stable response speed under high load, while fully utilizing redundant resources to improve business processing capabilities under low load. This model optimizes resource allocation efficiency through a closed-loop feedback mechanism, avoids performance bottlenecks caused by business fluctuations, and improves user experience and system reliability.

[0106] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0107] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An online management system for exhibition pictures, characterized in that, Comprise: User behavior analysis module, based on the number of daily active users, average session length, average page views per user to build user engagement state model output user engagement state coefficient; Commercial value analysis module, based on the monthly recurring revenue, conversion rate of paying users and average revenue per user to build business conversion state model output business conversion state coefficient; Spread state analysis module, based on the number of new user registration, the number of new activity creation and the number of social media sharing times to build growth and spread state model output growth and spread state coefficient; Performance analysis module, based on the user engagement state coefficient, business conversion state coefficient and the average picture upload time under the total picture storage and the system average response time to build upload-response adaptation model output upload-response adaptation coefficient; Picture increment optimization module, based on the growth and spread state coefficient, upload-response adaptation coefficient and the current daily new picture quantity to build picture increment optimization model output target daily new picture quantity.

2. The online management system for exhibition pictures and videos according to claim 1, characterized in that, The picture increment optimization model is expressed as: ; wherein, represents the target daily new picture quantity, represents the current daily new picture quantity, represents the growth and spread state coefficient, represents the upload-response adaptation coefficient, represents the adjustment rate, represents the adaptation threshold.

3. The online management system for exhibition pictures and videos according to claim 2, characterized in that, The working content of the performance analysis module includes: Get user engagement state coefficient, business conversion state coefficient, total picture storage, average picture upload time, system average response time; The total picture storage is compared with the maximum allowed picture storage, and the picture storage index is obtained by ratio processing; The average picture upload time and the system average response time are maximum-minimum normalized to obtain the picture upload time index and the response time index; Based on the user engagement state coefficient and the business conversion state coefficient, a business demand model is constructed to obtain a business demand coefficient, and the business demand model is expressed as: ; wherein, represents a business demand coefficient, represents a user engagement status coefficient, represents a business conversion status coefficient, represents a user engagement elasticity coefficient and , represents a business conversion elasticity coefficient and , the , the and the greater the value the greater the business demand; Based on the business demand coefficient and the picture storage index, the picture upload time index and the response time index are constructed to obtain the upload-response adaptation degree, and the upload-response adaptation model is expressed as: ; wherein, represents upload-response fitness, represents business demand coefficient, represents storage load impact factor, represents picture upload time index, represents response time index, represents weight coefficient and , the and the greater the value, the better the system performance and the fitness of the business demand.

4. The online management system for exhibition pictures and videos according to claim 3, characterized in that, The working content of the spread state analysis module includes: Get the number of new user registration, the number of new activity creation and the number of social media sharing times; The number of new user registration, the number of new activity creation and the number of social media sharing times are maximum-minimum normalized to obtain the new user registration index, the new activity creation index and the sharing times index; Based on the new user registration index, the new activity creation index and the sharing times index, a growth and spread state model is constructed to obtain a growth and spread state coefficient, and the growth and spread state model is expressed as: ; wherein, represents the growth and propagation state coefficient, represents the new user registration index, represents the new activity creation index, represents the sharing times index, said and the greater the value the better the propagation.

5. The online management system for exhibition pictures and videos according to claim 3, characterized in that, The working content of the commercial value analysis module includes: Get the monthly recurring revenue, conversion rate of paying users and average revenue per user; The monthly recurring revenue, conversion rate of paying users and average revenue per user are maximum-minimum normalized to obtain the monthly recurring revenue index, average revenue per user index and conversion rate of paying users index; Based on the monthly recurring revenue index, average revenue per user index and conversion rate of paying users index, a business conversion state model is constructed to obtain a business conversion state coefficient, and the business conversion state model is expressed as: ; wherein, represents a business conversion status coefficient, represents a monthly recurring revenue index, represents an average revenue per user index, represents a paying user conversion rate index, represents a weight coefficient and , the and the greater the value the better the business performance.

6. The online management system for exhibition pictures and videos according to claim 3, characterized in that, The working content of the user behavior analysis module includes: Get the number of daily active users, average session length, average page views per user; The daily active user number, the average session duration, and the average page browsing amount per user are maximum-minimum normalized to obtain an active user index, a session duration index, and a browsing amount index; A user participation state model is constructed based on the active user index, the session duration index, and the browsing amount index to obtain a user participation state coefficient, and the user participation state model is represented as: ; wherein, represents a user engagement status coefficient, represents an active user index, represents a conversation length index, represents a browsing volume index, represents a weight coefficient and , the and the greater the value the better the user group engagement status.

7. The online management system for exhibition pictures and videos according to claim 4, characterized in that, The new user registration number refers to the number of newly registered independent users per week, which can be specifically implemented by using a user registration log statistical method, is used to quantify the user growth scale, the new activity creation number refers to the number of new activities created by the host per month, which can be specifically counted by creating records in the activity management background, and is used to reflect the business expansion capability, the social media sharing number refers to the daily number of times that a user shares a picture to a social media through the system, which can be specifically obtained by API interface grabbing third-party platform sharing data, and is used to measure the content dissemination effect.

8. The online management system for exhibition pictures and videos according to claim 5, characterized in that, The monthly regular income refers to the monthly stable income obtained through a subscription service, which can be specifically implemented by using periodic subscription income data recorded by a financial system, and is used to reflect the sustainability of the business model of the system, the paid user conversion rate refers to the proportion of free users converted into paid users, which can be specifically calculated by using user account state change records and the total number of registered users, and is used to measure the user payment willingness and business conversion efficiency, and the average income per user refers to the average income obtained from each user in a specific period, which can be specifically calculated by using total income divided by the number of active users, and is used to evaluate the value contribution of a single user.

9. The online management system for exhibition pictures and videos according to claim 6, characterized in that, The daily active user number refers to the number of users who log in to the system and perform effective operations per day, which can be specifically implemented by using a user login log statistical module, and is used to reflect the basic active scale of the user group, the average session duration refers to the average duration of a single user logging in to the system to perform operations, which can be specifically obtained by using user behavior point data, and is used to represent the depth of the user using the system, and the average page browsing amount per user refers to the average number of pages browsed by a single user in a session, which can be specifically implemented by using a page access log analysis module, and is used to measure the interaction intensity of the user and the content.

Images