View processing method for multi-mode electronic information system

Abstract

The invention relates to the technical field of image processing, in particular to a multi-modal electronic information system view processing method, which comprises the following steps of: acquiring image data, analyzing and determining data features and spatial distribution, and generating a feature positioning map; key content and background information in the image are identified and marked according to the feature positioning map, and a key content mapping map is generated; and adjusting image coding parameter setting based on the key content mapping graph. According to the method, compression of different levels is applied to key content and background information, so that the storage and transmission efficiency is optimized, and meanwhile, the most important image quality is reserved. Besides, the strategy of monitoring the network state in real time and adjusting the transmission rate and the compression rate ensures the optimization of data transmission under different network conditions, and reduces the risk of data transmission error or delay. By identifying repeated or redundant content, data stream processing is optimized, the burden of the system is reduced, and the efficiency and reliability of data processing are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a multimodal electronic information system view processing method. Background Art

[0002] Image processing is a key branch in the field of electronic information systems that focuses on manipulating digital images using algorithms. The technology involves acquiring, analyzing, processing, compressing, and reconstructing images acquired from a variety of different sources such as cameras, satellites, scanners, etc. Electronic information system view processing is used to process and optimize view or image data in electronic systems. The purpose of this processing method is to improve the representation of data, increase processing efficiency, and enhance the visual experience of the end user.

[0003] However, existing technologies are insufficient in image processing efficiency and automation. It is difficult to effectively distinguish the content of an image, which may cause key visual information to be indiscriminately compressed or lost during processing. Especially in applications that require high-quality image output, this processing not only increases the burden of storage and transmission, but also damages the use value of the image. Existing methods also show limitations in network adaptability, lacking the ability to flexibly adjust transmission parameters to adapt to real-time network status changes, which often leads to low transmission efficiency and data loss in a dynamic network environment, or causes network congestion, affecting the transmission of other devices in the LAN. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a multimodal electronic information system view processing method.

[0005] In order to achieve the above object, the present invention adopts the following technical solution, a multimodal electronic information system view processing method, comprising the following steps:

[0006] Collect image data, analyze and determine data features and spatial distribution, and generate a feature location map; identify and mark key content and background information in the image based on the feature location map, and generate a key content mapping map;

[0007] Based on the key content mapping diagram, adjusting the image encoding parameter settings, using lossless compression for the key content, and generating a key content encoding result; encoding the background information with a compression rate of more than 50% to generate an encoding optimized image;

[0008] Monitor network status in real time, collect network bandwidth and delay data, and generate a network status report; based on the network status report, adjust the data transmission rate and compression rate, and generate a transmission parameter adjustment result;

[0009] Repetitive or redundant content in the image data is identified, and the data stream is processed according to the identification result to generate a data stream optimization result.

[0010] Preferably, the step of acquiring the feature positioning map is:

[0011] Collect image data, extract data features from the image data, and analyze the shape and size of each feature to obtain preliminary data features;

[0012] Based on the preliminary data features, the spatial distribution density of each feature in the image is calculated using the following formula:

[0013]

[0014] Among them, MD represents the spatial distribution density, m represents the total number of features, and c k represents the coverage area of ​​the kth feature, p k Represents the priority weight of the kth feature;

[0015] Based on the spatial distribution density, the feature representation of the image is optimized according to the spatial distribution density to generate a feature localization map.

[0016] Preferably, the steps of obtaining the key content mapping diagram are:

[0017] Using the feature location map, analyzing key content and background information in the image, distinguishing them through edge segmentation, and marking the key content to obtain preliminary marked key content data;

[0018] Based on the preliminary marked key content data, refine the boundary and attribute of each key content, adjust the accuracy of each marked area, and obtain accurately marked key content data;

[0019] Based on the accurately marked key content data, a key content map is constructed, wherein the key content map includes the distribution of each key content and background information in the image.

[0020] Preferably, the steps of obtaining the key content encoding result are:

[0021] Receiving the key content map, analyzing the key content in the key content map, determining the image area that needs lossless compression, determining the encoding format and compression level, and obtaining the encoding parameter data for preliminary adjustment;

[0022] Based on the preliminarily adjusted encoding parameter data, refining the encoding parameter settings, optimizing the encoding process to match the fidelity requirements of key content, and obtaining optimized encoding parameter settings;

[0023] Based on the optimized encoding parameter settings, lossless compression is applied to the key content area marked in the mapping image to generate a key content encoding result.

[0024] Preferably, the steps of obtaining the coding optimized image are:

[0025] Identifying and separating background information from the key content map, analyzing the color, texture and illumination of the background part, determining the compression rate, and obtaining preliminarily separated background information data;

[0026] Based on the initially separated background information data, a compression ratio is set to obtain a compression parameter setting;

[0027] Based on the compression parameter setting, the background information is coded and compressed using the set compression rate to generate a coding optimized image.

[0028] Preferably, the steps of obtaining the network status report are:

[0029] Monitor network status, collect real-time data on network bandwidth and latency, and obtain preliminary network performance data;

[0030] Based on the preliminary network performance data, the overall health index of the network is calculated using the following formula:

[0031]

[0032] Among them, H represents the network health index, YR represents the average network delay, and B represents the average network bandwidth utilization rate;

[0033] Based on the health index, the maximum network delay time, bandwidth utilization and average transmission rate are continuously summarized to generate a network status report.

[0034] Preferably, the steps of obtaining the transmission parameter adjustment result are:

[0035] Receiving the network status report, analyzing the network maximum delay time, bandwidth utilization and average transmission rate in the network status report to obtain a current network performance overview;

[0036] Based on the current network performance profile, the data transmission rate is calculated using the following formula:

[0037]

[0038] Among them, S represents the adjusted data transmission rate, K represents the network capacity benchmark value, D represents the current network bandwidth utilization rate, and L represents the average network delay;

[0039] Based on the data transmission rate, the settings of the network device are adjusted, a new data transmission rate is implemented, and a transmission parameter adjustment result is obtained.

[0040] Preferably, the steps of obtaining the data flow optimization result are:

[0041] Identify repeated or redundant elements in image data through deep learning models and obtain a preliminary list of identified repeated content;

[0042] Based on the initially identified duplicate content list, the proportion of redundant content data to the original data is calculated using the following formula:

[0043]

[0044] Where R represents the redundancy rate of the data stream, n is the number of data blocks identified as redundant, and u i is the size of the i-th redundant data block, T is the total size of the image data;

[0045] According to the redundancy rate, determine whether it exceeds a preset threshold α. If R>α, delete all duplicate contents and compress the remaining data; if R≤α, only compress and generate a data stream optimization result.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are:

[0047] In the present invention, different levels of compression are applied to key content and background information, thereby optimizing storage and transmission efficiency while retaining the most important image quality. In addition, the strategy of real-time monitoring of network status and adjusting transmission rate and compression ratio ensures the optimization of data transmission under different network conditions and reduces the risk of data transmission errors or delays. By identifying repeated or redundant content and optimizing data flow processing, the burden on the system is reduced and the efficiency and reliability of data processing are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the steps of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] See also Figure 1 The present invention provides a technical solution, a multimodal electronic information system view processing method, comprising the following steps:

[0051] Collect image data, analyze and determine data features and spatial distribution, and generate a feature location map; based on the feature location map, identify and mark the key content and background information in the image, and generate a key content mapping map.

[0052] Based on the key content mapping diagram, the image encoding parameter settings are adjusted, and lossless compression is used for the key content to generate the key content encoding result; the background information is encoded with a compression rate of more than 50% to generate a coding optimized image.

[0053] Monitor network status in real time, collect network bandwidth and delay data, and generate network status reports; based on the network status reports, adjust data transmission rate and compression rate, and generate transmission parameter adjustment results.

[0054] Identify repeated or redundant content in image data, process the data stream based on the identification results, and generate data stream optimization results.

[0055] Specifically, different levels of compression are applied to key content and background information to optimize storage and transmission efficiency while retaining the most important image quality. In addition, the strategy of real-time monitoring of network status and adjusting transmission rate and compression ratio ensures the optimization of data transmission under different network conditions and reduces the risk of data transmission errors or delays. By identifying repeated or redundant content and optimizing data flow processing, the burden on the system is reduced and the efficiency and reliability of data processing are improved.

[0056] The steps to obtain the feature location map are:

[0057] Collect image data, extract data features from the image data, and analyze the shape and size of each feature to obtain preliminary data features;

[0058] Based on the preliminary data features, the spatial distribution density of each feature in the image is calculated using the following formula:

[0059]

[0060] Among them, MD represents the spatial distribution density, m represents the total number of features, and c k represents the coverage area of ​​the kth feature, p k Represents the priority weight of the kth feature;

[0061] Based on the spatial distribution density, the feature representation of the image is optimized according to the spatial distribution density to generate a feature localization map.

[0062] Specifically, image data is collected and analyzed, including the evaluation of the shape, size and spatial position of different features in the image through a convolutional neural network, to ensure that each feature in the extracted data features is accurately identified and effectively distinguished, and further based on these data features, feature enhancement processing is performed to enhance the visibility and distinguishability of key details in the image. This processing step includes adjusting the contrast and brightness of the image, and applying edge enhancement to optimize feature boundaries, so that the obtained preliminary data features can be more accurately used for feature positioning and analysis in subsequent processing to obtain preliminary data features.

[0063] The benefit of the formula is that, by weighted summing the coverage area and priority weight of each feature, a value that comprehensively reflects the spatial distribution density of the feature in the image can be calculated, which helps the subsequent image processing steps to encode and compress the image according to the feature density; c k The steps to obtain the parameters are to calculate the coverage area of ​​each feature, p k The steps of obtaining parameters are to assign values ​​according to the importance rating of the features;

[0064] Calculation process: There are three features, whose coverage areas are c1 = 0.5 square meters, c2 = 0.3 square meters, and c3 = 0.2 square meters, and the corresponding priority weights are p1 = 1.0, p2 = 0.8, and p3 = 0.6; insert the values ​​according to the formula for calculation:

[0065]

[0066] The result shows that the average feature spatial distribution density in the image is 0.286 square meters per feature. This density value can be used to generate feature localization maps in subsequent steps. According to this density value, the parameters of the image processing algorithm can be adjusted to optimize the visualization effect of the features.

[0067] Based on the spatial distribution density, local detail enhancement is performed on each feature, and specific filters are used to enhance the local details of the image, such as using a high-pass filter to enhance edge information, thereby obtaining a feature location map.

[0068] The steps to obtain the key content map are:

[0069] Using the feature location map, analyze the key content and background information in the image, distinguish them through edge segmentation, and mark the key content to obtain preliminary marked key content data;

[0070] Based on the initially marked key content data, refine the boundaries and attributes of each key content, adjust the accuracy of each marked area, and obtain accurately marked key content data;

[0071] Based on the precisely labeled key content data, a key content map is constructed, which includes the distribution of each key content and background information in the image.

[0072] Specifically, to identify the key content and background information in the image, first use edge detection to distinguish the boundary between the key content and the background. Edge detection relies on the gradient change of pixel brightness. The edge strength and direction determine the boundary of the content. Then, use region growing to extend these boundaries to the surrounding pixels to improve the accuracy of segmentation. A unique identifier is assigned to each identified content, and the coordinate data of its core and boundary are recorded. This method ensures the continuity and integrity of the boundary and avoids mis-segmentation by gradually optimizing the boundary recognition threshold. These operations enable the key content to be distinguished from the background information.

[0073] Using the initially marked key content data, refine the boundaries and features of each key content, mainly by adjusting the local contrast of the image to improve the visibility of the boundaries, and use dynamic threshold technology to adjust the threshold according to local image features. At the same time, analyze the color and texture differences of each area to ensure the consistency and accuracy of the distinction effect. Each area is re-marked and refined according to the uniqueness of its color and texture, thereby accurately defining the characteristics of each key area and ensuring that subsequent operations can accurately identify and use this data.

[0074] Based on the precisely marked key content data, the key content map,this map shows the distribution of various areas in the image. By applying layer overlay and transparency adjustment, the characteristics of each key area in the map, such as position, size and shape, are consistent with the original image, enhancing the visual effect and ease of use of the image. During the generation of the map.

[0075] The steps to obtain the key content encoding results are:

[0076] Receiving a key content map, analyzing key content in the key content map, determining an image area that needs lossless compression, determining an encoding format and a compression level, and obtaining encoding parameter data for preliminary adjustment;

[0077] Based on the initially adjusted encoding parameter data, the encoding parameter settings are refined, the encoding process is optimized to match the fidelity requirements of the key content, and the optimized encoding parameter settings are obtained;

[0078] Based on the optimized encoding parameter settings, lossless compression is applied to the key content area marked in the mapping image to generate the key content encoding result.

[0079] Specifically, based on the received key content map, the importance of each area in the image is identified, and the need for lossless compression is determined according to the complexity and detail of the content. The dynamic range and color depth of the image are considered to set a suitable compression algorithm and parameters for each key area. For example, a higher level of compression is used for high-detail areas to ensure that image quality is not lost, ensuring that all details visually maintain the original texture. Through this method, the image encoding parameters are adjusted, the storage and transmission efficiency of the entire image is optimized, and the preliminary adjusted encoding parameter data is obtained.

[0080] Based on the preliminarily adjusted encoding parameter data, each parameter is further adjusted, including re-evaluation of ratio, resolution and color depth.

[0081] Based on the optimized encoding parameter settings, lossless compression operations are performed. For the key content areas marked in the mapping image, lossless compression algorithms designed for image detail preservation, such as FLIF and JPEG-2000, are used. These algorithms can effectively compress image data while ensuring the integrity of key visual information, especially in the processing of color gradients and fine textures. Through this method, key content encoding results that maintain the original visual effects are generated, ensuring consistent image performance on various display devices.

[0082] The steps to obtain the encoding optimized image are:

[0083] Identify and separate background information from the key content map, analyze the color, texture and lighting of the background features, determine the compression rate, and obtain preliminary separated background information data;

[0084] Based on the initially separated background information data, a compression ratio is set to obtain compression parameter settings;

[0085] Based on the compression parameter settings, the background information is encoded and compressed using the set compression rate to generate an encoding optimized image.

[0086] Specifically, after receiving the key content map, the background and key content are first defined and the boundaries of each area are identified; then the color saturation of each area is measured, the clarity of the texture is checked, and the light intensity is evaluated; for backgrounds under different lighting conditions (such as natural light and artificial light), different processing standards are used to judge the impact in order to determine the visual importance of each background area, thereby providing a basis for the selection of the compression rate.

[0087] Based on the initially separated background information data obtained from the first step, the compression parameters of the background information are continued to be set; first, by evaluating the visual importance of each background area, the specific compression rate is determined, which includes setting a predetermined compression threshold for each area, which is determined based on color saturation and texture complexity, ensuring that important areas are compressed less to maintain details, while other areas can apply a higher compression rate.

[0088] Perform the encoding process of the background information, using the set compression rate; first apply the selected compression algorithm to the background area, pay special attention to the quality control of the compression process to ensure that the loss of details is minimized. In this process, the quantization level of the encoding algorithm is adjusted and the appropriate entropy coding technology is used to optimize the data flow, so as to achieve good data compression.

[0089] The steps to obtain the network status report are:

[0090] Monitor network status, collect real-time data on network bandwidth and latency, and obtain preliminary network performance data;

[0091] Based on the preliminary network performance data, the overall health index of the network is calculated using the following formula:

[0092]

[0093] Among them, H represents the network health index, YR represents the average network delay, and B represents the average network bandwidth utilization rate;

[0094] Based on the health index, the maximum network delay time, bandwidth utilization and average transmission rate are continuously summarized to generate a network status report.

[0095] Specifically, real-time data about network bandwidth and latency are collected. These monitoring tools are deployed at key nodes in the network to continuously monitor data traffic and response time. The collected data include the number of packets transmitted per second and the transmission delay of each packet. Through real-time analysis of these data, network congestion or data packet loss problems can be immediately discovered, and measures can be taken to adjust the measures.

[0096] The formula is useful in that it more flexibly reflects the impact of the product of bandwidth and latency on the network health index by introducing the square root. YR represents the average network latency, which is calculated by collecting network response time data within a certain period of time through monitoring tools. B represents the average network bandwidth usage, which is calculated by analyzing the ratio of the amount of data passing through the network to the total network bandwidth.

[0097] Calculation process: In the target time window, the average network delay is 100 milliseconds and the bandwidth utilization rate is 70%, that is, YR = 100 milliseconds and B = 70% = 0.7. Substituting these values ​​into the formula, we get:

[0098]

[0099] The result shows that the network health index is 0.119, which means that the network status is poor and measures need to be taken to optimize latency and bandwidth usage; between 0.2-0.4 means that the network has a certain latency and high bandwidth utilization, and some performance problems may occur, so the network status needs to be checked frequently; and less than 0.2 means that the network latency is high, the bandwidth utilization is very high, the network status is poor, and congestion and latency are often encountered.

[0100] Based on the calculated network health index, a network status report is generated, which summarizes the key performance indicators of the network, including maximum latency, bandwidth utilization, and average data transmission rate.

[0101] The steps for obtaining the transmission parameter adjustment results are:

[0102] Receive network status reports, analyze the network's highest delay time, bandwidth utilization, and average transmission rate in the network status reports, and obtain an overview of current network performance;

[0103] Based on the current network performance profile, calculate the data transmission rate using the following formula:

[0104]

[0105] Among them, S represents the adjusted data transmission rate, K represents the network capacity benchmark value, D represents the current network bandwidth utilization rate, and L represents the average network delay;

[0106] Based on the data transmission rate, the settings of the network equipment are adjusted, a new data transmission rate is implemented, and a transmission parameter adjustment result is obtained.

[0107] Specifically, identify the network's maximum delay time, minimum bandwidth utilization and average transmission rate. These indicators are obtained through network monitoring. The maximum network delay time reflects the longest time from the sending to the receiving of a data packet, which is usually used to evaluate network congestion and data fluency; the minimum bandwidth utilization indicates the lowest usage of the network bandwidth during the observation period; the average transmission rate is calculated by the ratio of the total amount of transmitted data to the total time, and is an important indicator for measuring the overall performance of the network. By analyzing these data, we can understand the real-time operating status of the network in detail, adjust strategies in time to optimize performance, and provide a basis for subsequent network maintenance and upgrades.

[0108] The benefit of the formula is that it provides a method for dynamically adjusting the data transmission rate by combining the natural logarithm of the network capacity benchmark value K with the square of the bandwidth utilization rate D and the square root of the sum of the delay L; it takes into account the joint impact of bandwidth and delay, and processes K in the form of natural logarithms, which increases the sensitivity to small changes and makes the adjustment more detailed and adaptable to changes in network status. Among them, K (network capacity benchmark value) is obtained through actual network design planning and historical maximum throughput data, and generally depends on the physical and protocol architecture of the network. D (current network bandwidth utilization) is data collected in real time, reflecting the percentage of current network traffic to the maximum theoretical traffic. L (average network delay) represents the average transmission time of data packets from source to destination.

[0109] Calculation process: K = 1000Mbps, indicating the maximum capacity or benchmark capacity of the network. D = 50%, indicating the current bandwidth utilization. L = 100ms, indicating the average delay time.

[0110] First, convert D to the same magnitude as L for the sum of squares; this requires adjustment because D is expressed as a percentage and should be calculated in its actual numerical form:

[0111] D = 50% × 1000Mbps = 500Mbps

[0112] Substituting into the formula:

[0113]

[0114] Get the adjustment factor of the data transmission rate.

[0115] Apply this data rate scaling factor to the base bandwidth:

[0116] Adjusted Transmission Rate=S×K=0.0138×1000Mbps=13.8Mbps

[0117] Therefore, the adjusted data transmission rate is 13.8Mbps, which means that under the current network conditions, in order to maintain the performance of the network and take into account the delay and bandwidth utilization, the transmission rate of the image data should be adjusted to 13.8Mbps to avoid a significant impact on the network. This adjustment helps to optimize network traffic and manage network congestion.

[0118] After determining the data transmission rate, gradually perform configuration adjustments on network devices, determine network traffic management strategies by analyzing the data transmission rate, and apply the settings to actual network operations to ensure that the network can operate efficiently at the new transmission rate, reduce packet latency, and enhance network responsiveness and data processing efficiency. The final adjustment results will optimize the performance of the entire network, ensure the continuity and stability of network services, and provide support for maintaining a healthy network and improving user experience.

[0119] The steps to obtain data flow optimization results are as follows:

[0120] Identify repeated or redundant elements in image data through deep learning models and obtain a preliminary list of identified repeated content;

[0121] Based on the initially identified duplicate content list, calculate the proportion of redundant content data to the original data using the following formula:

[0122]

[0123] Where R represents the redundancy rate of the data stream, n is the number of data blocks identified as redundant, and u i is the size of the i-th redundant data block, T is the total size of the image data;

[0124] According to the redundancy rate, determine whether it exceeds the preset threshold α. If R>α, delete all duplicate content and compress the remaining data; if R≤α, only compress it to generate data flow optimization results.

[0125] Specifically, the entire image dataset is scanned, and a deep learning algorithm is used to identify patterns and structures in the image, distinguish between unique and repeated elements in the image, encode the features of each image element, and compare these codes to determine which ones are repeated. This process involves calculating the hash value of each image element and using a hash table to quickly identify duplicate content, reducing unnecessary storage and processing.

[0126] The benefit of the formula is that it provides an intuitive method to quantify the proportion of redundant content in the entire data set, which can guide subsequent data compression or deletion decisions and make data storage more efficient. The size of each data block u i and the total data size T are extracted from the metadata of the image file. For example, if an image dataset consists of 5 identical images, each with a size of 200KB, then u i =200KB, n=5, T=1000KB, the redundancy rate is calculated as: This result shows that since all images are completely repeated, the redundancy rate of the entire dataset reaches the maximum, which means that 4 duplicate images can be deleted and only one original image can be retained, thereby significantly reducing storage requirements.

[0127] Based on the redundancy calculation results, if the redundancy rate R exceeds the preset threshold α, for example, α is set to 0.3, it means that if more than 30% of the content in the data is redundant, all identified duplicate content will be deleted and the remaining data will be compressed. This process uses JPEG or PNG compression to lossily compress the image data. The compressed data will be repackaged and stored, thereby improving the efficiency of data transmission and reducing storage costs.

[0128] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A multimodal electronic information system view processing method, characterized in that: The following steps are involved: Collect image data, analyze and determine data features and spatial distribution, and generate feature location maps; According to the feature location map, identifying and marking key content and background information in the image to generate a key content mapping map; Based on the key content mapping diagram, adjusting the image encoding parameter settings, applying lossless compression to the key content, and generating a key content encoding result; The background information is encoded with a compression rate of more than 50% to generate an encoding optimized image; Monitor network status in real time, collect network bandwidth and delay data, and generate a network status report; based on the network status report, adjust the data transmission rate and compression rate, and generate a transmission parameter adjustment result; Repetitive or redundant content in the image data is identified, and the data stream is processed according to the identification result to generate a data stream optimization result.

2. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps of obtaining the feature positioning map are as follows: Collect image data, extract data features from the image data, and analyze the shape and size of each feature to obtain preliminary data features; Based on the preliminary data features, the spatial distribution density of each feature in the image is calculated using the following formula: Among them, MD represents the spatial distribution density, m represents the total number of features, and c k represents the coverage area of ​​the kth feature, p k Represents the priority weight of the kth feature; Based on the spatial distribution density, the feature representation of the image is optimized according to the spatial distribution density to generate a feature localization map.

3. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps for obtaining the key content map are: Using the feature location map, analyzing key content and background information in the image, distinguishing them through edge segmentation, and marking the key content to obtain preliminary marked key content data; Based on the preliminary marked key content data, refine the boundary and attribute of each key content, adjust the accuracy of each marked area, and obtain accurately marked key content data; Based on the accurately marked key content data, a key content map is constructed, wherein the key content map includes the distribution of each key content and background information in the image.

4. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps for obtaining the key content encoding result are: Receiving the key content map, analyzing the key content in the key content map, determining the image area that needs lossless compression, determining the encoding format and compression level, and obtaining the encoding parameter data for preliminary adjustment; Based on the preliminarily adjusted encoding parameter data, refining the encoding parameter settings, optimizing the encoding process to match the fidelity requirements of key content, and obtaining optimized encoding parameter settings; Based on the optimized encoding parameter settings, lossless compression is applied to the key content area marked in the mapping image to generate a key content encoding result.

5. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps of obtaining the coding optimized image are: Identifying and separating background information from the key content map, analyzing the color, texture and illumination of the background part, determining the compression rate, and obtaining preliminarily separated background information data; Based on the initially separated background information data, a compression ratio is set to obtain a compression parameter setting; Based on the compression parameter setting, the background information is coded and compressed using the set compression rate to generate a coding optimized image.

6. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps of obtaining the network status report are: Monitor network status, collect real-time data on network bandwidth and latency, and obtain preliminary network performance data; Based on the preliminary network performance data, the overall health index of the network is calculated using the following formula: Among them, H represents the network health index, YR represents the average network delay, and B represents the average network bandwidth utilization rate; Based on the health index, the maximum network delay time, bandwidth utilization and average transmission rate are continuously summarized to generate a network status report.

7. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps of obtaining the transmission parameter adjustment result are: Receiving the network status report, analyzing the network maximum delay time, bandwidth utilization and average transmission rate in the network status report to obtain a current network performance overview; Based on the current network performance profile, the data transmission rate is calculated using the following formula: Among them, S represents the adjusted data transmission rate, K represents the network capacity benchmark value, D represents the current network bandwidth utilization rate, and L represents the average network delay; Based on the data transmission rate, the settings of the network device are adjusted, a new data transmission rate is implemented, and a transmission parameter adjustment result is obtained.

8. The multimodal electronic information system view processing method according to claim 1, characterized in that: The steps for obtaining the data flow optimization result are: Identify repeated or redundant elements in image data through deep learning models and obtain a preliminary list of identified repeated content; Based on the initially identified duplicate content list, the proportion of redundant content data to the original data is calculated using the following formula: Where R represents the redundancy rate of the data stream, n is the number of data blocks identified as redundant, and u i is the size of the i-th redundant data block, T is the total size of the image data; According to the redundancy rate, determine whether it exceeds a preset threshold α. If R>α, delete all duplicate contents and compress the remaining data; if R≤α, only compress and generate a data stream optimization result.

Images