Picture loading method and device based on self-service terminal and electronic equipment

Abstract

The invention discloses a picture loading method and device based on a self-service terminal and electronic equipment, and relates to the field of financial science and technology. The method comprises the steps of obtaining a target service type to which a to-be-processed picture belongs; determining the business importance degree of the to-be-processed picture according to the historical behavior data, the page type and the page area of the to-be-processed picture; based on the visual proximity, the function relevance and the data relevance, determining the coupling degree between the pictures; based on the target service type, grading according to the picture size, the picture quality, the service importance degree and the coupling degree between the pictures of the to-be-processed picture to obtain a picture level; and determining a loading strategy of the to-be-processed picture according to the target service type and the picture level, and executing picture loading. According to the technical scheme, the picture loading efficiency and quality are improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly to the field of financial technology, specifically to a method, apparatus, and electronic device for loading images based on a self-service terminal. Background Technology

[0002] In self-service terminal transaction scenarios, users often encounter experience problems caused by abnormal image loading. One type occurs during the transaction interface initialization phase, where lightweight elements such as text have been rendered, but some large images, due to excessive transmission time, result in prolonged blank periods or incomplete loading in certain areas (such as incomplete content in logo images). Another type involves advertising images inserted during the waiting period in the transaction process; when a large number of concurrently loaded images are displayed, the combined effect of delayed loading strategies and network bandwidth limitations leads to interface lag, layout flickering, or operation interruption.

[0003] How to load images from self-service terminals has become a critical issue that urgently needs to be addressed in the industry. Summary of the Invention

[0004] This application provides an image loading method, apparatus, and electronic device based on a self-service terminal to improve the efficiency and quality of image loading.

[0005] In a first aspect, embodiments of this application provide an image loading method based on a self-service terminal, comprising:

[0006] Obtain the target business type of the image to be processed;

[0007] The business importance of the image to be processed is determined based on its historical behavior data, page type, and page region.

[0008] The coupling degree between images is determined based on visual proximity, functional correlation, and data correlation.

[0009] Based on the target business type, the images to be processed are classified according to their size, quality, importance of the business, and coupling between the images to obtain the image level.

[0010] The loading strategy for the image to be processed is determined based on the target business type and the image level, and the image loading is then executed.

[0011] Secondly, embodiments of this application also provide an image loading device based on a self-service terminal, comprising:

[0012] The business type acquisition module is used to obtain the target business type to which the image to be processed belongs;

[0013] The business importance module is used to determine the business importance of the image to be processed based on its historical behavior data, page type, and page area.

[0014] The coupling module is used to determine the coupling degree between images based on visual proximity, functional correlation, and data correlation.

[0015] The image grading module is used to grade the images to be processed based on the target business type, according to the image size, image quality, business importance, and coupling degree between the images, to obtain the image level;

[0016] The image loading module is used to determine the loading strategy of the image to be processed based on the target business type and the image level, and then execute the image loading.

[0017] Thirdly, embodiments of this application also provide an electronic device, which includes:

[0018] One or more processors;

[0019] Storage device for storing one or more programs;

[0020] When one or more programs are executed by one or more processors, the one or more processors implement any of the image loading methods based on self-service terminals provided in the embodiments of this application.

[0021] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the image loading methods based on a self-service terminal provided in embodiments of this application.

[0022] Fifthly, embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements any of the image loading methods based on a self-service terminal provided in embodiments of this application.

[0023] The technical solution of this application determines the target business type of the image to be processed, and combines the optimization objectives of the target business type to classify the images according to key factors such as image size, image quality, business importance, and coupling between images, thereby obtaining a precise image level. Combining the target business type and the image level, a differentiated loading strategy is adopted for image loading processing, which can effectively improve the efficiency and quality of image loading and optimize the overall performance of the self-service terminal. Attached Figure Description

[0024] Figure 1 This is a flowchart of an image loading method based on a self-service terminal according to Embodiment 1 of this application;

[0025] Figure 2 This is a flowchart of another image loading method based on a self-service terminal provided according to Embodiment 2 of this application;

[0026] Figure 3 This is a schematic diagram of the structure of an image loading device based on a self-service terminal according to Embodiment 3 of this application;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the image loading method based on a self-service terminal according to the embodiments of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart of an image loading method based on a self-service terminal according to Embodiment 1 of this application. This embodiment is applicable to situations involving multi-dimensional feature fusion and dynamic hierarchical loading optimization of images in self-service terminals. It can be executed by an image loading device based on the self-service terminal, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S101. Obtain the target business type of the image to be processed;

[0033] S102. Determine the business importance of the image to be processed based on its historical behavior data, page type, and page area.

[0034] S103. Determine the coupling degree between images based on visual proximity, functional correlation, and data correlation;

[0035] S104. Based on the target service type, classify the images to be processed according to their size, quality, service importance, and coupling between the images to obtain image levels;

[0036] S105. Determine the loading strategy for the image to be processed based on the target service type and the image level, and execute image loading.

[0037] In self-service terminal image loading scenarios, based on the core functional attributes of the images to be processed, differences in user attention, and their impact on the operation process, images are categorized into business types, and core optimization objectives are preset for each type. The first type is transaction data images, including transaction vouchers, business reports, and other images carrying core business information, which attract high user attention (directly affecting users' judgment of the authenticity of transactions). The optimization objective for the loading process is to ensure image rendering quality and data accuracy. The second type is densely displayed images, including multi-element aggregation images such as advertising slots, function menus, and card displays, which attract moderate user attention (affecting user operation path selection). The optimization objective is to ensure the smoothness of concurrent loading of multiple images. The third type is high-frequency, low-attention images, including interface decorative elements, background images, and other non-functional images, which attract low user attention (only affecting the continuity of visual experience). The optimization objective is to minimize memory and storage space usage. By determining the target business type of the images to be processed in the self-service terminal and setting differentiated optimization objectives for each business type, a basis can be provided for determining subsequent dynamic loading strategies, thereby achieving precise control of resource allocation and ultimately improving the overall image loading performance of the self-service terminal.

[0038] The historical behavior data of the image to be processed includes key information such as historical operation logs and event tracking data generated by users in relation to the image, which can characterize the interaction features between users and the image. The page type where the image to be processed is located is determined based on the specific business function of the page, such as a transfer confirmation page, an advertising carousel page, or an account query page, which have significant business attributes. The page area where the image to be processed is located refers to the specific layout position of the image within its page, such as the main operation area, sidebar area, or notification area. By combining the historical behavior data, page type, and page area of ​​the image to be processed, the business importance of the image can be accurately determined, thus making the business importance a crucial basis for dynamically determining the image loading strategy.

[0039] Visual proximity characterizes the visual positional relationship between the image to be processed and other images in the page layout; functional relevance characterizes whether the image to be processed and other images are associated with the same business function, such as whether the image to be processed needs to be used simultaneously with other images in the process of implementing the business function; data relevance characterizes whether the image to be processed and other images depend on the same data source. By combining these three factors—visual proximity, functional relevance, and data relevance—the coupling degree between the image to be processed and other images can be determined, thus allowing the coupling degree between images to serve as the basis for dynamically determining image loading strategies.

[0040] The image size and quality of the images to be processed are also determined. Image size can be directly obtained by parsing its binary header information, in KB; image quality can be determined based on the corresponding image resolution, color depth, and compression distortion rate. Since the optimization goals of different business types vary, image levels are determined based on the target business type, according to its corresponding optimization goals, combined with the image size, image quality, business importance, and inter-image coupling. Because the optimization goals of different business types are different, the grading strategies adopted are also different. During the grading process, the roles of image size, image quality, business importance, and inter-image coupling also differ. For example, transaction data graphs focus more on image quality, so image size and image quality have a more significant impact on the grading of transaction data graphs; dense display graphs have relatively lower requirements for image quality and focus more on the smoothness of concurrent image loading, so image size and inter-image coupling are more critical in grading; the optimization goal of high-frequency, low-interest graphs is to minimize memory and storage space usage, so business importance plays a dominant role in grading. Through the above grading operations, image levels matching the target business type are obtained, thereby improving the accuracy and applicability of the image grading results.

[0041] The loading strategy for images to be processed is dynamically determined based on the target business type and image level, ensuring that the determined loading strategy varies depending on the target business type or image level. Loading strategies can include various types such as preloading and lazy loading, and can dynamically adjust the loading parameters used by the loading technology according to actual needs, thereby employing an adaptive dynamic loading strategy to perform image loading processing. By determining the target business type of the images to be processed, and combining the optimization goals of the target business type, the images are classified according to key factors such as image size, image quality, business importance, and inter-image coupling, resulting in a precise image level. By combining the target business type and image level, and adopting differentiated loading strategies for image loading processing, the efficiency and quality of image loading can be effectively improved, optimizing the overall performance of the self-service terminal.

[0042] The technical solution of this embodiment determines the target business type of the image to be processed, and combines the optimization objectives of the target business type to classify the images according to key factors such as image size, image quality, business importance, and coupling between images, thereby obtaining accurate image levels. By combining the target business type and image levels, a differentiated loading strategy is adopted for image loading processing, which can effectively improve the efficiency and quality of image loading and optimize the overall performance of the self-service terminal.

[0043] In one optional implementation, determining the loading strategy for the image to be processed based on the target service type and the image level, and then executing image loading, includes: selecting a target loading technology from candidate loading technologies based on the target service type and the image level, and obtaining parameters of the target loading technology; determining the values ​​of the parameters based on the network status and terminal performance of the self-service terminal to form a target loading strategy; and executing the target loading strategy to load the image to be processed.

[0044] The target business type determines the general direction of the loading strategy: transaction data graphs prioritize clear and accurate data presentation, with image quality taking precedence; densely displayed graphs require rapid display of large amounts of image content, prioritizing loading speed; and high-frequency, low-attention graphs, while frequently used, receive little user attention, requiring resource conservation as the priority. Image level affects priority and resource allocation, with priority decreasing sequentially from first to fourth level. Different resources can be allocated based on image level, with higher-priority images receiving more computing resources and bandwidth to ensure better loading performance. Contextual information such as network status and terminal performance of the self-service terminal can be dynamically collected to dynamically adjust loading strategy parameters, achieving optimal loading results in different environments. Network status is categorized as strong, weak, or offline; terminal performance is determined by CPU utilization and memory usage, categorized as high-performance or low-performance.

[0045] The transaction data graph loading strategy is as follows: Level 1: Lossless compression, network image formats, full caching of pre-loaded content delivery network (CDN), and scalable vector graphics degradation. In high-performance terminals and strong network environments, this scheme can fully utilize terminal computing power and network bandwidth to ensure lossless image quality and rapid loading. If terminal performance is low or in a weak network environment, the scope of the full CDN cache can be adjusted appropriately, prioritizing caching of critical data to reduce data transmission volume. Simultaneously, the algorithm complexity of lossless compression can be dynamically adjusted based on network conditions to balance loading speed and quality. Level 2: Lossy compression combined with on-demand loading, partial caching, and delayed loading. In strong networks and high-performance terminals, the lossy compression ratio can be set lower to ensure image quality, the on-demand loading range can be appropriately expanded, and the delayed loading interval can be shortened. In weak networks or low-performance terminals, the lossy compression ratio is increased, the data volume is reduced, the on-demand loading range is narrowed, and the delayed loading interval is extended to adapt to network and terminal limitations. Level 3: Lossy compression combined with delayed loading, responsive cropping, and placeholders. Under high-performance terminals and strong network conditions, the precision of responsive cropping can be set higher, and the display of placeholders can be richer. If the terminal performance is poor or the network is weak, the precision of responsive cropping should be reduced, the display of placeholders simplified, and priority given to ensuring fast image loading. The fourth level uses deep compression combined with interactive preview image loading. Under good network and terminal conditions, deep compression can maximize the compression ratio while maintaining a certain level of recognizability, and the clarity of the preview image can also be appropriately improved. In harsh environments, the deep compression ratio is further increased, the preview image quality is reduced, and the amount of data transmitted is decreased.

[0046] The dense image loading strategy is as follows: Level 1: Sprite sheet image composition, prefetch progressive loading, and sharpness optimization. With strong networks and high-performance terminals, sprite sheet image composition can include more details, prefetch progressive loading can proceed faster, and sharpness optimization can be more advanced. With weak networks or low-performance terminals, the number of details in the sprite sheet image composition is reduced, the prefetch progressive loading speed is slowed down, and the degree of sharpness optimization is reduced to lower resource and network requirements. Level 2: Progressive loading of network image formats, on-demand cropping, and cache control. With strong networks and high-performance terminals, the on-demand cropping range can be more flexible, and the cache control time can be shorter to achieve faster image updates and display. With weak networks or low-performance terminals, the on-demand cropping range is limited, and the cache control time is extended to reduce data interaction and processing. Level 3: Delayed loading and compressed 64-bit placeholders. With high-performance terminals and strong networks, the delayed loading time can be set shorter, and the compression rate of the 64-bit placeholders can be lower to ensure the placeholder display effect. When terminal performance is poor or network is weak, extend the lazy loading time, increase the compression ratio of the 64 placeholders in the base, and reduce memory usage and data transmission. At the fourth level, use a cascading stylesheet alternative for minimalist compression and lazy loading. Under good conditions, minimalist compression can perform moderate compression while maintaining basic display quality, and the lazy loading interval can be shorter. Under adverse conditions, increase the intensity of minimalist compression and extend the lazy loading interval.

[0047] The high-frequency, low-interest image loading strategy is as follows: Level 1: Intelligent pre-downloading, deep compression of local caching, and update detection. With strong networks and high-performance terminals, the scope of intelligent pre-downloading can be wider, the update frequency of deep compression of local caching can be higher, and the update detection interval can be shorter. With weak networks or low-performance terminals, the scope of intelligent pre-downloading is reduced, the update frequency of local caching is decreased, the update detection interval is extended, and resource consumption is reduced. Level 2: Scalable vector graphics icon library and on-demand loading of component-level caching. With strong networks and high-performance terminals, the richness of the scalable vector graphics icon library can be higher, and the scope of on-demand loading of component-level caching can be larger. With weak networks or low-performance terminals, the icon library is simplified, and the scope of component-level caching is reduced. Level 3: Cascading style sheet generation and lazy loading of low-resolution placeholders. With high-performance terminals and strong networks, the complexity of cascading style sheet generation can be appropriately increased, and the display effect of low-resolution placeholders can be better. With poor terminal performance or weak network, cascading style sheet generation is simplified, and the quality of low-resolution placeholders is reduced. Level 4: Pure cascading style sheets are used to completely remove image resources. This approach is less affected by the terminal status, but it can better render the effects of pure cascading stylesheets on high-performance terminals and load related stylesheet files faster when the network is good.

[0048] Based on the network status and terminal performance of the self-service terminal, the values ​​of the parameters in the corresponding loading strategy are determined in the manner described above, such as compression rate, loading time interval, cache range, etc., thereby forming the target loading strategy and executing the strategy to load the image to be processed.

[0049] Example 2

[0050] Figure 2 This is a flowchart of another image loading method based on a self-service terminal according to Embodiment 2 of this application. The technical solution of this embodiment is further refined based on the above technical solution. See also Figure 2 The image loading method shown is based on a self-service terminal and includes:

[0051] S201. Obtain the target business type of the image to be processed;

[0052] S202. Determine the business importance of the image to be processed based on its historical behavior data, page type, and page region.

[0053] S203. Determine the coupling degree between images based on visual proximity, functional correlation, and data correlation;

[0054] S204. Match the target service type with the preset association relationship between candidate service types and candidate weight combinations to obtain the target weight combination associated with the image to be processed.

[0055] S205. Using the target weight combination, the image size, image quality, the importance of the business and the coupling degree between the images are weighted to obtain the quality score of the image to be processed.

[0056] S206. Using a preset quality score range and the quality score of the image to be processed, determine the image level to which the image to be processed belongs;

[0057] S207. Determine the loading strategy for the image to be processed based on the target service type and the image level, and execute image loading.

[0058] For each business type, a pre-defined candidate weight combination is established. This candidate weight combination is determined based on the optimization objective of that business type, including weights for image size, image quality, business importance, and inter-image coupling. For example, for transaction data graphs, where image quality is a primary concern, the weights for image size and quality in the associated candidate weight combination are higher than those for business importance and inter-image coupling. For instance, the weights for image size, image quality, business importance, and inter-image coupling could be 0.4, 0.4, 0.1, and 0.1, respectively. For densely displayed graphs, where the smoothness of concurrent image loading is a primary concern, the weights for inter-image coupling, business importance, image size, and image quality in the associated candidate weight combination decrease sequentially. For instance, the weights for image size, image quality, business importance, and inter-image coupling could be 0.2, 0.1, 0.3, and 0.4, respectively. For high-frequency, low-attention images, the focus is on saving resource consumption. The weight corresponding to the importance of business is absolutely dominant in the associated candidate weight combination. For example, the weights corresponding to image size, image quality, importance of business and coupling between images can be 0.1, 0.05, 0.8 and 0.05 respectively.

[0059] For any image to be processed, the target business type to which the image belongs is determined. The correlation between the target business type and candidate business types and candidate weight combinations is matched to obtain a target weight combination. This target weight combination is then used to weight the image size, image quality, business importance, and inter-image coupling of the image to be processed, resulting in a quality score. The quality score of the image to be processed is compared with preset image level score thresholds: if the quality score is equal to or greater than the first score threshold (e.g., 0.8), the image level is level one; if the quality score is less than the first score threshold but equal to or greater than the second score threshold (e.g., 0.6), the image level is level two; if the quality score is less than the second score threshold but equal to or greater than the third score threshold (e.g., 0.4), the image level is level three; if the quality score is less than the third score threshold, the image level is level four. Subsequently, combining the target business type and image level, a loading strategy is dynamically determined for the image to be processed, and the corresponding dynamic loading strategy is used to perform image loading processing. By performing the above-mentioned grading operations, we obtain image levels that match the target business type, thereby improving the accuracy and applicability of the image grading results.

[0060] In one optional implementation, determining the business importance of the image to be processed based on its historical behavior data, page type, and page region includes: extracting the access frequency, average dwell time, and subsequent operation trigger rate of the image from its historical behavior data, and determining user importance based on the access frequency, average dwell time, and subsequent operation trigger rate; matching the page type with a preset page type and the association between page type importance to obtain the page type importance of the image to be processed; matching the page region with a preset page region and the association between page region importance to obtain the page region importance of the image to be processed; and fusing the user importance, page type importance, and page region importance to obtain the business importance of the image to be processed.

[0061] For quantitative assessment of business importance, the frequency of page visits, average dwell time, and subsequent operation trigger rate of the image to be processed can be extracted from historical behavioral data such as historical operation logs and event tracking data. The subsequent operation trigger rate is used to characterize whether the image to be processed is associated with the confirmation process of a key transaction. The user importance I is determined using the following formula. user :

[0062]

[0063] Furthermore, the page type of the image to be processed is determined, and its correlation with preset page types and page type importance is matched to obtain the page type importance of the image to be processed. For example, page types may include transfer confirmation pages, advertising carousel pages, cash deposit and withdrawal pages, account query pages, service management pages, and notification and announcement pages, etc., and a preset page type importance is assigned to each page type, such as a page type importance of 5 for transfer confirmation pages and 2 for advertising carousel pages. In addition, the page area where the image to be processed is located is determined, such as the main operation area, sidebar area, advertising display area, notification and announcement area, and multimedia display area, etc., and each page area has a preset area importance, such as an area importance of 5 for the main operation area and 2 for the sidebar area. By normalizing user importance, page type importance, and page area importance, and using a weighted fusion method, the business importance of the image to be processed is obtained. By integrating historical behavior data, page type, and page area multi-dimensional indicators, the business importance of the image to be processed is dynamically calculated, breaking through the limitations of a single dimension, improving the accuracy of business importance, and providing a highly reliable basis for differentiated image loading strategies.

[0064] The technical solution of this embodiment determines the target business type of the image to be processed and obtains a target weight combination that matches the target business type. Using this target weight combination, the image size, image quality, business importance, and inter-image coupling of the image to be processed are weighted to obtain a quality score. The quality score of the image to be processed is compared with a preset image level score threshold to obtain the image level. Subsequently, combining the target business type and image level, a loading strategy is dynamically determined and executed, improving the accuracy and applicability of the image grading results through hierarchical operations.

[0065] In one optional implementation, determining the coupling degree between images based on visual proximity, functional association, and data association includes: using the images to be processed in the self-service terminal as nodes, determining the edge weights between different nodes according to the visual proximity, functional association, and data association to obtain an image association graph; and determining the coupling degree between the images to be processed based on the image association graph.

[0066] Each image to be processed in the automated terminal is treated as a node in the image association graph, denoted as N. i (i = 1, 2, ..., n). For any two nodes N i and N j Based on the visual proximity, functional relevance, and data relevance of two nodes, edge weights are determined, resulting in an image association graph containing nodes and edge weights. For any image to be processed, the coupling relationship between the image to be processed and other images is determined based on the node and edge weights of the image to be processed in the image association graph, thus obtaining the inter-image coupling degree of the image to be processed.

[0067] For example, based on the image association graph, the co-occurrence frequency between different nodes is determined according to historical access path data. Key nodes are selected from the image association graph based on the co-occurrence frequency and edge weights, and the inter-image coupling degree of the i-th node is determined according to the node and edge weights in the image association graph.

[0068] The historical access path data includes all images triggered during a user's historical access to the self-service terminal, as well as the triggering order between these images. Multiple images triggered during a single access can be sorted based on their trigger timestamps to obtain the historical access path data for that single access. For any image to be processed, such as the i-th image, the historical access path data containing that image can be obtained. The co-occurrence count between the i-th image and other images is then read from each historical access path data. Based on the co-occurrence count and the edge weights of other nodes, the importance of the i-th node is determined. Key nodes are then selected from the image association graph based on the importance of the i-th node. Finally, the shortest path length L from the i-th node to the key node is determined based on the nodes and edge weights in the image association graph.i Furthermore, the shortest path length is normalized to obtain the inter-image coupling degree C of the i-th node. i :

[0069]

[0070] The above processing quantifies the coupling relationship between images by constructing an image association graph, uses historical access path data to determine the co-occurrence frequency and key nodes, and then calculates the normalized coupling degree between images, effectively improving the calculation accuracy of the coupling degree between images.

[0071] In one optional implementation, using the image to be processed in the self-service terminal as a node, the edge weights between different nodes are determined based on visual proximity, functional association, and data association to obtain an image association graph. This includes: calculating the visual proximity weight between the image to be processed and other images based on the center point coordinates of the image to be processed and the center point coordinates of other images, as well as the maximum layout distance threshold of the page; determining whether the image to be processed and other images belong to the same operation step group, and determining the functional association weight of the image to be processed based on the determination result; verifying whether the image to be processed and other images depend on the same data source, and determining the data association weight of the image to be processed based on the verification result; and fusing the visual proximity weight, functional association weight, and data association weight to obtain the edge weights between the image to be processed and other images, thus obtaining the image association graph.

[0072] Each image is considered as a node in an image association graph, denoted as N. i (i = 1, 2, ..., n). For any two nodes N i and N j Get the maximum layout distance threshold D of the page. max Based on the center point coordinates of different images, calculate the visual proximity weight S between the i-th node and the j-th node. ij :

[0073]

[0074] Among them, (x i ,y i (x) represents the coordinates of the center point of the i-th image. j ,y j D represents the coordinates of the center point of the j-th image; max This is the maximum layout distance threshold for the page.

[0075] Determine whether the i-th node and the j-th node belong to the same operation step group, and determine the functional association weight of the image to be processed based on the determination result: if they belong to the same operation step group, the functional association weight F is... ij The value is 1; otherwise, the functional association weight F is 1. ijThe value is set to 0. Simultaneously, it is verified whether the images corresponding to the i-th node and the j-th node depend on the same data source. If they depend on the same data source, the data association weight is set to 1; otherwise, the data association weight is set to 0. Furthermore, the visual proximity weight, functional association weight, and data association weight are weighted and fused using the following formula to obtain the edge weight W between the i-th node and the j-th node. ij :

[0076] W ij =ω1·S ij +ω2·F ij +ω3·D ij .

[0077] By constructing image association graphs based on multiple dimensions such as visual proximity, functional relevance, and data relevance, the relationships between images can be reflected more accurately and comprehensively. This provides a reliable basis for subsequent processing based on image association graphs and helps improve the accuracy and effectiveness of related processing.

[0078] Example 3

[0079] Figure 3 This is a schematic diagram of an image loading device based on a self-service terminal according to Embodiment 3 of this application. This embodiment is applicable to situations involving multi-dimensional feature fusion and dynamic hierarchical loading optimization of images in self-service terminals. This image loading device based on a self-service terminal can be implemented in hardware and / or software, and can be configured in an electronic device. (Reference) Figure 3 The specific structure of the image loading device 300 based on the self-service terminal is as follows:

[0080] The business type acquisition module 310 is used to obtain the target business type to which the image to be processed belongs;

[0081] The business importance module 320 is used to determine the business importance of the image to be processed based on its historical behavior data, page type, and page area.

[0082] The coupling module 330 is used to determine the coupling degree between images based on visual proximity, functional correlation and data correlation.

[0083] Image grading module 340 is used to grade the images to be processed based on the target business type, according to the image size, image quality, business importance and coupling degree between the images, to obtain the image level;

[0084] Image loading module 350 is used to determine the loading strategy of the image to be processed according to the target business type and the image level, and to execute image loading.

[0085] In one alternative implementation, the image grading module 340 includes:

[0086] The target weight unit is used to match the target service type with the preset association relationship between the candidate service type and the candidate weight combination to obtain the target weight combination associated with the image to be processed.

[0087] The image quality unit is used to weight the image size, image quality, the importance of the business, and the coupling degree between the images using the target weight combination to obtain the quality score of the image to be processed.

[0088] The image level unit is used to determine the image level to which the image to be processed belongs by using a preset quality score range and the quality score of the image to be processed.

[0089] In one optional implementation, the business importance module 320 includes:

[0090] The user importance unit is used to extract the access frequency, average dwell time and subsequent operation trigger rate of the image to be processed from the historical behavior data of the image to be processed, and to determine the user importance based on the access frequency, average dwell time and subsequent operation trigger rate.

[0091] The page type unit is used to match the page type with the preset page type and page type importance to obtain the page type importance of the image to be processed;

[0092] The page region unit is used to match the relationship between the page region it is located on and the preset page region and the page region importance to obtain the page region importance of the image to be processed;

[0093] The business importance unit is used to integrate the user importance, page type importance, and page area importance to obtain the business importance of the image to be processed.

[0094] In one alternative implementation, the coupling module 330 includes:

[0095] The image association graph unit is used to determine the edge weights between different nodes based on the visual proximity, functional association and data association, using the images to be processed in the self-service terminal as nodes, to obtain the image association graph.

[0096] The coupling degree unit is used to determine the inter-image coupling degree of the images to be processed based on the image association graph.

[0097] In one optional implementation, the image association graph unit is specifically used for:

[0098] Based on the center point coordinates of the image to be processed and the center point coordinates of other images, as well as the maximum layout distance threshold of the page, calculate the visual proximity weight between the image to be processed and other images.

[0099] Determine whether the image to be processed belongs to the same operation step group as other images, and determine the functional association weight of the image to be processed based on the determination result;

[0100] Verify whether the image to be processed depends on the same data source as other images, and determine the data association weight of the image to be processed based on the verification results;

[0101] The visual proximity weight, functional association weight, and data association weight are fused to obtain the edge weights between the image to be processed and other images, thus obtaining the image association graph.

[0102] In one alternative implementation, the image loading module 350 includes:

[0103] The target loading technology unit is used to select a target loading technology from candidate loading technologies based on the target service type and the image level, and to obtain the parameters of the target loading technology;

[0104] The target loading strategy unit is used to determine the value of the parameter based on the network status and terminal performance of the self-service terminal, and form a target loading strategy.

[0105] The image loading unit is used to execute the target loading strategy to load the image to be processed.

[0106] The image loading device based on a self-service terminal provided in this application embodiment can execute the image loading method based on a self-service terminal provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the image loading method based on a self-service terminal.

[0107] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0108] Example 4

[0109] Figure 4This is a schematic diagram of the structure of an electronic device 410 implementing the image loading method based on a self-service terminal according to an embodiment of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the application described and / or claimed herein.

[0110] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0111] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the image loading method based on a self-service terminal.

[0113] In some embodiments, the image loading method based on a self-service terminal can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the image loading method based on a self-service terminal described above can be performed. Alternatively, in other embodiments, processor 411 can be configured for the image loading method based on a self-service terminal by any other suitable means (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0118] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0119] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0120] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0121] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for loading images based on a self-service terminal, characterized in that, include: Obtain the target business type of the image to be processed; The business importance of the image to be processed is determined based on its historical behavior data, page type, and page region. The coupling degree between images is determined based on visual proximity, functional correlation, and data correlation. Based on the target business type, the images to be processed are classified according to their size, quality, importance of the business, and coupling between the images to obtain the image level. The loading strategy for the image to be processed is determined based on the target business type and the image level, and the image loading is then executed.

2. The method according to claim 1, characterized in that, Based on the target service type, the images to be processed are classified according to their size, quality, service importance, and inter-image coupling to obtain image levels, including: The target service type is matched with the preset association between candidate service types and candidate weight combinations to obtain the target weight combination associated with the image to be processed. Using the target weight combination, the image size, image quality, the importance of the business, and the coupling degree between the images are weighted to obtain the quality score of the image to be processed; The image level to which the image to be processed belongs is determined by using a preset quality score range and the quality score of the image to be processed.

3. The method according to claim 1 or 2, characterized in that, The step of determining the business importance of the image to be processed based on its historical behavior data, page type, and page region includes: The access frequency, average dwell time, and subsequent operation trigger rate of the image to be processed are extracted from the historical behavior data of the image to be processed, and the user importance is determined based on the access frequency, average dwell time, and subsequent operation trigger rate. The page type is matched with the preset page type and the relationship between page type importance to obtain the page type importance of the image to be processed; The page region is matched with the preset page region and the page region importance to obtain the page region importance of the image to be processed; The importance of the user, the importance of the page type, and the importance of the page region are combined to obtain the business importance of the image to be processed.

4. The method according to claim 1 or 2, characterized in that, The determination of the coupling degree between images based on visual proximity, functional correlation, and data correlation includes: Using the images to be processed in the self-service terminal as nodes, the edge weights between different nodes are determined based on the visual proximity, functional correlation and data correlation to obtain the image correlation graph; Based on the image association graph, the coupling degree between the images to be processed is determined.

5. The method according to claim 4, characterized in that, Using the images to be processed in the self-service terminal as nodes, the edge weights between different nodes are determined based on visual proximity, functional relevance, and data relevance to obtain an image association graph, including: Based on the center point coordinates of the image to be processed and the center point coordinates of other images, as well as the maximum layout distance threshold of the page, calculate the visual proximity weight between the image to be processed and other images. Determine whether the image to be processed belongs to the same operation step group as other images, and determine the functional association weight of the image to be processed based on the determination result; Verify whether the image to be processed depends on the same data source as other images, and determine the data association weight of the image to be processed based on the verification results; The visual proximity weight, functional association weight, and data association weight are fused to obtain the edge weights between the image to be processed and other images, thus obtaining the image association graph.

6. The method according to claim 1, characterized in that, Based on the target service type and the image level, determine the loading strategy for the image to be processed, and execute image loading, including: Based on the target service type and the image level, a target loading technology is selected from the candidate loading technologies, and the parameters of the target loading technology are obtained; The values ​​of the parameters are determined based on the network status and terminal performance of the self-service terminal to form a target loading strategy; The target loading strategy is executed to load the image to be processed.

7. An image loading device based on a self-service terminal, characterized in that, include: The business type acquisition module is used to obtain the target business type to which the image to be processed belongs; The business importance module is used to determine the business importance of the image to be processed based on its historical behavior data, page type, and page area. The coupling module is used to determine the coupling degree between images based on visual proximity, functional correlation, and data correlation. The image grading module is used to grade the images to be processed based on the target business type, according to the image size, image quality, business importance, and coupling degree between the images, to obtain the image level; The image loading module is used to determine the loading strategy of the image to be processed based on the target business type and the image level, and then execute the image loading.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the image loading method based on a self-service terminal as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the image loading method based on a self-service terminal as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the image loading method based on a self-service terminal according to any one of claims 1-6.

Images