Method, device and equipment for loading image file in cloud disk based on user social relationship

Abstract

The invention discloses a method, a device and equipment for loading an image file in a cloud disk based on a user social relationship. The method comprises the following steps: collecting user social relationship data, constructing a friend social relationship graph, analyzing a social relationship between a user and a friend, and evaluating the influence of the friend on user preference. The friend relationship weight is dynamically adjusted, and the interaction change between the user and the friend is displayed in real time; analyzing an image file concerned by a user in multiple dimensions, and extracting key information of the image file; segmenting the image file of the long video, and identifying image file segments interested by the user; performing preference matching on the image files according to the key information through combination of the social relationship and user behavior preference, formulating a loading strategy of the image files, and evaluating interests of the user in different image files; and according to a preference matching result, different image files are loaded according to priorities, and a loading strategy of the image files is personalized. The loading strategy of the image file is optimized, and the individual requirements of the user are met.

Description

Technical Field

[0001] This invention relates to the field of cloud storage technology, and in particular to a method, apparatus, and device for loading image files from a cloud drive based on user social relationships. Background Technology

[0002] Currently, cloud storage has become a common tool for users to store and share image files. Users can upload photos and videos to the cloud and share them with others via group sharing or shared links. However, as the clarity of image files continues to improve, file sizes are also increasing. During group activities (such as company team building, class reunions, etc.), users often upload a large number of image files, resulting in significant bandwidth and time consumption when loading these files. Users typically only focus on image files containing themselves and their friends, and are not interested in other files; existing loading methods cannot meet this personalized need.

[0003] Existing technologies suffer from several technical problems. Firstly, their image file loading strategies are relatively simplistic and often fail to consider social relationships between users and their friends. This leads to wasted bandwidth and time when loading large amounts of high-definition image files. Secondly, for long video files, users are often only interested in the portions containing themselves and their friends, and current technologies cannot accurately load these specific segments. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides a method, apparatus, and device for loading image files from a cloud drive based on user social relationships. By analyzing the social relationships between users and their friends, the image file loading strategy is optimized to meet users' personalized needs, improve user experience, and reduce data consumption.

[0005] In a first aspect, embodiments of the present invention provide a method for loading image files from a cloud drive based on user social relationships, comprising: Collect user social relationship data, construct a friend social relationship graph, analyze the social relationships between users and their friends, assess the influence of friends on user preferences, dynamically adjust the weight of friend relationships, analyze friend content preferences, and display changes in user-friend interactions in real time; The system performs multi-dimensional analysis of video files that users are interested in, extracts key information from these files, and provides data support for preference matching and loading strategies. It also segments long video files to identify video file segments that users are interested in. By combining social relationships with user behavior preferences, image files are matched to preferences based on key information, image file loading strategies are formulated, and user interest in different image files is assessed. Based on preference matching results, different image files are loaded according to priority, and a personalized image file loading strategy is formulated to obtain image files that the user is interested in.

[0006] In a second aspect, embodiments of the present invention provide an apparatus for loading image files from a cloud drive based on user social relationships, comprising: The data collection module is used to collect users' social relationship data, construct a friend social relationship graph, analyze the social relationships between users and their friends, assess the influence of friends on user preferences, dynamically adjust the weight of friend relationships, analyze friend content preferences, and display changes in user-friend interactions in real time. The analysis module is used to analyze the video files that users are interested in from multiple dimensions, extract key information from the video files, provide data support for preference matching and loading strategies, and segment long video files to identify video file segments that users are interested in. The preference matching module combines social relationships with user behavior preferences, matches image files to preferences based on key information, formulates image file loading strategies, and assesses user interest in different image files. The file loading module is used to load different image files according to priority based on preference matching results, personalize the image file loading strategy, and obtain image files that users are interested in.

[0007] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising: one or more processors; a memory for storing one or more programs; and when one or more programs are executed by one or more processors, causing one or more processors to implement the method for loading image files from a cloud drive based on user social relationships provided in any embodiment of the present invention.

[0008] Fourthly, the present invention discloses a computer-readable storage medium for storing a computer program; when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed method for loading image files from a cloud drive based on user social relationships.

[0009] Fifthly, embodiments of this disclosure provide a computer program product, including at least one of a computer program and instructions, wherein when the computer program and at least one of the instructions are executed by an electronic device, the steps of the method for loading image files from a cloud drive based on user social relationships described in the first aspect are implemented.

[0010] Compared with the prior art, the present invention has the following beneficial effects: This invention is applicable to integration with multiple platforms such as social media platforms, cloud storage services, and online video platforms, thereby expanding its application scope and user base. By deeply mining friend relationships to accurately determine user preferences, it achieves precise loading of image files. Users can quickly obtain image files that are truly of interest and enjoy a good viewing experience in different network environments, greatly improving user satisfaction and optimizing the user experience.

[0011] By leveraging precise analysis of friend relationships, high-definition loading of image files that users don't care about is avoided, reducing user waiting time, effectively saving traffic and storage resources, lowering system operating costs, and improving resource utilization, platform economic benefits, and market competitiveness.

[0012] By analyzing users' social relationships with their friends, the social interaction between users and friends in sharing and browsing image files is enhanced. Users can more easily view high-quality image files related to their friends, promoting interaction and sharing among users and increasing user stickiness on the social platform. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating the method for loading image files from a cloud drive based on user social relationships disclosed in this invention. Figure 2 This invention discloses a method for loading image files from a cloud drive based on user social relationships, which includes a flowchart for collecting user social relationship data. Figure 3 This is a schematic diagram illustrating the social relationships in the method for loading image files from a cloud drive based on user social relationships disclosed in this invention. Figure 4 This is a schematic diagram of the device for loading image files from a cloud drive based on user social relationships, as disclosed in this invention. Figure 5 This invention discloses a structural diagram of a device that loads image files from a cloud drive based on user social relationships. Detailed Implementation

[0014] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0015] based on Figure 1 The present invention describes a scenario in which image files are loaded from a cloud drive based on user social relationships, comprising: S1. Collect user social relationship data, construct a friend social relationship graph, analyze the social relationship between users and their friends, assess the influence of friends on user preferences, dynamically adjust the weight of friend relationships, analyze friend content preferences, and display the changes in interaction between users and their friends in real time. S2. Analyzes video files that users are interested in from multiple dimensions, extracts key information from the video files, and provides data support for preference matching and loading strategies; it also segments long video files to identify video file segments that users are interested in; and enables on-demand loading to improve resource utilization efficiency.

[0016] S3. By combining social relationships with user behavior preferences, image file preferences are matched based on key information to formulate image file loading strategies and assess user interest in different image files; preference matching includes user preference matching and friend preference matching. Optimize user experience: By deeply mining friend relationships to accurately determine user preferences, thus achieving precise loading of image files.

[0017] S4. Based on preference matching results, load different image files according to priority, and formulate personalized image file loading strategies to obtain image files that users are interested in. This ensures user experience and resource utilization efficiency. Users can quickly obtain image files that they are truly interested in and have a good viewing experience in different network environments, greatly improving user satisfaction. Personalized image file recommendations and display are provided.

[0018] In one embodiment of the first aspect, after constructing a friend social relationship graph, the friend relationship weight is calculated based on the evaluation results of each friend, and the friend relationship weight is dynamically adjusted according to changes in social relationships to predict users' interest in certain types of image files; by using accurate analysis of friend relationships, high-definition loading of image files that users do not care about is avoided, effectively saving traffic and storage resources and reducing the operating costs of the system.

[0019] In one embodiment of the first aspect, such as Figure 2 As shown in step S11, construct a social relationship graph of friends. Based on the social functions of the cloud drive, obtain the user's friend list and group member social information to construct the user's friend relationship graph, including the intimacy and interaction frequency between friends. Intimacy is measured by the frequency and intensity of interaction behaviors between the user and friends, while interaction frequency is determined by counting the number of interactions between the user and friends. Interaction behaviors include liking, commenting, and sharing.

[0020] For example, if a user and friend A exchange private messages every week and frequently like each other's posts, then their intimacy and interaction frequency are relatively high.

[0021] In one embodiment of the first aspect, such as Figure 3 As shown in S12, social relationships include user interactions with friends, joint activities, and follow status of friends' activities.

[0022] User-friend interaction behavior analysis includes analyzing the frequency and content types of user interactions with friends to determine the degree of attention users pay to different types of friends. For example, a user frequently likes friend B's travel photos but rarely interacts with friend C's food sharing, indicating that the user is more interested in travel content and less interested in food content.

[0023] User-friend co-participation activity identification includes recognizing activities that users and friends participate in together and recording the types and content characteristics of image files generated during these activities. This can further reveal user preferences in specific scenarios. Examples of such activities include company team building activities and class events. For instance, if a user and friend D took numerous photos of natural scenery during multiple outdoor activities, it suggests that the user may have a high interest in natural landscape image files.

[0024] User-friend interaction dynamic monitoring includes tracking the frequency and duration of user browsing of friends' activities to determine the degree of user interest in the images and files within those activities. For example, if a user frequently and extensively browses friend E's photography activities, it indicates a high level of interest in that friend's content and a likely high level of interest in photography-related images and files.

[0025] In one embodiment of the first aspect, S13. Assessing the influence of friends on user preferences includes assessing the influence of friends on social networks, such as the number of followers a friend has, the popularity of their posted content, etc., to determine the potential influence of friends on user preferences. Friends with higher social influence may have more relevant video files that attract more user attention.

[0026] For example, if friend F is a well-known food blogger whose food videos often attract a lot of attention, then users are likely to be highly interested in the food-related video files he posts.

[0027] In one embodiment of the first aspect, S14. Friend relationship weight calculation: Based on the analysis results of interaction behavior, joint participation in activities, dynamic attention, and influence, a weight value is assigned to each friend's evaluation result. The higher the weight value, the greater the influence of the friend on the user's preferences. The weight calculation formula can comprehensively consider factors such as interaction frequency, intimacy, and joint activity participation. For example, the friend relationship weight can be calculated by comprehensively considering interaction frequency (40%), intimacy (30%), and joint activity participation (30%). The specific value can be quantified through relevant algorithms and models.

[0028] In one embodiment of the first aspect, S15. The friend relationship weight is dynamically adjusted by monitoring changes in the user's interaction behavior with friends in real time and dynamically adjusting the friend relationship weight. For example, if the user's interaction frequency with a certain friend increases recently, such as liking and commenting every day, then the weight of that friend is increased accordingly to more accurately reflect the user's current preference.

[0029] In one embodiment of the first aspect, S16. Friend relationship tag identification and classification management includes adding tags to friends, such as "family," "colleague," "classmate," "photography enthusiast," etc., and classifying and managing friends according to the degree of influence of different tags on user preferences. Users may pay different amounts of attention to friends with different tags. For example, users may pay more attention to photos of "family" friends, while paying less attention to work-related images of "colleague" friends. At the same time, friends can also be grouped according to tags to more accurately analyze the differences in user preferences in different social circles.

[0030] In one embodiment of the first aspect, S17. Analyzing friends' content preferences includes analyzing the types and content characteristics of image files posted by friends to obtain content that the user may be interested in. If a user's friends frequently post travel photos and the user frequently views and likes them, it indicates that the user may be interested in travel-related image files. Furthermore, elements such as people, scenes, and styles in the image files posted by friends can be further analyzed to uncover more detailed user preference information. For example, if friends' travel photos are mostly of natural scenery and the user interacts frequently with these photos, it can be inferred that the user has a high interest in natural scenery image files.

[0031] In one embodiment of the first aspect, S18. Friend social network expansion analysis includes analyzing the user's direct friend relationships, expanding the user's indirect friend relationships (including friends of friends), and mining potential social connections and preference influences. By analyzing the expanded relationships of the social network, it is possible to predict in advance the user's potential interest in certain types of video files, thereby more comprehensively mining user preferences. For example, user friend G's friend H posted a highly creative short video, which gained widespread dissemination and attention on the social network, and the user also became interested in the video after seeing friend G share it.

[0032] In one embodiment of the first aspect, S21. Image file preprocessing includes classifying and labeling image files stored in a cloud drive, identifying the file type (such as photos, videos) and format (such as JPEG, MP4, etc.); and performing preliminary screening of image files to remove duplicate or low-quality files.

[0033] Based on information such as the file's creation time, modification time, and filename, we can make an initial judgment about the possible themes and scenarios of the video files. For example, video files with the words "graduation ceremony" in their filenames are likely related to graduation-related activities, which can help us to more effectively explore user preferences in graduation scenarios during subsequent analysis.

[0034] In one embodiment of the first aspect, multi-dimensional analysis of image files of interest to users includes person identification and annotation, content classification and analysis, and resolution grading.

[0035] In one embodiment of the first aspect, S22. Person recognition and annotation includes using facial recognition technology to identify and annotate persons in image files; the annotated persons are combined with facial expression recognition to analyze their emotional states, such as smiling or angry, to further explore user preferences for different emotional scenarios. The location and frequency of the user, friends, and group members appearing in the image files are annotated. For video files, keyframes are extracted for person recognition, and the time intervals in which persons appear in the video are annotated. For example, a user may prefer to browse photos containing happy smiles from friends, while showing less interest in photos of friends with serious expressions.

[0036] In one embodiment of the first aspect, S23. Content classification and analysis: Image recognition and video analysis are used to classify the content of the image files, such as landscapes, people, and event scenes. Key features of the image files, such as color, composition, and scene changes, are analyzed to better match user preferences.

[0037] For example, users may prefer landscape photos with vibrant colors and unique compositions, while showing little interest in landscape photos with monotonous tones and ordinary compositions. Extracting object and scene elements from image files and establishing a detailed tagging system is crucial. For instance, in a travel photo, identifying elements such as "mountains," "lakes," and "ancient buildings" and adding corresponding tags allows for more accurate matching of image files that align with user interests during preference matching.

[0038] In one embodiment of the first aspect, S24. Clarity grading: The image files are graded in terms of clarity based on parameters such as resolution and encoding format. An index of different clarity versions is generated for each image file so that the clarity to be loaded can be selected according to user preferences, such as high definition (1080p and above), standard definition (720p), and low definition (480p and below).

[0039] Analyzing the file size and loading time of video files in different resolution versions provides data support for optimizing subsequent loading strategies. For example, while high-definition (HD) video files offer better image quality, they are larger and take longer to load, whereas low-definition (HD) versions load faster. By appropriately selecting the resolution version, we can reduce data consumption and waiting time while ensuring a good user experience.

[0040] In one embodiment of the first aspect, S25. The long video file is segmented. The long video file is divided into multiple segments using video analysis technology. The priority of each segment is determined based on its content characteristics (such as the appearance of people, scene type, etc.) and user preference information. Each segment is labeled with its start and end times.

[0041] Extract keyframes from each segment or generate thumbnails for the segments, allowing users to quickly preview and select segments of interest. For example, in a long video of a family gathering, extract key segments that include interactions between the user and multiple friends.

[0042] In one embodiment of the first aspect, preference matching of image files based on key information includes user preference matching, friend preference matching, and social network expansion preference matching; User preference matching combines user social relationship data with user behavior data to prioritize and match video files based on user preferences. Furthermore, it considers user behavior data such as historical browsing time and download frequency for different types of video files to further adjust priorities. Priorities are categorized as high, medium, and low. High-priority files are marked as those of the user or their high-priority friends; medium-priority files are marked as those of medium-priority friends; and low-priority files are marked as those of low-priority friends or files where no friend appears.

[0043] Friend preference matching categorizes and matches image files based on friend tags and content preference analysis. For example, if a user places a higher preference on photos of "family" friends and pays more attention to image files containing specific events (such as family gatherings or holiday celebrations), then image files that meet these criteria will be loaded first. For image files containing multiple friend tags, a comprehensive evaluation is performed based on the priority and combination of tags.

[0044] Social Network-Based Preference Matching: Leveraging the analysis results of social network-based preference matching, we can uncover users' potential interests in video files. For example, a friend of a friend of a user posts a highly creative short video on a technology theme, and this video receives widespread attention and praise on social networks. By analyzing the user's level of attention to the content shared by their friend and its relevance to the video's theme, we can infer that the user has a potential interest in video files. In this case, such video files are included in the preference matching scope and assigned a certain priority.

[0045] In one embodiment of the first aspect, formulating an image file loading strategy includes: loading different resolution versions according to priority, and formulating an image file loading strategy based on preference matching results. For high-priority image files, high-definition versions are loaded first; for medium-priority image files, standard-definition or high-definition versions are selectively loaded based on the user's network conditions and device performance; for low-priority image files, low-definition versions are loaded or only thumbnails are loaded.

[0046] Loading strategies are adjusted based on social relationships and friend tags: Given users' varying levels of attention to different friends and differences in preferences across different scenarios, video files containing high-weight friends or those relevant to the user's current scenario are given higher loading priority and improved clarity. The loading order of video files is adjusted according to friend tag priority and content characteristics. For example, video files containing "family" friends are loaded first, followed by "friends," and finally "colleagues." Furthermore, video files under the same tag are further sorted based on how well their content matches the user's preferences.

[0047] Optimize loading decisions using historical data: Continuously optimize loading strategies by combining users' historical loading behavior and feedback information. For example, if users frequently switch to high-definition versions after loading low-definition versions, it indicates that users have a high demand for high-definition for this type of video file. In subsequent loading strategies, the initial loading resolution of such video files can be appropriately increased, or some data from the high-definition version can be preloaded to shorten the time users wait for high-definition content.

[0048] In summary, this invention observes and verifies user social relationship analysis and image file loading strategies through user interface and system operation. For example, users can intuitively experience the actual effect of the technical solution by viewing image file loading speed, resolution selection, and recommended content. The collection and processing of user social relationship data and image file analysis data can be traced through system logs and data records. For example, the system can record information such as user interactions with friends, image file loading requests, and response times, providing data support for the collection of infringement evidence.

[0049] By constructing a social relationship graph of friends, we can analyze users' social relationships and comprehensively evaluate the impact of friends on user preferences. We dynamically adjust the weight of friend relationships and display real-time changes in user interactions with friends, ensuring the accuracy and timeliness of preference matching.

[0050] Multi-dimensional analysis of video files: Preprocessing video files, identifying people, classifying content, and grading resolution to extract key information. For long video files, segment processing is performed to accurately identify segments that users are interested in, enabling on-demand loading and improving resource utilization efficiency.

[0051] Example 2: Based on Example 1, this invention further proposes a device for loading image files from a cloud drive based on user social relationships, such as... Figure 4 As shown, it includes: The data collection module 01 is used to collect user social relationship data, construct a friend social relationship graph, analyze the social relationship between users and friends, evaluate the influence of friends on user preferences, dynamically adjust the weight of friend relationships, and display the changes in interaction between users and friends in real time. Analysis module 02 is used to analyze the video files that users are interested in from multiple dimensions, extract key information from the video files, provide data support for preference matching and loading strategies, and segment long video files, analyze friends' content preferences, and identify video file segments that users are interested in. The preference matching module 03 is used to combine social relationships and user behavior preferences to match image files with user preferences based on key information, formulate image file loading strategies, and assess users’ interest in different image files. File loading module 04 is used to load different image files according to priority based on the matching results of user preferences, formulate personalized image file loading strategies, and obtain image files that the user is interested in.

[0052] In one embodiment of the second aspect, after constructing the friend social relationship graph module, the process includes: analyzing the social relationships between users and their friends, assessing the influence of friend social relationships on user preferences, calculating friend relationship weights based on the assessment results of each friend, dynamically adjusting friend relationship weights according to changes in social relationships, tagging and classifying friend relationships, analyzing friend preferences and the expansion of friend social relationships, and predicting user interest in certain types of image files. Social relationships include interactive behaviors between users and their friends, jointly participated activities, and the level of attention paid to friend activities.

[0053] In one embodiment of the second aspect, preference matching includes: user preference matching and friend preference matching.

[0054] In one embodiment of the second aspect, constructing a friend social relationship graph includes: obtaining the user's friend list and group member social information based on the social functions of the cloud drive, and constructing the user's friend relationship graph, including the intimacy and interaction frequency between friends.

[0055] In one embodiment of the second aspect, the user-friend interaction behavior analysis includes analyzing the operation frequency and content type of the user-friend interaction behavior to determine the user's level of attention to different types of friends; the user-friend joint activity identification includes identifying the user and friends jointly participating in activities and recording the image file types and content characteristics generated in these activities; the user-friend dynamic attention analysis includes statistically analyzing the frequency and dwell time of the user browsing the friend's dynamics and analyzing and judging the user's level of attention to the image files in the friend's dynamics.

[0056] In one embodiment of the second aspect, assessing the influence of friends on user preferences includes assessing the influence of friends on social networks to determine the potential influence of friends on user preferences.

[0057] In one embodiment of the second aspect, the calculation of friend relationship weight includes assigning a weight value to each friend evaluation result based on interactive behavior, joint participation in activities, dynamic attention, and influence analysis results. The higher the weight value, the greater the influence of the friend on the user's preferences.

[0058] In one embodiment of the second aspect, the friend relationship is dynamically adjusted by monitoring changes in the interaction behavior between the user and their friends in real time and dynamically adjusting the friend relationship weight.

[0059] In one embodiment of the second aspect, friend relationship tag identification and classification management includes adding tags to friends and classifying them according to the degree of influence of friends with different tags on user preferences. Simultaneously, friends are grouped according to tags to more accurately analyze user preference differences across different social circles.

[0060] In one embodiment of the second aspect, analyzing friends' content preferences includes: analyzing the types and content characteristics of image files posted by friends to obtain content that the user may be interested in.

[0061] In one embodiment of the second aspect, social network extension analysis includes analyzing the direct relationships between users' friends and the extended indirect relationships, where indirect relationships include the friend relationships between friends, to uncover potential social connections and preference influences.

[0062] In one embodiment of the second aspect, the multi-dimensional analysis of image files of interest to the user includes image file preprocessing, classifying and labeling image files stored in the cloud drive, identifying the type and format of the files; and performing preliminary screening of image files to remove duplicate or low-quality files. Based on information such as the file's creation time, modification time, and filename, a preliminary judgment can be made about the possible subject and scene of the image file.

[0063] In one embodiment of the second aspect, multi-dimensional analysis of image files of interest to users includes person identification and annotation, content classification and analysis, and resolution grading. In one embodiment of the second aspect, person recognition and annotation includes using facial recognition technology to identify and annotate people in image files; the annotated people are combined with facial expression recognition to analyze the emotional state of the people and explore the user's preferences for different emotional scenarios.

[0064] The location and frequency of the user, friends, and group members in the image file are marked; for video files, keyframes are extracted for person recognition, and the time intervals in which the person appears in the video are marked.

[0065] In one embodiment of the second aspect, content classification and analysis includes classifying the content of image files using image recognition and video analysis, analyzing key features of the image files, and matching user preferences.

[0066] Extracting key information from image files includes extracting objects and scene elements from the image files and establishing a detailed tagging system.

[0067] In one embodiment of the second aspect, the sharpness classification includes classifying the image file according to its parameters; and analyzing the file size and loading time of the image file to provide data support for subsequent loading strategy optimization.

[0068] In one embodiment of the second aspect, the file segmentation processing of long video images includes using video analysis technology to segment them into multiple segments, determining the priority of each segment based on the content characteristics of each segment and user preference information, and extracting keyframes of each segment or generating thumbnails of the segments.

[0069] In one embodiment of the second aspect, preference matching of image files based on key information includes user preference matching, friend preference matching, and social network expansion preference matching; user preference matching includes combining user social relationship data with user behavior data to perform preference matching of image files with priority; and adjusting the priority by referring to user behavior data for different types of image files; Friend preference matching involves classifying and matching image files based on friend tags and content preference analysis results. For image files containing multiple friend tags, a comprehensive evaluation is performed based on the priority and combination of tags.

[0070] In one embodiment of the second aspect, social network expansion interest mining involves using the analysis results of social network expansion preference matching to uncover users' potential interests in video files. By analyzing the degree of attention users pay to content shared by their friends and its relevance to the video topic, it can be inferred that users have a potential interest in video files.

[0071] In one embodiment of the second aspect, formulating an image file loading strategy includes formulating an image file loading strategy according to priority, adjusting the loading strategy based on social relationships and friend tags, and optimizing the loading strategy based on historical data.

[0072] Example 3 Figure 5 A schematic diagram of a device for loading image files from a cloud drive based on user social relationships is provided as an embodiment of the present invention. Figure 5 As shown, the device for loading image files from a cloud drive based on user social relationships includes at least one processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in the device for loading image files from a cloud drive based on user social relationships can be one or more. Figure 5 Taking a processor 310 as an example; the processor 310, memory 320, input device 330, and output device 340 in the device that loads image files from the cloud drive based on user social relationships can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0073] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules (e.g., acquisition module, analysis module, preference matching module, and file loading module) corresponding to the method for loading image files from a cloud drive based on user social relationships in this embodiment of the invention. The processor 310 executes the software programs, instructions, and modules stored in the memory 320 to perform various functional applications and data processing of the device for loading image files from a cloud drive based on user social relationships, thereby implementing the aforementioned method for loading image files from a cloud drive based on user social relationships.

[0074] The memory 320 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 320 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include memory remotely configured relative to the processor 310, which can be connected via a network to a device that loads image files from a cloud drive based on user social relationships. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0075] Input device 330 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device for loading image files from the cloud drive based on user social relationships. Output device 340 may include a display device such as a screen.

[0076] This invention also discloses a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the steps of the method for loading image files from a cloud drive based on user social relationships disclosed in any of the foregoing embodiments.

[0077] In an exemplary embodiment, a computer program product is also provided, including at least one of a computer program and instructions, wherein when the computer program and instructions are executed by an electronic device, the steps of the above-described method for loading image files from a cloud drive based on user social relationships are implemented.

[0078] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0079] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0080] The above description is merely illustrative of the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for loading image files from a cloud drive based on user social relationships, characterized in that, include: Collect user social relationship data, construct a friend social relationship graph, analyze the social relationship between users and their friends, and assess the influence of friends on user preferences; Dynamically adjust the weight of friend relationships, analyze friend content preferences, and display real-time changes in user interactions with friends; The system performs multi-dimensional analysis of video files that users are interested in, extracts key information from these files, and provides data support for preference matching and loading strategies. It also segments long video files to identify video file segments that users are interested in. By combining social relationships with user behavior preferences, image files are matched to preferences based on key information, image file loading strategies are formulated, and user interest in different image files is assessed. Based on preference matching results, different image files are loaded according to priority, and a personalized image file loading strategy is formulated to obtain image files that the user is interested in.

2. The method for loading image files from a cloud drive based on user social relationships according to claim 1, characterized in that: The construction of the friend social relationship graph includes: obtaining the user's friend list and group member social information based on the social functions of the cloud drive; the friend relationship graph includes the intimacy and interaction frequency between friends.

3. The method for loading image files from a cloud drive based on user social relationships according to claim 2, characterized in that: The social relationships between users and their friends include the user's interactive behaviors with their friends, activities they participate in together, and the status of their friends' activities. Interactive behavior analysis includes analyzing the frequency and content types of user interactions with friends to determine the degree of user attention to different types of friends. User-friend joint activity identification includes identifying users and friends participating in activities together, and recording the image file types and content characteristics generated in these activities; The analysis of user-friend dynamic attention includes counting the frequency and duration of users browsing their friends' dynamics, and analyzing and judging the degree of attention users pay to image files in their friends' dynamics.

4. The method for loading image files from a cloud drive based on user social relationships according to claim 3, characterized in that: Assessing the impact of friends on user preferences includes evaluating the influence of friends on social networks to determine their potential impact on user preferences.

5. The method for loading image files from a cloud drive based on user social relationships according to claim 4, characterized in that: The calculation of friend relationship weighting involves assigning a weight value to each friend's evaluation result based on interactive behavior, joint participation in activities, dynamic attention, and influence analysis results. The higher the weight value, the greater the influence of that friend on user preferences.

6. The method for loading image files from a cloud drive based on user social relationships according to claim 5, characterized in that: Dynamic adjustment of friend relationships includes real-time monitoring of changes in user interaction behavior with friends and dynamically adjusting the weight of friend relationships.

7. The method for loading image files from a cloud drive based on user social relationships according to claim 6, characterized in that: The friend relationship tag identification and classification management includes adding tags to friends and classifying them according to the degree of influence of different tags on user preferences; it also groups friends according to tags in order to more accurately analyze the differences in user preferences in different social circles.

8. The method for loading image files from a cloud drive based on user social relationships according to claim 1, characterized in that: The friend content preference analysis includes analyzing the types and content characteristics of image files posted by friends to obtain content that users may be interested in.

9. The method for loading image files from a cloud drive based on user social relationships according to claim 8, characterized in that: Social network expansion analysis includes analyzing the direct relationships between users' friends and the expanded indirect relationships, including the friend relationships between friends, to uncover potential social connections and preference influences.

10. The method for loading image files from a cloud drive based on user social relationships according to claim 9, characterized in that: The multi-dimensional analysis of image files of interest to users includes image file preprocessing, classifying and labeling image files stored in the cloud drive, and identifying file types and formats; preliminary screening of image files to remove duplicate or low-quality files; and preliminary determination of the theme and scene of image files based on their creation time, modification time, and filename information.

11. The method for loading image files from a cloud drive based on user social relationships according to claim 10, characterized in that: The multi-dimensional analysis of image files that users are interested in includes person identification and annotation, content classification and analysis, and resolution grading.

12. The method for loading image files from a cloud drive based on user social relationships according to claim 11, characterized in that: The person recognition and annotation includes using facial recognition technology to identify and annotate people in image files; the annotated people are combined with facial expression recognition to analyze the emotional state of the people and explore the user's preferences for different emotional scenarios. The location and frequency of the user, friends, and group members in the image file are marked; for video files, keyframes are extracted for person recognition, and the time intervals in which people appear in the video are marked. Content classification and analysis includes classifying the content of image files using image recognition and video analysis, analyzing the key features of image files, and matching user preferences; extracting key information from image files includes extracting object and scene elements from image files and establishing a detailed tagging system.

13. The method for loading image files from a cloud drive based on user social relationships according to claim 12, characterized in that: The resolution grading includes classifying the image file's resolution based on its parameters; and analyzing the image file's file size and loading time to provide data support for subsequent loading strategy optimization.

14. The method for loading image files from a cloud drive based on user social relationships according to claim 1, characterized in that: The segmentation processing of long video files includes using video analysis technology to divide it into multiple segments, determining the priority of each segment based on its content characteristics and user preference information, and extracting keyframes from each segment or generating a thumbnail for each segment.

15. The method for loading image files from a cloud drive based on user social relationships according to claim 14, characterized in that: The method of matching image files based on key information includes user preference matching, friend preference matching, and social network expansion preference matching; user preference matching includes combining user social relationship data with user behavior data to match image files according to priority; at the same time, the priority is adjusted by referring to user behavior data for different types of image files; Friend preference matching includes classifying and matching image files based on the analysis results of friend tags and friend content preferences; For image files containing multiple friend tags, a comprehensive evaluation is conducted based on the priority and combination of tags; Social network extended preference matching involves using the analysis results of social network extended preference matching to uncover users' potential interests in image files.

16. The method for loading image files from a cloud drive based on user social relationships according to claim 15, characterized in that: The image file loading strategy includes prioritizing image file loading strategies, adjusting loading strategies based on social relationships and friend tags, and optimizing loading strategies based on historical data.

17. A device for loading image files from a cloud drive based on user social relationships, characterized in that, include: The data collection module is used to collect users' social relationship data, build a social relationship graph of friends, analyze the social relationship between users and their friends, and evaluate the influence of friends on users' preferences. Dynamically adjust the weight of friend relationships, analyze friend content preferences, and display real-time changes in user interactions with friends; The analysis module is used to analyze the video files that users are interested in from multiple dimensions, extract key information from the video files, and segment long video files to identify video file segments that users are interested in. The preference matching module combines social relationships with user behavior preferences, matches image files to preferences based on key information, formulates image file loading strategies, and assesses user interest in different image files. The file loading module is used to load different image files according to priority based on preference matching results, personalize the image file loading strategy, and obtain image files that users are interested in.

18. An electronic device, characterized in that, The electronic device includes: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for loading image files from a cloud drive based on user social relationships as described in any one of claims 1-16.

19. A computer-readable storage medium, characterized in that, Used to store computer programs; when the computer programs are executed by a processor, they implement the steps of the method for loading image files from a cloud drive based on user social relationships as described in any one of claims 1-16.

20. A computer program product, comprising at least one of a computer program and instructions, characterized in that, When at least one of the computer program or instructions is executed by an electronic device, it implements claim 1. The steps of the method for loading image files from a cloud drive based on user social relationships as described in any one of 16.

Images