Cloud mobile phone mirror image adaptation method and device, electronic equipment and storage medium

Abstract

The invention provides a cloud mobile phone mirror image adaptation method and device, electronic equipment and a storage medium, and relates to the technical field of cloud computing, and the method comprises the steps: obtaining village feature data and user behavior data of a target region, and carrying out the cleaning and structuralization processing of the village feature data and the user behavior data, so as to generate structuralized feature information and behavior record information; further, the structured feature information is quantitatively analyzed to extract village feature tags, the behavior record information is subjected to data mining analysis to extract user demand tags, and then functional components and configuration schemes are selected from a pre-constructed mirror image component library through similarity matching according to the tags to generate a customized cloud mobile phone mirror image template; and then the customized mirror image template is distributed to target user terminal equipment through an automatic deployment platform. Therefore, the problem that in the prior art, cloud mobile phones are not widely popularized due to the fact that the cloud mobile phone mirror image adopts a'one-cut 'general scene design and lacks function adaptation to different village regional characteristic industries can be solved.

Description

Technical Field

[0001] This disclosure relates to the field of cloud computing technology, and in particular to a cloud phone image adaptation method and apparatus, electronic device and storage medium. Background Technology

[0002] Cloud phones, as a significant product of the integration of cloud computing and virtualization technologies, are widely used in rural digital transformation. Related technologies utilize the collaborative processes of hardware resource virtualization, operating system cloud migration, and application containerization deployment to construct a low-cost smart terminal technology system. However, existing cloud phone image generation methods directly employ a unified template design without integrating dual-dimensional analysis of village geographical characteristics and user behavior data. This may lead to insufficient adaptability or functional redundancy, thus affecting the widespread adoption of digital technology. This single-point technical design cannot address the differentiated needs of mountainous and plain villages in scenarios such as agricultural technology services and e-commerce functions, resulting in excessively long image iteration cycles and manual adaptation costs accounting for over 70% of the total cost, severely hindering the efficiency improvement of rural digitalization. Summary of the Invention

[0003] This disclosure provides a cloud phone image adaptation method, apparatus, electronic device, and storage medium. Its main purpose is to at least partially solve one of the technical problems in related technologies.

[0004] According to a first aspect of this disclosure, a cloud phone image adaptation method is provided, comprising: Acquire village feature data and user behavior data of the target area, and clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information; Quantitative analysis of structured feature information is performed to extract village feature tags, and data mining analysis of behavioral record information is performed to extract user demand tags. Based on village feature tags and user demand tags, functional components and configuration schemes are selected from a pre-built image component library through similarity matching to generate a customized cloud phone image template; Customized cloud phone image templates are distributed to target users' terminal devices through an automated deployment platform; Based on target user usage data and updated village characteristic data, the customized cloud phone image template is dynamically optimized and iterated.

[0005] Optionally, acquire village characteristic data and user behavior data for the target area, including: Village feature data is generated by obtaining information on the village's geographical location, population structure, and economic industries from external data source interfaces. User behavior trajectories are recorded through embedded data acquisition algorithms or application programming interfaces, and the trajectories are anonymized and invalid information is filtered to form standardized user behavior data.

[0006] Optionally, data mining analysis can be performed on the behavioral record information to extract user demand tags, including: Clustering algorithms are used to group user behavior feature vectors to identify user groups with similar behavior patterns; The user groups are evaluated to determine the optimal number of groups, and user demand types are summarized based on the grouping results to generate user demand tags.

[0007] Optionally, the mirror component library includes functional components, interaction templates, and configuration schemes, and sets feature tags for each component; The labels for functional components include applicable industries and operational difficulty; the labels for interactive templates include user groups and interactive features; and the labels for configuration schemes include network adaptation strategies and security permission settings.

[0008] Optionally, the customized cloud phone image template can be distributed to the target user's terminal device via an automated deployment platform, including: Generate cloud phone instances in batches based on the number of users, and load customized cloud phone image templates; Send a mirror access link or activation credential to the target user via push notification service. The link or credential contains user identity verification information.

[0009] Optionally, based on target user usage data and updated village characteristic data, the customized cloud phone image template can be dynamically optimized and iterated, including: Monitor target users' usage rate, error rate, and feedback content regarding cloud phone images; Regularly regenerate feature tags and demand tags based on updated village feature data, and adjust the component configuration and parameter settings of the customized cloud phone image template according to the new tags and user feedback.

[0010] According to a second aspect of this disclosure, a cloud phone image adaptation device is provided, comprising: The acquisition unit is used to acquire village feature data and user behavior data in the target area, and to clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information. The extraction unit is used to perform quantitative analysis on structured feature information to extract village feature tags, and to perform data mining analysis on behavioral record information to extract user demand tags. The generation unit is used to select functional components and configuration schemes from a pre-built image component library based on village feature tags and user demand tags through similarity matching, and generate a customized cloud phone image template. The distribution unit is used to distribute customized cloud phone image templates to the target users' terminal devices through an automated deployment platform. The optimization unit is used to dynamically optimize and iterate the customized cloud phone image template based on target user usage data and updated village characteristic data.

[0011] Optionally, the acquisition unit is also used for: Village feature data is generated by obtaining information on the village's geographical location, population structure, and economic industries from external data source interfaces. User behavior trajectories are recorded through embedded data acquisition algorithms or application programming interfaces, and the trajectories are anonymized and invalid information is filtered to form standardized user behavior data.

[0012] Optionally, the extraction unit is also used for: Clustering algorithms are used to group user behavior feature vectors to identify user groups with similar behavior patterns; The user groups are evaluated to determine the optimal number of groups, and user demand types are summarized based on the grouping results to generate user demand tags.

[0013] Optionally, the mirror component library includes functional components, interaction templates, and configuration schemes, and sets feature tags for each component; The labels for functional components include applicable industries and operational difficulty; the labels for interactive templates include user groups and interactive features; and the labels for configuration schemes include network adaptation strategies and security permission settings.

[0014] Optionally, the distribution unit is also used for: Generate cloud phone instances in batches based on the number of users, and load customized cloud phone image templates; Send a mirror access link or activation credential to the target user via push notification service. The link or credential contains user identity verification information.

[0015] Optionally, the optimization unit is also used for: Monitor target users' usage rate, error rate, and feedback content regarding cloud phone images; Regularly regenerate feature tags and demand tags based on updated village feature data, and adjust the component configuration and parameter settings of the customized cloud phone image template according to the new tags and user feedback.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0017] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0018] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0019] The cloud phone image adaptation method, apparatus, electronic device, and storage medium disclosed herein acquire village feature data and user behavior data of the target area, clean and structure them to generate structured feature information and behavior record information, then quantitatively analyze the structured feature information to extract village feature tags, and perform data mining analysis on the behavior record information to extract user demand tags. Based on these tags, functional components and configuration schemes are selected from a pre-built image component library through similarity matching to generate a customized cloud phone image template. Subsequently, the customized image template is distributed to the target user terminal device through an automated deployment platform. At the same time, the customized image template is dynamically optimized and iterated based on the target user usage data and updated village feature data. Therefore, this technology can solve the problem that existing cloud phone images adopt a "one-size-fits-all" general scenario design, which lacks functional adaptation to the regional characteristics and industries of different villages and fails to meet the interactive needs of users of different ages and cultural levels. This results in insufficient image adaptability and low practicality, which in turn restricts the popularization of cloud phones in rural areas and hinders the downward flow of rural digital dividends. The technology can achieve the goal of generating personalized cloud phone images for different villages with "a thousand villages, a thousand faces" that are accurately tailored to their geographical characteristics, economic structure, population composition and user needs. This will improve the relevance and practicality of the images to the actual needs of rural areas, lower the threshold for rural users to use smart terminals, promote the large-scale application of cloud phones in rural areas, unleash rural digital productivity, and provide strong support for the digital development of rural areas.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1This is a flowchart illustrating a cloud phone image adaptation method provided in an embodiment of the present disclosure. Figure 2 This is a schematic diagram of the structure of a cloud phone image adaptation device provided in an embodiment of the present disclosure; Figure 3 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0022] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] The cloud phone image adaptation method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings.

[0024] Figure 1 This is a flowchart illustrating a cloud phone image adaptation method provided in an embodiment of this disclosure.

[0025] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain village feature data and user behavior data of the target area, and clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information.

[0026] In this embodiment of the disclosure, in order to achieve personalized adaptation of cloud phone images to villages in the target area, it is first necessary to obtain two types of core data related to the characteristics of villages and user behavior in the area: village characteristic data can cover information reflecting the village's geographical attributes, population structure, economic industry type, public service resources, etc., and user behavior data can include the user's operation trajectory, function usage records, and interaction information generated on various related platforms or terminal devices. For the two types of raw data obtained, cleaning and structuring processing operations need to be performed. Cleaning processing can include removing invalid records, redundant information, and sensitive privacy information. Structuring processing can transform the raw data into structured characteristic information and behavior record information with standardization, validity, and analyzability by standardizing data formats, establishing a unified data model, and defining data fields, thus laying the data foundation for the subsequent tag extraction stage. As one implementation method, village characteristic data can be obtained from external data sources such as government open databases and map service platforms. Specifically, it includes the village's latitude and longitude (whether it is a mountainous area), population age distribution, main crops or types of characteristic handicrafts, number of schools / hospitals, etc. User behavior data can be collected by embedding a data collection SDK in a cloud mobile client or by cooperating with commonly used local apps such as village government service apps and local e-commerce platforms to call APIs. Cleaning can remove incorrect formatting and duplicate behavior records and hide sensitive personal information. After structuring, a village characteristic information table and a user behavior record table are formed.

[0027] By systematically acquiring and standardizing key data from the target area, the problems of disorganized raw data, interference from invalid information, and low data availability were effectively solved. This provided high-quality, standardized data support for the subsequent extraction of accurate village feature tags and user demand tags, directly ensuring the accuracy and reliability of the subsequent personalized cloud phone image generation process.

[0028] Step 102: Perform quantitative analysis on the structured feature information to extract village feature tags, and perform data mining analysis on the behavior record information to extract user demand tags.

[0029] In this embodiment, to accurately depict the characteristics of villages and user needs in the target area, in-depth analysis is required based on the structured feature information and behavioral record information generated in the aforementioned steps. For the structured feature information, statistical analysis tools are used to quantify the data in dimensions such as village geography, population, industry, and public services. Core indicators (such as the proportion of specific populations, the proportion of industry types, and the proportion of high-frequency related information) are calculated, and significant features (such as features where a certain type of attribute data exceeds a preset threshold) are extracted. The quantification results and significant features are integrated and transformed into village feature tags that can reflect the core characteristics of the village. For the behavioral record information, data mining techniques are used to deeply process data such as user operation trajectories, function usage frequency, and interaction preferences. This includes data association and integration, handling of missing and outlier values, feature extraction and filtering, and then summarizing user behavior patterns through models such as cluster analysis and classification algorithms. In this way, user demand tags that can accurately represent user functional needs and operating habits are extracted, providing accurate demand basis for subsequent image customization. As one implementation method, statistical analysis tools such as Excel and Python can be used to calculate core indicators such as the proportion of the village's population aged 18-40 and the average opening time of a certain type of APP to extract village feature tags. Users with similar behavioral patterns are classified by K-means clustering algorithm, and the demand types of unlabeled users are predicted by classification algorithms such as decision tree and random forest. Finally, a standardized set of village feature tags and user demand tags are formed.

[0030] By using quantitative analysis and data mining techniques, structured data is transformed into concrete and standardized feature tags and demand tags, which effectively solves the problem that structured data is difficult to directly associate with image customization requirements and that potential user needs cannot be accurately identified. This provides a clear demand guide for matching compatible components from the image component library, and directly improves the accuracy and adaptability of subsequent personalized cloud phone image generation.

[0031] Step 103: Based on village feature tags and user demand tags, select functional components and configuration schemes from the pre-built image component library through similarity matching to generate a customized cloud phone image template.

[0032] In this embodiment, to generate a customized cloud phone image template that meets the needs of villages in the target area, a matching process is first carried out based on a pre-built image component library. This image component library can cover various functional components that support the implementation of cloud phone functions, interactive configurations that meet user interaction experience, and configuration schemes that ensure system operation. Each component in the library is labeled with corresponding feature tags to adapt to matching requirements. Based on the village feature tags and user requirement tags extracted in the aforementioned steps, the two types of tags are converted into structured feature vectors. Through a pre-set similarity matching algorithm (such as calculating the overlap between tags, feature vector similarity, etc.), the feature tags of each component and configuration scheme in the image component library are compared, and functional components and configuration schemes with similarity higher than a pre-set threshold are selected. Subsequently, combined with the core characteristics of villages in the target area and key user needs, the selected functional components and configuration schemes are optimized and adjusted in detail, including functional priority sorting, interface adaptation adjustment, system parameter configuration optimization, and security settings configuration for specific groups of people. Finally, they are integrated to form a customized cloud phone image template with personalized adaptation capabilities. As one implementation method, the mirror component library can include functional components such as agricultural technology knowledge apps and e-commerce live streaming plugins, interactive templates such as large font interface layouts, and configuration schemes such as data saving modes and paid permission control. Village feature tags [terrain = mountainous, dominant industry = crop farming] and user demand tags [operation complexity = simple, core demand = agricultural technology learning] can be converted into feature vectors. These vectors are then matched with crop pest and disease control apps in the component library (tags [applicable industry = crop farming, applicable terrain = mountainous]) using a cosine similarity algorithm. After filtering, the font size of the interface is adjusted for elderly users, and commonly used agricultural technology apps are set as homepage priority functions to form customized mirror templates.

[0033] By matching tags for similarity and making targeted adjustments to components and configurations, the problem of existing general cloud phone images lacking regional and user-needs adaptability is effectively solved. This ensures that the customized cloud phone image templates can accurately match the industrial characteristics and user needs of the target villages, significantly improving the practicality and user acceptance of the images, and laying the foundation for the efficient deployment and use of the images in the future.

[0034] Step 104: Distribute the customized cloud phone image template to the target user's terminal device through the automated deployment platform.

[0035] In this embodiment, to achieve efficient and accurate delivery of customized cloud phone image templates to target user terminals, a pre-built automated deployment platform is required to perform the distribution operation. This platform first triggers an automated deployment process, generating cloud phone instances based on the customized cloud phone image template in batches using pre-defined scripts, according to the target user scale of the target region. This ensures that each generated cloud phone instance maintains consistency with the customized image template in terms of functionality and configuration. Subsequently, it connects to the user management system, and based on the target user list stored in the system (including user accounts, device identifiers, and other key information), it pushes the image usage entry point (such as login links, activation codes, etc.) using information delivery methods adapted to the usage habits of rural users, ensuring that target users can easily obtain and activate the customized image. Simultaneously, the customized cloud phone images distributed this time are version-marked, and key data during the deployment process (such as the number of users covered, image activation success rate, initial usage feedback, etc.) is recorded, forming a deployment report to support subsequent image management and iteration. As one implementation method, corresponding cloud phone instances can be generated in batches according to the number of users in the target village. Combined with the user list such as villagers' mobile phone numbers / ID numbers provided by the village collective, login links can be pushed via SMS or village government affairs APP. The mirror is marked with "XX Village June 2025 version" and data such as the number of users covered and the success rate of activation are recorded.

[0036] Through automated deployment and precise distribution mechanisms, the problems of low efficiency, uneven coverage, and high barriers to user acquisition and activation in traditional manual image deployment are effectively solved. This ensures that customized images can quickly and accurately reach target rural users, while also reducing the difficulty of users operating customized cloud phones. It provides efficient support for the large-scale implementation and popularization of customized cloud phone images in rural areas.

[0037] Step 105: Based on the target user usage data and updated village characteristic data, dynamically optimize and iterate the customized cloud phone image template.

[0038] In this embodiment, to ensure that the customized cloud phone image template continuously meets the dynamic needs of villages and users in the target area, dynamic optimization and version iteration are carried out based on target user usage data and updated village characteristic data. First, a data tracking and update mechanism is established to collect target user usage data of the current customized image in real time or periodically (including the frequency of function use, retention, abnormal error information during operation, and user-initiated feedback or suggestions, etc.). At the same time, updated village characteristic data reflecting the current status of the village is obtained (such as village industrial structure adjustment, increase or decrease of public service facilities, changes in population structure, etc.). Based on the newly acquired data, the aforementioned quantitative analysis and data mining logic is reused to reassess the matching degree between the existing customized image template and the current village characteristics and user needs, and to identify problems such as functional redundancy, mismatched configuration, or missing requirements in the image. According to the assessment results, the customized cloud phone image template is adjusted and optimized in a targeted manner, including adding or removing functional components, adjusting interaction configuration, and optimizing system parameters. After optimization, the image template is version-marked, and an iterative version is released to replace the old image, thereby realizing the dynamic updating of the image template. As one implementation method, it is possible to monitor in real time the uninstallation status of apps within the mirror, frequently clicked functions, and operational complexity issues reported by users. Every three months, the data analysis model is re-run in conjunction with updated feature data such as newly added cooperatives in villages and rural tourism projects. In this way, new homestay booking and scenic spot navigation apps can be added to the iterative version, or the system default font size can be increased to adapt to the needs of elderly users.

[0039] By dynamically tracking data and iteratively optimizing the image, the problem of existing cloud phone images being fixed once generated and unable to adapt to the dynamic changes in village and user needs is effectively solved. This ensures that the customized image always maintains a high degree of fit with the actual needs of the target area, which not only extends the applicable period of the image but also continuously improves the user experience, providing a guarantee for the long-term stable application of cloud phone technology in rural areas.

[0040] The cloud phone image adaptation method disclosed herein acquires village feature data and user behavior data of the target area, cleans and structures them to generate structured feature information and behavior record information, then quantitatively analyzes the structured feature information to extract village feature tags, and performs data mining analysis on the behavior record information to extract user demand tags. Based on these tags, functional components and configuration schemes are selected from a pre-built image component library through similarity matching to generate a customized cloud phone image template. Subsequently, the customized image template is distributed to the target user's terminal device through an automated deployment platform. Simultaneously, the customized image template is dynamically optimized and iterated based on the target user's usage data and updated village feature data. Therefore, it can... This technology addresses the problem that existing cloud phone images, due to their "one-size-fits-all" general design, lack functional adaptation to the unique industries of different villages and fail to meet the interactive needs of users of different ages and cultural backgrounds. This results in insufficient image adaptability and low practicality, hindering the popularization of cloud phones in rural areas and impeding the downward flow of digital dividends to rural areas. The goal is to generate personalized cloud phone images for each village, tailored to its geographical characteristics, economic structure, population composition, and user needs, thus improving the relevance and practicality of the images to actual rural needs. This lowers the barrier to entry for rural users to use smart terminals, promotes the large-scale application of cloud phones in rural areas, unleashes rural digital productivity, and provides strong support for rural digital development.

[0041] Within the technical framework revealed in step 101, acquiring village characteristic data and user behavior data in the target area can be further specified as follows: obtaining village geographical location, population structure, and economic industry information from external data source interfaces to generate village characteristic data; recording user behavior trajectories through embedded data acquisition algorithms or application programming interfaces, and desensitizing and filtering invalid information from the behavior trajectories to form standardized user behavior data.

[0042] Specifically, in step 101, when obtaining village feature data for the target area, standardized interfaces are used to connect to external data sources such as government open databases and map service platforms. During the interface call process, the data interaction protocol preset by the data source party is followed to obtain the target village's geographical location information (including precise latitude and longitude coordinates, terrain attributes such as whether it belongs to mountainous or plain areas), population structure information (covering detailed data such as the total population of the village, the population distribution ratio of each age group, and the male-female ratio), and economic industry information (specifically including the village's leading industry type such as the main crop varieties, whether there are characteristic handicrafts or agricultural product processing industries, etc.). These obtained information are integrated to form the initial village feature data. When acquiring user behavior data, two specific methods are adopted: First, an embedded data acquisition algorithm (i.e., a data acquisition SDK) is built into the cloud phone client. Second, cooperation is established with commonly used applications in rural areas, such as village government service apps and local agricultural e-commerce platforms. By calling the open application programming interfaces (APIs) of these applications, the user's behavior trajectory on the cloud phone or cooperative apps is recorded in real time (including the types of applications opened by the user each day, search keywords in each application, product browsing records and purchase categories on e-commerce platforms, and duration of function usage, etc.). Subsequently, the recorded behavior trajectory data is anonymized, specifically hiding sensitive personal information such as the user's mobile phone number and ID card number. At the same time, data verification algorithms are used to filter invalid information, such as removing operation records with incorrect formats (such as click logs with missing fields) and duplicated behavior data (such as multiple records of the same operation due to network latency). Finally, standardized user behavior data with uniform format and valid information is formed.

[0043] By clearly defining the types of external data sources and interface interaction methods, the authority and accuracy of village characteristic data are ensured, avoiding information bias caused by messy data sources. The combination of embedded data acquisition algorithms and APP interfaces can comprehensively cover the behavioral scenarios of rural users. At the same time, the anonymization process and invalid information filtering not only protect user privacy and security but also improve the quality of user behavior data, providing a high-quality initial data foundation for subsequent data cleaning and structuring processing.

[0044] Within the technical framework revealed in step 102, data mining analysis of behavioral record information to extract user demand tags can be further specified as follows: using clustering algorithms to group user behavior feature vectors to identify user groups with similar behavioral patterns; evaluating user groups to determine the optimal number of groups; and summarizing user demand types based on the grouping results to generate user demand tags.

[0045] Specifically, in step 102, when performing data mining analysis on the behavior record information to extract user demand tags, firstly, based on the structured user behavior record table, the scattered user behavior data (such as click records, dwell time, operation sequences, interaction content, etc.) are linked and integrated according to user ID or device ID to construct a user-behavior matrix. Missing data in the matrix is ​​filled with the mean or marked as "no such behavior," while abnormal operation records such as 100 clicks within 1 second are removed. Then, data standardization is achieved by converting dwell time into a relative proportion and normalizing the number of clicks to the 0-1 range, generating user behavior feature vectors. Subsequently, the K-means clustering algorithm is used, based on Euclidean distance or cosine similarity, to group user behavior feature vectors, grouping users with similar behavior patterns into the same group (for example, users who click the shopping cart 5 times a day and place 3 orders per week are grouped into one category, while users who browse information for 1 hour a day and almost never place orders are grouped into another category). When determining the optimal number of groups, an evaluation method combining the elbow method and the silhouette coefficient is adopted: by testing the clustering results under different K values, the silhouette coefficient corresponding to each K value is calculated, and the K value with the highest silhouette coefficient is selected as the optimal number of groups, avoiding fragmentation of demand due to too many groups or confusion of demand due to too few groups. Finally, for each user group after the optimal grouping, the commonalities of their core behavioral characteristics are statistically analyzed (e.g., a certain group frequently uses the search function and the search terms are mostly agricultural product prices). Based on these commonalities, user demand types are summarized (e.g., "agricultural product price inquiry and sales demand"), and clear tag names (e.g., "agricultural product production and sales demand type") and descriptions are defined for each demand type, forming a reusable demand type dictionary, and finally generating standardized user demand tags.

[0046] The K-means clustering algorithm is used to accurately group user behavior features. The elbow method and silhouette coefficient are combined to ensure the optimal number of groups, effectively avoiding the bias in user group segmentation. Based on the commonalities of group behavior, the demand types are summarized and tags are generated, so that the tags can accurately reflect the real needs of users. This provides a reliable demand basis for subsequent accurate matching with the image component library, and further improves the adaptability of customized cloud phone images.

[0047] Furthermore, in this embodiment of the disclosure, the image component library includes functional components, interaction templates, and configuration schemes, and sets feature tags for each component; wherein, the tags for functional components include applicable industries and operational difficulty, the tags for interaction templates include user groups and interaction characteristics, and the tags for configuration schemes include network adaptation strategies and security permission settings.

[0048] Specifically, the mirror component library comprises three core categories: functional components, interactive templates, and configuration schemes. Each component or scheme within each category has a clearly defined unique feature tag. Functional components include applications and tool plugins supporting various scenarios for rural users, such as agricultural technology knowledge apps adapted for agricultural production and e-commerce live-streaming plugins for agricultural product sales. Their feature tags strictly include applicable industry and operational difficulty: the applicable industry tag is determined based on the rural industry scenario corresponding to the component; for example, an agricultural technology knowledge app is labeled "Applicable Industry = Planting," and an e-commerce live-streaming plugin is labeled "Applicable Industry = E-commerce / Specialty Agricultural Products." The operational difficulty tag is based on the complexity of the component's operation steps; for example, a simple agricultural technology query tool for elderly users is labeled "Operation Difficulty = Simple," and a professional e-commerce data analysis plugin for young users is labeled "Operation Difficulty = Medium." The interaction templates include interface layouts and operation flows adapted to the usage habits of different user groups, such as a large-font desktop layout for elderly users and a high-frequency function shortcut layout for young people returning to their hometowns. Their feature tags include user groups and interaction characteristics: the user group tag clearly identifies the target audience for the component, such as the large-font desktop layout being labeled "User Group = Elderly Users," and the shortcut layout being labeled "User Group = Young People Returning to Their Hometowns"; the interaction characteristic tag describes the interface and operation features, such as the former being labeled "Interaction Characteristics = Large Font + Fewer Steps," and the latter being labeled "Interaction Characteristics = High-Frequency Function Shortcuts + Multi-Window Switching." The configuration scheme includes parameter settings to ensure stable operation and secure use of the image, such as a data-saving mode adapted to weak network environments in rural areas, and a permission control scheme to protect the consumption safety of the elderly and children. Its feature tags include network adaptation strategies and security permission settings: the network adaptation strategy tag corresponds to network environment requirements, such as the data-saving mode being labeled "Network Adaptation Strategy = Weak Network Optimization"; the security permission setting tag clearly defines the scope of permission control, such as the elderly and children permission scheme being labeled "Security Permission Settings = Non-Essential Paid Permissions Disabled."

[0049] By setting precise and differentiated feature tags for the different components of the mirror component library, the suitable scenarios, operational requirements, and operating conditions of each component are clearly identifiable. Subsequently, when matching village feature tags with user demand tags, the system can quickly locate the perfectly matching component, greatly improving matching efficiency and accuracy. At the same time, the setting of network adaptation and security permission-related tags also ensures that the mirror can adapt to the rural network environment and protect user security, further meeting the actual usage needs in rural areas.

[0050] Within the technical framework disclosed in step 104, distributing customized cloud phone image templates to target users' terminal devices through an automated deployment platform can be further specified as follows: generating cloud phone instances in batches according to the number of users and loading customized cloud phone image templates; sending image access links or activation credentials to target users through a message push service, wherein the link or credential contains user identity verification information.

[0051] Specifically, in step 104, when the customized cloud phone image template is distributed to the target user's terminal device through the automated deployment platform, the automated deployment platform first triggers the preset automated deployment process. The platform will first connect to the user management system to obtain the number of users in the target village, and then generate the corresponding number of cloud phone instances in batches according to the obtained number of users through built-in script instructions. During the generation process, the platform will automatically "copy" the customized cloud phone image template generated in step 103 and load it into each cloud phone instance. The verification algorithm ensures that all cloud phone instances and customized cloud phone image templates are completely consistent in terms of functional modules, interface configuration, and parameter settings, avoiding usage problems caused by instance differences. Subsequently, the automated deployment platform connects to a message push service (such as an SMS service interface or a message push module of a village government affairs APP), and simultaneously extracts a list of target users from the user management system (including users' personal mobile phone numbers, unique device identifiers, etc.). Based on this list, it sends an image access link or activation credential to each target user. The access link is a URL address containing user identity verification information (verification information includes user account ID and a unique identifier bound to the device), and the activation credential is a randomly generated 6-8 digit verification code (the verification code is pre-associated and bound to the user account within the system). When a user clicks the access link through their terminal device, they must complete identity verification (the system automatically matches the user ID and device identifier in the link), or enter the activation credential to complete verification. Only after successful verification can the user access and use the cloud phone instance loaded with the customized image.

[0052] By generating cloud phone instances in batches and loading customized images through script commands, the efficiency of image distribution is greatly improved, avoiding repetitive operations and errors during manual deployment. The access links or activation credentials containing identity verification information can effectively prevent unauthorized access to customized images by non-target users, ensuring the security of image usage. At the same time, relying on SMS or village government affairs APP push methods also fits the daily usage habits of rural users, reducing the operational threshold for users to obtain and use customized images.

[0053] Within the technical framework revealed in step 105, the customized cloud phone image template is dynamically optimized and iterated based on target user usage data and updated village feature data. This can be further specified as follows: monitoring the target user's usage rate, operation error rate, and feedback content of the cloud phone image; periodically regenerating feature tags and demand tags based on updated village feature data; and adjusting the component configuration and parameter settings of the customized cloud phone image template according to the new tags and user feedback.

[0054] Specifically, in step 105, when dynamically optimizing and iterating the customized cloud phone image template based on target user usage data and updated village characteristic data, the monitoring module associated with the automated deployment platform first collects target user usage data of the cloud phone image in real time: the function usage rate is determined by statistically analyzing the average daily number of times each function component is opened, the duration of a single use, and the percentage of usage frequency (such as the weekly usage of the agricultural technology query APP and the operation frequency of the e-commerce transaction plugin); the operation error rate is statistically analyzed by recording the operation abnormality logs reported by the system (such as the number of times the function button is clicked, the frequency of data loading failures, and records of operation steps being stuck); the feedback content is collected through the feedback entry built into the cloud phone image (such as the "Feedback" button) to collect text suggestions, function requirements, or problem descriptions submitted by users (such as "the font is too small to see clearly" or "I hope to add an agricultural product logistics query function"). Subsequently, according to a preset cycle (e.g., every 3 months), updated village characteristic data (such as new rural tourism projects, changes in the number of cooperatives, the establishment of schools / hospitals, and adjustments in population age structure) is obtained by connecting to external data sources. This updated data, along with newly collected user usage data, is then input into the aforementioned statistical analysis tools and data mining models. The village characteristic tag extraction process (e.g., adding the "rural tourism leading industry" tag) and user demand tag generation process are then re-executed (e.g., adjusting the weight of the "elderly user interaction needs" tag). Finally, based on the newly generated tags and the previously collected user usage data (e.g., marking components with a usage rate of less than 5% as to be removed and functions with an error rate of more than 10% as to be repaired) and feedback, the customized cloud phone image template undergoes component configuration adjustments (e.g., adding a scenic spot navigation APP and deleting low-usage information components) and parameter setting optimizations (e.g., increasing the system default font size and fixing the running parameters of frequently reported error functions). After optimization, a new version number is assigned to the image template (e.g., "XX Village September 2025 Iteration Version"), forming the iterated customized cloud phone image template.

[0055] By accurately monitoring function usage rate, operation error rate, and user feedback, issues such as functional redundancy and operational defects in the image template can be quickly identified. By combining updated village feature data to regenerate tags and adjust configurations, it can be ensured that the image template adapts to changes in village development and user needs in a timely manner. This effectively prevents the image from becoming detached from actual use cases due to dynamic changes in needs, continuously improves the practicality of the image and the user experience, and ensures the long-term adaptability of cloud phone technology in rural areas.

[0056] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0057] Corresponding to the cloud phone image adaptation method described above, this disclosure also proposes a cloud phone image adaptation device. Since the device embodiments of this disclosure correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to the method embodiments described above, and will not be repeated here.

[0058] Figure 2 This is a schematic diagram of the structure of a cloud phone image adaptation device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is used to acquire village feature data and user behavior data of the target area, and to clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information. Extraction unit 22 is used to perform quantitative analysis on structured feature information to extract village feature tags, and to perform data mining analysis on behavior record information to extract user demand tags. The generation unit 23 is used to select functional components and configuration schemes from the pre-built image component library based on village feature tags and user demand tags through similarity matching, and generate a customized cloud phone image template. Distribution unit 24 is used to distribute customized cloud phone image templates to the terminal devices of target users through an automated deployment platform; Optimization unit 25 is used to dynamically optimize and iterate the customized cloud phone image template based on target user usage data and updated village feature data.

[0059] The cloud phone image adaptation device disclosed herein acquires village feature data and user behavior data of the target area, cleans and structures them to generate structured feature information and behavior record information, then quantitatively analyzes the structured feature information to extract village feature tags, and performs data mining analysis on the behavior record information to extract user demand tags. Based on these tags, functional components and configuration schemes are selected from a pre-built image component library through similarity matching to generate a customized cloud phone image template. Subsequently, the customized image template is distributed to the target user's terminal device through an automated deployment platform. Simultaneously, the customized image template is dynamically optimized and iterated based on the target user's usage data and updated village feature data. Therefore, it can... This technology addresses the problem that existing cloud phone images, due to their "one-size-fits-all" general design, lack functional adaptation to the unique industries of different villages and fail to meet the interactive needs of users of different ages and cultural backgrounds. This results in insufficient image adaptability and low practicality, hindering the popularization of cloud phones in rural areas and impeding the downward flow of digital dividends to rural areas. The goal is to generate personalized cloud phone images for each village, tailored to its geographical characteristics, economic structure, population composition, and user needs, thus improving the relevance and practicality of the images to actual rural needs. This lowers the barrier to entry for rural users to use smart terminals, promotes the large-scale application of cloud phones in rural areas, unleashes rural digital productivity, and provides strong support for rural digital development.

[0060] Furthermore, in one possible implementation of this embodiment, the acquisition unit 21 is also used for: Village feature data is generated by obtaining information on the village's geographical location, population structure, and economic industries from external data source interfaces. User behavior trajectories are recorded through embedded data acquisition algorithms or application programming interfaces, and the trajectories are anonymized and invalid information is filtered to form standardized user behavior data.

[0061] Furthermore, in one possible implementation of this embodiment, the extraction unit 22 is also used for: Clustering algorithms are used to group user behavior feature vectors to identify user groups with similar behavior patterns; The user groups are evaluated to determine the optimal number of groups, and user demand types are summarized based on the grouping results to generate user demand tags.

[0062] Furthermore, in one possible implementation of this embodiment, the mirror component library includes functional components, interaction templates, and configuration schemes, and sets feature tags for each component; The labels for functional components include applicable industries and operational difficulty; the labels for interactive templates include user groups and interactive features; and the labels for configuration schemes include network adaptation strategies and security permission settings.

[0063] Furthermore, in one possible implementation of this embodiment, the distribution unit 24 is also used for: Generate cloud phone instances in batches based on the number of users, and load customized cloud phone image templates; Send a mirror access link or activation credential to the target user via push notification service. The link or credential contains user identity verification information.

[0064] Furthermore, in one possible implementation of this embodiment, the optimization unit 25 is also used for: Monitor target users' usage rate, error rate, and feedback content regarding cloud phone images; Regularly regenerate feature tags and demand tags based on updated village feature data, and adjust the component configuration and parameter settings of the customized cloud phone image template according to the new tags and user feedback.

[0065] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0066] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0067] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0068] like Figure 3As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 302 or a computer program loaded from storage unit 308 into RAM (Random Access Memory) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0069] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0070] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the cloud phone image adaptation method. For example, in some embodiments, the cloud phone image adaptation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the aforementioned cloud phone image adaptation method by any other suitable means (e.g., by means of firmware).

[0071] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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.

[0072] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0073] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable 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. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0074] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. 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).

[0075] 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 LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0076] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via 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. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0077] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0078] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0079] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0080] 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 disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0081] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. A cloud phone image adaptation method, characterized in that, include: Obtain village feature data and user behavior data of the target area, and clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information; The structured feature information is quantitatively analyzed to extract village feature tags, and the behavior record information is analyzed by data mining to extract user demand tags. Based on the village feature tags and user demand tags, functional components and configuration schemes are selected from the pre-built image component library through similarity matching to generate a customized cloud phone image template; The customized cloud phone image template is distributed to the target user's terminal device through an automated deployment platform; Based on target user usage data and updated village characteristic data, the customized cloud phone image template is dynamically optimized and iterated.

2. The method according to claim 1, characterized in that, The acquisition of village characteristic data and user behavior data in the target area includes: The village's geographical location, population structure, and economic industry information are obtained from external data source interfaces to generate the village's characteristic data; User behavior trajectories are recorded through embedded data acquisition algorithms or application programming interfaces, and the trajectories are anonymized and invalid information is filtered to form standardized user behavior data.

3. The method according to claim 1, characterized in that, The step of performing data mining analysis on the behavior record information to extract user demand tags includes: Clustering algorithms are used to group user behavior feature vectors to identify user groups with similar behavior patterns; The user group is evaluated to determine the optimal number of groups, and the user demand types are summarized based on the grouping results to generate the user demand tags.

4. The method according to claim 1, characterized in that, The mirror component library includes functional components, interaction templates, and configuration schemes, and sets feature tags for each component; The labels for the functional components include applicable industries and operational difficulty; the labels for the interaction templates include user groups and interaction characteristics; and the labels for the configuration schemes include network adaptation strategies and security permission settings.

5. The method according to claim 1, characterized in that, The step of distributing the customized cloud phone image template to the target user's terminal device through an automated deployment platform includes: Generate cloud phone instances in batches according to the number of users, and load the customized cloud phone image template; A mirror access link or activation credential is sent to the target user via a push notification service, wherein the link or credential contains user identity verification information.

6. The method according to claim 1, characterized in that, The dynamic optimization and version iteration of the customized cloud phone image template based on target user usage data and updated village characteristic data includes: Monitor the target users' usage rate, error rate, and feedback content regarding the cloud phone image function; Feature tags and demand tags are regenerated periodically by combining updated village feature data, and the component configuration and parameter settings of the customized cloud phone image template are adjusted based on the new tags and user feedback.

7. A cloud phone image adaptation device, characterized in that, include: The acquisition unit is used to acquire village feature data and user behavior data of the target area, and to clean and structure the village feature data and user behavior data to generate structured feature information and behavior record information. The extraction unit is used to perform quantitative analysis on the structured feature information to extract village feature tags, and to perform data mining analysis on the behavior record information to extract user demand tags. The generation unit is used to select functional components and configuration schemes from a pre-built image component library based on the village feature tags and user demand tags through similarity matching, and generate a customized cloud phone image template. The distribution unit is used to distribute the customized cloud phone image template to the target user's terminal device through an automated deployment platform; The optimization unit is used to dynamically optimize and iterate the customized cloud phone image template based on target user usage data and updated village feature data.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images