Mobile terminal big data contrastive analysis system and mobile terminal

Abstract

The invention provides a mobile terminal big data contrastive analysis system and a mobile terminal. The mobile terminal big data contrastive analysis system comprises a data acquisition module, a cache unit and an intelligent comparison processor which are arranged on a mobile terminal side, the data acquisition module is used for collecting big data generated by the mobile terminal; the cache unit is used for caching big data generated by the mobile terminal; and the intelligent comparison processor is used for extracting the big data from the cache unit, dynamically adjusting a comparison strategy according to an application scene corresponding to the big data, performing big data comparison analysis according to the adjusted comparison strategy, outputting an analysis result, and completing big data comparison analysis on a mobile terminal side. According to the technical scheme, the problems of network delay, data transmission safety, privacy protection and the like caused by big data comparison and analysis on a server side in the prior art can be solved, the data access speed can be increased through the cache unit, and the requirements for real-time performance and high efficiency are met.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a mobile terminal big data comparison and analysis system and a mobile terminal. Background Art

[0002] Comparative analysis of big data on mobile terminals can better understand user behavior and needs, so as to make more accurate decisions. For example, by analyzing the user's geographic location, device type, usage time, etc., developers can understand the user's behavior pattern, and then optimize the APP's functions and interface design to improve the user experience. In related technologies, by transmitting big data to the server for comparative analysis and processing, and then returning the analysis results to the mobile terminal, this method will bring about problems such as network latency, data transmission security and privacy protection. Moreover, with the increase in data volume and the diversification of processing requirements, this processing mode is increasingly difficult to meet the requirements of real-time and efficiency. Summary of the invention

[0003] The present invention provides a mobile terminal big data comparison and analysis system and a mobile terminal, which are used to solve the problems of network delay, data transmission security and privacy protection, and difficulty in meeting the real-time and high efficiency requirements in the traditional processing method of transmitting big data to a server for comparison and analysis and then returning the analysis results to the mobile terminal.

[0004] The present invention provides a mobile terminal big data comparison and analysis system, comprising: A data acquisition module, a cache unit and an intelligent comparison processor arranged on the mobile terminal side; The data acquisition module is used to collect big data generated by the mobile terminal; The cache unit is used to cache the big data generated by the mobile terminal; The intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

[0005] According to the mobile terminal big data comparison and analysis system provided by the present invention, the data acquisition module is arranged between the operating system layer and the application layer of the mobile terminal; the data acquisition module includes a capture unit, a filtering unit, a monitoring unit and a compression unit; The capture unit is used to directly intercept and capture the original data stream generated by the application program; The filtering unit is used to filter key data, wherein the key data includes application data with high user interaction frequency and long residence time, and metadata related to geographic location and timestamp; The monitoring unit is used to monitor the update or abnormality of the application in real time; The compression unit is used to compress the selected key data.

[0006] According to the mobile terminal big data comparison and analysis system provided by the present invention, the cache unit includes a plurality of sub-cache modules working in parallel, each sub-cache module is responsible for storing a specific type of data; Each sub-cache module is equipped with an independent data manager, which is used to evaluate the importance of data and adjust the cache strategy according to the importance of the data; The importance of the data is determined based on the access frequency and the assigned weight value; The cache strategy is adjusted according to a least recently used algorithm and a least frequently used algorithm.

[0007] According to the mobile terminal big data comparison and analysis system provided by the present invention, the cache unit also includes: Distributed consistency protocols, message queues, and version control mechanisms; The distributed consistency protocol is used to maintain data consistency in each sub-cache module; The message queue is used for asynchronous communication between various sub-cache modules; The version control mechanism is used to track the status changes of each data item. When a data item changes, the version number is used to determine whether the corresponding data items on other nodes need to be updated.

[0008] According to the mobile terminal big data comparison and analysis system provided by the present invention, the intelligent comparison processor includes: The resource management module is used to monitor the complexity of the current processing task and the system load, and increase or decrease the number of computing nodes according to the complexity of the current processing task and the system load.

[0009] According to the mobile terminal big data comparison and analysis system provided by the present invention, the intelligent comparison processor also includes: The anomaly detection module is used to compare the newly stored data with the normal behavior model and classify the newly stored data using a trained classifier. If the classification result is abnormal data, the newly stored data is marked as abnormal data and deleted.

[0010] According to the mobile terminal big data comparison and analysis system provided by the present invention, the normal behavior model is a machine learning model including an online learning algorithm. The normal behavior model is used to dynamically receive and process new data points, and adjust internal parameters in real time through an incremental learning algorithm.

[0011] According to the mobile terminal big data comparison and analysis system provided by the present invention, the online learning algorithm includes a gradient descent method and a stochastic gradient descent method, and the real-time adjustment of internal parameters through an incremental learning algorithm includes: updating local model parameters according to analysis results.

[0012] According to the mobile terminal big data comparison and analysis system provided by the present invention, the intelligent comparison processor also includes: Data type identification module and algorithm matching module; The data type identification module determines whether the data belongs to the structured or unstructured category by analyzing the metadata and content characteristics of the data; The algorithm matching module is used to select a corresponding comparison algorithm according to the data type. If the data type is structured data, the comparison algorithm is a rule-based query algorithm or a hash algorithm; if the data type is unstructured data, the comparison algorithm is a deep learning network algorithm.

[0013] The present invention also provides a mobile terminal, comprising a data acquisition module, a cache unit and an intelligent comparison processor; The data acquisition module is used to collect big data generated by the mobile terminal; The cache unit is used to cache the big data generated by the mobile terminal; The intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

[0014] The present invention provides a mobile terminal big data comparison and analysis system and a mobile terminal, wherein the mobile terminal big data comparison and analysis system comprises a data acquisition module, a cache unit and an intelligent comparison processor arranged on the mobile terminal side; the data acquisition module is used to collect big data generated by the mobile terminal; the cache unit is used to cache the big data generated by the mobile terminal; the intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison and analysis according to the adjusted comparison strategy, and output the analysis results. By completing the big data comparison and analysis on the mobile terminal side, the problems of network delay, data transmission security and privacy protection, etc. caused by the traditional big data comparison and analysis on the server side can be solved, and the data access speed can be improved through the cache unit to meet the requirements of real-time and high efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 This is one of the functional structure diagrams of the mobile terminal big data comparison and analysis system provided by an embodiment of the present invention; Figure 2 This is the second functional structure diagram of the mobile terminal big data comparison and analysis system provided by an embodiment of the present invention; Figure 3 It is a functional structure diagram of a mobile terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Figure 1 The flowchart of the mobile terminal big data comparison and analysis system provided by the embodiment of the present invention is as follows: Figure 1 As shown, the mobile terminal big data comparison and analysis system provided by the embodiment of the present invention includes: A data acquisition module 101, a cache unit 103 and an intelligent comparison processor 102 are arranged on the mobile terminal side; The data collection module 101 is used to collect big data generated by the mobile terminal; The cache unit 103 is used to cache the big data generated by the mobile terminal; The intelligent comparison processor 102 is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

[0019] In an embodiment of the present invention, the intelligent comparison processor integrates a machine learning model with a traditional comparison algorithm to form a powerful hybrid intelligent system. The machine learning model is trained based on historical comparison results, and can learn the potential associations and patterns between data to predict the comparison results of new data, which is particularly effective when processing large-scale data sets because it can significantly reduce the consumption of computing resources. For example, when identifying user behavior patterns, the model can learn the association between certain behavior sequences and specific user groups, so as to make quick judgments when encountering similar behaviors. The traditional comparison algorithm is used to verify the prediction accuracy of the machine learning model, and ensure the reliability of the comparison results by accurately matching the feature vectors of the data. This two-pronged strategy not only significantly improves the accuracy of the comparison, but also ensures that the optimal comparison effect can be achieved at different data levels by dynamically adjusting the algorithm weights. For example, when the amount of data is small, the system may rely more on the traditional comparison algorithm, and when the amount of data is huge, it relies more on the prediction ability of the machine learning model to balance accuracy and processing speed.

[0020] The traditional mobile terminal big data comparative analysis method is to transmit the big data to the server for comparative analysis and processing, and then return the analysis results to the mobile terminal. This method will bring about problems such as network latency, data transmission security and privacy protection. Moreover, with the increase in data volume and the diversification of processing requirements, this processing mode is increasingly difficult to meet the requirements of real-time and efficiency.

[0021] The mobile terminal big data comparison and analysis system provided by the embodiment of the present invention includes a data acquisition module, a cache unit and an intelligent comparison processor arranged on the mobile terminal side; the data acquisition module is used to collect big data generated by the mobile terminal; the cache unit is used to cache the big data generated by the mobile terminal; the intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison and analysis according to the adjusted comparison strategy, and output the analysis results. By completing the big data comparison and analysis on the mobile terminal side, the problems of network delay, data transmission security and privacy protection, etc. caused by the traditional big data comparison and analysis on the server side can be solved, and the data access speed can be improved through the cache unit to meet the requirements of real-time and high efficiency.

[0022] Based on any of the above embodiments, the data acquisition module is arranged between the operating system layer and the application layer of the mobile terminal; the data acquisition module includes a capture unit, a filtering unit, a monitoring unit and a compression unit; The capture unit is used to directly intercept and capture the original data stream generated by the application program; In the embodiment of the present invention, the capture unit can directly intercept and capture the original data stream generated by the application without additional intermediate processing or conversion.

[0023] The filtering unit is used to filter key data, wherein the key data includes application data with high user interaction frequency and long residence time, and metadata related to geographic location and timestamp; The embodiments of the present invention can filter out key data that meets the comparison conditions by presetting the data filtering mechanism. For example, when it comes to user behavior analysis, the module will give priority to collecting application data with high user interaction frequency and long residence time, as well as metadata related to geographic location and timestamp. For example, in a social media application, the data collection module will pay special attention to the user's likes, comments and sharing behaviors, as well as the time and place of these behaviors, so as to provide valuable information for subsequent comparison.

[0024] The monitoring unit is used to monitor the update or abnormality of the application in real time; In the embodiment of the present invention, the monitoring unit is located above the operating system layer and has the ability to continuously monitor changes in data flows at the application layer. The monitoring unit can capture any changes in data flows in real time during the execution of the application program, including but not limited to file operations, network communications, and database interactions, through hooking technology or syscall interception and other means. Once a change in data flow is detected, the monitoring unit will immediately trigger the data collection process to ensure that all data related to the comparison can be captured and stored in a timely manner, thereby improving the timeliness and accuracy of subsequent data comparisons.

[0025] For example, at the technical implementation level, the monitoring unit can use the inotify mechanism under the Linux platform or the ReadDirectoryChangesW function under the Windows platform to monitor file system change events. At the same time, use the libpcap or WinPcap library to capture network data packets, and use SQL injection detection tools such as SQLMap to monitor database query statements. The monitoring unit can be seamlessly integrated into the operating system environment and monitor data activities at the application layer in an imperceptible and efficient manner, thereby providing a steady stream of real-time data input for the data acquisition module, ensuring the efficient operation and accurate results of the entire comparison system.

[0026] The embodiment of the present invention can respond to updates or abnormal situations of the application program in real time through the monitoring unit, thereby ensuring the timeliness and integrity of the collected data, improving the efficiency and accuracy of the subsequent comparison process, and reducing unnecessary data transmission and storage costs.

[0027] The compression unit is used to compress the selected key data to reduce the data volume without losing important information, thereby speeding up data transmission and reducing storage space requirements.

[0028] In an embodiment of the present invention, the data filtering mechanism in the data acquisition module will filter out the key data that needs to be retained according to preset rules or algorithms; these key data will be sent to the compression unit for data compression. The compression unit can adopt existing high-efficiency compression algorithms, such as LZ77, LZ78, Huffman coding or more advanced compression technologies such as Brotli. In an embodiment of the present invention, the Brotli compression algorithm is used. The Brotli compression algorithm can provide a faster decompression speed while maintaining a high compression ratio, which is very suitable for big data processing scenarios of mobile terminals. In addition, the relationship between compression efficiency and processing time can be balanced by setting a reasonable compression level to ensure that the data volume can be effectively reduced without excessively increasing the processing burden of the system. In this way, not only can the speed of data transmission be significantly improved, but also the storage cost can be effectively reduced, thereby meeting the needs of big data processing of mobile terminals.

[0029] In the embodiment of the present invention, the compression unit performs efficient compression processing on the data determined to be critical after filtering, ensuring that the data volume is reduced without losing any important information, thereby increasing the speed of data transmission and reducing the required storage space.

[0030] According to the mobile terminal big data comparison and analysis system provided by the present invention, the cache unit includes a plurality of sub-cache modules working in parallel, each sub-cache module is responsible for storing a specific type of data; In an embodiment of the present invention, the cache unit is a distributed memory architecture, which is composed of multiple sub-cache modules working in parallel, and each sub-cache module is responsible for storing a specific type of data, such as text, image, audio or video. The advantage of this design is that, on the one hand, it can effectively reduce data access delays because the data is stored in multiple nodes in a dispersed manner, avoiding single-point bottlenecks; on the other hand, it ensures fast retrieval and comparison of different types of data, and improves the concurrency of data processing. For example, when processing a large amount of image data, the system can allocate the image data to a dedicated image cache module and use image processing algorithms for pre-processing, such as scaling, rotation or color adjustment, to speed up the subsequent comparison process.

[0031] Each sub-cache module is equipped with an independent data manager, which is used to evaluate the importance of data and adjust the cache strategy according to the importance of the data, ensuring that the most commonly used or most important data is always in the cache.

[0032] The importance of the data is determined based on the access frequency and the assigned weight value; The cache strategy is adjusted according to a least recently used algorithm and a least frequently used algorithm.

[0033] In an embodiment of the present invention, an independent data manager is integrated in each sub-cache module, and the manager is responsible for monitoring and analyzing the usage of the data stored in the module. For example, the access frequency of the data can be calculated by recording the timestamp of each time the data is accessed; at the same time, a weight value can be assigned to each piece of data, and the value can be dynamically adjusted according to the importance of the data. Secondly, the data manager regularly evaluates the importance of all data according to preset algorithms such as the least recently used algorithm (LRULeast Recently Used) and the least frequently used algorithm (LFULeast Frequently Used), and adjusts the cache strategy accordingly. For example, when the cache space is insufficient, the data manager will automatically remove those data with low access frequency and low importance, and retain those data with high access frequency and importance. In addition, it is also possible to combine machine learning technology to predict which data may be frequently accessed in the future by learning historical access patterns, so as to load these data into the cache in advance and further optimize the cache strategy.

[0034] In the embodiment of the present invention, each sub-cache module is equipped with an independent data manager, which can automatically adjust the cache strategy according to the access frequency and importance of the data, ensuring that the most commonly used or most important data is always in the cache to achieve fast access and comparison, improve the system's response speed and user experience. The system can effectively improve data processing efficiency and reduce unnecessary data loading time, thereby significantly improving overall performance.

[0035] According to the mobile terminal big data comparison and analysis system provided by the present invention, the cache unit also includes: Distributed consistency protocols, message queues, and version control mechanisms; The distributed consistency protocol is used to maintain data consistency in each sub-cache module; The message queue is used for asynchronous communication between various sub-cache modules; The version control mechanism is used to track the status changes of each data item. When a data item changes, the version number is used to determine whether the corresponding data items on other nodes need to be updated.

[0036] In an embodiment of the present invention, data synchronization can be achieved through a distributed consistency protocol, a message queue, and a version control mechanism, and real-time synchronization of data between various sub-cache modules can be achieved, ensuring that data consistency can be maintained even in the case of high concurrent access, thereby effectively avoiding comparison errors caused by data asynchrony. Distributed consistency protocols, such as Paxos or Raft protocols, can ensure data consistency of all participating nodes; message queues such as Kafka or RabbitMQ implement asynchronous communication between various sub-cache modules to ensure that data updates can be propagated to all relevant nodes in a timely and accurate manner; the version control mechanism can track the state changes of each data item. When a data item changes, the version number is used to determine whether the corresponding data items on other nodes need to be updated, thereby ensuring data consistency and accuracy. It not only improves the response speed of the system, but also enhances the stability and reliability of the system, and is particularly suitable for processing data comparison tasks in large-scale concurrent access scenarios.

[0037] Based on any of the above embodiments, the intelligent comparison processor includes: The resource management module is used to monitor the complexity of the current processing task and the system load, and increase or decrease the number of computing nodes according to the complexity of the current processing task and the system load.

[0038] In an embodiment of the present invention, an expandable computing resource pool is configured inside the intelligent comparison processor, and the resource pool can dynamically adjust the allocation of computing resources according to the complexity of the current processing task. When processing a large amount of data, the system can automatically increase the number of computing nodes, so as to effectively cope with the high load situation that may occur in the big data environment, and ensure the stable operation and efficient processing capacity of the system. When it is detected that the amount of data to be processed increases significantly, the resource management module will automatically start the preset resource expansion strategy. For example, computing nodes can be dynamically added through elastic computing services such as AWSEC2 Auto Scaling provided by cloud service providers. These additional computing nodes can be virtual machines or physical servers, which will be added to the existing computing resource pool to participate in data processing tasks together. In addition, in order to ensure that the newly added nodes can quickly participate in the processing flow, the necessary software environment can be deployed on each node in advance, and task scheduling and data distribution can be performed through distributed computing frameworks such as Apache Hadoop or Spark. After the data processing is completed, the resource management module can also reduce the number of computing nodes according to actual needs to save costs and maintain resource utilization efficiency. The embodiment of the present invention can effectively improve the processing speed and flexibility of mobile terminal big data, while reducing the risk of system crash caused by the surge in data volume.

[0039] In an embodiment of the present invention, the intelligent comparison processor further includes: The anomaly detection module is used to compare the newly stored data with the normal behavior model and classify the newly stored data using a trained classifier. If the classification result is abnormal data, the newly stored data is marked as abnormal data and deleted.

[0040] In an embodiment of the present invention, the anomaly detection module can automatically identify and mark data points that deviate from the normal distribution or do not conform to the expected behavior pattern by applying statistical methods and machine learning techniques to the input data for in-depth analysis, thereby assisting the system to filter out abnormal data, thereby significantly improving the accuracy and reliability of the comparison results. A normal behavior model is established based on historical data, which can be accomplished through a variety of statistical methods, such as using parameters such as mean and standard deviation to define a normal range; introducing machine learning algorithms such as support vector machines, clustering algorithms or deep learning models to train a classifier that can distinguish between normal data and abnormal data; in actual operation, when a new data point enters the system, the anomaly detection module will compare it with the existing normal behavior model and evaluate it using the trained classifier. If a data point is found to be significantly deviated from the normal range, it will be marked as abnormal data and excluded from the subsequent comparison process, which can effectively reduce the impact of abnormal data on the final comparison results and ensure the stability and accuracy of the system.

[0041] In an embodiment of the present invention, the normal behavior model is a machine learning model including an online learning algorithm, and the normal behavior model is used to dynamically receive and process new data points and adjust internal parameters in real time through an incremental learning algorithm.

[0042] The online learning algorithm includes a gradient descent method and a stochastic gradient descent method. The real-time adjustment of internal parameters by an incremental learning algorithm includes: updating local parameters of the model according to the analysis results.

[0043] The normal behavior model can dynamically receive and process new data points generated by the comparison operation as feedback information while the system is running continuously. By implementing an incremental learning algorithm, the model can adjust its internal parameters in real time to reflect the latest changes in the data set, thereby keeping the model's predictive performance matched to the actual distribution of the data and ensuring the system's predictive accuracy and adaptability. When the system receives new comparison results, these results are immediately used to update the model parameters without retraining the entire model. For example, assuming that we are using a support vector machine SVM model for comparison, an online SVM algorithm can be used, which allows only the affected support vectors to be locally updated after each new sample is received, rather than recalculating all support vectors. In this way, even in the case of streaming data input, the model can quickly adapt to new features of the data while maintaining low computational complexity and storage requirements, ensuring the efficiency and intelligence of the system when processing big data on mobile terminals.

[0044] In an embodiment of the present invention, the intelligent comparison processor further includes: Data type identification module and algorithm matching module; The data type identification module determines whether the data belongs to the structured or unstructured category by analyzing the metadata and content characteristics of the data; The algorithm matching module is used to select a corresponding comparison algorithm according to the data type. If the data type is structured data, the comparison algorithm is a rule-based query algorithm or a hash algorithm; if the data type is unstructured data, the comparison algorithm is a deep learning network algorithm.

[0045] The embodiment of the present invention can dynamically identify and respond to the characteristics of different data types, so as to automatically select the most suitable comparison algorithm during the processing process. When the system receives structured data, the intelligent comparison processor will give priority to using traditional algorithms for comparison, because traditional algorithms usually show high efficiency and accuracy when processing data sets with fixed formats and clear logic; while in the face of unstructured data, such as text, images or videos, the processor will turn to the use of machine learning models, which are trained to understand and parse complex, non-fixed pattern information, so as to achieve more efficient and more accurate comparison results. In order to realize the above-mentioned adaptive algorithm selection mechanism, a set of data type identification modules and algorithm matching strategies are integrated into the intelligent comparison processor. The data type identification module determines whether the data belongs to a structured or unstructured category by analyzing the metadata and content characteristics of the data. For example, if the data contains predefined fields and formats, such as database records or table data, it is classified as structured data; conversely, if the data lacks a clear structure, such as free text or multimedia files, it is regarded as unstructured data. Once the data type is determined, the algorithm matching strategy will select the corresponding comparison algorithm according to the preset rules. For structured data, the system may call rule-based query languages ​​such as SQL or hash algorithms for fast comparison; for unstructured data, the system may start deep learning networks, such as convolutional neural networks (CNN) for image comparison, or long short-term memory networks (LSTM) for text analysis, to achieve intelligent comparison. This adaptive mechanism ensures that the system can always use the optimal algorithm when processing various types of big data, thereby significantly improving the comparison speed and accuracy.

[0046] In some embodiments of the present invention, the intelligent comparison processor also includes a result verification module, which is used to enhance the accuracy and reliability of the system, and ensure the correctness of the comparison results by implementing a secondary verification mechanism. After the initial comparison, the result verification module uses an independent algorithm or data set to check the results again to identify and correct any potential errors or inconsistencies, thereby improving the overall comparison accuracy. For example, a rule-based verification method, that is, to check whether the comparison results meet the expected standards according to preset business logic or data integrity rules. Alternatively, a machine learning model is used to train the model to identify the correct comparison mode, and then the model is applied to the comparison results to evaluate its accuracy. In addition, the result verification module also has a recording function, which can record the operation process, parameter settings and final results of each comparison in detail. This information is crucial for subsequent system maintenance and performance optimization, helps to analyze comparison efficiency, identify bottlenecks, and guide the iterative upgrade of the algorithm to ensure that the system continues to operate efficiently.

[0047] The embodiments of the present invention not only improve the accuracy of the comparison, but also enhance the transparency and traceability of the system, so that any comparison result can be reviewed and verified, which is particularly important for scenarios that process sensitive or high-value data, such as financial transactions, medical diagnosis, or legal evidence analysis, ensuring the fairness and credibility of data processing.

[0048] In some embodiments of the present invention, the intelligent comparison processor also includes a user feedback interface, which can enhance the adaptability and accuracy of the system. The user feedback interface allows the end user to directly participate in the review process of the comparison results. By providing positive or negative feedback, the user can correct the misjudgment or omission that the system may produce. These feedback information is then collected by the system and integrated as part of the training data set. By continuously using user feedback to train and optimize the machine learning model, the system can gradually improve its recognition and comparison accuracy, thereby improving the overall intelligence level and ensuring that the comparison results are more in line with actual needs and expectations. The design and integration of the user feedback interface can be completed in a variety of ways. For example, a feedback module can be embedded in the application of the mobile terminal. When the user receives the comparison result, he can choose to accept, reject or modify the result and attach a brief explanation of the reason. These operations will trigger the application to send a feedback signal to the intelligent comparison processor, which contains the user's choice and additional information. On the server side, after receiving the feedback, the intelligent comparison processor will parse and convert it into a data format that the machine learning model can understand, and then update the model parameters in real time through the online learning algorithm, so that the model can learn from each user interaction and adjust its decision logic. In addition, in order to ensure the generalization ability of the model and avoid overfitting, the system also needs to regularly use a large amount of historical feedback data for offline training to ensure that the model remains efficient and accurate when processing new data. Through this closed-loop learning mechanism, the system can continue to evolve and eventually reach a higher level of intelligence.

[0049] like Figure 2 As shown, the data acquisition module is arranged between the operating system layer and the application layer of the mobile terminal, so as to directly obtain the original data stream generated by the application, and pre-process the data through the built-in filter component; the cache unit includes a first-level cache and a second-level cache, wherein the first-level cache is located near the intelligent comparison processor and is used to store the most recently frequently accessed data, and the second-level cache is used to store less frequently accessed but still important data; the intelligent comparison processor includes a hardware accelerator and a programmable logic array, wherein the hardware accelerator is used to execute complex comparison algorithms, and the programmable logic array can dynamically adjust the comparison strategy according to different application scenarios, and the intelligent comparison processor also integrates a machine learning model, which can automatically optimize the comparison algorithm according to historical comparison results.

[0050] In actual operation, the big data generated by the mobile terminal is first captured by the data acquisition module. Subsequently, the key data that meets the comparison conditions is screened out through the preset data filtering mechanism. This process effectively improves the efficiency and accuracy of the subsequent comparison process. These key data will be sent to the cache unit for temporary storage. The unit adopts a distributed memory architecture and consists of multiple sub-cache modules working in parallel. Each sub-cache module is responsible for storing a specific type of data. This design not only reduces data access latency, but also ensures fast retrieval and comparison of different types of data, thereby improving the processing power of the entire system. Finally, the intelligent comparison processor comes into play. It integrates a machine learning model and a traditional comparison algorithm. The machine learning model is trained based on historical comparison results to predict the comparison results of new data; while the traditional comparison algorithm is used to verify the prediction accuracy of the machine learning model. The combination of the two can significantly improve the accuracy of the comparison.

[0051] By dynamically adjusting the algorithm weights, the intelligent comparison processor can ensure the best comparison results at different data levels. Throughout the process, the data acquisition module, cache unit and intelligent comparison processor work closely together to achieve fast intelligent comparison of big data on mobile terminals, solving the efficiency and accuracy issues of data comparison in a big data environment.

[0052] In the embodiment of the present invention, the fast intelligent comparison system of mobile terminal big data can effectively solve the problem of efficient and accurate comparison of mobile terminal data in a big data environment. The data acquisition module ensures the timely capture and preprocessing of key data, the cache unit provides low-latency data storage and retrieval services, and the intelligent comparison processor achieves high-precision and high-efficiency data comparison. These three components work together to build a powerful and flexible comparison system that can maintain high performance and high reliability in various complex scenarios.

[0053] The mobile terminal big data comparison and analysis system provided by the embodiment of the present invention collects big data generated by the mobile terminal through a data acquisition module; a cache unit temporarily stores the data to be compared to improve the processing speed; an intelligent comparison processor executes an efficient comparison algorithm to ensure accuracy and rapid response; and solves the new problems such as network delay, data transmission security and privacy protection brought about by the centralized processing mode of the server in the prior art, thereby improving the real-time and efficiency of data comparison.

[0054] The embodiment of the present invention further provides a mobile terminal, including a data acquisition module, a cache unit and an intelligent comparison processor; The data acquisition module is used to collect big data generated by the mobile terminal; The cache unit is used to cache the big data generated by the mobile terminal; The intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

[0055] Figure 3 An example of a physical structure diagram of a mobile terminal is shown in FIG. Figure 3 As shown, the mobile terminal may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The memory 330 includes a computer program, an operating system and acquired data, and the processor 310 may call the logic instructions in the memory 330.

[0056] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0057] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0058] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mobile terminal big data comparison and analysis system, characterized in that: include: A data acquisition module, a cache unit and an intelligent comparison processor arranged on the mobile terminal side; The data acquisition module is used to collect big data generated by the mobile terminal; The cache unit is used to cache the big data generated by the mobile terminal; The intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

2. The mobile terminal big data comparison and analysis system according to claim 1, characterized in that: The data acquisition module is arranged between the operating system layer and the application layer of the mobile terminal; the data acquisition module comprises a capture unit, a filtering unit, a monitoring unit and a compression unit; The capture unit is used to directly intercept and capture the original data stream generated by the application program; The filtering unit is used to filter key data, wherein the key data includes application data with high user interaction frequency and long residence time, and metadata related to geographic location and timestamp; The monitoring unit is used to monitor the update or abnormality of the application in real time; The compression unit is used to compress the selected key data.

3. The mobile terminal big data comparison and analysis system according to claim 1, characterized in that: The cache unit includes a plurality of sub-cache modules working in parallel, each sub-cache module is responsible for storing a specific type of data; Each sub-cache module is equipped with an independent data manager, which is used to evaluate the importance of data and adjust the cache strategy according to the importance of the data; The importance of the data is determined based on the access frequency and the assigned weight value; The cache strategy is adjusted according to a least recently used algorithm and a least frequently used algorithm.

4. The mobile terminal big data comparison and analysis system according to claim 3, characterized in that: The cache unit also includes: Distributed consistency protocols, message queues, and version control mechanisms; The distributed consistency protocol is used to maintain data consistency in each sub-cache module; The message queue is used for asynchronous communication between various sub-cache modules; The version control mechanism is used to track the status changes of each data item. When a data item changes, the version number is used to determine whether the corresponding data items on other nodes need to be updated.

5. The mobile terminal big data comparison and analysis system according to claim 1, characterized in that: The intelligent comparison processor comprises: The resource management module is used to monitor the complexity of the current processing task and the system load, and increase or decrease the number of computing nodes according to the complexity of the current processing task and the system load.

6. The mobile terminal big data comparison and analysis system according to claim 5, characterized in that: The intelligent comparison processor also includes: The anomaly detection module is used to compare the newly stored data with the normal behavior model and classify the newly stored data using a trained classifier. If the classification result is abnormal data, the newly stored data is marked as abnormal data and deleted.

7. The mobile terminal big data comparison and analysis system according to claim 6, characterized in that: The normal behavior model is a machine learning model including an online learning algorithm. The normal behavior model is used to dynamically receive and process new data points and adjust internal parameters in real time through an incremental learning algorithm.

8. The mobile terminal big data comparison and analysis system according to claim 7, characterized in that: The online learning algorithm includes a gradient descent method and a stochastic gradient descent method. The real-time adjustment of internal parameters by an incremental learning algorithm includes: updating local parameters of the model according to the analysis results.

9. The mobile terminal big data comparison and analysis system according to claim 5, characterized in that: The intelligent comparison processor also includes: Data type identification module and algorithm matching module; The data type identification module determines whether the data belongs to the structured or unstructured category by analyzing the metadata and content characteristics of the data; The algorithm matching module is used to select a corresponding comparison algorithm according to the data type. If the data type is structured data, the comparison algorithm is a rule-based query algorithm or a hash algorithm; if the data type is unstructured data, the comparison algorithm is a deep learning network algorithm.

10. A mobile terminal, characterized in that: It includes a data acquisition module, a cache unit and an intelligent comparison processor; The data acquisition module is used to collect big data generated by the mobile terminal; The cache unit is used to cache the big data generated by the mobile terminal; The intelligent comparison processor is used to extract the big data from the cache unit, dynamically adjust the comparison strategy according to the application scenario corresponding to the big data, and perform big data comparison analysis according to the adjusted comparison strategy to output the analysis results.

Images