CN117829096B - Intelligent terminal display system based on data resources - Google Patents
Intelligent terminal display system based on data resources Download PDFInfo
- Publication number
- CN117829096B CN117829096B CN202410252066.3A CN202410252066A CN117829096B CN 117829096 B CN117829096 B CN 117829096B CN 202410252066 A CN202410252066 A CN 202410252066A CN 117829096 B CN117829096 B CN 117829096B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- user
- sub
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006399 behavior Effects 0.000 claims abstract description 126
- 238000000034 method Methods 0.000 claims abstract description 103
- 230000005540 biological transmission Effects 0.000 claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 71
- 238000005457 optimization Methods 0.000 claims abstract description 64
- 238000013461 design Methods 0.000 claims abstract description 58
- 230000015654 memory Effects 0.000 claims abstract description 51
- 238000005516 engineering process Methods 0.000 claims abstract description 45
- 238000012544 monitoring process Methods 0.000 claims abstract description 41
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 238000012423 maintenance Methods 0.000 claims abstract description 25
- 230000002452 interceptive effect Effects 0.000 claims abstract description 22
- 238000013144 data compression Methods 0.000 claims abstract description 10
- 230000006872 improvement Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 98
- 238000004458 analytical method Methods 0.000 claims description 89
- 230000008569 process Effects 0.000 claims description 47
- 238000007726 management method Methods 0.000 claims description 44
- 230000008451 emotion Effects 0.000 claims description 33
- 230000003993 interaction Effects 0.000 claims description 33
- 230000000007 visual effect Effects 0.000 claims description 31
- 238000006243 chemical reaction Methods 0.000 claims description 30
- 238000009826 distribution Methods 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 24
- 230000036541 health Effects 0.000 claims description 23
- 230000001133 acceleration Effects 0.000 claims description 22
- 230000000694 effects Effects 0.000 claims description 19
- 238000003909 pattern recognition Methods 0.000 claims description 14
- 238000007906 compression Methods 0.000 claims description 13
- 230000006835 compression Effects 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 13
- 230000002787 reinforcement Effects 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 11
- 230000014759 maintenance of location Effects 0.000 claims description 11
- 238000003058 natural language processing Methods 0.000 claims description 10
- 238000003012 network analysis Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 5
- 238000013079 data visualisation Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 238000012300 Sequence Analysis Methods 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 4
- 238000013468 resource allocation Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013506 data mapping Methods 0.000 claims description 3
- 238000005206 flow analysis Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 9
- 238000007405 data analysis Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 10
- 238000004088 simulation Methods 0.000 description 6
- 230000003860 sleep quality Effects 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 4
- 238000010921 in-depth analysis Methods 0.000 description 4
- 230000026676 system process Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000015219 food category Nutrition 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The invention discloses an intelligent terminal display system based on data resources in the technical field of intelligent display, which comprises a data optimization module, an efficiency coding optimization module, a dynamic updating module, a behavior prediction module, an information extraction module, a path optimization module, an interactive design module and a maintenance monitoring module. In the invention, the speed and the instantaneity of data processing are obviously improved by integrating the data processing and updating mechanism. The application of the memory computing framework and the parallel processing technology greatly reduces the time for data access and processing, so that the system can quickly respond and update information in real time. The latest data can be reflected in real time, and the user is ensured to obtain the latest information and data analysis results. By introducing the efficiency coding optimization module, the system achieves significant improvement in data compression and transmission efficiency. The application of the sparse coding and information bottleneck method optimizes the data structure and reduces unnecessary information redundancy.
Description
Technical Field
The invention relates to the technical field of intelligent display, in particular to an intelligent terminal display system based on data resources.
Background
The technical field of intelligent display is a highly developed field combining information technology and display technology. In this technical field, the smart display is not simply to show information, but can adjust the display contents and manner according to the needs of users, changes in the environment, and real-time update of data. The technology relates to multiple aspects of big data analysis, artificial intelligence, graphic processing, user interaction design and the like, and aims to improve the readability and the interactivity level of information. Smart display technology is widely used in a variety of applications including, but not limited to, public information presentations, personal devices, commercials, education and entertainment, and the like.
The intelligent terminal display system based on data resource is one system utilizing information technology, especially data analysis and artificial intelligent algorithm to optimize display content. The purpose of such a system is to provide a more dynamic and interactive user experience that enables the end user to obtain more relevant and timely information. By analyzing large amounts of data from different sources, the most relevant information and visual content can be presented, thereby achieving the effects of improving user satisfaction, enhancing information transfer efficiency, and promoting more efficient decisions.
Although the prior art achieves a certain effect in information display and user interaction, obvious delay still exists in data processing and updating speed, so that the information display is difficult to reflect the latest data in real time. In addition, existing systems fail to adequately account for the specific needs and environmental changes of the user in terms of processing and presentation of data, making the presentation content less targeted and adaptable. Although the prior art has advanced in terms of data compression and storage efficiency, in terms of optimizing the accuracy of data transmission and processing, information loss of data during transmission and processing is likely to occur, affecting the quality and reliability of the final display content. While the prior art works well in processing static data, its update mechanism appears too stiff and slow in the face of dynamically changing data streams. Limiting the response speed and flexibility of the system in dealing with rapidly changing information and environments. While the prior art can provide basic spatiotemporal data processing functionality, it is still significantly inadequate in terms of in-depth analysis of user behavior patterns and prediction of user demand. Making it difficult for the system to efficiently use spatio-temporal data to optimize the user experience and improve the relevance of the service. Although the prior art has some text processing capability, it still lacks an efficient and accurate mechanism in terms of automatic summary generation and key information highlighting. This makes it still necessary for the user to consume a great deal of time and effort in browsing and understanding a great deal of information. While the prior art has had an infrastructure in terms of content distribution, the ideal state has not been reached in terms of achieving optimization of content distribution. In particular, there is a lack of in-depth analysis and learning of user geographical location, network conditions and content preferences, such that content distribution efficiency and user satisfaction are not optimal.
Based on the above, the present invention designs an intelligent terminal display system based on data resources to solve the above problems.
Disclosure of Invention
The invention aims to provide a data resource-based intelligent terminal display system, which aims to solve the problems that although the prior art provided in the background art achieves a certain effect in the aspects of information display and user interaction, obvious delay still exists in the aspects of data processing and updating speed, so that the information display is difficult to reflect the latest data in real time. In addition, existing systems fail to adequately account for the specific needs and environmental changes of the user in terms of processing and presentation of data, making the presentation content less targeted and adaptable. While the prior art has advanced in terms of data compression and storage efficiency, the performance of the system is still not satisfactory in optimizing the accuracy of data transmission and processing. The data is easy to lose information in the transmission and processing process, and the quality and reliability of the final display content are affected. While the prior art works well in processing static data, its update mechanism appears too stiff and slow in the face of dynamically changing data streams. Limiting the response speed and flexibility of the system in dealing with rapidly changing information and environments. While the prior art can provide basic spatiotemporal data processing functionality, it is still significantly inadequate in terms of in-depth analysis of user behavior patterns and prediction of user demand. Making it difficult for the system to efficiently use spatio-temporal data to optimize the user experience and improve the relevance of the service. Although the prior art has some text processing capability, it still lacks an efficient and accurate mechanism in terms of automatic summary generation and key information highlighting. This makes it still necessary for the user to consume a great deal of time and effort in browsing and understanding a great deal of information. While the prior art has had an infrastructure in terms of content distribution, the ideal state has not been reached in terms of achieving optimization of content distribution. Especially lacking in-depth analysis and learning of user geographical location, network conditions and content preferences, such that content distribution efficiency and user satisfaction fail to reach an optimal state.
In order to achieve the above purpose, the present invention provides the following technical solutions: the intelligent terminal display system based on the data resource comprises a data optimization module, an efficiency coding optimization module, a dynamic updating module, a behavior prediction module, an information extraction module, a path optimization module, an interactive design module and a maintenance monitoring module;
The data optimization module analyzes and processes data by adopting a parallel data processing algorithm based on the requirements of the intelligent terminal, implements dynamic memory management and an intelligent cache strategy based on a prediction model, optimizes data storage and access by combining a least recently used algorithm, and generates an acceleration data stream;
The efficiency coding optimization module performs format conversion on data by adopting sparse coding based on the accelerated data stream, optimizes the redundancy of the data by adopting an entropy coding technology, compresses and constructs the data by adopting an information bottleneck method, and generates a structured data stream;
The dynamic updating module analyzes a data change rule through a dynamic model based on a structured data stream by utilizing a complex network theory, adopts a self-adaptive learning algorithm to carry out self-adjustment according to the data change, updates the data stream and matches the current environment and the user requirement to generate a real-time updated data stream;
The behavior prediction module analyzes the movement trend and time law of the user by using a geographic position analysis and time sequence prediction model based on the data flow updated in real time, synthesizes the past behavior data of the user by using a machine learning algorithm to perform pattern recognition, and generates a user behavior insight result;
The information extraction module processes text content by adopting a natural language processing technology based on user behavior insight results, extracts key sentences from information by using a text summarization algorithm, and utilizes text clustering and emotion analysis to carry out structuring and emotion judgment on the content so as to generate a key information summary;
The path optimization module analyzes and optimizes the decision process of the content distribution network by adopting a reinforcement learning method based on the key information abstract, examines the performances of various data transmission paths by adopting a network analysis technology, adjusts the transmission strategy by combining user behaviors and network state data, and generates an optimized transmission path;
the interactive design module plans and constructs an interface based on an optimized transmission path by adopting a user center design principle and an interactive design method, and converts data into a chart through a data visualization technology to generate a user interactive interface;
The maintenance monitoring module adopts a performance monitoring tool and a data security protocol to conduct routine inspection and security assessment based on a user interaction interface, ensures running stability and data security through real-time monitoring and automatic updating management strategies, and generates maintenance and security condition analysis results.
Preferably, the acceleration data stream comprises an adjusted data access rate, a data processing period and a memory response time, the structured data stream comprises a unified data format, a compressed data volume and an optimized data index, the real-time updated data stream comprises dynamically-changed user preference, instant environment data and updated interaction information, the user behavior insight result comprises an identified user behavior mode, a predicted user requirement and an analyzed time trend, the key information abstract comprises a summary topic word, a key sentence extraction and a key event summary, the optimized transmission path comprises a selected network channel, an adjusted transmission protocol and an optimized routing strategy, the user interaction interface comprises a customized interface layout, user preference design elements and interaction convenience optimization, and the maintenance and safety condition analysis result comprises a detected system performance index, an identified safety risk point and a proposed improvement measure.
Preferably, the data optimization module comprises a memory acceleration sub-module, a cache optimization sub-module and a parallel processing sub-module;
The memory acceleration submodule adopts APACHE SPARK frames based on intelligent terminal requirements, performs data segmentation and task scheduling by utilizing RDD and DAG execution engines of the memory acceleration submodule, and optimizes a data access flow by using a MapReduce algorithm, wherein a Map step is used for data mapping and conversion, a Reduce step is used for data aggregation and summarization, a memory use threshold and an allocation strategy are regulated by dynamic memory management, a future data access mode is predicted by combining a prediction algorithm based on a time sequence, cache data is managed by using a least recently used algorithm, and an acceleration memory data flow is generated;
The cache optimization submodule is used for training a classification model by utilizing historical access data based on a cache replacement strategy based on machine learning based on the accelerated memory data flow, predicting future access frequency of data items, wherein parameters comprise the historical access frequency and a time stamp, performing cache decision by a least recently used algorithm, and performing cache update by combining a real-time data access mode to generate an optimized cache data flow;
And the parallel processing sub-module is based on the optimized cache data flow, adopts a MapReduce algorithm again, wherein the Map step distributes data to multiple nodes for parallel processing, and the Reduce step summarizes the processing result of each node, optimizes the calculation resource allocation by setting the task parallelism parameter, and utilizes APACHE SPARK to process the data to generate an acceleration data flow.
Preferably, the efficiency coding optimization module comprises a format conversion sub-module, a compression strategy sub-module and a coding efficiency sub-module;
the format conversion submodule selects a base vector based on the accelerated data stream by utilizing a dictionary learning algorithm, and parameters comprise sparsity control and reconstruction error limit, so that the data maintains core information and unnecessary dimensionality in the conversion process to generate a data stream after format conversion;
the compression strategy submodule distributes multi-length coding character strings according to probability distribution of data through Huffman coding and arithmetic coding based on the data stream after format conversion, and parameters comprise probability distribution of symbols and length limitation of coding to generate a compressed data stream;
The coding efficiency submodule optimizes redundancy between input data and output data by utilizing mutual information theory based on the compressed data stream by adopting an information bottleneck method, parameters comprise an information retention threshold and a compression level, and the structured data stream is generated by changing the information quantity while maintaining the data structure by evaluating and balancing the relationship between data compression and information retention.
Preferably, the dynamic updating module comprises a data flow management sub-module, a change prediction sub-module and an updating strategy sub-module;
The data flow management submodule is based on the structured data flow, and the dynamic graph of the data flow is constructed, wherein the dynamic graph comprises key nodes and paths in the data flow selected by utilizing a graph theory algorithm, the data flow is optimized by analyzing connectivity and data transmission efficiency among the nodes, a management strategy adopts a network flow analysis technology, and the flow of data in a network is adjusted by referring to the processing capacity of the nodes and the transmission bandwidth of edges, so that a management optimized data flow is generated;
the change prediction submodule predicts the state of a future data stream by adopting a time sequence analysis method and an adaptive learning algorithm based on management optimization data stream and an autoregressive moving average model, adjusts parameters of a prediction model according to real-time data cycle by an online machine learning method, matches the latest change of the data stream, predicts the change of the future data stream and generates a prediction adjustment data stream;
The updating strategy submodule adjusts the data flow based on prediction, adopts a Q-learning method, evaluates the effect of the data updating strategy by defining a reward function, refers to the timeliness and the accuracy of data updating by the reward function, carries out dynamic updating of the data flow by selecting the optimal data updating strategy through cyclic trial and error learning by a reinforcement learning algorithm, and matches the current environment and the user requirement to generate a data flow updated in real time.
Preferably, the behavior prediction module comprises a space-time analysis sub-module, a pattern recognition sub-module and a demand prediction sub-module;
The space-time analysis submodule tracks the geographic position data of the user based on the data flow updated in real time by combining a geographic information system and an autoregressive moving average model, analyzes the data including longitude, latitude and place frequency, simultaneously analyzes the time law of the place accessed by the user, sets parameters, refers to a time window and a data sliding step length, draws the behavior trend of the user in multiple times and spaces, and generates a space-time behavior analysis result;
The pattern recognition submodule analyzes the behavior pattern of the user through a support vector machine and a random forest algorithm based on the space-time behavior analysis result, refers to parameters of frequency, place access sequence and time duration of user activities, recognizes and generalizes the behavior rules and habits of the user through analysis of historical behavior data of the user, and generates a user pattern recognition result;
the demand prediction sub-module is used for analyzing past purchasing behavior, site access and time cost of a user by utilizing a convolutional neural network and a long-short-term memory network based on a user mode identification result, and parameters to be referred comprise historical purchasing data, access frequency and average residence time, and predicting future demand trend of the user through comprehensive analysis of the historical behavior of the user to generate a user behavior insight result.
Preferably, the information extraction module comprises a keyword extraction sub-module, a summary generation sub-module and an information highlighting sub-module;
The keyword extraction submodule carries out text analysis by combining a TF-IDF algorithm with part-of-speech tagging based on a user behavior insight result through a natural language processing technology, the TF-IDF algorithm calculates the key degree of words in a document set, a word part tagging is assisted to determine a word function, words associated with user behaviors are identified, parameter settings comprise word frequency counting and document frequency inversion, common words are filtered, keywords reflecting the user behaviors and interests are extracted, and a keyword extraction result is generated;
The abstract generation submodule analyzes the text structure and the keyword distribution based on the keyword extraction result by an extraction abstract method, selects sentences comprising keywords to be combined, refers to the positions of the sentences in the text, the keyword density and the text logic structure, enables the selected sentences to summarize text contents and reflect user interest points, and generates a text abstract result;
The information highlighting sub-module classifies subjects of summary contents by using a K-means clustering algorithm based on text summary results and combining text clustering and emotion analysis technology, an emotion analysis tool evaluates emotion tendencies of each part of contents, parameters refer to the number of clusters and the vocabulary range of emotion analysis, key information in texts is highlighted, and a key information summary is generated.
Preferably, the path optimization module comprises a behavior analysis sub-module, a cache adjustment sub-module and a transmission optimization sub-module;
The behavior analysis submodule adopts a reinforcement learning method based on key information abstract, evaluates and adjusts the data request of the user through a Q learning algorithm, analyzes rules behind the behavior of the user according to the history access record and the preference mode, including the access frequency and time distribution of the user to the multi-type content, and generates a user behavior analysis result;
the cache adjustment submodule adjusts the priority of the content in the cache by utilizing the least recently used strategy to cooperate with a dynamic content prefetching method based on the analysis result of the user behavior, and refers to the limitation of the cache space and the update frequency of the content to ensure that the most frequently requested data is kept in the cache to generate a cache adjustment result;
the transmission optimization submodule adopts a network analysis technology and real-time user behavior data based on a cache adjustment result, selects an optimal transmission path of the data through a Dijkstra algorithm, and generates an optimal transmission path by taking the parameters of the current state of the network, including delay, bandwidth utilization rate and transmission cost.
Preferably, the interactive design module comprises an interface layout sub-module, an information display sub-module and a visual design sub-module;
The interface layout submodule is used for focusing on the requirements and preferences of a user to construct an interface based on an optimized transmission path by adopting a user center design principle, and comprises the steps of defining screen layout, arranging navigation elements and positions of interaction components to generate a user interface layout result;
The information display sub-module displays information by adopting an information architecture and a visual design principle based on a user interface layout result, improves the readability of the information by using a layering design, an information grouping and a method for highlighting key information, and generates an information display design result;
The visual design sub-module is used for displaying a design result based on information, converting the data into a chart and a graph by utilizing a data visual technology, selecting a chart type comprising a histogram, a line graph and a pie chart, customizing a visual style comprising color, size and interaction function, assisting a user in analyzing the data and the information through visual elements, and generating a user interaction interface.
Preferably, the maintenance monitoring module comprises a performance monitoring sub-module, a security check sub-module and an update management sub-module;
The performance monitoring submodule collects and analyzes system operation indexes including CPU (central processing unit) utilization rate, memory consumption, network delay and disk I/O (input/output) rate by adopting New Relic tools based on a user interaction interface, assists in evaluating the overall health condition and operation efficiency of the system, and excavates and solves performance bottlenecks to generate performance monitoring results;
The security inspection sub-module adopts a Nessus tool to conduct security scanning and vulnerability identification of the system based on the performance monitoring result, evaluates the effectiveness of data protection measures, ensures the integrity and confidentiality of the system and user data, and generates a security inspection result;
the update management sub-module monitors the latest states of the software version and the security patch by adopting a WSUS tool based on the security check result, automatically evaluates the version of the current software of the system to compare with the latest released version, determines the priority and compatibility of the update, automatically downloads and installs the update and the patch, and generates maintenance and security condition analysis results.
Compared with the prior art, the invention has the beneficial effects that: by integrating the data processing and updating mechanism, the speed and the real-time performance of the data processing are obviously improved. The application of the memory computing framework and the parallel processing technology greatly reduces the time for data access and processing, so that the system can quickly respond and update information in real time. The latest data can be reflected in real time, and the user is ensured to obtain the latest information and data analysis results. By introducing the efficiency coding optimization module, the system achieves significant improvement in data compression and transmission efficiency. The application of the sparse coding and information bottleneck method optimizes the data structure, reduces unnecessary information redundancy, and ensures the high efficiency and accuracy of data transmission. This not only improves the efficiency of storage and transmission, but also ensures the integrity and reliability of the data during transmission and processing. The introduction of the dynamic update module improves the processing power of the system for dynamic data streams. By utilizing complex network theory and self-adaptive learning algorithm, the system can flexibly respond to data change and update information content in time, thereby improving the adaptability and response speed of the system in a changing environment. By implementing spatiotemporal data analysis and behavior prediction, the system can understand user behavior in depth, optimizing data presentation and service provision. This not only enhances the predictive capabilities of the system, but also improves the relevance and effectiveness of the service through accurate data analysis. And the integration of the information extraction module and the path optimization module further improves the processing efficiency of the data content and the performance of network transmission. Highlighting of text summaries and key information greatly improves the speed of user understanding and browsing information, while an optimized content distribution network ensures the efficiency and stability of data transmission. The addition of the maintenance monitoring module ensures the stable operation and data security of the system. Through regular performance monitoring and security inspection, the system can timely find and solve potential security risks and performance bottlenecks, so that the reliability of the system and the security of user data are guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a smart terminal display system based on data resources according to the present invention;
FIG. 2 is a system frame diagram of a smart terminal display system based on data resources according to the present invention;
FIG. 3 is a schematic diagram of a data optimization module in a smart terminal display system based on data resources according to the present invention;
FIG. 4 is a schematic diagram showing an efficiency code optimization module in a smart terminal display system based on data resources according to the present invention;
FIG. 5 is a schematic diagram showing a dynamic update module in a smart terminal display system based on data resources according to the present invention;
FIG. 6 is a schematic diagram showing a behavior prediction module in an intelligent terminal display system based on data resources according to the present invention;
FIG. 7 is a schematic diagram showing an information extraction module in a smart terminal display system based on data resources according to the present invention;
FIG. 8 is a schematic diagram of a path optimization module in a smart terminal display system based on data resources according to the present invention;
FIG. 9 is a schematic diagram showing an interactive design module in a smart terminal display system based on data resources according to the present invention;
fig. 10 is a schematic diagram of a maintenance monitoring module in an intelligent terminal display system based on data resources according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a technical solution: the intelligent terminal display system based on the data resource comprises a data optimization module, an efficiency coding optimization module, a dynamic updating module, a behavior prediction module, an information extraction module, a path optimization module, an interactive design module and a maintenance monitoring module;
the data optimization module analyzes and processes data by adopting a parallel data processing algorithm based on the requirements of the intelligent terminal, implements dynamic memory management and an intelligent cache strategy based on a prediction model, optimizes data storage and access by combining a least recently used algorithm, and generates an acceleration data stream;
the efficiency coding optimization module performs format conversion on data by adopting sparse coding based on the accelerated data stream, optimizes the redundancy of the data by adopting an entropy coding technology, compresses and constructs the data by adopting an information bottleneck method, and generates a structured data stream;
the dynamic updating module analyzes a data change rule by utilizing a complex network theory through a dynamic model based on the structured data stream, adopts a self-adaptive learning algorithm to carry out self-adjustment according to the data change, updates the data stream and matches the current environment and the user requirement to generate a real-time updated data stream;
The behavior prediction module analyzes the movement trend and time rule of the user by using a geographic position analysis and time sequence prediction model based on the data flow updated in real time, synthesizes the past behavior data of the user by using a machine learning algorithm to perform pattern recognition, and generates a user behavior insight result;
The information extraction module processes the text content by adopting a natural language processing technology based on the user behavior insight result, extracts key sentences from the information by using a text summarization algorithm, and constructs and judges the emotion of the content by using text clustering and emotion analysis to generate a key information summary;
The path optimization module analyzes and optimizes the decision process of the content distribution network by adopting a reinforcement learning method based on the key information abstract, inspects the performance of various data transmission paths by a network analysis technology, adjusts the transmission strategy by combining user behavior and network state data, and generates an optimized transmission path;
the interactive design module plans and constructs an interface based on an optimized transmission path by adopting a user center design principle and an interactive design method, and converts data into a chart by a data visualization technology to generate a user interactive interface;
the maintenance monitoring module adopts a performance monitoring tool and a data security protocol to conduct routine inspection and security assessment based on a user interaction interface, ensures running stability and data security through real-time monitoring and automatic updating management strategies, and generates maintenance and security condition analysis results.
The accelerating data flow comprises an adjusted data access rate, a data processing period and a memory response time, the structured data flow comprises a unified data format, a compressed data volume and an optimized data index, the real-time updated data flow comprises dynamically-changed user preference, instant environment data and updated interaction information, the user behavior insight result comprises an identified user behavior mode, a predicted user demand and an analyzed time trend, the key information abstract comprises a summary topic vocabulary, key sentence extraction and key event summarization, the optimized transmission path comprises a selected network channel, an adjusted transmission protocol and an optimized routing strategy, the user interaction interface comprises a customized interface layout, user preference design elements and interaction convenience optimization, and the maintenance and safety condition analysis result comprises a detected system performance index, an identified safety risk point and proposed improvement measures.
In the data optimization module, the system adopts a memory computing framework to process various data formats including texts, pictures, videos and the like according to the requirements of the intelligent terminal. The data is divided into a plurality of small blocks by a parallel data processing algorithm, such as MapReduce, the small blocks are processed in parallel by a Map step, such as filtering and sequencing, and the output of the Map step is summarized and reduced by a Reduce step. In combination with dynamic memory management, the system automatically adjusts memory allocation according to the data access frequency and the prediction model, and the least recently used algorithm is adopted to optimize the storage and access of data in the memory. The operation generates an acceleration data stream, so that the data processing and access speed is improved, and meanwhile, the delay is reduced, and the system can quickly respond to the user request.
In the efficiency coding optimization module, the system firstly carries out format conversion on the accelerated data stream through a sparse coding technology, the technology realizes data compression by reducing the number of zero elements in data representation, then further reduces the redundancy of the data by utilizing an entropy coding technology, and codes with different lengths are distributed by calculating probability distribution of the data. Information bottleneck methods are then used to optimize the structure of the data stream, balancing the relationship between data compression and information retention by minimizing the loss of mutual information between the input and output. The series of operations generate structured data streams, so that the storage and transmission efficiency of data is improved.
In the dynamic updating module, the system analyzes the change rule of the structured data stream by utilizing a complex network theory and a dynamic model, and combines an adaptive learning algorithm, such as online learning and incremental learning, to dynamically adjust model parameters according to real-time data. In this way, the system can quickly adapt to the change of environment and user requirements, and update the data stream in real time. This mechanism ensures real-time and relevance of the data content so that the user always receives the latest and most relevant information.
In the behavior prediction module, the system analyzes the movement trend and time law of the user through a geographic position analysis and a time sequence prediction model, such as a hidden Markov model and a cyclic neural network. The system collects historical behavior data of the user, and carries out deep analysis by combining a machine learning algorithm to identify patterns and rules of the user behavior. Through the comprehensive analysis, the system can predict the future behavior trend of the user and generate the user behavior insight result. The intelligent terminal can prepare and push related content in advance, and user experience and satisfaction are greatly improved.
In the information extraction module, the system adopts natural language processing technology, such as word frequency-inverse document frequency (TF-IDF) algorithm and text abstract generation technology, to carry out deep analysis on text content in the user behavior insight result. The system extracts key sentences and topic words from a large number of texts through a natural language processing technology, and further carries out structuring and emotion judgment on the content by combining text clustering and emotion analysis to generate a key information abstract. Such processing not only improves the usability and accessibility of information, but also enables a user to quickly acquire core content of information.
In the path optimization module, the system analyzes and optimizes the decision process of the content distribution network by adopting a reinforcement learning method, such as Q learning, based on the key information abstract. Through network analysis technology, the system evaluates the performance of different data transmission paths and adjusts the transmission strategy in combination with user behavior and network state data. The operation generates an optimized transmission path, so that the efficiency and stability of data transmission are improved, and the user is ensured to receive the data in the shortest time.
In the interactive design module, the system builds and optimizes the user interface based on the optimized transmission path by adopting a user center design principle and an interactive design method, such as an information architecture and a visual design principle. The complex data is converted into a visual format which is easy to understand through a data visualization technology, such as the design of a chart and a graph, so as to generate a user interaction interface. The usability and the aesthetic property of the interface are improved, and the interaction and the communication efficiency between the user and the system are enhanced.
In the maintenance monitoring module, the system performs routine checks of system performance and security based on the user interaction interface using performance monitoring tools such as New Relic and data security protocols. By means of real-time monitoring and automatic updating of management strategies, the system can timely find and solve potential problems, and stability of the system and safety of data are guaranteed. Operation generation maintenance and safety condition analysis results help an administrator to know the system state and the safety level in time, and continuous and safe operation of the intelligent terminal is ensured.
Referring to fig. 2 and 3, the data optimization module includes a memory acceleration sub-module, a cache optimization sub-module, and a parallel processing sub-module;
The memory acceleration submodule adopts APACHE SPARK frames based on intelligent terminal requirements, performs data segmentation and task scheduling by utilizing RDD and DAG execution engines of the frames, performs data mapping and conversion by using a MapReduce algorithm, performs data aggregation and summarization by using a Map step, adjusts a memory use threshold and an allocation strategy by using dynamic memory management, predicts a future data access mode by combining a prediction algorithm based on a time sequence, manages cache data by using a least recently used algorithm, optimizes a data access flow, and generates an acceleration memory data stream;
The cache optimization submodule is used for training a classification model by utilizing historical access data based on a cache replacement strategy based on machine learning based on the accelerated memory data flow, predicting future access frequency of data items, wherein parameters comprise the historical access frequency and a time stamp, performing cache decision by a least recently used algorithm, and performing cache update by combining a real-time data access mode to generate an optimized cache data flow;
and the parallel processing sub-module is based on the optimized cache data flow, and adopts a MapReduce algorithm again, wherein the Map step distributes data to multiple nodes for parallel processing, the Reduce step summarizes the processing result of each node, and the task parallelism parameter is set to optimize the calculation resource allocation, and the Map step utilizes APACHE SPARK to process the data and generate an acceleration data flow.
In the memory acceleration sub-module, the system adopts APACHE SPARK framework to process various data formats, such as JSON, CSV or Parquet, based on the data processing requirement of the intelligent terminal. The module utilizes a resilient distributed data set (RDD) and Directed Acyclic Graph (DAG) execution engine for data segmentation and task scheduling. Specifically, the Map function processes each data item, such as filtering and conversion, and the Reduce function aggregates and aggregates all Map results using the Map Reduce algorithm of APACHE SPARK. In addition, the dynamic memory management automatically adjusts memory usage according to the workload, predicts an unused data access mode in combination with a time sequence-based prediction algorithm, and intelligently caches data by using a Least Recently Used (LRU) algorithm, thereby optimizing the data access flow. The series of operations generate the accelerated memory data stream, so that the data processing speed and response time are improved, and the system delay is effectively reduced.
In the cache optimization sub-module, based on the accelerated memory data stream, the sub-module analyzes the historical access data through a machine learning algorithm, such as a decision tree or a support vector machine, and builds a classification model to predict future access frequency of the data item. The process involves extracting data features such as access frequency and last access time stamp, and then applying a least recently used algorithm to optimize the caching decisions. By monitoring the data access mode in real time, the system can dynamically update the cache content to ensure that the high-frequency access data is kept in the cache. The caching strategy not only improves the data access speed, but also reduces the pressure of back-end storage, and generates an optimized cache data stream, thereby improving the overall system performance.
In the parallel processing sub-module, based on the optimized cache data flow, the sub-module continues to process data by adopting a MapReduce algorithm. In the process, the Map step distributes data to different nodes for parallel processing, and each node performs the same operation, such as data filtering or conversion. And the Reduce step is responsible for summarizing the processing results of all the nodes and carrying out data aggregation and summarization. The sub-module optimizes the computing resource allocation by adjusting the task parallelism parameter, such as setting the partition number of Spark jobs. The APACHE SPARK framework supports operations that make data processing more efficient. After the execution is finished, the generated acceleration data flow greatly improves the speed of data processing and analysis, so that the system can quickly respond to user inquiry and data analysis requests, thereby improving user experience and the data processing capacity of the system.
It is assumed that in a smart terminal display system scenario of an e-commerce platform, the system needs to process and analyze shopping behavior data of a user to optimize merchandise recommendation. In the memory acceleration sub-module, the system adopts APACHE SPARK framework to process user behavior data, including data items such as user ID, commodity ID, browsing time and purchase history, and specific simulation values are user ID: "U12345", commodity ID: "P67890", browsing time: "2023-08-01 12:30:00", purchase history: { "P12345": 3, "P67890": 1}. And (3) screening activity data of the user in a specific time period by using a Map function through a MapReduce algorithm, and summarizing the data by using a Reduce function to construct a user behavior profile. In the cache optimization sub-module, based on the accelerated memory data flow of the user behavior, the system uses a decision tree algorithm to analyze the access frequency and the latest access time of the user, such as the access frequency: 5 times per week, last access time: "2023-08-01 15:00:00", and apply a least recently used algorithm to optimize the cache such that frequently accessed commodity data remains in the cache. Such a caching strategy improves the speed and efficiency of data access. In the parallel processing sub-module, the optimized cache data flow is utilized, the data is distributed to different processing nodes for parallel processing, such as filtering and aggregating commodity browsing data, and the partition number of Spark jobs is set to be 10, so that the parallelism and the efficiency of data processing are improved. Finally, the generated acceleration data stream contains shopping preferences and behavior patterns of the user, such as that the user U12345 tends to purchase electronic products on weekends, and the analysis result is directly used for improving the accuracy and individuation degree of commodity recommendation, so that the user satisfaction degree and the purchase conversion rate are improved.
Referring to fig. 2 and fig. 4, the efficiency coding optimization module includes a format conversion sub-module, a compression strategy sub-module, and a coding efficiency sub-module;
The format conversion submodule selects a base vector based on the accelerated data stream by utilizing a dictionary learning algorithm, and parameters comprise sparsity control and reconstruction error limit, so that the data maintains core information and unnecessary dimensionality in the conversion process to generate a data stream after format conversion;
the compression strategy submodule distributes multi-length coding character strings according to probability distribution of data through Huffman coding and arithmetic coding based on the data stream after format conversion, and parameters comprise probability distribution of symbols and length limitation of coding to generate a compressed data stream;
The coding efficiency submodule optimizes redundancy between input data and output data by utilizing mutual information theory based on the compressed data stream by adopting an information bottleneck method, parameters comprise an information retention threshold and a compression level, and the structured data stream is generated by changing the information quantity while maintaining the data structure by evaluating and balancing the relationship between data compression and information retention.
In the format conversion sub-module, the data stream is first processed through a dictionary learning algorithm that selects a set of basis vectors for each data type, such as image or text. The process involves setting sparsity control parameters to determine the sparsity level and reconstruction margin of error of the data representation to ensure that the unnecessary dimensions are removed while maintaining the data core information. Including applying a linear transformation to the raw data, projecting it into a low-dimensional space defined by the basis vectors, thereby generating a format-converted data stream. The conversion preserves the important characteristics of the data while reducing its dimensionality, thereby optimizing the efficiency and speed of subsequent processing.
In the compression strategy submodule, the data stream after format conversion is further subjected to Huffman coding and arithmetic coding. The process assigns different data items with different lengths of code strings based on probability distributions of the data, wherein common data items are assigned shorter codes and unusual ones are assigned longer codes. The parameter settings include probability distribution and coding length constraints of the data items, ensuring that the coding process is both efficient and reduces the loss of information. In this way, the compressed data stream occupies less memory space and transmission bandwidth, while retaining all the information required for decoding.
In the coding efficiency sub-module, the system processes the compressed data stream by adopting an information bottleneck method, and redundancy between input data and output data is optimized. The method comprises the steps of setting an information retention threshold and a compression level parameter, and further compressing data while ensuring the retention of key information. In this way, the system evaluates and balances the relationship between data compression and information retention, ensuring that the data maintains its structure and usability while reducing storage space and transmission time. The finally generated structured data stream is compact and rich in information, and is suitable for efficient data processing and analysis.
It is assumed that in a smart terminal display system scenario of a health management platform, the system needs to process and analyze health data of users to provide personalized health advice and nutrition guidance. In the format conversion sub-module, the system processes health data of the user by adopting a dictionary learning algorithm, wherein the health data comprises data items such as step number, heart rate, sleep quality and food type taken, and the specific simulation numerical value is the step number: "10234", heart rate: "78 bpm", sleep quality: "good", food category: "vegetables, meats, fruits". By setting the sparsity control parameter to 0.2 and the reconstruction error bound to 0.05, the data is converted to a low-dimensional representation containing the primary health indicator. In the compression strategy submodule, the data stream after format conversion is further processed through Huffman coding and arithmetic coding, and the coding length is distributed according to the occurrence frequency of each health index, so that the compressed data stream is generated. The data stream effectively reduces the volume of the original data, and simultaneously reserves all health information required during decoding, so that the data transmission is more efficient. In the coding efficiency sub-module, the system further processes the compressed data stream by an information bottleneck method, setting the information retention threshold to 0.8 and the compression level to be medium. This process ensures that critical health information of the user is preserved even while data is compressed to reduce storage and transmission requirements. Finally, the generated structured data stream is used for efficient data processing and analysis, providing personalized advice to the user based on his health data, such as recommending a suitable exercise type based on heart rate and number of steps, or improving eating habits based on food intake advice.
Referring to fig. 2 and 5, the dynamic update module includes a data stream management sub-module, a change prediction sub-module, and an update policy sub-module;
The data flow management submodule is based on the structured data flow, and the data flow management submodule is used for optimizing the data flow by constructing a dynamic graph of the data flow and analyzing the connectivity and the data transmission efficiency among nodes by utilizing a graph theory algorithm, and the management strategy is used for adjusting the flow of data in a network by adopting a network flow analysis technology and referring to the node processing capacity and the transmission bandwidth of edges to generate a management optimized data flow;
The change prediction submodule predicts the state of a future data stream by adopting a time sequence analysis method and an adaptive learning algorithm and an autoregressive moving average model, adjusts parameters of a prediction model according to real-time data circulation by an online machine learning method, matches the latest change of the data stream, predicts the change of the future data stream and generates a prediction adjustment data stream;
The updating strategy submodule adjusts the data flow based on prediction, adopts a Q-learning method, evaluates the effect of the data updating strategy by defining a reward function, refers to the timeliness and the accuracy of the data updating by the reward function, carries out dynamic updating of the data flow by selecting the optimal data updating strategy through cyclic trial and error learning by the reinforcement learning algorithm, and matches the current environment and the user requirement to generate the data flow updated in real time.
In the data stream management sub-module, by building a dynamic graph of the data stream, the sub-module uses graph theory algorithms to identify and select key nodes and paths in the data stream. The process includes determining an optimal transmission path for data in the network using a shortest path algorithm or a maximum flow algorithm. The algorithm takes into account the node processing power and the transmission bandwidth of the connection path to optimize the data flow. Specifically including calculating the efficiency of all paths in the network and then selecting the most efficient path to transmit data. The method ensures the high-efficiency flow of data in the network, reduces the transmission delay, and improves the data processing capacity of the whole network, thereby generating the data flow for management optimization.
In the change prediction sub-module, based on the data flow which is managed and optimized, a time sequence analysis method and an adaptive learning algorithm are adopted to predict the state of the data flow. Specifically, the method comprises the steps of analyzing historical data flow changes and predicting future states by using an autoregressive moving average (ARMA) model or a seasonal ARIMA model. The model dynamically adjusts its parameters according to the real-time data to accommodate the latest changes in the data stream. By this approach, the sub-modules are able to predict future trends and possible points of change of the data stream, thereby generating a predictively adjusted data stream, which helps the system to be ready in advance to cope with expected data changes.
In the update policy sub-module, a Q-learning reinforcement learning method is employed to define and optimize a data update policy based on the predictively adjusted data stream. In this process, a reward function is defined to evaluate the effect of different data update policies, where the reward function takes into account the timeliness and accuracy of the data update. Through the continuous trial-and-error process, the system learns and selects the optimal data updating strategy to realize the dynamic updating of the data stream. The method enables the system to automatically adjust the data updating mechanism according to the current environment and the user demand, thereby generating a data stream updated in real time and ensuring that the user always receives the latest and most relevant information.
It is assumed that in a smart terminal display system scenario for an intelligent traffic management system, the system needs to process and analyze urban traffic flow data to optimize traffic light control. In the data flow management sub-module, the data items processed by the system comprise the traffic flow of each traffic intersection, the state of a signal lamp and a time stamp, and the specific analog value is the traffic flow: "vehicle/min: 45", signal light status: "red light", timestamp: "2023-09-01 07:30:00". By means of the shortest path algorithm, the system determines an optimal data transmission path, reduces the transmission delay of data in the urban traffic network, and improves the response speed of the signal lamp adjustment strategy. In the change prediction sub-module, the system adopts an autoregressive moving average model to analyze the traffic flow data of each intersection in the past week and predicts the traffic flow change trend in the future hour. In the process, the system dynamically adjusts model parameters according to the real-time traffic flow data so as to adapt to the latest change of traffic flow. In this way, the sub-module can generate a data stream for prediction adjustment, so as to help the traffic management system to prepare for the increase of the traffic flow in advance, such as adjusting the signal lamp period in advance, so as to avoid congestion. In the update strategy sub-module, the system defines and optimizes the update strategy of the signal lamp by adopting a Q-learning method based on the data flow of the prediction adjustment. The reward function considers timeliness of signal lamp updating and influence on traffic flow, such as reducing vehicle waiting time and improving crossing traffic efficiency. The system learns and selects the optimal signal lamp updating strategy through the continuous trial-and-error process so as to dynamically adjust the signal lamps at all intersections in the city and ensure smooth traffic. The method enables the intelligent traffic management system to automatically adjust the signal lamp according to the real-time traffic condition, thereby reducing congestion and improving the road use efficiency.
Referring to fig. 2 and 6, the behavior prediction module includes a space-time analysis sub-module, a pattern recognition sub-module, and a demand prediction sub-module;
The space-time analysis submodule is used for tracking the geographic position data of the user based on the data flow updated in real time by combining a geographic information system and an autoregressive moving average model, analyzing the time law of the access place of the user, setting a reference time window and a data sliding step length by parameters, drawing the behavior trend of the user in multiple times and spaces, and generating a space-time behavior analysis result;
The pattern recognition submodule analyzes the behavior pattern of the user through a support vector machine and a random forest algorithm based on the space-time behavior analysis result, refers to parameters of frequency, place access sequence and time duration of user activities, recognizes and generalizes the behavior rules and habits of the user through analysis of historical behavior data of the user, and generates a user pattern recognition result;
The demand prediction sub-module analyzes past purchasing behavior, site access and time cost of a user by utilizing a convolutional neural network and a long-term and short-term memory network based on a user mode identification result, refers to parameters including historical purchasing data, access frequency and average residence time, predicts future demand trend of the user through comprehensive analysis of the user historical behavior, and generates a user behavior insight result.
In the spatio-temporal analysis sub-module, the system processes the data stream updated in real-time, including the user's geographic location data formatted as longitude, latitude, and time stamps by combining the geographic information system and an autoregressive moving average model. The sub-module analyzes the frequency of user activity at different times and places using a time window and a data sliding step, for example, setting the time window to 30 minutes and the sliding step to 5 minutes, to capture the user's movement pattern. The data flow is optimized by analyzing and determining key nodes and paths in the data flow using graph theory algorithms such as Dijkstra or Floyd-Warshall. The execution result of the operation is to generate a space-time behavior analysis result, reveal the movement trend and mode of the user and provide a basis for subsequent behavior prediction.
In the pattern recognition sub-module, based on the space-time behavior analysis result, the user behavior data is subjected to deep analysis by using a support vector machine and a random forest algorithm. The data formats processed by the sub-module include frequency, place access order and time duration of user activity, combined with user historical behavior data to identify behavior patterns. By setting algorithm parameters such as kernel function type, tree depth and random sample proportion, the submodule recognizes the rule and habit of user behavior and generates a user mode recognition result. The results reveal typical behavior and activity patterns of the user, which are critical for customizing personalized services and recommendations.
In the demand prediction sub-module, a convolutional neural network and a long-short-term memory network are utilized, and the sub-module analyzes past purchasing behavior, site access and time cost of a user. The processed data formats include historical purchase records, access frequency, and average residence time. Setting network parameters such as layer number, neuron number and activation function, and training parameters such as learning rate and batch size, and predicting future demand trend of the user by comprehensively analyzing historical behaviors of the user by the submodule. The generated user behavior insight result can guide the intelligent terminal display system to provide more accurate and timely information, and the actual requirements of users are met.
It is assumed that in a smart terminal display scenario of an urban traffic management system, the system needs to process and analyze travel data of urban residents to optimize traffic flow and reduce congestion. In the space-time analysis sub-module, the system processes the traffic flow data updated in real time, including the geographic position data of the vehicle formatted as longitude, latitude and time stamp, and the specific analog value is longitude: "104.0668", latitude: "30.5728", timestamp: "2023-09-01 08:30:00". The sub-module captures the movement pattern of the vehicle using a time window of 15 minutes and a data sliding step of 5 minutes and uses a graph theory algorithm to determine key nodes and paths in the traffic flow, thereby optimizing the traffic flow in the city. In the pattern recognition sub-module, based on the space-time behavior analysis result, the system uses a support vector machine and a random forest algorithm to analyze behavior data of the vehicle, wherein the data format comprises the moving frequency, the route selection sequence and the time duration of the vehicle, and the simulation numerical value is the moving frequency: "4 times per day", route selection order: "home- > office- > supermarket- > home", time duration: "30 minutes". The data is used to identify travel patterns and peak hours of urban residents. In the demand prediction submodule, a convolutional neural network and a long-short-period memory network are utilized, the submodule analyzes the past trip records and route selection of residents, the data format comprises trip times, common routes and residence time, and the simulation numerical value is the trip times: "20 times per week", route: "family- > subway station", residence time: "20 minutes". Through analysis, the system predicts future travel demands and possible congestion points, and the generated user behavior insight result is used for guiding adjustment of traffic signals and planning of bus routes so as to meet actual travel demands of residents and optimize traffic conditions of the whole city.
Referring to fig. 2 and 7, the information extraction module includes a keyword extraction sub-module, a summary generation sub-module, and an information highlighting sub-module;
The keyword extraction submodule carries out text analysis by combining a TF-IDF algorithm with a part-of-speech tagging based on a user behavior insight result through a natural language processing technology, the TF-IDF algorithm calculates the key degree of words in a document set, a part-of-speech tagging is used for assisting in determining a word function, words associated with user behaviors are identified, parameter settings comprise word frequency counting and document frequency inversion, common words are filtered, keywords reflecting the user behaviors and interests are extracted, and a keyword extraction result is generated;
the abstract generation sub-module analyzes the text structure and the keyword distribution based on the keyword extraction result by an extraction abstract method, selects sentences comprising keywords to be combined, and refers to the positions of the sentences in the text, the keyword density and the text logic structure, so that the selected sentences can summarize the text content and reflect the interest points of the user to generate a text abstract result;
The information highlighting sub-module classifies subjects of the summary content by using a K-means clustering algorithm based on a text summary result and combining text clustering and emotion analysis technology, an emotion analysis tool evaluates emotion tendencies of each part of content, parameters refer to the number of clusters and the vocabulary range of emotion analysis, key information in a text is highlighted, and a key information summary is generated.
In the keyword extraction sub-module, text data generated by a user is processed by combining a TF-IDF algorithm and part-of-speech tagging through a natural language processing technology. The data format is user reviews or feedback text, such as product reviews on the user's online platform. Firstly, the TF-IDF algorithm calculates the importance degree of each word in a document set, and by setting the parameters of word frequency count and document frequency inversion and assisting part-of-speech tagging in natural language processing, important words such as nouns, adjectives and the like are identified as keyword candidates. The system then filters out common but insignificant words, such as "and", "yes", etc., thereby extracting keywords that are closely related to the user's behavior and interests. Finally, the generated keyword extraction results are presented in a list form, and basic data is provided for subsequent content abstracts and information highlighting.
And in the abstract generation sub-module, based on the keyword extraction result, adopting an extraction type abstract method to carry out structural analysis on the text. The process includes evaluating the structure, keyword density, and logical relationship of sentences in the text, selecting sentences that contain high frequency keywords and have significant locations in the text, such as sentences of the introduction or conclusion section, and constructing a text abstract. The method not only captures the main content of the text, but also ensures that the abstract can reflect the interest points and behavior trends of the user, and the generated text abstract result is displayed in a concise paragraph form, so that a quick information browsing experience is provided.
In the information highlighting sub-module, based on the text abstract result, the system further refines the information by combining text clustering and emotion analysis techniques. The summary content is classified by topic using a K-means clustering algorithm and the emotional tendency of each part of the content is evaluated by an emotion analysis tool, such as positive, negative or neutral. The parameter setting refers to the cluster number and the emotion vocabulary range, so that the key information and emotion colors in the text are efficiently and accurately identified. The key information and emotion colors are highlighted in the text, so that the user can quickly identify the main content and emotion of the text, the generated key information abstract is rich in information and clear in emotion, and the reading and understanding efficiency of the user is effectively improved.
It is assumed that in a smart terminal display system scenario of an online education platform, the system needs to process and analyze user's course comment data to optimize course recommendation and content update. In the information extraction module, the data items processed by the keyword extraction sub-module comprise user comment texts, such as' the lesson is very practical, the explanation is deep and shallow, but the lesson data is slightly insufficient. ". The key words of practical, deep-in shallow-out and course data are extracted by the system by using a TF-IDF algorithm and combining part-of-speech tagging. The abstract generation sub-module selects sentences containing words, which are very practical, and the deep and shallow explanation is used as text abstracts based on keywords to reflect the main evaluation and interest points of the user on courses. The information highlighting sub-module further analyzes emotion of the abstract content, and recognizes that 'very practical' and 'deep-in shallow-out' are positive emotions, and 'slightly insufficient data' are slightly negative emotions. In the intelligent terminal display system, key information is highlighted so that other users and course providers can quickly learn about the advantages of courses and where improvements are needed. The simulated numerical value of the operation is that the key word is "practical" and has a TF-IDF score of 0.8, a score of "deep in and shallow out" of 0.75, and the emotion analysis result shows that the "very practical" positive emotion score is 0.9, and the "insufficient material" negative emotion score is 0.6. The detailed data processing and analysis results enable the platform to provide course recommendations more in line with user requirements and feedback, thereby improving user satisfaction and educational quality of the platform.
Referring to fig. 2 and 8, the path optimization module includes a behavior analysis sub-module, a buffer adjustment sub-module, and a transmission optimization sub-module;
The behavior analysis sub-module adopts a reinforcement learning method based on the key information abstract, evaluates and adjusts the data request of the user through a Q learning algorithm, analyzes rules behind the behavior of the user according to the historical access record and the preference mode, including the access frequency and time distribution of the user to the multi-type content, and generates a user behavior analysis result;
the cache adjustment submodule adjusts the priority of the content in the cache by utilizing the least recently used strategy to cooperate with a dynamic content prefetching method based on the analysis result of the user behavior, and refers to the limitation of the cache space and the update frequency of the content to ensure that the most frequently requested data is kept in the cache to generate a cache adjustment result;
Based on the buffer adjustment result, the transmission optimization submodule adopts a network analysis technology and real-time user behavior data, selects an optimal transmission path of the data through Dijkstra algorithm, and generates an optimal transmission path by taking the parameters of the current state of the network, including delay, bandwidth utilization rate and transmission cost.
In the behavior analysis sub-module, the system evaluates and adjusts the user's data requests by reinforcement learning methods, particularly Q-learning algorithms. The data format is mainly based on historical access records and preference modes of users, and specifically comprises access frequency and time distribution of the users to various types of content. The system identifies rules of user behavior by analyzing the data, for example, users browsing video content more frequently in the evening and preferring to read news in the morning. The Q learning algorithm dynamically adjusts the strategy, optimizes the user experience through rewarding and punishment mechanisms, and the generated user behavior analysis result reveals the preference and behavior mode of the user and provides basis for subsequent cache adjustment and transmission optimization.
In the cache adjustment sub-module, based on the user behavior analysis result, the system optimizes the cache by combining the least recently used policy with the dynamic content prefetching method. The submodule takes the limitation of the cache space and the update frequency of the content into consideration, and preferentially reserves the data most likely to be accessed by the user. For example, if the analysis shows that the user will view a particular type of video every night, the video will be cached preferentially. By the method, the cache adjustment submodule ensures that data with high access frequency is kept in the cache, data loading time is reduced, and the generated cache adjustment result improves the overall performance and user experience of the system.
In the transmission optimization sub-module, a network analysis technology and real-time user behavior data are adopted to optimize a data transmission path based on the cache adjustment result. Using the Dijkstra algorithm, the sub-module calculates and selects the optimal transmission path in the network, taking into account the delay, bandwidth utilization and transmission cost of the current network. The method ensures that the data is transmitted through the most effective path, reduces the delay and the cost of data transmission, and improves the data transmission efficiency. The generated optimized transmission path provides faster and more stable data access service for the user, thereby improving the satisfaction degree of the user and the quality of service.
It is assumed that in a smart terminal display scenario of an intelligent news recommendation system, the system needs to process and analyze the user's reading behavior data to optimize news recommendations. In the behavior analysis submodule, the system adopts a Q learning algorithm to analyze the reading history of a user, and the specific data format comprises a user ID, a read news ID, reading time and residence time, wherein the simulation numerical value is the user ID: "U4567", read news ID: [ "N123", "N456" ], read time: ["2023-10-01 10:30:00","2023-10-01 11:00:00"], residence time: [120, 300] sec. Through analysis, the system analyzes the preference and reading time distribution of the user on different types of news content, and generates a user behavior analysis result. In the buffer adjustment sub-module, according to the analysis result of the user behavior, the system adjusts the priority of the news content in the buffer by using the latest least-used strategy and the dynamic content prefetching method, so that the news types frequently accessed by the user are ensured to be kept in the buffer, the loading time is shortened, and the user experience is improved. In the transmission optimization sub-module, the system determines an optimal transmission path of the news content by using a Dijkstra algorithm according to the cache adjustment result and the real-time user behavior data. The analog data includes the current state of the network such as delay: 50ms, bandwidth utilization: 75%, transmission cost: 0.2 units. By the method, the system ensures that news content can be quickly transmitted to the user through the most effective path, reduces waiting time, improves timeliness and accuracy of news pushing, and accordingly generates an optimized transmission path, and ensures that the user always receives the latest and most relevant news content.
Referring to fig. 2 and 9, the interactive design module includes an interface layout sub-module, an information display sub-module, and a visual design sub-module;
The interface layout sub-module is based on an optimized transmission path, adopts a user center design principle, pays attention to the requirements and preferences of users to construct an interface, and comprises the steps of defining screen layout, arranging navigation elements and the positions of interaction components to generate a user interface layout result;
The information display sub-module displays information by adopting an information architecture and a visual design principle based on a user interface layout result, improves the readability of the information by using a layering design, an information grouping and a method for highlighting key information, and generates an information display design result;
The visual design sub-module is used for displaying a design result based on information, converting the data into a chart and a graph by utilizing a data visual technology, selecting a chart type comprising a histogram, a line graph and a pie chart, customizing a visual style comprising color, size and interaction function, assisting a user in analyzing the data and the information through visual elements, and generating a user interaction interface.
In the interface layout sub-module, a user center design principle is adopted, and the system builds an interactive interface based on an optimized transmission path and focusing on meeting the requirements and preferences of users. The process involves a detailed analysis of the user's usage habits and preferences, and the collected data formats include user interface operational records, feedback, and browsing history. According to the data, the system defines a screen layout, positions of navigation elements and interaction components are arranged, and interface layout is ensured to be visual and easy to use. The specific implementation process comprises the steps of creating a layout prototype, performing user test, and adjusting layout design according to feedback. The user interface layout result generated by the operation aims at improving user experience and ensuring that the user can efficiently access and operate required functions.
In the information display sub-module, based on the layout result of the user interface, the system displays information by adopting an information architecture and a visual design principle. Including organizing information using a hierarchical design so that users can easily find desired content, grouping information and highlighting key information helps users quickly identify important content. The data format comprises a plurality of media types such as text, pictures and video, and the system performs layout and display according to the importance and relevance of the content. The implementation effect of the refinement operation is that the readability of information and the information retrieval efficiency of users are improved, and the generated information display design result enables the users to understand and absorb the displayed information more quickly.
In the visualization design sub-module, the system converts complex data into charts and graphs by using a data visualization technology, and displays design results based on information. Selecting an appropriate chart type, such as a bar chart, a line chart or a pie chart, customizing the visual style, including color, size and interactive functions, according to the characteristics of the data and the requirements of the user. The goal of this process is to help the user more easily parse data and information through visual elements. Specific operational flows include data preprocessing, selection of an appropriate chart type, customizing visual styles, and integrating visual elements in a user interface. The user interaction interface generated by operation is attractive in appearance and rich in functions, so that a user can intuitively understand the back data and information, and the overall user experience is improved.
It is assumed that in the smart terminal display scenario of an intelligent health management platform, the system needs to process and analyze the health data of the user to optimize health and activity recommendations. The interface layout sub-module designs a user-friendly health instrument panel according to historical health data and activity preferences of a user, wherein data items comprise step numbers, heart rate, sleep quality and diet records, and simulation values are the step numbers: "10000 steps", heart rate: "75 times/min", sleep quality: "good", diet record: "Low sugar high protein". The information display sub-module adopts clear hierarchical design based on the layout result of the user interface, displays the health data in groups, and highlights key information such as abnormal heart rate or sleep quality reduction, so that a user can clearly identify health trend and potential problems. The visual design submodule converts the data into a chart and a graph to provide visual health trend analysis for a user, the chart type comprises a heart rate change chart, a step number histogram and a sleep quality pie chart, and visual style customization is carried out by using a bluish green tone liked by the user to assist the user to quickly analyze the health condition and the activity effect of the user through visual elements.
Referring to fig. 2 and 10, the maintenance monitoring module includes a performance monitoring sub-module, a security inspection sub-module, and an update management sub-module;
The performance monitoring submodule collects and analyzes system operation indexes including CPU utilization rate, memory consumption, network delay and disk I/O rate by adopting New Relic tools based on a user interaction interface, assists in evaluating the overall health condition and operation efficiency of the system, and excavates and solves performance bottlenecks to generate performance monitoring results;
Based on the performance monitoring result, the security inspection sub-module adopts a Nessus tool to perform security scanning and vulnerability identification of the system, evaluates the effectiveness of data protection measures, ensures the integrity and confidentiality of the system and user data, and generates a security inspection result;
Based on the security check result, the update management sub-module monitors the latest states of the software version and the security patch by adopting a WSUS tool, automatically evaluates the version of the current software of the system to compare with the latest released version, determines the priority and compatibility of the update, automatically downloads and installs the update and the patch, and generates maintenance and security condition analysis results.
In the performance monitoring sub-module, the system automatically collects and analyzes various system operation indexes from the user interaction interface through New Relic tools. The metrics include CPU usage, memory consumption, network latency, and disk I/O rate, with data formats being percentages (CPU usage, memory consumption) or milliseconds (network latency). Through real-time analysis of the data, the system can assist in assessing the health condition and the operating efficiency of the whole system, and simultaneously identify and solve performance bottlenecks, such as excessive CPU utilization rate or memory leakage. The method specifically comprises the steps of setting threshold alarms, analyzing performance trends and generating performance reports, and finally generating performance monitoring results by operation to assist system administrators and developers in optimizing system performance.
In the security inspection sub-module, the system utilizes a Nessus tool to conduct deep system security scanning and vulnerability identification according to the performance monitoring result. The data format relates to system vulnerability reporting, including vulnerability classes, affected system components, and repair suggestions. By automating the scanning and vulnerability recognition processes, the system evaluates the effectiveness of current data protection measures and ensures the integrity and confidentiality of the system and user data. The specific execution process comprises the steps of vulnerability database updating, scanning plan setting, vulnerability scanning execution and result analysis, and finally, a security check result is generated to provide a system security state and improvement measures.
In the update management sub-module, the system automatically monitors and evaluates the latest state of the software version and security patch using a WSUS tool. The data format relates to software version number and security patch details, including patch number and repair content. Based on the security check results, the system automatically determines the priority and compatibility of the updates, and then automatically downloads and installs the required updates and patches. This process ensures that the system remains up to date, thereby reducing security risks. The method comprises the steps of checking update, evaluating compatibility, scheduling update plan and executing update, and finally generating maintenance and safety condition analysis results to help maintain system stability and safety.
It is assumed that in the intelligent terminal display system of a large-scale online retail platform, the maintenance monitoring module is responsible for ensuring the stable operation and data security of the system. The data items collected by the performance monitoring sub-module by using New Relic tools comprise a CPU utilization average value of 60%, a memory consumption of 4GB, a network delay of 100ms and a disk I/O rate of 50MB/s. The security report generated by the security inspection sub-module through the Nessus tool indicates that three medium-level vulnerabilities exist in the system, and related system components comprise a Web server and a database, and related software and patches are suggested to be updated immediately. The data monitored by the update management sub-module using the WSUS tool includes a current software version of 1.4 and a latest version of 1.5, with two security patches to be installed. After the monitoring and updating operation is implemented, the overall performance of the system is improved, the CPU utilization rate is reduced to 50%, the memory consumption is reduced to 3GB, the network delay is reduced to 80ms, and the disk I/O rate is increased to 60MB/s. The security holes are repaired in time, and the security of the system and user data is improved. Through this series of control and updating, intelligent terminal display system can provide more smooth and safe user experience, ensures that retail platform can high-efficient, steady operation.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (7)
1. The intelligent terminal display system based on the data resource is characterized by comprising a data optimization module, an efficiency coding optimization module, a dynamic updating module, a behavior prediction module, an information extraction module, a path optimization module, an interactive design module and a maintenance monitoring module;
The data optimization module analyzes and processes data by adopting a parallel data processing algorithm based on the requirements of the intelligent terminal, implements dynamic memory management and an intelligent cache strategy based on a prediction model, optimizes data storage and access by combining a least recently used algorithm, and generates an acceleration data stream;
The data optimization module comprises a memory acceleration sub-module, a cache optimization sub-module and a parallel processing sub-module;
The memory acceleration submodule adopts APACHE SPARK frames based on intelligent terminal requirements, performs data segmentation and task scheduling by utilizing RDD and DAG execution engines of the memory acceleration submodule, and optimizes a data access flow by using a MapReduce algorithm, wherein a Map step is used for data mapping and conversion, a Reduce step is used for data aggregation and summarization, a memory use threshold and an allocation strategy are regulated by dynamic memory management, a future data access mode is predicted by combining a prediction algorithm based on a time sequence, cache data is managed by using a least recently used algorithm, and an acceleration memory data flow is generated;
The cache optimization submodule is used for training a classification model by utilizing historical access data based on a cache replacement strategy based on machine learning based on the accelerated memory data flow, predicting future access frequency of data items, wherein parameters comprise the historical access frequency and a time stamp, performing cache decision by a least recently used algorithm, and performing cache update by combining a real-time data access mode to generate an optimized cache data flow;
the parallel processing sub-module is based on an optimized cache data stream, adopts a MapReduce algorithm again, wherein a Map step distributes data to multiple nodes for parallel processing, a Reduce step summarizes the processing result of each node, and optimizes computing resource allocation by setting task parallelism parameters, and utilizes APACHE SPARK to perform data processing to generate an accelerated data stream, wherein the accelerated data stream comprises an adjusted data access rate, a data processing period and memory response time;
The efficiency coding optimization module performs format conversion on data by adopting sparse coding based on the accelerated data stream, optimizes the redundancy of the data by adopting an entropy coding technology, compresses and constructs the data by adopting an information bottleneck method, and generates a structured data stream;
The dynamic updating module analyzes a data change rule through a dynamic model based on a structured data stream by utilizing a complex network theory, adopts a self-adaptive learning algorithm to carry out self-adjustment according to the data change, updates the data stream and matches the current environment and the user requirement to generate a real-time updated data stream;
The dynamic updating module comprises a data flow management sub-module, a change prediction sub-module and an updating strategy sub-module;
The data flow management submodule is based on the structured data flow, and the dynamic graph of the data flow is constructed, wherein the dynamic graph comprises key nodes and paths in the data flow selected by utilizing a graph theory algorithm, the data flow is optimized by analyzing connectivity and data transmission efficiency among the nodes, a management strategy adopts a network flow analysis technology, and the flow of data in a network is adjusted by referring to the processing capacity of the nodes and the transmission bandwidth of edges, so that a management optimized data flow is generated;
the change prediction submodule predicts the state of a future data stream by adopting a time sequence analysis method and an adaptive learning algorithm based on management optimization data stream and an autoregressive moving average model, adjusts parameters of a prediction model according to real-time data cycle by an online machine learning method, matches the latest change of the data stream, predicts the change of the future data stream and generates a prediction adjustment data stream;
The updating strategy submodule adjusts the data flow based on prediction, adopts a Q-learning method, evaluates the effect of the data updating strategy by defining a reward function, refers to the timeliness and the accuracy of data updating by the reward function, carries out dynamic updating of the data flow by selecting the optimal data updating strategy through cyclic trial and error learning by a reinforcement learning algorithm, and matches the current environment and the user requirement to generate a data flow updated in real time;
The behavior prediction module analyzes the movement trend and time law of the user by using a geographic position analysis and time sequence prediction model based on the data flow updated in real time, synthesizes the past behavior data of the user by using a machine learning algorithm to perform pattern recognition, and generates a user behavior insight result;
The behavior prediction module comprises a space-time analysis sub-module, a pattern recognition sub-module and a demand prediction sub-module;
The space-time analysis submodule tracks the geographic position data of the user based on the data flow updated in real time by combining a geographic information system and an autoregressive moving average model, analyzes the data including longitude, latitude and place frequency, simultaneously analyzes the time law of the place accessed by the user, sets parameters, refers to a time window and a data sliding step length, draws the behavior trend of the user in multiple times and spaces, and generates a space-time behavior analysis result;
The pattern recognition submodule analyzes the behavior pattern of the user through a support vector machine and a random forest algorithm based on the space-time behavior analysis result, refers to parameters of frequency, place access sequence and time duration of user activities, recognizes and generalizes the behavior rules and habits of the user through analysis of historical behavior data of the user, and generates a user pattern recognition result;
The demand prediction sub-module is used for analyzing past purchasing behavior, site access and time cost of a user by utilizing a convolutional neural network and a long-term and short-term memory network based on a user mode identification result, and parameters to be referred comprise historical purchasing data, access frequency and average residence time, and predicting future demand trend of the user through comprehensive analysis of the historical behavior of the user to generate a user behavior insight result;
The information extraction module processes text content by adopting a natural language processing technology based on user behavior insight results, extracts key sentences from information by using a text summarization algorithm, and utilizes text clustering and emotion analysis to carry out structuring and emotion judgment on the content so as to generate a key information summary;
The path optimization module analyzes and optimizes the decision process of the content distribution network by adopting a reinforcement learning method based on the key information abstract, examines the performances of various data transmission paths by adopting a network analysis technology, adjusts the transmission strategy by combining user behaviors and network state data, and generates an optimized transmission path;
the interactive design module plans and constructs an interface based on an optimized transmission path by adopting a user center design principle and an interactive design method, and converts data into a chart through a data visualization technology to generate a user interactive interface;
The maintenance monitoring module adopts a performance monitoring tool and a data security protocol to conduct routine inspection and security assessment based on a user interaction interface, ensures running stability and data security through real-time monitoring and automatic updating management strategies, and generates maintenance and security condition analysis results.
2. The intelligent terminal display system based on data resources of claim 1, wherein: the structured data stream comprises a unified data format, a compressed data volume and an optimized data index, the real-time updated data stream comprises dynamically-changed user preference, instant environment data and updated interaction information, the user behavior insight result comprises an identified user behavior mode, a predicted user demand and an analyzed time trend, the key information abstract comprises an abstract topic vocabulary, key sentence extraction and key event summarization, the optimized transmission path comprises a selected network channel, an adjusted transmission protocol and an optimized routing strategy, the user interaction interface comprises a customized interface layout, user preference design elements and interaction convenience optimization, and the maintenance and safety condition analysis result comprises a detected system performance index, an identified safety risk point and proposed improvement measures.
3. The intelligent terminal display system based on data resources of claim 1, wherein: the efficiency coding optimization module comprises a format conversion sub-module, a compression strategy sub-module and a coding efficiency sub-module;
the format conversion submodule selects a base vector based on the accelerated data stream by utilizing a dictionary learning algorithm, and parameters comprise sparsity control and reconstruction error limit, so that the data maintains core information and unnecessary dimensionality in the conversion process to generate a data stream after format conversion;
the compression strategy submodule distributes multi-length coding character strings according to probability distribution of data through Huffman coding and arithmetic coding based on the data stream after format conversion, and parameters comprise probability distribution of symbols and length limitation of coding to generate a compressed data stream;
The coding efficiency submodule optimizes redundancy between input data and output data by utilizing mutual information theory based on the compressed data stream by adopting an information bottleneck method, parameters comprise an information retention threshold and a compression level, and the structured data stream is generated by changing the information quantity while maintaining the data structure by evaluating and balancing the relationship between data compression and information retention.
4. The intelligent terminal display system based on data resources of claim 1, wherein: the information extraction module comprises a keyword extraction sub-module, a summary generation sub-module and an information highlighting sub-module;
The keyword extraction submodule carries out text analysis by combining a TF-IDF algorithm with part-of-speech tagging based on a user behavior insight result through a natural language processing technology, the TF-IDF algorithm calculates the key degree of words in a document set, a word part tagging is assisted to determine a word function, words associated with user behaviors are identified, parameter settings comprise word frequency counting and document frequency inversion, common words are filtered, keywords reflecting the user behaviors and interests are extracted, and a keyword extraction result is generated;
The abstract generation submodule analyzes the text structure and the keyword distribution based on the keyword extraction result by an extraction abstract method, selects sentences comprising keywords to be combined, refers to the positions of the sentences in the text, the keyword density and the text logic structure, enables the selected sentences to summarize text contents and reflect user interest points, and generates a text abstract result;
The information highlighting sub-module classifies subjects of summary contents by using a K-means clustering algorithm based on text summary results and combining text clustering and emotion analysis technology, an emotion analysis tool evaluates emotion tendencies of each part of contents, parameters refer to the number of clusters and the vocabulary range of emotion analysis, key information in texts is highlighted, and a key information summary is generated.
5. The intelligent terminal display system based on data resources of claim 1, wherein: the path optimization module comprises a behavior analysis sub-module, a cache adjustment sub-module and a transmission optimization sub-module;
The behavior analysis submodule adopts a reinforcement learning method based on key information abstract, evaluates and adjusts the data request of the user through a Q learning algorithm, analyzes rules behind the behavior of the user according to the history access record and the preference mode, including the access frequency and time distribution of the user to the multi-type content, and generates a user behavior analysis result;
the cache adjustment submodule adjusts the priority of the content in the cache by utilizing the least recently used strategy to cooperate with a dynamic content prefetching method based on the analysis result of the user behavior, and refers to the limitation of the cache space and the update frequency of the content to ensure that the most frequently requested data is kept in the cache to generate a cache adjustment result;
the transmission optimization submodule adopts a network analysis technology and real-time user behavior data based on a cache adjustment result, selects an optimal transmission path of the data through a Dijkstra algorithm, and generates an optimal transmission path by taking the parameters of the current state of the network, including delay, bandwidth utilization rate and transmission cost.
6. The intelligent terminal display system based on data resources of claim 1, wherein: the interactive design module comprises an interface layout sub-module, an information display sub-module and a visual design sub-module;
The interface layout submodule is used for focusing on the requirements and preferences of a user to construct an interface based on an optimized transmission path by adopting a user center design principle, and comprises the steps of defining screen layout, arranging navigation elements and positions of interaction components to generate a user interface layout result;
The information display sub-module displays information by adopting an information architecture and a visual design principle based on a user interface layout result, improves the readability of the information by using a layering design, an information grouping and a method for highlighting key information, and generates an information display design result;
The visual design sub-module is used for displaying a design result based on information, converting the data into a chart and a graph by utilizing a data visual technology, selecting a chart type comprising a histogram, a line graph and a pie chart, customizing a visual style comprising color, size and interaction function, assisting a user in analyzing the data and the information through visual elements, and generating a user interaction interface.
7. The intelligent terminal display system based on data resources of claim 1, wherein: the maintenance monitoring module comprises a performance monitoring sub-module, a security check sub-module and an update management sub-module;
The performance monitoring submodule collects and analyzes system operation indexes including CPU (central processing unit) utilization rate, memory consumption, network delay and disk I/O (input/output) rate by adopting New Relic tools based on a user interaction interface, assists in evaluating the overall health condition and operation efficiency of the system, and excavates and solves performance bottlenecks to generate performance monitoring results;
The security inspection sub-module adopts a Nessus tool to conduct security scanning and vulnerability identification of the system based on the performance monitoring result, evaluates the effectiveness of data protection measures, ensures the integrity and confidentiality of the system and user data, and generates a security inspection result;
the update management sub-module monitors the latest states of the software version and the security patch by adopting a WSUS tool based on the security check result, automatically evaluates the version of the current software of the system to compare with the latest released version, determines the priority and compatibility of the update, automatically downloads and installs the update and the patch, and generates maintenance and security condition analysis results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252066.3A CN117829096B (en) | 2024-03-06 | 2024-03-06 | Intelligent terminal display system based on data resources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252066.3A CN117829096B (en) | 2024-03-06 | 2024-03-06 | Intelligent terminal display system based on data resources |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117829096A CN117829096A (en) | 2024-04-05 |
| CN117829096B true CN117829096B (en) | 2024-05-14 |
Family
ID=90506303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410252066.3A Active CN117829096B (en) | 2024-03-06 | 2024-03-06 | Intelligent terminal display system based on data resources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829096B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184501A (en) * | 2011-03-24 | 2011-09-14 | 上海博路信息技术有限公司 | Electronic coupon system of mobile terminal |
| DE202023105444U1 (en) * | 2023-09-19 | 2023-09-29 | Ankit Agarwal | Deep learning based system to improve the performance of sentiment analysis on social media data using management strategies |
| CN117273414A (en) * | 2023-11-23 | 2023-12-22 | 苏州航天***工程有限公司 | System and method for analyzing and identifying big data of smart city |
| CN117271981A (en) * | 2023-11-21 | 2023-12-22 | 湖南嘉创信息科技发展有限公司 | Artificial intelligence management system based on cross-platform data interaction |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10896421B2 (en) * | 2014-04-02 | 2021-01-19 | Brighterion, Inc. | Smart retail analytics and commercial messaging |
-
2024
- 2024-03-06 CN CN202410252066.3A patent/CN117829096B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184501A (en) * | 2011-03-24 | 2011-09-14 | 上海博路信息技术有限公司 | Electronic coupon system of mobile terminal |
| DE202023105444U1 (en) * | 2023-09-19 | 2023-09-29 | Ankit Agarwal | Deep learning based system to improve the performance of sentiment analysis on social media data using management strategies |
| CN117271981A (en) * | 2023-11-21 | 2023-12-22 | 湖南嘉创信息科技发展有限公司 | Artificial intelligence management system based on cross-platform data interaction |
| CN117273414A (en) * | 2023-11-23 | 2023-12-22 | 苏州航天***工程有限公司 | System and method for analyzing and identifying big data of smart city |
Non-Patent Citations (2)
| Title |
|---|
| 国内基于大数据的信息推荐研究进展:核心内容;孙雨生;朱金宏;李亚奇;;现代情报;20200801(第08期);全文 * |
| 融媒体信息推荐模型构建与信息推荐方法研究;崔金栋;陈思远;;情报科学;20200701(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117829096A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110781321B (en) | Multimedia content recommendation method and device | |
| US9928526B2 (en) | Methods and systems that predict future actions from instrumentation-generated events | |
| CN108549957B (en) | Internet topic trend auxiliary prediction method and system and information data processing terminal | |
| US10452984B2 (en) | System and method for automated pattern based alert generation | |
| US20220083896A9 (en) | Systems and methods for improved modelling of partitioned datasets | |
| McKelvey et al. | Visualizing communication on social media: Making big data accessible | |
| JP5848199B2 (en) | Impact prediction device, impact prediction method, and program | |
| Cutrona et al. | Semantically-enabled optimization of digital marketing campaigns | |
| Williamson | Reassembling children as data doppelgangers: How databases are making education machine-readable | |
| CN114996549A (en) | Intelligent tracking method and system based on active object information mining | |
| Gyódi et al. | Informing policy with text mining: technological change and social challenges | |
| CN113157871B (en) | News public opinion text processing method, server and medium applying artificial intelligence | |
| CN117829096B (en) | Intelligent terminal display system based on data resources | |
| Xu et al. | The mobile media based emergency management of web events influence in cyber-physical space | |
| Dan | Intelligent English resource recommendation and teaching effect based on symmetric SDAE collaborative filtering algorithm | |
| CN111209394A (en) | Text classification processing method and device | |
| Todorova-Ekmekci et al. | Analysis and Evaluation of New Digital Media Usage, Impact and Presence. | |
| CN109635092A (en) | Analyze method, apparatus, medium and the electronic equipment of employee's working condition | |
| KR20230059364A (en) | Public opinion poll system using language model and method thereof | |
| CN113722288A (en) | Modeling method for time-space data statistics | |
| CN116361445B (en) | Prediction method and device for Tibetan bilingual user interest labels | |
| Wang et al. | Research on Abnormal Behavior Prediction by Integrating Multiple Indexes of Student Behavior and Text Information in Big Data Environment | |
| Zadorozhny et al. | A framework for performance evaluation of user modeling servers for web applications | |
| Sun et al. | Evolutionary learner profile optimization using rare and negative association rules for micro open learning | |
| CN113569557B (en) | Information quality identification method, device, equipment, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |