A real-time data analysis system, method, device and medium driven by 5G messages

Abstract

The present invention relates to the field of communication technologies, and discloses a real-time data analysis system, method, device and medium driven by 5G messages. The method includes: first receiving 5G messages and collecting multivariate data, obtaining a real-time data group through steps such as parsing, extraction, and retrieval, then performing fluctuation analysis on it, identifying key fluctuation nodes to calculate the change rate, thereby restoring the real-time business scenario and classifying and tagging, determining the service channel and then analyzing the channel quality to calculate the data throughput, further optimizing the channel configuration and calculating the channel utilization rate, then generating an analysis permission key based on the channel utilization rate, querying corresponding rules to extract data identifiers, and finally generating a data analysis report of 5G messages based on the data identifiers, forming a complete data processing and analysis link. The present invention can improve the analysis efficiency of real-time data.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular, to a real-time data analysis system, method, device, and medium based on 5G message driving. Background Art

[0002] In the current era of rapid digital development and information explosion, real-time data analysis plays a crucial role in decision-making and business optimization in various industries. With the large-scale commercialization and popularization of 5G technology, its characteristics of high speed, low latency, and large connection bring new opportunities for real-time data transmission and processing.

[0003] In many industries, whether it is e-commerce precision marketing, financial risk control, industrial production process monitoring, or smart city operation management, traditional data analysis methods often rely on periodic data collection and offline processing modes. On the one hand, this lagging analysis method is difficult to meet the ever-changing market dynamic needs, unable to timely capture the change trends of business key nodes, resulting in enterprises missing the best decision-making opportunities; on the other hand, in the face of the vast and wide-source data flood, traditional methods have obvious shortcomings in the timeliness of data transmission and the efficiency of processing, thus affecting the analysis efficiency of real-time data. Therefore, a real-time data analysis method based on 5G message driving is needed to improve the analysis efficiency of real-time data. Summary of the Invention

[0004] The present invention provides a real-time data analysis system, method, device, and medium based on 5G message driving, and its main purpose is to improve the analysis efficiency of real-time data.

[0005] To achieve the above object, a real-time data analysis method based on 5G message driving provided by the present invention includes:

[0006] Receiving a 5G message, collecting multi-source data information in the 5G message, parsing a data source identifier corresponding to the multi-source data information, extracting a data feature code associated with the data source identifier, and retrieving a real-time data group corresponding to the data feature code;

[0007] Performing fluctuation analysis on data items in the real-time data group to obtain a fluctuation trend sequence, identifying key fluctuation nodes in the fluctuation trend sequence, and calculating a node change rate corresponding to the key fluctuation nodes;

[0008] Based on the change rate, restoring a real-time business scenario corresponding to the real-time data group, performing label classification on the real-time business scenario to obtain a classification scenario label, and querying key label elements in the classification scenario label, and marking element core points corresponding to the key label elements;

[0009] Based on the core element points, determine the service channel corresponding to the real-time data group, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0010] Based on the channel utilization rate, generate an analysis permission key corresponding to the real-time data group, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0011] To solve the above problems, the present invention also provides a real-time data analysis system driven by 5G messages, and the system includes:

[0012] A data retrieval module, configured to receive a 5G message, collect multi-source data information in the 5G message, parse the data source identifier corresponding to the multi-source data information, extract the data feature code associated with the data source identifier, and retrieve the real-time data group corresponding to the data feature code;

[0013] A change rate calculation module, configured to perform fluctuation analysis on data items in the real-time data group to obtain a fluctuation trend sequence, identify key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation nodes;

[0014] A core point annotation module, configured to restore the real-time service scenario corresponding to the real-time data group based on the change rate, perform label classification on the real-time service scenario to obtain classification scenario labels, and query key label elements in the classification scenario labels to annotate the core element points corresponding to the key label elements;

[0015] A channel utilization rate calculation module, configured to determine the service channel corresponding to the real-time data group based on the core element points, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0016] A report generation module, configured to generate an analysis permission key corresponding to the real-time data group based on the channel utilization rate, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0017] To solve the above problems, the present invention also provides an electronic device, and the electronic device includes:

[0018] At least one processor; and,

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to implement the above-mentioned real-time data analysis driven by 5G messages.

[0021] To solve the above problems, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned real-time data analysis driven by 5G messages.

[0022] It can be seen that the present invention captures market fluctuations in real time in the financial field by receiving 5G messages and collecting multi-source data information in the 5G messages, providing accurate basis for risk control and investment decisions, and improving the timeliness and scientificity of decisions; in industrial production, it can immediately obtain equipment operation parameters, optimize production processes, and enhance production efficiency and stability; in the construction of smart cities, it helps to quickly integrate multi-source data such as transportation and environment, realize intelligent management, and improve the overall efficiency of urban operation. Further, the present invention analyzes the fluctuations of data items in the real-time data group to obtain a fluctuation trend sequence, which can clearly understand the dynamic change law of the data, accurately capture the ups and downs of the data. Whether it is the rise and fall of market prices, the peaks and valleys of network traffic, or the fluctuations of equipment performance parameters, etc., can be accurately presented, making the change trend of the data clear at a glance. Based on the change rate, the present invention restores the real-time business scenario corresponding to the real-time data group, can accurately understand business dynamics, and trace the changes of the business at key nodes through the change rate. For example, the change rate of sales data can present the immediate effect of promotional activities. Based on the element core points, the present invention determines the service channel corresponding to the real-time data group, can accurately locate the data transmission path closely matching the core service requirements, reduce unnecessary resource consumption and data redundancy, improve transmission efficiency, help optimize business processes, enhance the business response speed by ensuring the transmission of key data in an efficient channel, and generate an analysis permission key corresponding to the real-time data group based on the channel utilization rate, which can ensure the security and compliance of data transmission, accurately allocate permission keys according to the channel utilization rate, and only compliant real-time data groups can obtain transmission permissions, effectively preventing illegal data from occupying channel resources. Therefore, a real-time data analysis system, method, device and medium driven by 5G messages proposed in the embodiments of the present invention can improve the analysis efficiency of real-time data. Description of the Drawings

[0023] Figure 1 Schematic diagram of an application environment for real-time data analysis driven by 5G messages provided by an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of a process for real-time data analysis driven by 5G messages provided by an embodiment of the present invention;

[0025] Figure 3 Schematic diagram of modules of a real-time data analysis system driven by 5G messages provided by an embodiment of the present invention;

[0026] Figure 4 Schematic diagram of the internal structure of an electronic device for implementing real-time data analysis driven by 5G messages provided by an embodiment of the present invention;

[0027] The realization, functional features and advantages of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0028] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] The embodiments of the present invention provide a method for real-time data analysis driven by 5G messages, which can be applied to an application environment such as Figure 1 where the client communicates with the server through the network. The server can collect and receive 5G messages through the client, collect the multi-source data information in the 5G messages, parse the data source identifier corresponding to the multi-source data information, extract the data feature code associated with the data source identifier, and retrieve the real-time data group corresponding to the data feature code; perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify the key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation nodes; based on the change rate, restore the real-time business scenario corresponding to the real-time data group, perform label classification on the real-time business scenario to obtain classification scenario labels, and query the key label elements in the classification scenario labels to mark the element core points corresponding to the key label elements; based on the element core points, determine the service channel corresponding to the real-time data group, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0030] Based on the channel utilization rate, generate an analysis permission key corresponding to the real-time data group, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0031] Refer to Figure 2 As shown, it is a schematic flowchart of real-time data analysis driven by 5G messages provided by an embodiment of the present invention. In the embodiment of the present invention, the real-time data analysis driven by 5G messages includes the following steps S1-S5:

[0032] S1. Receive a 5G message, collect the multi-source data information in the 5G message, parse the data source identifier corresponding to the multi-source data information, extract the data feature code associated with the data source identifier, and retrieve the real-time data group corresponding to the data feature code.

[0033] By receiving 5G messages and collecting the multi-source data information in the 5G messages, the present invention can, in the financial field, capture market fluctuations in real time, provide accurate basis for risk control and investment decisions, and improve the timeliness and scientificity of decisions; for industrial production, it can immediately obtain equipment operation parameters, optimize production processes, and enhance production efficiency and stability; in the construction of smart cities, it helps to quickly integrate multi-source data such as transportation and environment, realize intelligent management, and improve the overall efficiency of urban operation.

[0034] Among them, the 5G message refers to a new type of message communication service based on the 5G network, which integrates the advantages of various communication methods. It not only supports rich media formats such as text, pictures, audio, and video, but also has the characteristics of strong interactivity and high intelligence. Compared with traditional text messages, 5G messages can carry more complex and larger amounts of information, enabling more efficient information transmission and interaction, and becoming an important carrier for many industries to achieve digital transformation and real-time data interaction. For example, in the intelligent customer service scenario, the communication between users and enterprise customer service can be quickly and richly carried out through 5G messages. Enterprises can send users information such as product introductions and operation guides with pictures and texts; the multi-source data information refers to a data set from different data sources with various data types and formats, covering structured data (such as tabular data in a database), semi-structured data (such as data in XML and JSON formats), and unstructured data (such as images, audio, video, text files, etc.). These data can be collected from various terminal devices, sensors, business systems, and Internet platforms, etc., and contain rich business information and user behavior information, etc. Taking the intelligent transportation system as an example, the multi-source data information may include vehicle driving speed, location, road conditions (camera image data), traffic signal status (sensor data), and driver's operation behavior (such as braking, accelerating, etc. data). Optionally, the collection of multi-source data information in the 5G message can be achieved through data collection tools, such as: tools like Flume, Kafka Connect, etc.

[0035] Furthermore, by parsing the data source identifier corresponding to the multi-source data information, the present invention extracts the data feature code associated with the data source identifier, which helps to accurately trace the data, clarify the generation source and channel of the data, thereby enhancing the credibility and reliability of the data, being able to quickly screen and classify massive data, improving the efficiency of data processing, and making the subsequent analysis work more targeted and accurate.

[0036] Among them, the data source identifier refers to specific information or a marker used to uniquely determine the data source, which can be a unique string, digital code, IP address, device number, database table name, etc. For example, in an industrial Internet of Things scenario, for data collected by sensors on different production lines, the data source identifier may be the unique device number of each sensor. In this way, when receiving a large amount of data from different sensors, the data source identifier can quickly distinguish which specific device on which production line generated the data; the data feature code refers to a code that is closely associated with the data source and can represent the key features or attributes of the data generated by the data source. It can be generated based on factors such as the data type, format, generation time range, and specific business meaning. For example, for a sales data data source of an e-commerce platform, the data feature code may include information such as product category codes (such as electronic products category, clothing category, etc.), sales time features (such as quarter, month, etc.), and sales area codes. Through these feature codes, specific categories of product sales data can be quickly screened out, and when conducting data analysis, it can more accurately focus on specific business scenarios, such as analyzing the sales trend of electronic products in a specific area in a certain quarter. Optionally, the parsing of the data source identifier corresponding to the multi-source data information can be implemented through a label classification tool, such as: the Label Studio tool. These tools can automatically classify data based on the existing label system to determine the data source identifier; the extraction of the data feature code associated with the data source identifier can be implemented through a hash function algorithm, such as: hash functions such as MD5 or SHA-256. The key data fields in the data source are hashed to obtain a fixed-length hash value as the data feature code.

[0037] Furthermore, by retrieving the real-time data group corresponding to the data feature code, the present invention can quickly locate the data set closely related to specific features, greatly improving the efficiency of data query and acquisition, reducing the time cost of blindly searching in massive data, and helping to promptly capture data changes associated with the key features of the business, providing accurate and targeted basis for real-time decision-making.

[0038] Among them, the real-time data group refers to the finally retrieved real-time data set that precisely corresponds to the data feature code. These data not only meet the range defined by the key identification information but also have immediacy in time and can dynamically reflect the actual situation of the current business scenario. For example, in a financial transaction scenario, the real-time data group is a data set that instantaneously obtains data such as the current transaction amount, information of both parties to the transaction, and the market real-time exchange rate according to a specific transaction feature code.

[0039] As an embodiment of the present invention, retrieving the real-time data group corresponding to the data feature code includes: identifying the key identification information corresponding to the data feature code; constructing a retrieval index framework corresponding to the key identification information; preliminarily screening the matchable data sets in the retrieval index framework; analyzing the strongly associated data blocks corresponding to the data subsets in the matchable data sets; and retrieving the real-time data group corresponding to the data feature code based on the strongly associated data blocks.

[0040] Among them, the key identification information refers to the core elements extracted from the data feature code that are representative and can guide the data retrieval direction. It can be a specific code defined based on the business scenario. For example, in e-commerce data, the key identification information can be product category codes (such as 3C digital, beauty, etc.), promotion activity codes, or quarterly and monthly identifiers reflecting the time attributes of the data, as well as regional sales partition codes, etc.; the retrieval index framework refers to a structured retrieval guidance system built based on the key identification information, which is equivalent to a "navigation map" for data retrieval. If the key identification information includes product category and time range, the retrieval index framework will build a hierarchical directory structure around these two dimensions, classify the data indexes of the same product category in different time periods together, and set corresponding index paths to quickly locate the area where the target data can be stored; the matchable data sets refer to the data sets screened from the massive data storage repository and having a certain correlation with the key identification information during the preliminary search using the retrieval index framework. It can contain multiple data subsets. For example, when retrieving urban traffic flow data with the region as the key identification information, the matchable data sets are those that are initially located through the index within the specified regional scope and contain traffic flow monitoring data for different road sections and different time periods; the strongly associated data blocks refer to the closely connected data combinations mined based on the internal logical relationships between the data, such as causal relationships and co-variation relationships, after in-depth analysis of the data subsets in the matchable data sets. Taking industrial production as an example, when monitoring the operating status of equipment, if the matchable data sets contain multiple data subsets such as equipment temperature, pressure, and vibration frequency, and through correlation analysis, it is found that there is a strong association between the increase in temperature, the increase in pressure, and the acceleration of the vibration frequency, these related data subsets constitute the strongly associated data blocks.

[0041] Further, the identification of the key identification information corresponding to the data feature code can be achieved through classification algorithms, such as: support vector machines, etc.; the construction of the retrieval index framework corresponding to the key identification information can be achieved through tree index structure methods, such as: B-trees, B+-trees, and other tree index structures; the preliminary screening of the matchable data sets in the retrieval index framework can be achieved through Boolean retrieval models, such as: widely used in the field of information retrieval, using the key identification information as the retrieval term, and screening the data sets by setting logical operators such as AND, OR, and NOT to connect the retrieval terms; the analysis of the strongly associated data blocks corresponding to the data subsets in the matchable data sets can be achieved through association rule mining algorithms, such as: Apriori and other algorithms; the retrieval of the real-time data group corresponding to the data feature code can be achieved through a stream data processing engine, such as: Apache Flink and other engines.

[0042] S2. Perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify the key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation nodes.

[0043] Through the fluctuation analysis of the data items in the real-time data group of the present invention, a fluctuation trend sequence is obtained, which can clearly insight into the dynamic change law of the data, accurately capture the ups and downs of the data. Whether it is the rise and fall of market prices, the high and low peaks of network traffic, or the fluctuations of device performance parameters, etc., can be accurately presented, making the change trend of the data clear at a glance.

[0044] Among them, the fluctuation trend sequence refers to an ordered set arranged in chronological order, which can clearly show the fluctuation change direction of the data. Connecting the fluctuation amplitude indicators corresponding to each time window in sequence according to time forms the fluctuation trend sequence, just like drawing a water level change curve for a river, which fully presents the ups and downs of the data over time.

[0045] As an embodiment of the present invention, the performing fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence includes: performing sorting processing on the data items in the real-time data group to obtain sorted data items; dividing the sorted data items into their corresponding time windows; calculating the statistical feature values corresponding to the data in the time windows; analyzing the eigenvectors corresponding to the statistical feature values; extracting the fluctuation amplitude indicators from the eigenvectors; and based on the fluctuation amplitude indicators, performing fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence.

[0046] Among them, the sorted data items refer to an ordered data set obtained by rearranging each data item in the real-time data group according to specific rules (usually chronological order, data size order, etc.). For example, in a financial stock trading data group, data such as the transaction price and trading volume of each stock are arranged in chronological order of transactions. These arranged transaction price and trading volume data are the sorted data items; the time window refers to a defined time period interval for data observation and analysis. Just like when monitoring network traffic data, a 5-minute time window is used, and continuous traffic data is divided into segments every 5 minutes. Each such 5-minute time period is a time window; the statistical characteristic value refers to a representative value obtained by performing mathematical statistical operations on data within the same time window. Common ones include the mean, which reflects the average level of the data. For example, for a set of product sales price data within a certain time window, its mean represents the average selling price of the product during that period; the median can reflect the middle position of the data and can avoid the influence of extreme values; the eigenvector refers to a multi-dimensional vector representation constructed based on the statistical characteristic values of the time window. Taking the user access data of an e-commerce platform as an example, if the statistical characteristic values within a time window include the average user access duration, the average number of accessed pages, and the proportion of new user accesses, combining these three values into a three-dimensional vector, this vector is the eigenvector; the fluctuation amplitude index refers to a key parameter used to quantitatively describe the degree of data fluctuation. When analyzing power load data, if the eigenvectors of two consecutive time windows have a large difference in the dimensional values representing the load peak, this difference after processing is the fluctuation amplitude index.

[0047] Furthermore, the sorting process of the data items in the real-time data group can be achieved through sorting algorithms, such as: bubble sort, quick sort and other algorithms; the division of the sorted data items into their corresponding time windows can be achieved through window division methods, such as: fixed interval division method, sliding window method and other methods; the calculation of the statistical characteristic values corresponding to the data in the time window can be achieved through statistical functions in Excel, such as: AVERAGE, MEDIAN, STDEV and other functions; the analysis of the eigenvector corresponding to the statistical characteristic value can be achieved through the principal component analysis method, such as: when the statistical characteristic values are numerous and the data dimension is high, PCA can be used to extract the main components and combine them into an eigenvector; the extraction of the fluctuation amplitude index in the eigenvector can be achieved through the fluctuation amplitude calculation method, such as: first calculate the moving average of the statistical characteristic values of each dimension of the eigenvector respectively, and then subtract the corresponding moving average from the statistical characteristic value of the current eigenvector, and the obtained difference is used as the fluctuation amplitude index; the fluctuation analysis of the data items in the real-time data group can be achieved through the fluctuation analysis model, such as: ARIMA model, LSTM network and other models.

[0048] By identifying the key fluctuation nodes in the fluctuation trend sequence, the present invention can accurately locate important turning points in complex data fluctuations. These nodes often represent the critical change moments of the market, business, or system, such as sharp rise and fall points in the financial market, sudden changes in key parameters during the production process, etc.

[0049] Among them, the key fluctuation node refers to the specific position or moment corresponding to the fluctuation data point in the fluctuation trend sequence, which has significant characteristics, has an important impact on the overall trend, or marks a major change in the data. These nodes usually manifest as data mutations, abnormal peaks, troughs, or trend turning points, which can reflect the critical events or state changes experienced by the system, market, business process, etc. at a specific time or under specific conditions, such as the sharp drop point of the stock price in the financial market, the moment of sudden parameter change caused by equipment failure on the industrial production line, the sales explosion node of e-commerce sales data during promotional activities, etc. Optionally, the identification of the key fluctuation nodes in the fluctuation trend sequence can be achieved by methods based on thresholds, such as: fixed threshold method, adaptive threshold method, etc.

[0050] By calculating the node change rate corresponding to the key fluctuation node, the present invention can quantify the degree of data change at the key fluctuation node, accurately understand the change speed and amplitude of the data at these key turning points. Whether it is the sharp rise and fall of the market condition or the significant fluctuation of business indicators, it can be clearly presented by specific values.

[0051] Among them, the node change rate is an index used to measure the degree of change of the key fluctuation node, which reflects the change of the key fluctuation node under different samples and data groupings.

[0052] As an embodiment of the present invention, the calculation of the node change rate corresponding to the key fluctuation node includes:

[0053] Calculating the node change rate corresponding to the key fluctuation node by using the following formula: Among them, represents the node change rate corresponding to the key fluctuation node, represents the total number of node samples corresponding to the key fluctuation node, represents the quantity index corresponding to the node sample, represents the th sample value of the node sample, represents the average value of the node sample, represents the group quantity corresponding to the data grouping, represents the total number of data points in each group of data, represents the quantity index corresponding to the data point, represents the The standard value of each data point.

[0054] Specifically, the node sample refers to the data sample used to calculate the change rate of the key fluctuation node. These samples are related to the key fluctuation node, and each sample has a corresponding quantity index; the sample value refers to the specific value in the node sample, and these values are used to reflect the specific situation of the node sample when calculating the node change rate; the standard value refers to the data after standardization processing, which is obtained by transforming the original data through a specific transformation into a value with a specific mean and standard deviation.

[0055] S3. Based on the change rate, restore the real-time business scenario corresponding to the real-time data group, classify the real-time business scenario to obtain a classified scenario label, and query the key label elements in the classified scenario label, and mark the element core points corresponding to the key label elements.

[0056] Based on the change rate, the present invention restores the real-time business scenario corresponding to the real-time data group, can accurately insight into business dynamics, and trace the changes of the business at key nodes through the change rate. For example, the change rate of sales data can present the immediate effect of promotional activities.

[0057] Among them, the real-time business scenario refers to the actual business operation situation restored through scenario feature parameters. For example, at a certain time point, through a series of above analyses, scenario feature parameters such as production volume, cost, and market share are obtained, and comprehensively present the actual business operation state such as whether the business is in stable production, or in a promotional activity, or in response to a market competition crisis at that time.

[0058] As an embodiment of the present invention, the restoring the real-time business scenario corresponding to the real-time data group based on the change rate includes: analyzing the fluctuation amplitude range corresponding to the change rate; dividing the business fluctuation level corresponding to the real-time data group based on the fluctuation amplitude range; matching the business scenario type corresponding to the real-time data group based on the business fluctuation level; querying the scenario feature parameters corresponding to the business scenario type; and restoring the real-time business scenario corresponding to the real-time data group based on the scenario feature parameters.

[0059] Among them, the fluctuation amplitude range refers to the interval determined according to the change rate, which reflects the degree of data change. For example, by calculating the maximum value, minimum value of the change rate and common fluctuation intervals, a range from the minimum fluctuation to the maximum fluctuation is defined, which is a quantitative interval for measuring the fluctuation of data within a certain period of time; the business fluctuation level refers to the classification of the business fluctuation degree based on the fluctuation amplitude range. For example, the fluctuation amplitude range is divided into three levels: small, medium, and large. When the fluctuation amplitude is within a smaller interval, the corresponding business fluctuation level is low; when the fluctuation amplitude is in the medium interval, the business fluctuation level is medium; when the fluctuation amplitude is large, the business fluctuation level is high; the business scenario type refers to the business scenario category corresponding to different business fluctuation levels. For example, the low fluctuation level may correspond to the business stable operation scenario, such as the daily stable production scenario; the medium fluctuation level may correspond to the business adjustment scenario, such as the scenario where the sales volume changes due to product promotion; the high fluctuation level may correspond to the business crisis or opportunity scenario, such as the scenario where the market share changes sharply due to the competitor launching a disruptive product; the scenario feature parameter refers to various parameters that can describe the characteristics of the business scenario type. For example, for the daily stable production scenario, its scenario feature parameters may include stable production volume, fixed production cycle, low cost fluctuation, etc.; for the product promotion scenario, the scenario feature parameters may include the short-term growth amplitude of sales volume, promotion cost, market response time, etc.; for the scenario of sharp market share change, the scenario feature parameters may include the market share change rate, competitor's strategy parameters, the effect of its own coping strategy, etc.

[0060] Furthermore, the analysis of the fluctuation amplitude range corresponding to the change rate can be achieved through range analysis methods, such as: statistical interval method, quantile method, etc.; the division of the business fluctuation level corresponding to the real-time data group can be achieved through a rule-based division method, such as: dividing the level according to business characteristics and pre-set rules; the matching of the business scenario type corresponding to the real-time data group can be achieved through a neural network model, such as: training the model with a large amount of historical data so that it can accurately output the corresponding business scenario type according to the characteristics such as the input business fluctuation level; the query of the scenario feature parameters corresponding to the business scenario type can be achieved through parameter query tools, such as: CPU-Z, Speccy, etc.; the restoration of the real-time business scenario corresponding to the real-time data group can be achieved through visualization tools, such as: Tableau, etc.

[0061] By classifying the real-time business scenarios to obtain classified scenario tags and querying the key tag elements in the classified scenario tags, the present invention can efficiently sort out complex business scenarios, make them well-organized through tag classification, facilitate quick positioning and understanding of various business situations, contribute to accurate analysis of business characteristics, and different classified scenario tags can highlight the unique attributes of the business, providing a direction for formulating targeted strategies.

[0062] Among them, the classified scenario tags refer to the representative identifiers given after summarizing and abstracting business scenarios according to various factors such as the characteristics, attributes, business process stages, and business goal achievement of real-time business scenarios. These tags are designed to classify and manage the complex business scenarios so as to more clearly identify, understand, and analyze different types of business scenario patterns and their characteristics. For example, in the e-commerce business, there may be classified scenario tags such as "daily sales scenario", "promotion activity scenario", "big promotion carnival scenario", "new product launch scenario", etc.; the key tag elements refer to the core words or phrases in the classified scenario tags that can accurately summarize and reflect the core characteristics, key driving factors, main business objects, or important business indicators of the scenario. They are the key information points further refined from the classified scenario tags and play an important role in deeply understanding the essence and influencing factors of business scenarios. For example, in the classified scenario tag of "promotion activity scenario", the key tag elements may include "discount strength", "categories of participating products", "promotion time range", "traffic source channels", etc. Optionally, the classification of the real-time business scenarios can be implemented through machine learning classification algorithms, such as decision tree algorithm, naive Bayes algorithm, etc.; the query of the key tag elements in the classified scenario tags can be implemented through element query tools, such as Firefox, Chrome, etc.

[0063] By marking the element core points corresponding to the key tag elements, the present invention can improve the accuracy of business understanding, enabling team members to quickly grasp the key points of the business. For example, accurately positioning the core audience and key selling points in marketing activities, which helps to optimize resource allocation and clarify the key investment directions.

[0064] Among them, the element core point refers to the essence condensed after coordinating the element semantics, information hierarchy, and dominant characteristics, accurately summarizing the key significance, core value, and pivotal role of the key tag element for the business scenario. For "live streaming with goods", the element core point is to utilize the popularity of the anchor and the advantages of live streaming interaction, focus on the unique selling points of the product during a specific period, and achieve the conversion of online product sales.

[0065] As an embodiment of the present invention, the marking of the element core points corresponding to the key tag elements includes: analyzing the element semantics corresponding to the key tag elements; dividing the information hierarchy corresponding to the key tag elements based on the element semantics; identifying the dominant features corresponding to the information in the information hierarchy; and marking the element core points corresponding to the key tag elements based on the dominant features.

[0066] Among them, the element semantics refers to the basic meaning carried by the key tag element, reflecting its essential meaning in the business scenario to which it belongs, and revealing the key information that the element wants to convey. It is like understanding the exact meaning of a word in a specific context. It is the cornerstone of subsequent analysis and determines the direction of the entire annotation process. For example, in "online marketing activities", "live streaming with goods" The element semantics of this key tag element; the information hierarchy refers to the hierarchical structure of various types of information derived from key tag elements according to the element semantics, according to dimensions such as the degree of information correlation, the depth of business impact, and the logical order. Taking "live streaming with goods" as an example, the first-level information can focus on the product itself, such as product features and advantages; the second level revolves around the anchor, involving the anchor's style and popularity; the third level is about the live streaming process, including the live streaming time period and duration; the dominant features refer to those prominent attributes in each information level that can influence business results, guide key business decisions, and play a key role in promoting or restricting business trends. At the product information level of "live streaming with goods", the unique selling point of the product is the dominant feature, which can directly attract the audience's interest and determine their willingness to buy. Compared with other general product descriptions, it is more influential and is the core focus of information at this level.

[0067] Furthermore, the analysis of the element semantics corresponding to the key label elements can be achieved through a word vector model, such as: Word2Vec and other models; the division of the information hierarchy corresponding to the key label elements can be achieved through a hierarchical clustering algorithm, such as: "Technical architecture upgrade" and "Data security management" can be first clustered into one category because they both involve technical levels, as a lower-level information hierarchy, and "Business process reengineering" is separately used as another higher level, thereby dividing the information hierarchy; the identification of the dominant features corresponding to the information in the information hierarchy can be achieved through a principal component analysis method, such as: it is found that equipment speed and temperature are the main factors affecting product quality, and the characteristics corresponding to these two factors that affect quality are the dominant features; the marking of the element core points corresponding to the key label elements can be achieved through a label propagation algorithm, such as: through the label propagation algorithm, starting from the identified dominant feature node, the importance label is propagated to the nodes related to it, and finally converged to the key label element node to form an element core point marking.

[0068] S4. Based on the element core points, determine the service channels corresponding to the real-time data group, analyze the channel quality corresponding to the service channels, calculate the data throughput corresponding to the service channels based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration.

[0069] Based on the element core points, the present invention determines the service channels corresponding to the real-time data group, which can accurately locate the data transmission path closely matching the core business requirements, reduce unnecessary resource consumption and data redundancy, improve the transmission efficiency, contribute to optimizing the business process, and enhance the business response speed by ensuring the transmission of key data in an efficient channel.

[0070] Among them, the service channel refers to a channel that relies on the selected transmission protocol and network architecture and is specifically used to transmit specific service data items to meet the key business requirements. In the video live broadcast service, the transmission path from the anchor end to the viewer end built based on the RTMP transmission protocol and the CDN (Content Delivery Network) architecture is the service channel.

[0071] As an embodiment of the present invention, the step of determining the service channels corresponding to the real-time data group based on the element core points includes: analyzing the key business requirements corresponding to the element core points; identifying the associated subsets in the real-time data group based on the key business requirements; evaluating the influence weight of the associated subsets on the business process; screening the service data items in the key business requirements based on the influence weight; querying the transmission protocol and network architecture adapted to the service data items; and determining the service channels corresponding to the real-time data group based on the transmission protocol and the network architecture.

[0072] Among them, the business critical requirements refer to the specific requirements extracted from the core points of elements that play a decisive and core role in achieving business goals, reflecting the key points that the business most needs to focus on and satisfy at the current stage. For example, in the scenario of the "618 Grand Promotion" in e-commerce, the core points of elements are "substantially increasing sales in the short term and optimizing the customer shopping experience", and its business critical requirements can be quickly processing a large number of orders, ensuring smooth payment, and accurately pushing preferential information; the associated subset refers to the data set in the real-time data group that is closely related to the determined business critical requirements. Taking the logistics and distribution business as an example, if the business critical requirement is to optimize the distribution route to reduce costs, then the set of data such as vehicle location, traffic conditions, cargo weight and volume, and distribution destination distribution in the real-time data group is the associated subset; the impact weight refers to the quantitative indicator that measures the size of the role played by each associated subset in promoting the business process and facilitating the realization of business critical requirements. Continuing with the above logistics and distribution business as an example, vehicle location data has a significant impact on the decision-making of immediately adjusting the distribution route and can have a relatively high weight; the data of cargo weight and volume has a relatively smaller direct impact on route adjustment, and the weight will be lower; the business data item refers to the data element selected from the associated subset based on the impact weight that has a key supporting effect on the business critical requirements. In the financial credit business, if the business critical requirement is to accurately evaluate the credit risk of customers, the associated subset includes data such as customer income, assets, liabilities, and consumption records. After evaluation, data items such as income stability and debt ratio; the transmission protocol refers to the agreement that stipulates a series of operation standards such as the rules, formats, order, and error correction for data transmission in the network. Commonly used ones such as the HTTP protocol are used for web data transmission. In different business scenarios, an appropriate transmission protocol should be selected according to the characteristics of the business data items; the network architecture refers to the layout mode of constructing the entire network system, covering elements such as the network topology structure (such as star, bus, ring, etc.), node distribution, and hierarchical division. Taking the cross-regional office of a large enterprise as an example, to meet the business critical requirements of multi-location collaborative work and massive data sharing.

[0073] Furthermore, the analysis of the key business requirements corresponding to the core points of the elements can be achieved through requirements analysis methods. For example, each sub-goal can be further refined to determine key business requirements such as "real-time understanding of employees' workload", "monitoring of equipment utilization rate", and "inventory warning and replenishment". The identification of the associated subsets in the real-time data group can be achieved through text mining methods, such as methods like cosine similarity. The evaluation of the impact weight of the associated subsets on the business process can be achieved through a weight calculation method based on information entropy. For example, calculate the information entropy of each factor in the associated subset. The smaller the information entropy, the greater the amount of information provided by the factor, and the higher the possible impact weight on the business process. The screening of business data items in the key business requirements can be achieved through the PCA method. For example, PCA transforms these data into new principal components, and based on the variance contribution rate of each principal component (similar to the impact weight), the original data items corresponding to the principal components with high variance contribution rates are selected, such as PM2.5 and sulfur dioxide concentration data, as the key business data items for evaluating air quality. The determination of the business channel corresponding to the real-time data group can be achieved through a network topology discovery tool. For example, if the business data item is video conference data, different paths from the conference room terminal to the server are tested, and the path with high bandwidth and low latency is selected as the business channel according to the performance results.

[0074] By analyzing the channel quality corresponding to the business channel, the present invention can ensure the smooth operation of the business, detect potential problems such as channel jamming, latency, or packet loss in advance, and optimize and adjust in a timely manner to ensure that key businesses such as video conferences and real-time financial transactions are not affected, and contribute to the precise allocation of resources. According to the quality of the channel, network bandwidth, server computing power and other resources are reasonably allocated.

[0075] Among them, the channel quality refers to the comprehensive manifestation of a series of key characteristics and performance indicators presented by the business channel during data transmission. It covers multiple aspects, including but not limited to the stability of signal strength to ensure that the signal does not fluctuate significantly and affect the accurate reception of data; the data transmission rate, which is directly related to the transmission efficiency of business data. For example, a high rate can enable the rapid transmission of large-capacity files; the level of packet loss rate, a lower packet loss rate indicates better data transmission integrity; the degree of latency, a lower latency is crucial for real-time services (such as video calls and online games) to ensure instant information interaction; and the degree of noise interference, a smaller noise interference can reduce the occurrence of data transmission errors. Optionally, the analysis of the channel quality corresponding to the business channel can be achieved through network performance testing tools, such as tools like Iperf and PingPlotter.

[0076] Furthermore, based on the channel quality, the present invention calculates the data throughput corresponding to the service channel, which helps to accurately plan the service carrying capacity, and can reasonably arrange task transmission accordingly, avoiding channel overload or idleness, and improving resource utilization efficiency.

[0077] Among them, the data throughput refers to the measure of the amount of data successfully transmitted through the service channel within a specific time period, which reflects the ability of the channel to effectively carry and transmit information per unit time, and is usually expressed in bits per second (bps), bytes per second (Bps) or other similar units. Its value depends on multiple factors, including the physical characteristics of the channel, such as bandwidth. The wider the bandwidth, the higher the data throughput that can be supported theoretically; the signal strength, noise level, packet loss rate in the channel quality, and the delay during the transmission process, etc. Optionally, the calculation of the data throughput corresponding to the service channel can be achieved through throughput calculation methods, such as Nyquist formula, Shannon theorem and other calculation methods.

[0078] Furthermore, based on the data throughput, the present invention optimizes the channel configuration of the real-time data group in the data transmission process, which can significantly improve the transmission efficiency, ensure fast and stable data transmission, can greatly accelerate the service processing speed, helps to reasonably allocate network resources, accurately allocate channels according to the throughput requirements of different data groups, avoid waste and imbalance of resources, and make the entire network system operate more efficiently.

[0079] Among them, the channel configuration refers to the specific channel usage plan tailored for the real-time data group, including selecting high-speed, low-latency, and high-stability channels for high-priority sensitive data groups, such as allocating dedicated low-latency fiber channels for real-time image data in online surgical remote assistance; arranging low-speed and low-cost channels for low-priority data groups, such as using ordinary Wi-Fi channels to transmit non-urgent notification files within an enterprise, and also involves multi-faceted planning such as channel switching strategies and load balancing.

[0080] As an embodiment of the present invention, the optimization of the channel configuration of the real-time data group in the data transmission process based on the data throughput includes: analyzing the transmission rate level corresponding to the data throughput; dividing the priority categories corresponding to the real-time data group based on the transmission rate level; evaluating the sensitivity of the data group to transmission delay under each priority according to the priority category; querying the available channel resources corresponding to the sensitivity; and optimizing the channel configuration of the real-time data group in the data transmission process based on the available channel resources.

[0081] Among them, the transmission rate level refers to different levels divided according to the numerical size of the data throughput, which intuitively reflects the speed of data flowing in the channel. For example, the data throughput can be divided into three levels: low speed (less than 10 Mbps), medium speed (10 Mbps - 100 Mbps), and high speed (greater than 100 Mbps); the priority category refers to the classification of real-time data groups based on the transmission rate level, combined with factors such as the criticality of the service and the real-time requirement. For example, in the financial transaction scenario, real-time transaction data has extremely high requirements for timeliness. If it corresponds to the high-speed transmission rate level, it will be classified as high priority; while some background statistical data has low transmission rate requirements and belongs to the low-speed level, and is correspondingly classified as low priority; the sensitivity refers to the tolerance of data groups under each priority to transmission delay. High-priority data groups, such as video data in video live streaming, can be noticed by the audience even with a slight delay and are extremely sensitive to transmission delay; low-priority data groups, such as regularly updated software logs, have little impact on the service even if the delay is several hours or even days, and the sensitivity is low; the available channel resources refer to all channels and their related attributes that can be allocated and used in the current network environment, including wired channels such as optical fibers and Ethernet, and wireless channels such as Wi-Fi, 4G / 5G, etc., their respective bandwidths, signal strengths, packet loss rates, as well as information such as the busyness and idle periods of the channels.

[0082] Further, analyzing the transmission rate level corresponding to the data throughput can be achieved through the threshold division method. For example, set the threshold for the low-speed level to less than 10 Mbps, the medium-speed level to 10 Mbps - 100 Mbps, and the high-speed level to greater than 100 Mbps; dividing the priority category corresponding to the real-time data group can be achieved through a category division model, such as decision tree classification, support vector machine and other models; evaluating the sensitivity of data groups under each priority to transmission delay can be achieved through the QoS method. For example, requiring the end-to-end delay to be less than 100 ms is regarded as a high sensitivity level; for low-priority file backup data groups, the delay requirement may be to complete the backup within several hours, and the delay sensitivity is low; querying the available channel resources corresponding to the sensitivity can be achieved through resource query tools, such as NRMS, SDN and other tools; optimizing the channel configuration of the real-time data group in the data transmission process can be achieved through a dynamic channel allocation algorithm, such as the greedy algorithm, etc.

[0083] By calculating the channel utilization rate corresponding to the channel configuration, the present invention can accurately understand the usage efficiency of network resources, provide a strong basis for business expansion. By understanding the utilization rate, it is possible to predict the channel carrying requirements of new services in advance, plan and optimize in advance, and ensure that the service quality does not degrade.

[0084] Among them, the channel utilization rate refers to the ratio of the actual data volume transmitted by the service channel to the theoretical maximum data transmission volume of the channel within a certain period of time, which is presented in the form of a percentage. This indicator intuitively reflects the degree to which channel resources are effectively utilized. For example, if a certain channel can theoretically transmit a maximum of 100 GB of data in one hour, and the actual data volume transmitted is 60 GB, then its channel utilization rate is 60%. The level of channel utilization rate is affected by various factors, including the bandwidth of the channel, the data volume transmitted, the transmission frequency, the error retransmission situation during data transmission, and the idle time of the channel, etc. Optionally, calculating the channel utilization rate corresponding to the channel configuration can be achieved through algorithms based on traffic statistics, such as: simple proportion algorithm, dynamic weighting algorithm, etc.

[0085] S5. Based on the channel utilization rate, generate an analysis permission key corresponding to the real-time data group, query the analysis rule corresponding to the analysis permission key, extract the data identifier in the analysis rule, and based on the data identifier, generate a data analysis report corresponding to the 5G message.

[0086] Based on the channel utilization rate, the present invention generates an analysis permission key corresponding to the real-time data group, which can ensure the safety and compliance of data transmission. The permission key is accurately allocated according to the channel utilization rate, and only the compliant real-time data group can obtain the transmission permission, effectively preventing illegal data from occupying channel resources.

[0087] Among them, the analysis permission key refers to a dedicated key that, after being verified by matching the compatibility value, is determined to be highly compatible with the real-time data group and can be authorized to start the analysis process of the real-time data group. When the matching compatibility value reaches the set threshold (such as 80 points, with a full score of 100 points), the initial key is officially confirmed as the analysis permission key.

[0088] As an embodiment of the present invention, generating an analysis permission key corresponding to the real-time data group based on the channel utilization rate includes: formulating a key generation rule corresponding to the real-time data group based on the channel utilization rate; querying the key character combination in the key generation rule; determining the initial key corresponding to the key character combination; verifying the matching compatibility value between the initial key and the real-time data group; and generating an analysis permission key corresponding to the real-time data group based on the matching compatibility value.

[0089] Among them, the key generation rule refers to a set of criteria formulated based on the status of channel utilization and combined with the characteristics of the real-time data group (such as the business importance, sensitivity, transmission frequency, etc. of the data). For example, if the channel utilization is in the high-load range (such as exceeding 80%), for critical data groups of real-time transactions, the key generation rule can tend to adopt a high-strength encryption algorithm, a complex key structure logic, require a longer key length and include numbers, uppercase and lowercase letters, and special characters to ensure the security of data transmission; the key character combination refers to the specific form of the character set used to form the key under the limitation of the key generation rule. For example, according to the above high-strength encryption rule, the key character combination can be selected from a character pool containing 26 uppercase and lowercase English letters, 10 digits, and 10 special characters such as "@#$%^&*"; the initial key refers to the preliminary password string generated according to the selected key character combination in a specific arrangement order. Taking the above combination as an example, directly determine "Ad3Bf#GhI9Jk" as the initial key of a certain real-time data group under the corresponding rule; the matching compatibility value refers to an index used to quantitatively evaluate the adaptation degree between the initial key and the real-time data group, which is calculated by comparing and analyzing the characteristics of the data group in multiple aspects such as format, data type, transmission protocol, etc. with the encryption characteristics of the initial key. For example, if the real-time data group is transmitted in XML format, the initial key encryption algorithm has specific adaptation optimizations for the XML structure.

[0090] Further, formulating the key generation rule corresponding to the real-time data group can be achieved through a policy-based method. For example, comprehensively evaluate the criticality of the business and the channel utilization, match corresponding policies for various real-time data groups, and thus determine the key generation rule; querying the key character combination in the key generation rule can be achieved through the rule engine matching query method. For example, if the rule is "10 digits including uppercase letters, digits, special characters and at least 2 special characters", the rule engine will perform a matching search in the predefined character combination set, and through an efficient pattern matching algorithm, quickly locate the key character combination that meets the requirements; determining the initial key corresponding to the key character combination can be achieved through a random generation algorithm. For example, ensure a certain degree of randomness by setting a seed value and generate an initial key like "45678912"; verifying the matching compatibility value between the initial key and the real-time data group can be achieved through a compatibility test framework. For example, build a compatibility test framework including modules such as data format parsing, transmission protocol adaptation, encryption and decryption performance testing, and use the framework to perform data verification to obtain the matching compatibility value; generating the analysis permission key corresponding to the real-time data group can be achieved through key generation tools. For example, tools such as Keygrip and OpenSSL.

[0091] The present invention can accurately locate required data by querying the analysis rules corresponding to the analysis license key and extracting the data identifier in the analysis rules, and can quickly find specific data associated with the license key in massive data, thereby improving data retrieval efficiency.

[0092] The analysis rule refers to a set of detailed data processing and analysis criteria pre-established for the real-time data group associated with the generated analysis license key, which covers the provisions of data extraction methods, screening conditions, conversion methods, and analysis processes. For example, in the financial data analysis scenario, for the transaction flow data group unlocked using a specific analysis license key, the analysis rule may stipulate that large transaction records within the past month are extracted in order of transaction time (screening conditions), the currency unit of the transaction amount is uniformly converted into RMB (conversion method), and the transaction frequency and amount distribution are calculated through a specific statistical model (analysis process); the data identifier refers to a label or code used to uniquely identify a specific data element or data subset in the analysis rule, which can accurately locate the data part that needs attention in a complex data set. For example, in an e-commerce sales data analysis case, according to the analysis rule, the data identifier can be "order number", "product category code", "customer region code", etc. Optionally, the query of the analysis rule corresponding to the analysis license key can be implemented by a rule query tool, such as RulerZ, FoFaX and other tools; the extraction of the data identifier in the analysis rule can be implemented by a syntax parsing tool, such as ANTLR and other tools.

[0093] Furthermore, the present invention generates a data analysis report corresponding to the 5G message based on the data identifier, which can accurately focus on key information. With the help of the data identifier, it can quickly lock the extremely valuable data fragments in the 5G message, such as user behavior, message popularity, etc., so that the report sticks to the core points.

[0094] Among them, the data analysis report refers to the written results formed after systematic organization and in-depth analysis of specific information screened and extracted by data identifiers for 5G message-related data. It covers many aspects, such as from the user dimension, including the user's reception frequency, reading time, interactive feedback (likes, comments, number of reposts), etc. of 5G messages, so as to understand user participation and preferences; from the content dimension, analyze the dissemination effect of different types of 5G messages (such as marketing, notification, and social), and which topics and formats are more popular; from the performance dimension, evaluate the success rate and delay of message sending, and reflect the quality of network transmission. Optionally, the generation of the data analysis report corresponding to the 5G message can be achieved through statistical analysis tools, such as: using the visualization function of the SPSS tool to generate bar charts and line charts to display the analysis results, and finally output a data analysis report containing detailed data, comparison charts and conclusion suggestions.

[0095] It can be seen that by receiving 5G messages and collecting diverse data information in the 5G messages, in the financial field, the present invention can capture market fluctuations in real time, providing accurate basis for risk control and investment decisions, and enhancing the timeliness and scientific nature of decisions; in industrial production, it can immediately obtain equipment operation parameters, optimize production processes, and enhance production efficiency and stability; in the construction of smart cities, it helps to quickly integrate multi-source data such as transportation and environment, achieve intelligent management, and improve the overall efficiency of urban operation. Further, by performing fluctuation analysis on the data items in the real-time data group, the present invention obtains a fluctuation trend sequence, which can clearly insight into the dynamic change law of the data, accurately capture the ups and downs of the data. Whether it is the rise and fall of market prices, the peak and trough of network traffic, or the fluctuation of equipment performance parameters, etc., can be accurately presented, making the change trend of the data clear at a glance. Based on the change rate, the present invention restores the real-time business scenario corresponding to the real-time data group, can accurately insight into business dynamics, and traces the changes of the business at key nodes through the change rate. For example, the change rate of sales data can present the immediate effect of promotional activities. Based on the element core points, the present invention determines the business channel corresponding to the real-time data group, can accurately locate the data transmission path closely matching the core business requirements, reduce unnecessary resource consumption and data redundancy, improve transmission efficiency, help optimize business processes, enhance the business response speed by ensuring the transmission of key data in an efficient channel. Based on the channel utilization rate, the present invention generates an analysis permission key corresponding to the real-time data group, can ensure the security and compliance of data transmission, accurately allocate permission keys according to the channel utilization rate, and only compliant real-time data groups can obtain transmission permissions, effectively preventing illegal data from occupying channel resources. Therefore, a real-time data analysis system, method, device and medium based on 5G message drive proposed in the embodiment of the present invention can improve the analysis efficiency of real-time data.

[0096] As Figure 3 shown, it is a functional module diagram of a real-time data analysis system based on 5G message drive of the present invention.

[0097] The real-time data analysis system 200 based on 5G message drive of the present invention can be installed in an electronic device. According to the functions achieved, the real-time data analysis system based on 5G message drive can include a data retrieval module 201, a change rate calculation module 202, a core point marking module 203, a channel utilization rate calculation module 204 and a report generation module 205. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0098] In this embodiment, the functions of each module / unit are as follows:

[0099] The data retrieval module 201 is configured to receive 5G messages, collect multi-source data information in the 5G messages, parse the data source identifiers corresponding to the multi-source data information, extract the data feature codes associated with the data source identifiers, and retrieve the real-time data groups corresponding to the data feature codes;

[0100] The change rate calculation module 202 is configured to perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify the key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rates corresponding to the key fluctuation nodes;

[0101] The core point annotation module 203 is configured to restore the real-time service scenario corresponding to the real-time data group based on the change rate, perform label classification on the real-time service scenario to obtain classification scenario labels, query the key label elements in the classification scenario labels, and annotate the element core points corresponding to the key label elements;

[0102] The channel utilization rate calculation module 204 is configured to determine the service channels corresponding to the real-time data group based on the element core points, analyze the channel quality corresponding to the service channels, calculate the data throughput corresponding to the service channels based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0103] The report generation module 205 is configured to generate an analysis permission key corresponding to the real-time data group based on the channel utilization rate, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0104] Optionally, when the data retrieval module 201 retrieves the real-time data group corresponding to the data feature code, it includes:

[0105] Identifying the key identification information corresponding to the data feature code;

[0106] Constructing a retrieval index framework corresponding to the key identification information;

[0107] Preliminarily screening the matchable data sets in the retrieval index framework;

[0108] Analyzing the strongly associated data blocks corresponding to the data subsets in the matchable data sets;

[0109] Retrieving the real-time data group corresponding to the data feature code based on the strongly associated data blocks.

[0110] Accordingly, when the change rate calculation module 202 performs fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, it includes:

[0111] Sort the data items in the real-time data group to obtain sorted data items;

[0112] Divide the sorted data items into their corresponding time windows;

[0113] Calculate the statistical feature values corresponding to the data in the time window;

[0114] Analyze the eigenvectors corresponding to the statistical feature values;

[0115] Extract the fluctuation amplitude index from the eigenvectors;

[0116] Based on the fluctuation amplitude index, perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence.

[0117] Optionally, when the core point annotation module 203 restores the real-time service scenario corresponding to the real-time data group based on the change rate, it includes:

[0118] Analyze the fluctuation amplitude range corresponding to the change rate;

[0119] Based on the fluctuation amplitude range, divide the service fluctuation level corresponding to the real-time data group;

[0120] Based on the service fluctuation level, match the service scenario type corresponding to the real-time data group;

[0121] Query the scenario feature parameters corresponding to the service scenario type;

[0122] Based on the scenario feature parameters, restore the real-time service scenario corresponding to the real-time data group.

[0123] Reliably, the core point annotation module 203 is specifically used to annotate the element core points corresponding to the key label elements, including:

[0124] Analyze the element semantics corresponding to the key label elements;

[0125] Based on the element semantics, divide the information levels corresponding to the key label elements;

[0126] Identify the dominant features corresponding to the information in the information levels;

[0127] Based on the dominant features, annotate the element core points corresponding to the key label elements.

[0128] Optionally, the channel utilization rate calculation module 204 is specifically configured to determine the service channel corresponding to the real-time data group based on the element core point, including:

[0129] Analyze the service key requirements corresponding to the element core point;

[0130] Based on the service key requirements, identify the associated subset in the real-time data group;

[0131] Evaluate the influence weight of the associated subset on the service process;

[0132] Based on the influence weight, screen the service data items in the service key requirements;

[0133] Query the transmission protocol and network architecture adapted to the service data items;

[0134] Based on the transmission protocol and the network architecture, determine the service channel corresponding to the real-time data group.

[0135] Furthermore, the channel utilization rate calculation module 204 is specifically configured to optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, including:

[0136] Analyze the transmission rate level corresponding to the data throughput;

[0137] Based on the transmission rate level, divide the priority categories corresponding to the real-time data group;

[0138] According to the priority categories, evaluate the sensitivity of the data groups at each priority to transmission delay;

[0139] Query the available channel resources corresponding to the sensitivity;

[0140] Based on the available channel resources, optimize the channel configuration of the real-time data group in the data transmission process.

[0141] As Figure 4 shown, it is a schematic structural diagram of an electronic device 1 for implementing real-time data analysis driven by 5G messages according to the present invention.

[0142] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a real-time data analysis program driven by 5G messages.

[0143] Among them, in some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device 1, connecting various components of the entire electronic device 1 through various interfaces and lines. By running or executing programs or modules stored in the memory 11 (such as executing a real-time data analysis program driven by 5G messages), and calling data stored in the memory 11, it performs various functions of the electronic device 1 and processes data.

[0144] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), magnetic memories, magnetic disks, optical discs, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as the mobile hard disk of the electronic device 1. In some other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Further, the memory 11 may also include both the internal storage unit and the external storage device of the electronic device 1. The memory 11 can not only be used to store application software installed on the electronic device 1 and various types of data, such as the code of a real-time data analysis program driven by 5G messages, but also be used to temporarily store data that has been output or will be output.

[0145] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is set to enable connection communication between the memory 11 and at least one processor 10, etc.

[0146] The communication interface 13 is used for communication between the above-mentioned electronic device 1 and other devices, including a network interface and a staff interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices 1. The staff interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the staff interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual staff interface.

[0147] Figure 4 Only the electronic device 1 with components is shown. Those skilled in the art can understand that Figure 4 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0148] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charging management, discharging management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include a variety of sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0149] It should be understood that the above embodiments are only for illustration purposes and are not limited by this structure within the scope of the patent invention.

[0150] A real-time data analysis program based on 5G message driving stored in the memory 11 of the electronic device 1 is a combination of multiple computer programs. When running in the processor 10, it can implement:

[0151] Receiving a 5G message, collecting multivariate data information in the 5G message, parsing the data source identifier corresponding to the multivariate data information, extracting the data feature code associated with the data source identifier, and retrieving the real-time data group corresponding to the data feature code;

[0152] Perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify the key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation nodes;

[0153] Based on the change rate, restore the real-time service scenario corresponding to the real-time data group, perform label classification on the real-time service scenario to obtain classification scenario labels, and query the key label elements in the classification scenario labels to mark the element core points corresponding to the key label elements;

[0154] Based on the element core points, determine the service channel corresponding to the real-time data group, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0155] Based on the channel utilization rate, generate an analysis permission key corresponding to the real-time data group, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0156] Specifically, for the specific implementation method of the above computer program by the processor 10, reference can be made to Figure 1 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0157] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0158] The present invention also provides a computer-readable storage medium, and the readable storage medium stores a computer program. When the computer program is executed by the processor of the electronic device 1, it can implement:

[0159] Receive a 5G message, collect the multi-source data information in the 5G message, parse the data source identifier corresponding to the multi-source data information, extract the data feature code associated with the data source identifier, and retrieve the real-time data group corresponding to the data feature code;

[0160] Perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify the key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation nodes;

[0161] Based on the change rate, restore the real-time service scenario corresponding to the real-time data group, perform label classification on the real-time service scenario to obtain classification scenario labels, and query the key label elements in the classification scenario labels to mark the element core points corresponding to the key label elements;

[0162] Based on the element core points, determine the service channel corresponding to the real-time data group, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration;

[0163] Based on the channel utilization rate, generate an analysis permission key corresponding to the real-time data group, query the analysis rules corresponding to the analysis permission key, extract the data identifiers in the analysis rules, and generate a data analysis report corresponding to the 5G message based on the data identifiers.

[0164] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0165] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, the functional modules in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0167] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0168] Therefore, in all aspects, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Accordingly, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced by the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0169] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0170] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The terms such as "second" are used to denote names and do not indicate any particular order.

[0171] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

[0172] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0173] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; if non-company software tools or components appear in the application embodiments, they are only used for example introduction and do not represent actual use; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A real-time data analysis method based on 5G message drive, characterized in that: The method comprises: Receive a 5G message, collect multivariate data information in the 5G message, parse a data source identifier corresponding to the multivariate data information, extract a data feature code associated with the data source identifier, and retrieve a real-time data group corresponding to the data feature code; Performing fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identifying key fluctuation nodes in the fluctuation trend sequence, and calculating the node change rate corresponding to the key fluctuation node; Based on the change rate, restore the real-time business scene corresponding to the real-time data group, classify the real-time business scene with labels to obtain classified scene labels, query key label elements in the classified scene labels, and mark the element core points corresponding to the key label elements; Based on the element core point, determine the service channel corresponding to the real-time data group, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization rate corresponding to the channel configuration; Based on the channel utilization, an analysis license key corresponding to the real-time data group is generated, an analysis rule corresponding to the analysis license key is queried, a data identifier in the analysis rule is extracted, and based on the data identifier, a data analysis report corresponding to the 5G message is generated.

2. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The retrieving the real-time data group corresponding to the data feature code includes: Identify key identification information corresponding to the data feature code; Constructing a search index framework corresponding to the key identification information; Preliminarily screening the matching data sets in the search index framework; Analyze the strongly associated data blocks corresponding to the data subset in the matchable data set; Based on the strongly associated data block, a real-time data group corresponding to the data feature code is retrieved.

3. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The performing fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence includes: Sorting the data items in the real-time data group to obtain sorted data items; Dividing the sorted data items into their corresponding time windows; Calculate the statistical characteristic value corresponding to the data in the time window; Analyzing the eigenvector corresponding to the statistical eigenvalue; Extracting a fluctuation range indicator from the feature vector; Based on the fluctuation amplitude index, a fluctuation analysis is performed on the data items in the real-time data group to obtain a fluctuation trend sequence.

4. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The restoring the real-time business scenario corresponding to the real-time data group based on the change rate includes: Analyze the fluctuation range corresponding to the change rate; Based on the fluctuation amplitude range, classify the business fluctuation level corresponding to the real-time data group; Based on the business fluctuation level, matching the business scenario type corresponding to the real-time data group; Query the scenario characteristic parameters corresponding to the business scenario type; Based on the scenario characteristic parameters, the real-time business scenario corresponding to the real-time data group is restored.

5. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The marking of the core point of the element corresponding to the key tag element includes: Analyze the element semantics corresponding to the key tag element; Based on the element semantics, divide the information level corresponding to the key tag element; identifying dominant features corresponding to information in the information hierarchy; Based on the dominant feature, the element core point corresponding to the key tag element is marked.

6. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The determining, based on the element core point, a service channel corresponding to the real-time data group includes: Analyze the key business requirements corresponding to the core points of the elements; Based on the business critical requirements, identifying a relevant subset of the real-time data group; Evaluate the influence weight of the associated subset on the business process; Based on the impact weights, filtering the business data items in the key business requirements; Query the transmission protocol and network architecture adapted by the business data item; Based on the transmission protocol and the network architecture, a service channel corresponding to the real-time data group is determined.

7. A real-time data analysis method based on 5G message drive as claimed in claim 1, characterized in that: The optimizing the channel configuration of the real-time data group in the data transmission process based on the data throughput includes: Analyzing the transmission rate level corresponding to the data throughput; Based on the transmission rate level, classify the priority categories corresponding to the real-time data groups; According to the priority category, evaluating the sensitivity of the data group at each priority level to transmission delay; Querying available channel resources corresponding to the sensitivity level; Based on the available channel resources, the channel configuration of the real-time data group in the data transmission process is optimized.

8. A real-time data analysis system based on 5G message drive, characterized in that: The system comprises: A data retrieval module is used to receive a 5G message, collect multivariate data information in the 5G message, parse a data source identifier corresponding to the multivariate data information, extract a data feature code associated with the data source identifier, and retrieve a real-time data group corresponding to the data feature code; A change rate calculation module is used to perform fluctuation analysis on the data items in the real-time data group to obtain a fluctuation trend sequence, identify key fluctuation nodes in the fluctuation trend sequence, and calculate the node change rate corresponding to the key fluctuation node; A core point marking module is used to restore the real-time business scene corresponding to the real-time data group based on the change rate, classify the real-time business scene with labels, obtain classified scene labels, query key label elements in the classified scene labels, and mark the element core points corresponding to the key label elements; A channel utilization calculation module, used to determine the service channel corresponding to the real-time data group based on the element core point, analyze the channel quality corresponding to the service channel, calculate the data throughput corresponding to the service channel based on the channel quality, optimize the channel configuration of the real-time data group in the data transmission process based on the data throughput, and calculate the channel utilization corresponding to the channel configuration; A report generation module is used to generate an analysis license key corresponding to the real-time data group based on the channel utilization, query the analysis rules corresponding to the analysis license key, extract the data identifier in the analysis rule, and generate a data analysis report corresponding to the 5G message based on the data identifier.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a real-time data analysis method based on 5G message driving as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements a real-time data analysis method based on 5G message drive as described in any one of claims 1 to 7.

Images