Settlement method and settlement device for Internet cross-regional traffic, and electronic equipment

Abstract

The invention provides an internet cross-regional traffic settlement method and device and electronic equipment, and the method comprises the steps: obtaining cross-regional traffic data of a plurality of time periods, encrypting the traffic data of the plurality of time periods to obtain corresponding Hash values, enabling the traffic data to at least comprise real-time traffic and a settlement rate, and enabling the real-time traffic and the settlement rate to be different from each other; the traffic types of the real-time traffic include IDC traffic, metropolitan area network traffic and CDN traffic; according to an intelligent contract of the Internet, the traffic data is written into a block chain of the Internet, and the traffic data of each time period comprises a hash value of the traffic data of the current time period and a hash value of the traffic data of the previous time period; and according to the traffic data of each time period of the uplink, determining traffic settlement fees of the plurality of time periods, and paying the traffic settlement fees to the target area. The problem of inaccurate Internet cross-regional traffic fee settlement in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology. Specifically, it relates to a method for settling cross-regional traffic on the Internet, a device for settling cross-regional traffic on the Internet, a computer-readable storage medium, and an electronic device. Background Art

[0002] With the continuous growth of Internet traffic demand, the Internet Data Center (IDC), as the core infrastructure of Internet services, bears a huge amount of network traffic and computing tasks. Especially in multi-regional Internet access services, the distribution, transmission, and settlement of traffic have become important links for coordination and profitability among operators. Traditional inter-regional settlement methods for IDCs mainly rely on fixed rates or simple traffic statistics models, and rely on manual rule setting and fixed rate models, making it difficult to fully adapt to the complex and ever-changing traffic exchange and revenue distribution needs among regions. In addition, with the expansion of business scale and the deepening of marketization, the accuracy of traffic statistics in each region has become increasingly prominent. Summary of the Invention

[0003] The main objective of the present application is to provide a method for settling cross-regional traffic on the Internet, a device for settling cross-regional traffic on the Internet, a computer-readable storage medium, and an electronic device, so as to at least solve the problem of inaccurate settlement of cross-regional Internet traffic fees in the prior art.

[0004] To achieve the above objective, according to one aspect of the present application, a method for settling cross-regional traffic on the Internet is provided, including: obtaining traffic data for multiple time periods across regions, and encrypting the traffic data for the multiple time periods to obtain corresponding hash values, where the traffic data at least includes real-time traffic and settlement rates, and the traffic types of the real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; writing the traffic data into the blockchain of the Internet according to the smart contract of the Internet, where each time period of the traffic data includes the hash value of the traffic data of this time period and the hash value of the traffic data of the previous time period; determining the traffic settlement fees for the multiple time periods according to the traffic data for each time period on the chain, and paying the traffic settlement fees to the target region.

[0005] Optionally, the obtaining traffic data for multiple time periods across regions includes: constructing a traffic prediction model, where the traffic prediction model is used to predict the traffic data for the (n + 1)-th time period according to the traffic data for n historical time periods within a historical time window; obtaining the settlement rate according to the traffic prediction model and a first formula, and the first formula is: wherein, R t+1 is the settlement rate; R0 is the base rate; α is the adjustment coefficient for controlling the rate adjustment range; μ and σ are respectively the mean and standard deviation of the historical traffic in the traffic data; is the predicted traffic value at time t+1 obtained according to the traffic prediction model.

[0006] Optionally, determining the traffic settlement cost for each of the time periods based on the traffic data of the multiple time periods on the chain and paying the settlement cost to the target area includes: based on the smart contract, determining the total traffic load value transmitted from a first area to the target area in a certain time period according to the traffic data and a second formula, where the second formula is: d i = w1·IDC + w2·Metro + w3·CDN + w4·Latency, where: d i is the total traffic load value for a certain time period; IDC, Metro, CDN, and Latency are respectively the IDC traffic, metro area network traffic, CDN traffic, and latency metric values; w1 to w4 are the weights for the IDC, Metro, CDN, and Latency dimensions respectively, set according to actual business requirements; based on the smart contract, determining the traffic settlement cost for the first area transmitting traffic to the target area in a certain time period according to the total traffic load value and a third formula, where the third formula is: C i = R i ·d i ·f i , where: C i is the traffic settlement cost; R i is the settlement rate at time t i , t i is a certain time period; d i is the traffic value at time t i ; f i is the calculation unit of the unit bandwidth traffic; paying the traffic settlement cost to the target area according to the smart contract and the preset settlement rules, where the preset settlement rules at least include a payment rule, and the payment rule is to automatically trigger the payment operation of the smart contract according to the traffic settlement cost.

[0007] Optionally, after obtaining the settlement rate according to the traffic prediction model and the first formula, the settlement method further includes: determining the mean square error of the settlement rate according to a fourth formula, the real-time traffic, and the predicted real-time traffic, where the predicted real-time traffic is the predicted value of the time period where the real-time traffic is located based on the traffic prediction model, and the fourth formula is: wherein, MSE is the mean square error; n is a natural number greater than 0; is the predicted real-time traffic; d i is the real-time traffic.

[0008] Optionally, after determining the traffic settlement cost for each of the time periods based on the traffic data of each of the time periods on the chain, the settlement method further includes: determining the individual settlement costs for the traffic data of various traffic types based on the traffic settlement costs for each of the time periods in multiple regions; judging whether the traffic data of various traffic types exceeds a first threshold according to the traffic data of various traffic types and an anomaly detection model, and judging whether the individual settlement costs exceed a second threshold according to the individual settlement costs and the anomaly detection model; in the case where it is judged that the traffic data of various traffic types exceeds the first threshold and / or the individual settlement costs exceed the second threshold, correcting the traffic data of various traffic types and / or the individual settlement costs.

[0009] Optionally, the settlement method further includes: confirming that the anomaly detection result is traffic anomaly in the case where it is judged that the traffic data of various traffic types exceeds the first threshold; confirming that the anomaly detection result is cost anomaly in the case where it is judged that the individual settlement costs exceed the second threshold.

[0010] Optionally, after confirming the anomaly detection result, the settlement method further includes: confirming the final settlement cost according to the anomaly detection result and the traffic data of various traffic types; confirming the adjusted settlement cost according to the final settlement cost and a fifth formula, and the fifth formula is: wherein, C adjusted is the adjusted settlement cost, ΔC is the settlement cost adjusted according to the anomaly detection result, A detected is the adjustment factor corresponding to the detected anomaly detection result, A total is the total adjustment factor of all possible anomaly detection results that may cause anomalies, and C represents the final settlement cost.

[0011] To achieve the above object, according to one aspect of the present application, there is provided a settlement device for cross-regional traffic on the Internet, which is applied to the above-mentioned settlement method for cross-regional traffic on the Internet. The settlement device includes: an acquisition module, configured to acquire traffic data for multiple time periods across regions, and encrypt the traffic data for the multiple time periods to obtain corresponding hash values. Among them, the traffic data at least includes real-time traffic and settlement rates. The traffic types of the real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; a writing module, configured to write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each piece of traffic data for each time period includes the hash value of the traffic data for this time period and the hash value of the traffic data for the previous time period; a determination module, configured to determine the traffic settlement fees for multiple time periods according to the traffic data for each time period that has been uploaded to the chain, and pay the traffic settlement fees to the target region.

[0012] According to another aspect of the present application, there is provided a computer-readable storage medium. The computer-readable storage medium includes a stored program. When the program runs, it controls the device where the computer-readable storage medium is located to execute the above-mentioned settlement method for cross-regional traffic on the Internet.

[0013] According to still another aspect of the present application, there is provided an electronic device, including: one or more processors, a memory, and one or more programs. Among them, the one or more programs are stored in the memory and are configured to be executed by the one or more processors. The one or more programs include those for executing the above-mentioned settlement method for cross-regional traffic on the Internet.

[0014] Applying the technical solution of the present application, first, traffic data for multiple time periods across regions is obtained. The obtained traffic data includes real-time traffic and settlement rates. The types of real-time traffic include multiple types, that is, the obtained traffic information can reflect the situation of multiple types of traffic in multiple time periods across regions, and the settlement rates can show the settlement rates of multiple types of traffic in multiple time periods across regions. Then, according to the smart contract, the obtained traffic data is written into the blockchain. The above various traffic data are encrypted to generate their corresponding hash values and are recorded depending on the chain structure of the blockchain. Each block of the blockchain contains the hash value of the current time period block and the hash value of the previous time period block. This chain structure ensures that historical data cannot be modified, the data has non-tamperability, and the validity of the hash value and the continuity of the entire blockchain are guaranteed. Finally, based on the traffic data on the chain, the traffic settlement fees for multiple time periods are determined, and the settlement fees are paid to the target region. The above settlement method calculates the total traffic settlement fees by obtaining multiple types of real-time traffic and the settlement rates corresponding to multiple types of real-time traffic. In this way, according to the changes of different types of real-time traffic in different regions at different time periods, the settlement fees corresponding to different types of real-time traffic can be flexibly adjusted, improving the settlement accuracy of different types of real-time traffic. Moreover, the traffic data is encrypted to generate hash values and recorded depending on the chain structure of the blockchain, ensuring the non-tamperability of the data, being able to more accurately reflect the actual traffic data, and thus enabling more accurate settlement. It solves the problem of inaccurate settlement of Internet cross-regional traffic fees in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0016] Figure 1 It shows a hardware structure block diagram of a mobile terminal for implementing a settlement method for Internet cross-regional traffic according to an embodiment of this application;

[0017] Figure 2 It shows a schematic flowchart of a settlement method for Internet cross-regional traffic according to an embodiment of this application;

[0018] Figure 3 It shows a schematic structural diagram of a settlement device for Internet cross-regional traffic according to an embodiment of this application.

[0019] Among them, the above accompanying drawings include the following reference numerals:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input / output device. Specific embodiments

[0021] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0022] In order to enable those skilled in the art of the present technology to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so as to implement the embodiments of the present application described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background art, with the continuous growth of Internet traffic demand, the Internet Data Center (IDC), as the core infrastructure of Internet services, bears a huge amount of network traffic and computing tasks. Especially in multi-region Internet access services, the distribution, transmission and settlement of traffic have become important links for coordination and profit among operators. The traditional IDC inter-region settlement method mainly relies on fixed rates or simple traffic statistics models, and depends on manual rule setting and fixed rate models, which are difficult to fully adapt to the complex and changeable traffic exchange and revenue distribution requirements among different regions. In addition, with the expansion of business scale and the deepening of marketization, the accuracy problem of traffic statistics in each region has become increasingly prominent.

[0025] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0026] Traffic Prediction Model: A traffic prediction model is a technology that, based on historical traffic data, uses mathematical algorithms or machine learning methods (such as time series models, Autoregressive Integrated Average model (ARIMA), or Long Short-Term Memory model) to predict the future trend of network traffic changes. By analyzing data patterns, the model can dynamically adjust resource allocation strategies, improving the prediction accuracy of the system and the network utilization efficiency.

[0027] Blockchain Technology: Blockchain technology is a distributed ledger technology that records data in a decentralized manner. Its features include data transparency, immutability, and a multi-party consensus mechanism. In this application, the blockchain is used to store settlement data, ensuring the authenticity and transparency of the data and reducing data disputes.

[0028] Smart Contract: A smart contract is an automated program running on the blockchain that is used to execute transactions or events according to predefined rules. In this application, the smart contract is responsible for the automated processing of settlement and payment, such as verifying settlement data, triggering payment requests, and generating payment vouchers, improving the settlement efficiency and accuracy.

[0029] Multi-Dimensional Traffic Analysis: Multi-dimensional traffic analysis refers to a method of analyzing and calculating by comprehensively considering different types of network data (such as Internet Data Center (IDC) traffic, metropolitan area network traffic, Content Delivery Network (CDN) traffic, and network latency, etc.) during the settlement process. By integrating various traffic characteristics, this technology can more accurately reflect the actual consumption of network resources and optimize the settlement results.

[0030] Anomaly Detection Algorithm: An anomaly detection algorithm is a technology based on statistical or machine learning methods used to identify abnormal behaviors or data deviations from massive data. For example, methods based on clustering analysis or rule matching can quickly detect anomalies in settlement data. In this application, this algorithm is used to detect settlement differences in real time and trigger the account adjustment process.

[0031] Dynamic Rate Adjustment: Dynamic rate adjustment refers to a mechanism that adjusts settlement rates using an automated algorithm according to the fluctuations of real-time network traffic. In this application, through the traffic prediction model, the rates are adjusted based on the peaks and valleys of the traffic to ensure that the settlement fees are more in line with the actual network load conditions.

[0032] Big Data Analysis Platform: The big data analysis platform is a platform that utilizes large-scale data storage and processing technologies (such as distributed system infrastructure (Hadoop), open-source distributed computing system (Apache Spark), etc.) to support real-time analysis, mining, and modeling of massive data. In this application, the platform is used for multi-dimensional analysis, anomaly detection, and trend prediction of settlement data to enhance the intelligence level of the settlement system.

[0033] Adjustment Optimization: Adjustment optimization is a processing method based on automation technology and rule algorithms for adjusting incorrect or abnormal settlement data. In this application, the adjustment process is automatically triggered through big data analysis and anomaly detection, and adjustment records are generated to reduce manual intervention and improve the accuracy and credibility of settlement data.

[0034] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application.

[0035] The method embodiments provided in the embodiments of this application can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is the hardware structure block diagram of the mobile terminal for a method of settling Internet cross-regional traffic in the embodiments of this application. As Figure 1 shown, the mobile terminal may include one or more ( Figure 1 only one is shown in Figure 1 a processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Among them, the above mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only illustrative and does not limit the structure of the above mobile terminal. For example, the mobile terminal may further include more or fewer components than Figure 1 shown in

[0036] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the settlement method of cross-region traffic on the Internet in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implements the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the mobile terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] In this embodiment, a settlement method for cross-region traffic on the Internet running on a mobile terminal, a computer terminal, or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0038] Figure 2 It is a flowchart of the settlement method for cross-region traffic on the Internet according to the embodiments of the present application. As Figure 2 shown, the method includes the following steps:

[0039] Step S1, obtain traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain a corresponding hash value, where the traffic data includes at least real-time traffic and settlement rates, and the traffic types of the real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic;

[0040] Specifically, traffic data from IDCs, metropolitan area networks, and CDNs in various regions are collected in real time, including but not limited to IDC traffic, metropolitan area network traffic, CDN traffic, and network latency, etc. This data covers multiple time periods, such as every 5 minutes, every hour, or every day. To ensure the security and integrity of the data, the system uses advanced encryption algorithms to encrypt the traffic data for each time period, generating a hash value corresponding to the data for that time period. The hash value, as the digital fingerprint of the data, can ensure that even minor changes in the data can be quickly identified. Through encryption and hash generation, this embodiment can significantly improve the security of data transmission and storage, reducing the risk of data tampering or leakage.

[0041] Step S2, according to the smart contract of the Internet, write the traffic data into the blockchain of the Internet. The traffic data for each time period includes the hash value of the traffic data for this time period and the hash value of the traffic data for the previous time period.

[0042] Specifically, the smart contract automatically executes the settlement and payment logic based on preset rules (such as settlement cycle, settlement standard, and payment process). Through blockchain technology, the encrypted traffic data and its hash value are stored on the blockchain. Each newly generated block contains the hash value of the traffic data for the current time period and the hash value of the traffic data for the previous time period. This chained structure ensures the immutability of the data because any modification of historical data will cause the hash value of subsequent blocks to become invalid, thus breaking the continuity of the entire chain. Through the combination of the smart contract and the blockchain, this embodiment realizes the transparent management of settlement data, and all settlement activities are traceable, improving the credibility and fairness of settlement.

[0043] Specifically, after collecting the traffic data, use encryption technology to encrypt this information, and then record the traffic data into the blockchain through the smart contract of the blockchain. The format of the record of the encrypted traffic data can be expressed as:

[0044] B = {(t1, d1, f1, R1), (t2, d2, f2, R2), …, (t i , d i , f i , R i )},

[0045] where: t i represents the data collection time; d i represents the traffic data at time t i ; f i represents the calculation unit of bandwidth or traffic (the unit can be MB or Gb); R i represents the settlement rate.

[0046] Step S3: Determine the traffic settlement fees for multiple time periods based on the traffic data of each time period uploaded to the blockchain, and pay the traffic settlement fees to the target area.

[0047] Specifically, the smart contract reads and processes all the traffic data uploaded to the blockchain, and automatically calculates the settlement fees for each time period based on the traffic data. When calculating, various types of traffic data are comprehensively considered, such as IDC traffic, metropolitan area network traffic, CDN traffic, and network latency, etc., to ensure the comprehensiveness and accuracy of the settlement process. Once the settlement fees are determined, the smart contract will automatically trigger the payment process, transferring the fees from the account of the traffic transmission area to the account of the receiving traffic area (target area) to achieve cross-regional settlement. Through the intelligent analysis of the data uploaded to the blockchain and automated settlement, this embodiment greatly improves the accuracy and efficiency of settlement, reduces the management cost, and ensures the real-time and fairness of settlement.

[0048] Through this embodiment, first, the traffic data for multiple time periods across regions is obtained, where the obtained traffic data includes real-time traffic and settlement rates. The types of real-time traffic include multiple types, that is, the obtained traffic information can reflect the conditions of various types of traffic for multiple time periods across regions, and the settlement rates can show the settlement rates for various types of traffic for multiple time periods across regions. Then, according to the smart contract, the obtained traffic data is written into the blockchain. The above various traffic data are encrypted to generate their corresponding hash values and are recorded depending on the chain structure of the blockchain. Each block in the blockchain contains the hash value of the current time period block and the hash value of the previous time period block. This chain structure ensures that historical data cannot be modified, the data has non-repudiation, and the validity of the hash value and the continuity of the entire blockchain are guaranteed. Finally, based on the traffic data uploaded to the blockchain, the traffic settlement fees for multiple time periods are determined, and the settlement fees are paid to the target area. The above settlement method calculates the total traffic settlement fees by obtaining various types of real-time traffic and the settlement rates corresponding to various types of real-time traffic. In this way, according to the changes of different types of real-time traffic in different time periods in different regions, the settlement fees corresponding to different types of real-time traffic can be flexibly adjusted, improving the settlement accuracy for different types of real-time traffic. Moreover, the traffic data is encrypted to generate hash values and recorded depending on the chain structure of the blockchain, ensuring the non-repudiation of the data, being able to more accurately reflect the actual traffic data, and thus enabling more accurate settlement. This solves the problem of inaccurate settlement of Internet cross-regional traffic fees in the prior art.

[0049] Specifically, the traffic data collected in step S1 may also include historical traffic, and the collected historical traffic and real-time traffic are formatted into a time series form:

[0050] D = {(t1, d1), (t2, d2), …, (t i , d i )},

[0051] where: t i represents the i-th time point; d i represents the traffic value at time t i (the unit can be Mbps); D is a time series.

[0052] To improve the accuracy of the subsequent traffic prediction model, the above historical traffic and real-time traffic data can be preprocessed. The above preprocessing includes denoising and normalization, where:

[0053] Denoising: Remove abnormal points and smooth the data using median filtering or other methods.

[0054] Normalization: Standardize the traffic value to [0, 1]. The formula is:

[0055]

[0056] where, d i ′ is the standardized traffic time series; d i represents the traffic value at time t i ; max(D) is the maximum value of the time series; min(D) is the minimum value of the time series.

[0057] Specifically, the IDC traffic data records the IDC traffic usage in different regions and time periods. The metropolitan area network traffic data includes the metropolitan area network traffic usage across regions. The CDN traffic data is the traffic generated in the content delivery network.

[0058] In some alternative embodiments, obtaining the traffic data for multiple time periods across regions in step S1 includes:

[0059] Step S11: Construct a traffic prediction model. The traffic prediction model is used to predict the traffic data for the (n + 1)-th time period based on the traffic data for n historical time periods within a historical time window;

[0060] Specifically, the traffic prediction model can be a time series model, an LSTM model, and an ARIMA model. The above models can effectively process time series data and capture the long-term dependence of traffic. Assume n = 5, that is, a prediction model is established based on the traffic data for the past 5 historical time periods to predict the traffic for the 6th time period.

[0061] where, the general expression of the prediction model is:

[0062]

[0063] Wherein: is the predicted flow at the next moment; f is the mapping function of the selected prediction model; n is the length of the historical time window used.

[0064] Step S12: Obtain the settlement rate according to the flow prediction model and the first formula. The first formula is:

[0065]

[0066] Wherein, R t+1 is the settlement rate; R0 is the base rate; α is the adjustment coefficient used to control the rate adjustment range; μ and σ are respectively the mean and standard deviation of the historical flow in the flow data; is the predicted flow value at time t + 1 obtained according to the flow prediction model.

[0067] Specifically, in practical applications, the dynamic rate R t+1 is applied to the inter - region settlement. According to the real - time flow d t+1 calculate the cost:

[0068] C t+1 = R t+1 ·d t+1 ,

[0069] Wherein: C t+1 is the settlement cost at time point t + 1; d t+1 is the real - time flow value at time point t + 1.

[0070] The above - mentioned dynamic settlement rate adjustment method based on the flow prediction model. The key to the dynamic adjustment of the rate lies in closely binding the settlement rate with the flow pattern. The flow pattern includes the peak flow pattern and the off - peak flow pattern, so that the peak flow and the off - peak flow correspond to high rates and low rates respectively, which incentives all parties to reasonably allocate flow resources. By combining the dynamic rate with the real - time flow, it can more accurately reflect the actual flow data, and the combination of the dynamic rate and the real - time flow can achieve more accurate calculation of the flow settlement cost. Because it can flexibly adjust the settlement cost according to the real - time flow change and the network conditions (peak flow pattern and off - peak flow pattern) in different regions, avoiding the limitations that the fixed rate cannot cope with flow fluctuations or network differences. By combining the flow prediction model and dynamically adjusting the settlement rate, the flow settlement cost is more matched with the real - time flow consumption, ensuring that all parties bear the cost according to the real flow data during settlement, thus improving the accuracy and fairness of the settlement.

[0071] In some alternative implementation manners, in step S3, according to the flow data of multiple time periods uploaded to the chain, determine the flow settlement cost for each time period and pay the settlement cost to the target region, including:

[0072] Step S31: Based on the smart contract, determine the total traffic load value transmitted from the first region to the target region during a certain period according to the traffic data and the second formula. The second formula is:

[0073] d i = w1·IDC + w2·Metro + w3·CDN + w4·Latency,

[0074] where: d i is the total traffic load value during a certain period; IDC, Metro, CDN, and Latency are the IDC traffic, metropolitan area network traffic, CDN traffic, and latency metric values respectively; w1 to w4 are the weights of the IDC, Metro, CDN, and Latency dimensions respectively, which are set according to actual business requirements;

[0075] Specifically, first generate a smart contract according to the preset settlement rules. The preset settlement rules include but are not limited to the settlement entity, settlement period, settlement standard, and payment process. Among them, the settlement entity is the settlement relationship between the regional branches and the headquarters. The settlement period is the period for paying the traffic settlement fees. For example, it is settled on a natural monthly basis. The settlement standard is based on the collected data and the pricing standards for different regions (such as IDC traffic, metropolitan area network traffic, and CDN traffic) (for example, the IDC traffic settlement rate is 1 yuan / M, and the metropolitan area network traffic is 3 yuan / M). The payment process is that the smart contract will automatically trigger a payment operation according to the calculated traffic settlement fees, and the payment amount will be transferred to the account of the corresponding regional company. Through weight allocation, the contributions of different traffic types are quantified, avoiding the neglect of a certain traffic type in the settlement and ensuring the fairness and reasonableness of the settlement results.

[0076] Step S32: Based on the smart contract, determine the traffic settlement fees for the traffic transmitted from the first region to the target region during a certain period according to the total traffic load value and the third formula. The third formula is:

[0077] C i = R i ·d i ·f i ,

[0078] where: C i is the traffic settlement fee; R i is the settlement rate at time t i , t i is a certain period; d i is the traffic value at time t i ; f i is the calculation unit of the unit bandwidth traffic.

[0079] Specifically, to improve the automation and transparency of traffic data settlement, smart contracts execute settlement rules on the blockchain. The smart contract automatically calculates the settlement fees for each time period according to the preset settlement rules and the third formula, and stores the calculation results on the blockchain to ensure the publicity, transparency, and immutability of the settlement results. The introduction of multi-dimensional traffic (multiple traffic types and weights corresponding to various traffic types) analysis and the automatic calculation of smart contracts significantly improve the comprehensiveness and accuracy of inter-regional settlement.

[0080] Step S33: According to the smart contract and the preset settlement rules, pay the traffic settlement fees to the target region. The preset settlement rules at least include a payment rule, and the payment rule is to automatically trigger the payment operation of the smart contract according to the traffic settlement fees.

[0081] Specifically, once the smart contract completes the calculation of the traffic settlement fees, it will automatically trigger the payment operation. According to the payment information in the smart contract, transfer the funds to the designated account of the target region, and each region can check the payment records at any time. After the payment is completed, the smart contract generates a settlement and payment feedback report and automatically sends it to each regional branch and the regional head office to ensure the transparency and traceability of all settlement activities. All the above operations will be recorded on the blockchain for easy auditing and account checking. Through the above smart contract process, the calculation and payment of traffic settlement fees are both automated. The processing of all traffic settlement fees depends on the rules of the smart contract, which not only ensures the accuracy of traffic data but also greatly improves the settlement efficiency and security.

[0082] In some embodiments, to ensure the accuracy of traffic data and prevent malicious tampering, the blockchain adopts a consensus mechanism (Byzantine Fault Tolerance, BFT), such as Proof of Work (PoW), Proof of Stake (PoS), etc., to verify the validity of transactions. Each participant (such as network service providers and settlement platforms in each region) needs to participate in verifying the accuracy of the data and reach a consensus. Through the verification of the consensus mechanism, the accuracy and legality of all traffic data are ensured, providing a trust basis for the automated execution of smart contracts. The smart contract can automatically calculate the traffic settlement fees and execute payment instructions based on this verified data without manual intervention, achieving efficient automation of settlement and payment. The combination of the consensus mechanism and the smart contract not only improves the transparency and efficiency of settlement but also enhances the security and anti-fraud capabilities of the system.

[0083] In some embodiments, once all the traffic settlement fees are automatically calculated and verified through a blockchain smart contract, the settlement results will be stored on the blockchain in a publicly transparent manner, and any participant can query the relevant settlement data and calculation results at any time. The query operation can be carried out through a blockchain browser, and anyone can trace and view the relevant settlement data and fees through the unique transaction hash value.

[0084] The query formula can be expressed as:

[0085] Q(t i ) = {H(C1), H(C2), …, H(C i )},

[0086] where: Q(t i ) is the query of the settlement result corresponding to time t i ; H(C i ) is the hash value corresponding to the traffic settlement fee C i .

[0087] The transparent display of the settlement data ensures fairness among all parties in the settlement and provides effective evidence for related disputes.

[0088] In some embodiments, each block in the blockchain contains a timestamp and a hash value, which ensures that the data will not be tampered with during storage and provides a perfect data traceability mechanism. During the settlement process, any party can trace back to the data at a specific time point according to the records in the blockchain, thereby verifying the accuracy and reliability of the data. Through data deposition and traceability, the historical process and results of the settlement data can be traced back to the source, enhancing the trustworthiness of the entire settlement process.

[0089] The data traceability formula is:

[0090] T(t i ) = H(C i ),

[0091] where: T(t i ) is the data deposition of time t i ; H(C i ) is the hash value corresponding to the traffic settlement fee C i .

[0092] Through the method of transparent management of settlement data based on blockchain technology, the problems of data transparency, traceability, and trust in existing inter-regional traffic settlement are solved. This innovative solution not only improves the security, accuracy, and transparency of settlement data, but also optimizes the settlement process, reduces the risk of human intervention, and thus enhances the settlement efficiency and the trust of all parties.

[0093] In some alternative embodiments, after obtaining the settlement rate according to the traffic prediction model and the first formula in step S12, the settlement method further includes:

[0094] Step S13: Determine the mean square error of the settlement rate according to the fourth formula, the real-time traffic, and the predicted real-time traffic, where the predicted real-time traffic is the predicted value of the real-time traffic in the time period where the real-time traffic is located based on the traffic prediction model, and the fourth formula is:

[0095]

[0096] where MSE is the mean square error; n is a natural number greater than 0; is the predicted real-time traffic; d i is the real-time traffic.

[0097] Specifically, in order to evaluate the accuracy of the adjusted settlement rate, the mean square error is calculated through the above fourth formula. For example, let n = 10, that is, collect the real-time traffic and the predicted real-time traffic of 10 historical time periods, and calculate the mean square error between these two sequences. Check whether the amplitude of the rate adjustment meets the actual business requirements to avoid over-adjustment or under-adjustment. Through the dynamic settlement rate adjustment method based on the traffic prediction model, the flexibility and fairness of inter-regional settlement can be significantly improved.

[0098] In some alternative embodiments, after determining the traffic settlement cost for each time period according to the on-chain traffic data in step S3, the settlement method further includes:

[0099] Step S4: Determine the separate settlement costs for the traffic data of various traffic types according to the traffic settlement costs for each time period of multiple regions.

[0100] Specifically, according to the usage of different types of traffic such as IDC traffic, metropolitan area network traffic, CDN traffic, and latency metrics, algorithms (such as linear regression, decision tree, or neural network) can be used to estimate the actual consumption of each type of traffic, and the respective settlement costs can be calculated accordingly. For example, the traffic weighted average algorithm can be used to calculate the respective costs according to the proportion of different traffic types in the total traffic. It is also possible to classify different types of traffic data through traffic tags or traffic identification algorithms, and the intelligent system can classify different types of traffic data, and then calculate the settlement costs for each type of traffic according to the settlement formula in the smart contract. The present application does not specifically limit the solution for determining the separate settlement costs for the traffic data of various traffic types.

[0101] Specifically, an anomaly detection model is constructed based on big data analysis technology. Through machine learning algorithms, this model deeply analyzes traffic data by combining historical traffic data and current real-time traffic data to automatically identify abnormal patterns. Commonly used anomaly detection models include clustering algorithms, time series analysis models, and rule engines. Among them, the clustering algorithm distinguishes normal settlement patterns from abnormal patterns by clustering similar data. The time series analysis model analyzes the time series of settlement data to identify abnormal points inconsistent with historical data. The rule engine detects whether there are abnormal settlement situations in real time based on set thresholds or business rules (such as sudden increase in traffic, abnormal delay, etc.).

[0102] Step S5: According to the traffic data of various traffic types and the anomaly detection model, determine whether the traffic data of various traffic types exceeds the first threshold, and according to the individual settlement fees and the anomaly detection model, determine whether the individual settlement fees exceed the second threshold.

[0103] Step S6: In the case where it is determined that the traffic data of various traffic types exceeds the first threshold and / or the individual settlement fees exceed the second threshold, correct the traffic data of various traffic types and / or the individual settlement fees.

[0104] Specifically, after determining the traffic settlement fees, further perform anomaly judgment based on the anomaly detection model. Assume that the first threshold is a traffic deviation exceeding 20%, and the second threshold is a settlement fee deviation exceeding 15%. By real-time monitoring and analyzing traffic data and individual settlement fees, once it is detected that the traffic data in a certain area exceeds the threshold, such as the IDC traffic surges to 120 Mbps (exceeding 20% of the original 100 Mbps), or the individual settlement fee is 16% higher than expected, the account adjustment process will be automatically triggered to correct the abnormal data. This correction can be to re-obtain and calculate the traffic data and individual settlement fees, or to use a correction model for correction.

[0105] In some optional embodiments, the settlement method further includes: when it is determined that the traffic data of various traffic types exceeds the first threshold, confirm that the anomaly detection result is traffic anomaly; when it is determined that the individual settlement fee exceeds the second threshold, confirm that the anomaly detection result is fee anomaly.

[0106] Specifically, according to the results of the anomaly detection model, clarify the anomaly type for subsequent targeted processing. For example, if it is detected that the IDC traffic surges from 100 Mbps to 120 Mbps, that is, it exceeds the first threshold, it is determined as a traffic anomaly, and automatic measures are taken, such as recalculating the traffic load and adjusting the settlement rate, etc. If the individual settlement fee increases from the expected 100 yuan to 116 yuan, exceeding the second threshold, it is determined as a fee anomaly, triggering the account adjustment process to recalculate the fee to ensure fair settlement.

[0107] In some embodiments, it is also possible to obtain the service quality situation across regions of the Internet. The service quality data includes network latency, bandwidth usage, etc. These may affect the individual settlement of fees or the settlement of traffic data. If there are anomalies, it is determined that the service quality is abnormal.

[0108] In some embodiments, for each of the above anomalies, classification processing is performed according to the type and severity of the anomaly. The severity is divided into minor anomalies and major anomalies. For example, a minor anomaly is a small fluctuation in traffic, and the system will automatically make adjustments and record them without manual intervention. For example, a major anomaly is that the individual settlement fee difference is too large or the traffic usage does not meet expectations, and the system will automatically initiate an account adjustment process and notify relevant personnel for review. When abnormal settlement data is detected, the account adjustment optimization process will be automatically triggered. This process includes the following steps:

[0109] Automatically correct errors: Based on historical traffic data and real-time traffic data, automatically correct the individual settlement fee or traffic data. For example, if there is an error in the traffic metering in a certain region, adjust it according to the normal traffic pattern to correct the abnormal data.

[0110] Intelligent account adjustment suggestions: Generate account adjustment suggestions according to the cause of the anomaly. The suggestions include recalculating the individual settlement fee, adjusting the traffic data, modifying the service quality parameters, etc. Manual reviewers can confirm or further adjust according to the suggestions.

[0111] Account adjustment feedback and execution: After manual review or confirmation by the smart contract, the account adjustment will be automatically executed. For the part involving fund transfer or data update, the system will ensure the timely effectiveness of the account adjustment result.

[0112] In some alternative embodiments, after confirming the anomaly detection result, the settlement method further includes:

[0113] Confirm the final settlement fee according to the anomaly detection result and the traffic data of various traffic types;

[0114] Specifically, in order to ensure the accurate detection and correction of settlement anomalies, the following optimization formula can be used:

[0115] C = f(IDC, Metro, CDN, Latency, Anomaly),

[0116] where: C represents the final traffic settlement fee; IDC is the IDC traffic data; Metro is the metropolitan area network traffic data; CDN is the CDN traffic data; Latency is the network latency data; Anomaly is the anomaly detection result, which is adjusted according to the detected anomaly type (such as traffic anomaly, fee anomaly, service quality anomaly, etc.); f is the mapping function of the selected anomaly detection model.

[0117] According to the final settlement fee and the fifth formula, confirm the adjusted settlement fee. The fifth formula is:

[0118]

[0119] Among them, C adjusted is the adjusted settlement fee, ΔC is the settlement fee adjusted according to the anomaly detection result, A detected is the adjustment factor corresponding to the detected anomaly detection result, A total is the total adjustment factor of all possible anomaly detection results that may generate anomalies, and C represents the final settlement fee. The adjustment of the settlement fee based on the anomaly detection result can effectively handle unexpected situations during the settlement process, such as sudden traffic changes or calculation errors, ensuring the accuracy and fairness of the settlement. The automatic account adjustment mechanism reduces the need for manual intervention, avoids delays and errors that may be caused by manual adjustment, and improves the automation level and efficiency of the settlement process.

[0120] In some embodiments, the traffic prediction model can be a prediction model based on deep learning, which can accurately predict the future traffic and settlement fees of IDC Internet access services. Using deep neural networks or convolutional neural networks, combined with multi-dimensional data such as historical traffic data, traffic settlement fees, and market environment, perform traffic trend prediction and settlement fee optimization. Use a large-scale historical traffic data set to train and optimize the above model, so as to improve the accuracy of traffic data prediction and traffic settlement fee estimation. Among them, Deep Neural Networks (DNN): Use the DNN model to process high-dimensional data and learn the complex relationship between traffic and settlement fees. Convolutional Neural Networks (CNN): Extract local features of data through convolutional layers to enhance the prediction ability of the model. Using deep learning technology can handle complex non-linear relationships and improve the accuracy of settlement prediction.

[0121] In some embodiments, by deploying computing resources at the edge nodes of the Internet, the processing task of traffic settlement fees is migrated from the traditional data center to the network edge close to the data source. This solution can process data in real time, reduce network latency, and improve settlement efficiency. Through intelligent edge computing nodes, the settlement parameters can be adjusted in real time, and the optimized results can be uploaded to the core server, which can reduce the pressure on the central server and make the settlement process more efficient. The key technologies used include the edge computing platform, data transmission and computing optimization, and real-time traffic monitoring. Edge computing platform: Edge computing nodes are arranged at the IDC and network access layers to process real-time settlement data. Data transmission and computing optimization: Through a distributed computing architecture, settlement data is processed in real time and automatically synchronized to the central server. Real-time traffic monitoring: Utilizing the computing power of edge nodes, network traffic is monitored in real time, and the settlement rate and settlement formula are automatically adjusted.

[0122] In some embodiments, an intelligent settlement dispute resolution mechanism is constructed based on artificial intelligence technologies (such as natural language processing and sentiment analysis). When a dispute arises between the settlement parties regarding the settlement result, the AI model can analyze the dispute content and automatically mediate according to the preset settlement rules. Through intelligent analysis and decision-making, human errors and emotional biases can be reduced, the efficiency of dispute resolution can be improved, and the fairness of dispute resolution can be enhanced. The key technologies used include natural language processing, sentiment analysis algorithms, and automatic decision-making models. Among them, natural language processing is to extract and process key information by analyzing the text or voice information in the settlement dispute. Sentiment analysis algorithms are to analyze the feedback of both parties in the dispute, identify emotions and positions, and thus make reasonable suggestions during the dispute process. The automatic decision-making model is to combine historical case data and smart contracts to automatically determine the solution and execute the corresponding operations.

[0123] The embodiment of the present application also provides a settlement device for Internet cross-regional traffic, which is applied to the settlement method of Internet cross-regional traffic. The settlement device includes: an acquisition module, configured to acquire traffic data for multiple time periods across regions and encrypt the traffic data for multiple time periods to obtain the corresponding hash value. Among them, the traffic data includes at least real-time traffic and settlement rate, and the traffic types of real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; a writing module, configured to write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each time period's traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period; a determination module, configured to determine the traffic settlement fees for multiple time periods according to the traffic data for each time period on the chain and pay the settlement fees to the target region.

[0124] The following introduces the settlement device for Internet cross-regional traffic provided by the embodiment of the present application.

[0125] Figure 3 It is a schematic diagram of a settlement device for cross - regional traffic on the Internet according to an embodiment of the present application. As Figure 3 shown, the device includes: an acquisition module 10, configured to acquire traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain a corresponding hash value. Among them, the traffic data at least includes real - time traffic and settlement rates. The traffic types of real - time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; a writing module 20, configured to write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each time - period traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period; a determination module 30, configured to determine the traffic settlement fees for multiple time periods according to the traffic data for each time period on the chain, and pay the settlement fees to the target region.

[0126] Through this embodiment, the acquisition module can be used to acquire traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain a corresponding hash value. Among them, the traffic data at least includes real - time traffic and settlement rates. The traffic types of real - time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; the writing module is configured to write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each time - period traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period; the determination module is configured to determine the traffic settlement fees for multiple time periods according to the traffic data for each time period on the chain, and pay the traffic settlement fees to the target region.

[0127] An embodiment of the present application provides a computer - readable storage medium. The above - mentioned computer - readable storage medium includes a stored program. Among them, when the above - mentioned program runs, it controls the device where the computer - readable storage medium is located to execute the above - mentioned settlement method for cross - regional traffic on the Internet.

[0128] Specifically, the settlement method for cross - regional traffic on the Internet includes:

[0129] Step S1: Acquire traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain a corresponding hash value. Among them, the traffic data at least includes real - time traffic and settlement rates. The traffic types of real - time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic;

[0130] Step S2: Write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each time - period traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period;

[0131] Step S3: Determine the traffic settlement fees for multiple time periods based on the traffic data for each time period on the chain, and pay the traffic settlement fees to the target area.

[0132] An embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, it implements at least the following steps:

[0133] Step S1: Obtain traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain the corresponding hash values. Among them, the traffic data at least includes real-time traffic and settlement rates. The traffic types of real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic;

[0134] Step S2: According to the smart contract of the Internet, write the traffic data into the blockchain of the Internet. Each time period's traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period;

[0135] Step S3: Determine the traffic settlement fees for multiple time periods based on the traffic data for each time period on the chain, and pay the traffic settlement fees to the target area.

[0136] The electronic device in this article can be a server, PC, PAD, mobile phone, etc.

[0137] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program initialized with at least the following method steps:

[0138] Step S1: Obtain traffic data for multiple time periods across regions, and encrypt the traffic data for multiple time periods to obtain the corresponding hash values. Among them, the traffic data at least includes real-time traffic and settlement rates. The traffic types of real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic;

[0139] Step S2: According to the smart contract of the Internet, write the traffic data into the blockchain of the Internet. Each time period's traffic data includes the hash value of the traffic data in this time period and the hash value of the traffic data in the previous time period;

[0140] Step S3: Determine the traffic settlement fees for multiple time periods based on the traffic data for each time period on the chain, and pay the traffic settlement fees to the target area.

[0141] Obviously, those skilled in the art should understand that the various modules or steps of the present application described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. They can be implemented by program code executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps among them can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0142] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0144] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for realizing in the processFigure 1 one or more processes and / or blocks Figure 1 steps of functions specified in one or more blocks.

[0146] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0147] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0148] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0149] By using the above-mentioned settlement method for cross-regional traffic on the Internet, the settlement device for cross-regional traffic on the Internet, the computer-readable storage medium, and the electronic device of the present application, the following beneficial effects can be achieved:

[0150] 1) The settlement method of the present application calculates the total traffic settlement cost by obtaining various types of real-time traffic and the settlement rates corresponding to various types of real-time traffic. In this way, the settlement cost corresponding to different types of real-time traffic can be flexibly adjusted according to the changes of different types of real-time traffic in different regions at different time periods, improving the settlement accuracy of different types of real-time traffic. Moreover, the traffic data is encrypted to generate a hash value and recorded depending on the chain structure of the blockchain, ensuring the immutability of the data and being able to more accurately reflect the actual traffic data, and thus enabling more accurate settlement. This solves the problem of inaccurate settlement of cross-regional traffic fees in the prior art.

[0151] 2) The settlement method of this application combines a traffic prediction model and dynamically adjusts the settlement rate based on machine learning and time series analysis techniques. This method can flexibly adapt to traffic fluctuations according to historical traffic data and trend prediction results, thereby optimizing the rationality and accuracy of settlement. Compared with the traditional fixed rate method, this method can effectively cope with sudden traffic and dynamic changes in network load between regions, reducing settlement deviations caused by abnormal traffic fluctuations.

[0152] 3) The settlement method of this application is based on the data transparency management of blockchain technology. All settlement data, traffic data, and financial data are stored through blockchain technology to ensure the immutability and traceability of the data. Smart contracts are automatically executed during the settlement process to ensure that all settlement parties follow unified standards, greatly enhancing the credibility of the data and the transparency of settlement.

[0153] 4) The smart contract-driven automated settlement and payment process in the settlement method of this application: Through smart contract technology, the present invention realizes the full automation of the settlement process. After the settlement report is generated, the smart contract will automatically verify the data correctness and trigger the payment process according to the contract terms. This method greatly improves the settlement efficiency, reduces the manual review link, and reduces the risk of human operation errors.

[0154] 5) The settlement method of this application incorporates an analysis method that integrates multi-dimensional data such as IDC traffic, metropolitan area network traffic, CDN traffic, network latency, and packet loss rate. Through an adaptive weighting mechanism and a feature fusion strategy, the correlation between different data sources is improved, enhancing the accuracy of traffic prediction. In addition, the anomaly detection model based on deep learning can identify abnormal traffic patterns and correct abnormal data, thereby optimizing the fairness of cross-regional settlement and ensuring that the traffic settlement fees are more in line with the actual network load situation.

[0155] 6) The settlement method of this application utilizes a big data analysis platform to monitor abnormal patterns of settlement fees and traffic data in real time. It can automatically detect settlement deviations and correct them through an intelligent account adjustment mechanism, reducing the need for manual intervention and improving the accuracy and reliability of settlement.

[0156] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, commodity or device comprising the element.

[0157] The above are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A settlement method for cross-regional Internet traffic, characterized in that, Including: Obtain traffic data for multiple time periods across regions, and encrypt the traffic data for the multiple time periods to obtain corresponding hash values. Among them, the traffic data at least includes real-time traffic and settlement rates. The traffic types of the real-time traffic include multiple types, and the traffic types include IDC traffic, metropolitan area network traffic, and CDN traffic; According to the smart contract of the Internet, write the traffic data into the blockchain of the Internet. Each piece of traffic data for each time period includes the hash value of the traffic data for this time period and the hash value of the traffic data for the previous time period; According to the traffic data for each time period on the chain, determine the traffic settlement fees for the multiple time periods, and pay the traffic settlement fees to the target region.

2. The settlement method according to claim 1, wherein The obtaining of traffic data for multiple time periods across regions includes: Construct a traffic prediction model, which is used to predict the traffic data for the (n + 1)-th time period according to the traffic data for n historical time periods within a historical time window; According to the traffic prediction model and the first formula, obtain the settlement rate. The first formula is: Among them, R t+1 is the settlement rate; R0 is the base rate; α is the adjustment coefficient used to control the rate adjustment range; μ and σ are the mean and standard deviation of the historical traffic in the traffic data respectively; is the predicted traffic value at time t + 1 obtained according to the traffic prediction model.

3. The settlement method according to claim 1, characterized in that The determining of the traffic settlement fee for each time period according to the traffic data for multiple time periods on the chain and paying the settlement fee to the target region includes: Based on the smart contract, according to the traffic data and the second formula, determine the total traffic load value transmitted from the first region to the target region during a certain time period. The second formula is: d i = w1·IDC + w2·Metro + w3·CDN + w4·Latency, Where: d i is the total traffic load value for a certain time period; IDC, Metro, CDN, and Latency are the IDC traffic, metropolitan area network traffic, CDN traffic, and latency metric values respectively; w1 to w4 are the weights of the IDC, Metro, CDN, and Latency dimensions, which are set according to actual business requirements; Based on the smart contract, according to the total traffic load value and the third formula, determine the traffic settlement fee for the first region to transmit traffic to the target region during a certain time period. The third formula is: C i = R i · d i · f i , Where: C i is the traffic settlement fee; R i is the settlement rate for time t i , t i is a certain time period; d i is the traffic value at time t i ; f i is the calculation unit of the traffic per unit bandwidth. According to the smart contract and the preset settlement rules, pay the traffic settlement fee to the target region. The preset settlement rules at least include a payment rule, and the payment rule is to automatically trigger the payment operation of the smart contract according to the traffic settlement fee.

4. The settlement method according to claim 2, wherein, After obtaining the settlement rate according to the traffic prediction model and the first formula, the settlement method further includes: According to the fourth formula, the real-time traffic, and the predicted real-time traffic, determine the mean square error of the settlement rate. Among them, the predicted real-time traffic is the predicted value of the real-time traffic for the time period where the real-time traffic is located based on the traffic prediction model. The fourth formula is: Among them, MSE is the mean square error; n is a natural number greater than 0; is the predicted real-time flow rate; d i is the real-time flow rate.

5. The settlement method according to claim 1, wherein After determining the traffic settlement fee for each time period according to the traffic data for each time period on the chain, the settlement method further includes: According to the traffic settlement fees for each time period of multiple regions, determine the separate settlement fees for the traffic data of various traffic types; According to the traffic data of various traffic types and the anomaly detection model, determine whether the traffic data of various traffic types exceeds the first threshold, and according to the separate settlement fees and the anomaly detection model, determine whether the separate settlement fees exceed the second threshold; In the case where the traffic data of various said traffic types exceeds the first threshold and / or the separately settled fees exceed the second threshold, correct the traffic data of various said traffic types and / or the separately settled fees.

6. The settlement method according to claim 5, characterized in that, The settlement method further includes: In the case where it is determined that the traffic data of various said traffic types exceeds the first threshold, confirm that the anomaly detection result is traffic anomaly; In the case where it is determined that the separately settled fees exceed the second threshold, confirm that the anomaly detection result is fee anomaly.

7. The settlement method according to claim 6, characterized in that After confirming the anomaly detection result, the settlement method further includes: According to the anomaly detection result and the traffic data of various said traffic types, confirm the final settlement fees; according to the final settlement fees and the fifth formula, confirm the adjusted settlement fees, and the fifth formula is: Among them, C adjusted is the adjusted settlement fee, ΔC is the settlement fee adjusted according to the abnormal detection result, A detected is the adjustment factor corresponding to the detected abnormal detection result, A total is the total adjustment factor of all abnormal detection results that may cause abnormalities, and C represents the final settlement fee.

8. A settlement device for cross-regional traffic on the Internet, characterized in that, Applied to the settlement method of the Internet cross-regional traffic according to any one of claims 1 to 7, the settlement device includes: An acquisition module, configured to acquire traffic data of multiple time periods across regions, and encrypt the traffic data of the multiple time periods to obtain a corresponding hash value. Among them, the traffic data at least includes real-time traffic and settlement rates. The traffic types of the real-time traffic include multiple types, and the traffic types include IDC traffic, metro area network traffic, and CDN traffic; A writing module, configured to write the traffic data into the blockchain of the Internet according to the smart contract of the Internet. Each piece of the traffic data of each time period includes the hash value of the traffic data of this time period and the hash value of the traffic data of the previous time period; A determination module, configured to determine the traffic settlement fees of multiple time periods according to the traffic data of each time period on the chain, and pay the traffic settlement fees to the target area.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the settlement method of the Internet cross-regional traffic according to any one of claims 1 to 7.

10. An electronic device, characterized in that, Including: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors. The one or more programs include those for executing the settlement method of the Internet cross-regional traffic according to any one of claims 1 to 7.

Images