Internet of Things card online billing authorization method, device, platform and storage medium

By introducing a pre-authorization mechanism and authorization calculation model in the online billing system, small traffic requests are authorized in advance, which solves the problem of the system's risk of crash under high load and improves system stability and response capabilities.

CN118659941BActive Publication Date: 2024-11-22E SURFING IOT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411143216.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-22
Estimated Expiration
2044-08-20

AI Technical Summary

Technical Problem

The online billing system lacks load capacity when handling a large number of concurrent requests, and poses a risk of system crash, especially when the billing tasks of the Internet of Things card are massive, it is difficult to effectively manage and control.

Method used

By introducing a pre-authorization mechanism in the online billing system, a pre-trained authorization calculation model is used to authorize small traffic requests in advance, and the authorization threshold is dynamically adjusted to adapt to system load and network traffic, reducing real-time computing pressure.

Benefits of technology

It effectively reduces the load and risk of system crash of the online billing system, improves the stability and responsiveness of the system, and ensures the timeliness and accuracy of services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118659941B_ABST
    Figure CN118659941B_ABST
Patent Text Reader

Abstract

The present application relates to an online billing authorization method, device, platform and storage medium for an Internet of Things card, wherein the method includes: when a flow request is received, the flow request is parsed to obtain the current flow remaining amount and the request amount; if the request amount is within the preset flow request range, the flow request is treated as a small flow request; an initial proportional coefficient is generated based on the current flow remaining amount and the request amount through a pre-trained authorization amount calculation model; the current system load and the current network traffic are obtained, and the initial proportional coefficient is dynamically adjusted to obtain a target proportional coefficient; based on the target proportional coefficient, the current flow remaining amount and the request amount, it is determined whether the pre-authorization conditions are met, and if so, the small flow request is authorized in advance. The present application can authorize small flow requests in advance, reduce the processing pressure of real-time calculation pre-occupancy of a large number of concurrent requests, and reduce the load of the online billing system and the risk of system crash.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to an Internet of Things card online billing authorization method, device, platform and storage medium. Background Art

[0002] Online Charging System (OCS) is a system used for real-time billing, usually used in fields such as telecommunications and network operators. The online billing system can calculate, manage and control users' fees in real time while users are using services to ensure the timeliness and accuracy of services.

[0003] The online billing system needs to carry the billing tasks of a large number of IoT cards. However, the current online billing system model has very strict requirements on system resources and performance. Especially when processing a large number of concurrent requests, the online billing system needs a very high load capacity, and there is a risk of system crash. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an Internet of Things card online billing authorization method, device, platform and storage medium to extract authorization for small traffic requests, reduce the processing pressure of real-time calculation pre-occupancy of a large number of concurrent requests, and reduce the load of the online billing system and the risk of system crash.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an Internet of Things card online billing authorization method, including:

[0006] When receiving a flow request, the flow request is parsed to obtain the current flow remaining amount and the requested amount;

[0007] If the requested amount is within the preset flow request range, the flow request is regarded as a small flow request;

[0008] Calculate the proportional coefficient between the remaining predicted amount and the requested predicted amount based on the current remaining traffic amount and the requested amount through a pre-trained authorization amount calculation model to obtain an initial proportional coefficient;

[0009] Acquire the current system load and the current network traffic, and dynamically adjust the initial proportionality coefficient based on the current system load and the current network traffic to obtain a target proportionality coefficient;

[0010] Based on the target proportional coefficient, the current remaining flow amount and the requested amount, it is determined whether the pre-authorization condition is met. If so, the small flow request is authorized in advance.

[0011] In order to solve the above technical problems, the embodiment of the present application provides an Internet of Things card online billing authorization device, including:

[0012] A request receiving unit, configured to parse the flow request upon receiving the flow request, and obtain the current flow remaining amount and the requested amount;

[0013] a request confirmation unit, configured to treat the flow request as a small flow request if the requested amount is within a preset flow request range;

[0014] A proportional coefficient generating unit, configured to calculate a proportional coefficient between a remaining predicted amount and a requested predicted amount based on the current remaining traffic amount and the requested amount through a pre-trained authorized amount calculation model, to obtain an initial proportional coefficient;

[0015] A proportionality coefficient adjustment unit, used to obtain a current system load and a current network flow, and dynamically adjust the initial proportionality coefficient based on the current system load and the current network flow to obtain a target proportionality coefficient;

[0016] The authorization extraction unit is used to determine whether the pre-authorization conditions are met based on the target proportional coefficient, the current remaining flow and the request amount, and if so, to pre-authorize the small flow request.

[0017] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide an Internet of Things platform, including one or more processors; a memory for storing one or more programs, so that one or more processors can implement any one of the above-mentioned Internet of Things card online billing authorization methods.

[0018] In order to solve the above technical problems, a technical solution adopted by the present invention is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements any one of the above-mentioned Internet of Things card online billing authorization methods.

[0019] The embodiment of the present invention provides an online billing authorization method, device, platform and storage medium for an Internet of Things card. The method includes: when a flow request is received, the flow request is parsed to obtain the current flow remaining amount and the request amount; if the request amount is within the preset flow request range, the flow request is used as a small flow request; the proportional coefficient between the remaining predicted amount and the request predicted amount is calculated based on the current flow remaining amount and the request amount by a pre-trained authorization amount calculation model to obtain an initial proportional coefficient; the current system load and the current network traffic are obtained, and the initial proportional coefficient is dynamically adjusted based on the current system load and the current network traffic to obtain a target proportional coefficient; based on the target proportional coefficient, the current flow remaining amount and the request amount, it is determined whether the pre-authorization condition is met, and if it is met, the small flow request is authorized in advance. When a small flow request is received, the embodiment of the present invention can pre-authorize the small flow request before the actual billing request arrives, which reduces the processing pressure occupied by the real-time calculation of a large number of concurrent requests, reduces the load of the online billing system and the risk of system crash, and is conducive to improving the stability of the online billing system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flowchart of the implementation process of the online billing authorization method for the Internet of Things card provided in the embodiment of the present application;

[0022] Figure 2 This is a flowchart of an implementation of an Internet of Things card online billing authorization method process provided by another embodiment of the present application;

[0023] Figure 3 is a specific implementation flow chart of step S3 provided in an embodiment of the present application;

[0024] Figure 4 This is a flowchart of an implementation of an Internet of Things card online billing authorization method process provided by another embodiment of the present application;

[0025] Figure 5 is a specific implementation flow chart of step S304 provided in an embodiment of the present application;

[0026] Figure 6 is a specific implementation flow chart of step S4 provided in an embodiment of the present application;

[0027] Figure 7is a specific implementation flow chart of step S5 provided in an embodiment of the present application;

[0028] Figure 8 This is a schematic diagram of an Internet of Things card online billing authorization device provided in an embodiment of the present application;

[0029] Fig. 9 It is a schematic diagram of the Internet of Things platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0033] The present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0034] It should be noted that the Internet of Things card online billing authorization method provided in the embodiment of the present application is generally executed by the Internet of Things platform, and accordingly, the Internet of Things card online billing authorization device is generally configured in the Internet of Things platform.

[0035] See also Figure 1 , Figure 1 A specific implementation of the online charging authorization method for an Internet of Things card is shown.

[0036] It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 The process sequence shown is limited to the following steps:

[0037] S1: When a traffic request is received, the traffic request is parsed to obtain the current remaining traffic amount and the requested amount.

[0038] The embodiment of the present application provides an online billing authorization method for an Internet of Things card, which authorizes some small traffic in advance before the user actually requests billing. By introducing a pre-authorization mechanism in the online billing system, pre-authorized small traffic requests can be served when the traffic is small, without waiting for the actual billing request calculation to be completed before authorization, thereby reducing the pressure and load on the online billing system. At the same time, the embodiment of the present application determines in advance that some requests are calculated directly after pre-authorization, which can avoid the pressure caused by a large number of requests pouring into the system at the same time, reduces the risk of system crashes, and ensures the stable operation of the system.

[0039] Specifically, when a traffic request is received, it is necessary to first determine whether the traffic request is a small traffic request, so the traffic request needs to be parsed to obtain the request amount and the current remaining traffic amount of the user corresponding to the traffic request.

[0040] S2: If the requested amount is within a preset flow request range, the flow request is regarded as a small flow request.

[0041] Specifically, since whether a request is a small flow is manually determined, the embodiment of the present application pre-sets a flow request range. When the request amount is within the flow request range, it means that the flow request corresponding to the request amount is a small flow request. Therefore, in the embodiment of the present application, it is determined whether the parsed request amount is within the preset flow request range. If it is, the flow request is determined as a small flow request; if not, the flow request is not determined as a small flow request, and the flow request is processed in real time according to the previous online billing system, and no authorization is required to be extracted.

[0042] It should be noted that the preset flow request range is set according to actual conditions and is not limited here. In a specific embodiment, a flow request with a request amount within (0,5M) is identified as a small flow request.

[0043] See also Figure 2 , Figure 2 A specific implementation after step S2 is shown, which is described in detail as follows:

[0044] S21: Determine whether the current remaining flow exceeds a preset flow value, and obtain a determination result;

[0045] S22: If the judgment result is that the current remaining flow exceeds the preset flow value, the small flow request is authorized in advance.

[0046] Specifically, when judging that the traffic request is a small traffic request, it is possible to judge whether the current remaining traffic of the user's IoT card is sufficient, that is, to judge whether the current remaining traffic exceeds the preset traffic value. If the current remaining traffic exceeds the preset traffic value, the embodiment of the present application can extract the authorization of the traffic request before the actual charging request, so as to process this part of the small traffic request in advance, thereby reducing the pressure of real-time processing of the subsequent online billing system, reducing the system load, and enhancing the stability of the system. If the current remaining traffic does not exceed the preset traffic value, it is necessary to further judge whether other authorizations can be performed based on the current system load and network traffic, that is, it is necessary to execute step S3 and subsequent steps.

[0047] It should be noted that the preset flow rate value is set according to the actual situation and is not limited here. In a specific embodiment, the preset flow rate value is 100M flow rate.

[0048] S3: Calculate the proportional coefficient between the remaining predicted amount and the requested predicted amount based on the current traffic remaining amount and the requested amount through a pre-trained authorization amount calculation model to obtain an initial proportional coefficient.

[0049] Specifically, an authorization quantity calculation model is trained through the random forest algorithm model. The authorization quantity calculation model predicts the user's request quantity and remaining consumption in the next time period based on the current traffic remaining amount and request amount, and obtains the remaining predicted amount and the request predicted amount. Then, the proportional coefficient between the remaining predicted amount and the request predicted amount is calculated to obtain the initial proportional coefficient.

[0050] See also Figure 3 , Figure 3 A specific implementation of step S3 is shown, which is described in detail as follows:

[0051] S31: Obtain the request frequency and timestamp corresponding to the low-flow request;

[0052] S32: constructing a feature vector with the current remaining traffic amount, the request amount, the request frequency and the timestamp to obtain a target feature vector;

[0053] S33: predicting the consumption of the requested amount and the remaining amount in the next time period based on the target feature vector by using the pre-trained authorization amount calculation model to obtain the requested predicted amount and the remaining predicted amount;

[0054] S34: Calculate the proportional coefficient between the remaining prediction amount and the requested prediction amount to generate the initial proportional coefficient.

[0055] Specifically, obtain the request frequency and timestamp of the IoT card corresponding to the small traffic request, and then construct a feature vector with the current traffic remaining amount R, request amount Q, request frequency F and timestamp T to obtain the target feature vector . The target feature vector The input is input into the pre-trained authorization quantity calculation model, and each decision tree of the pre-trained authorization quantity calculation model predicts the consumption of the request quantity and the remaining quantity in the next time period for the input target feature vector, and obtains the prediction result of each decision tree. The average value or voting result of the prediction results of all decision trees is used as the request prediction quantity and the remaining prediction quantity, and finally the proportional coefficient between the remaining prediction quantity and the request prediction quantity is calculated to generate the initial proportional coefficient.

[0056] See also Figure 4 , Figure 4 A specific implementation method before step S3 is shown, which is described in detail as follows:

[0057] S301: Collecting historical traffic data of each user, wherein the historical traffic data includes data usage, connection frequency, and request mode;

[0058] S302: constructing a feature vector based on the historical traffic data to obtain an initial feature vector, and performing preprocessing and data division on the initial feature vector to obtain a training data set and a test data set;

[0059] S303: Using the random forest algorithm model as an authorization quantity calculation model, and initializing model parameters of the authorization quantity calculation model to obtain an initialized authorization quantity calculation model;

[0060] S304: Training the initialized authorization quantity calculation model based on the training data set to obtain the pre-trained authorization quantity calculation model.

[0061] Specifically, historical traffic data of each user is collected, wherein the historical traffic data includes data usage, connection frequency, and request mode. Then, in order to ensure the integrity and accuracy of the data, missing values ​​and outliers are processed; then, the remaining traffic, request volume, request frequency, and timestamp in the historical traffic data are used to construct an initial feature vector, and the initial feature vector is standardized or normalized to eliminate the influence of different dimensions. The initial feature vector is divided into a training data set and a test data set using cross-validation or retention method. The random forest algorithm model is used as the authorization quantity calculation model, and the model parameters of the authorization quantity calculation model are initialized to obtain the initialized authorization quantity calculation model. Finally, the initialized authorization quantity calculation model is trained based on the training data set to obtain the pre-trained authorization quantity calculation model.

[0062] The model parameters include the number of trees, maximum depth, and sample splitting tree, etc. Among them, random forest is an integrated learning method that constructs multiple decision trees for prediction and combines the results of multiple decision trees to obtain the final prediction result.

[0063] See also Figure 5 , Figure 5 A specific implementation of step S304 is shown, which is described in detail as follows:

[0064] S3041: randomly extracting a plurality of sample subsets from the training data set to construct each decision tree of the initialized authorization quantity calculation model;

[0065] S3042: When constructing each node of each decision tree, randomly select the initial feature vector from the training data set as a candidate feature;

[0066] S3043: Selecting a target feature from the candidate features according to a preset selection method to split nodes of the decision tree to construct a target decision tree;

[0067] S3044: When the number of node samples is less than a preset threshold, multiple target decision trees are integrated to obtain the pre-trained authorization quantity calculation model.

[0068] Specifically, bootstrap sampling is used to randomly extract multiple sample subsets from the training data set to construct each decision tree. Using the bootstrap method for data extraction means that the training data for each tree is different, which helps to increase the diversity of the model. Then, when constructing each node of each decision tree, a portion of features are randomly selected from all features as candidate features. According to a preset selection method (such as information gain method and Gini impurity method), the target feature is selected from the candidate features to split the nodes of the decision tree to construct a target decision tree. The above steps are recursively executed until the number of node samples is less than the preset threshold, then multiple target decision trees are integrated to obtain the pre-trained authorization quantity calculation model.

[0069] It should be noted that the preset threshold is set according to actual conditions and is not limited here.

[0070] S4: Acquire the current system load and the current network traffic, and dynamically adjust the initial proportional coefficient based on the current system load and the current network traffic to obtain a target proportional coefficient.

[0071] Specifically, according to the system load and network traffic, the pre-authorization threshold and strategy are dynamically adjusted to ensure the flexibility and efficiency of the system. When the system load is high, the pre-authorization threshold can be lowered to make full use of system resources; when the system load is low, the pre-authorization threshold can be increased to ensure the stability and reliability of the system. In an embodiment of the present application, the initial proportional coefficient is dynamically adjusted based on the current system load and the current network traffic to dynamically adjust the pre-authorization threshold.

[0072] See also Figure 6 , Figure 6 A specific implementation of step S4 is shown, which is described in detail as follows:

[0073] S41: acquiring monitoring data in real time through a preset monitoring system, wherein the monitoring data includes system load data and network flow data;

[0074] S42: constructing a dynamic adjustment rule based on the monitoring data through an exponential function;

[0075] S43: Acquire the current system load and the current network traffic;

[0076] S44: dynamically adjusting the initial proportionality coefficient based on the current system load and the current network traffic through the dynamic adjustment rule to obtain the target proportionality coefficient.

[0077] Specifically, monitoring data is acquired in real time through a preset monitoring system, wherein the monitoring data includes system load data and network traffic data, the system load data includes indicators such as CPU utilization and memory utilization, and the network traffic data includes bandwidth utilization, data packet transmission rate, etc. Then, a dynamic adjustment rule is constructed based on the monitoring data through an exponential function, and the exponential function is as follows:

[0078] ;

[0079] Among them, L represents the system load, that is, the current workload of the system, which is usually expressed in some form of indicators or percentages, such as CPU utilization, memory utilization, etc. The level of system load directly affects the performance and resource utilization of the system. N represents network traffic, that is, the amount of data involved in the data transmission process. The size of network traffic reflects the current data transmission situation of the system and is also one of the important indicators of system load. is the initial proportionality coefficient, that is, the parameter that is dynamically adjusted according to the system load. After dynamic adjustment, the target proportionality coefficient is obtained. b and c are used to adjust the influence of network traffic and other factors on the pre-authorization proportionality coefficient. b represents the influence factor of network traffic, and c represents the influence factor of other factors. After the embodiment of the present application is calculated by an exponential function, the proportionality coefficient is adjusted to change dynamically according to the system load condition, so as to realize flexible adjustment of the pre-authorization proportionality coefficient under different load conditions.

[0080] S5: Based on the target proportional coefficient, the current remaining flow amount and the requested amount, determine whether the pre-authorization condition is met. If so, pre-authorize the small flow request.

[0081] See also Figure 7 , Figure 7 A specific implementation of step S5 is shown, which is described in detail as follows:

[0082] S51: multiplying the target proportional coefficient by the request amount to obtain a target request amount;

[0083] S52: If the current remaining traffic amount is greater than or equal to the target requested amount, a determination is made to determine whether the current remaining traffic amount and the requested amount meet a pre-authorization condition;

[0084] S53: If the current remaining traffic amount is greater than the target requested amount, it is determined that the current remaining traffic amount and the requested amount meet the pre-authorization condition, and the small traffic request is authorized in advance.

[0085] Specifically, the target ratio coefficient is multiplied by the request amount to obtain the target request amount; if the current remaining traffic amount is greater than the target request amount, the current remaining traffic amount and the request amount are judged to determine whether they meet the pre-authorization conditions. If the current remaining traffic amount is greater than the target request amount, the current remaining traffic amount and the request amount are judged to meet the pre-authorization conditions, and the small traffic request is authorized in advance; if the current remaining traffic amount is less than or equal to the target request amount, the small traffic request is not authorized, but real-time request processing is performed. That is, the conditions for pre-authorization can be expressed as:

[0086] ;

[0087] Among them, R is the current remaining flow, is the target proportional coefficient, and Q is the request volume. If the current remaining traffic is calculated to be greater than the target request volume, it means that the remaining traffic is sufficient and the process can be authorized in advance, thus avoiding the risk of over-authorization.

[0088] In the embodiment of the present application, when a flow request is received, the flow request is parsed to obtain the current flow remaining amount and the request amount; if the request amount is within the preset flow request range, the flow request is taken as a small flow request; the ratio coefficient between the remaining predicted amount and the request predicted amount is calculated based on the current flow remaining amount and the request amount by a pre-trained authorization amount calculation model to obtain an initial ratio coefficient; the current system load and the current network traffic are obtained, and the initial ratio coefficient is dynamically adjusted based on the current system load and the current network traffic to obtain a target ratio coefficient; based on the target ratio coefficient, the current flow remaining amount and the request amount, it is determined whether the pre-authorization condition is met, and if so, the small flow request is authorized in advance. When a small flow request is received, the embodiment of the present invention can pre-authorize the small flow request before the actual billing request arrives, which reduces the processing pressure occupied by the real-time calculation of a large number of concurrent requests, reduces the load of the online billing system and the risk of system crash, and is conducive to improving the stability of the online billing system.

[0089] Please refer to Figure 8 , as a response to the above Figure 1 The present application provides an embodiment of an online charging authorization device for an Internet of Things card, and the embodiment of the device is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various Internet of Things platforms.

[0090] like Figure 8 As shown, the Internet of Things card online charging authorization device of this embodiment includes: a request receiving unit 61, a request confirmation unit 62, a proportional coefficient generating unit 63, a proportional coefficient adjusting unit 64 and an authorization extracting unit 65, wherein:

[0091] The request receiving unit 61 is used to parse the flow request when receiving the flow request to obtain the current flow remaining amount and the requested amount;

[0092] A request confirmation unit 62, configured to treat the flow request as a small flow request if the requested amount is within a preset flow request range;

[0093] A proportional coefficient generating unit 63 is used to calculate a proportional coefficient between a remaining predicted amount and a requested predicted amount based on the current remaining traffic amount and the requested amount through a pre-trained authorized amount calculation model to obtain an initial proportional coefficient;

[0094] The proportionality coefficient adjustment unit 64 is used to obtain the current system load and the current network traffic, and dynamically adjust the initial proportionality coefficient based on the current system load and the current network traffic to obtain a target proportionality coefficient;

[0095] The authorization extraction unit 65 is used to determine whether the pre-authorization condition is met based on the target proportional coefficient, the current remaining flow amount and the request amount, and if so, pre-authorize the small flow request.

[0096] Further, the proportionality coefficient generating unit 63 includes:

[0097] A request frequency acquisition unit, used to acquire the request frequency and timestamp corresponding to the low-flow request;

[0098] A feature vector construction unit, configured to construct a feature vector from the current flow remaining amount, the request amount, the request frequency and the timestamp to obtain a target feature vector;

[0099] A predicted quantity generating unit, configured to predict the consumption of the requested quantity and the remaining quantity in the next time period based on the target feature vector by using the pre-trained authorized quantity calculation model, to obtain the requested predicted quantity and the remaining predicted quantity;

[0100] The coefficient calculation unit is used to calculate the proportional coefficient between the remaining prediction amount and the requested prediction amount to generate the initial proportional coefficient.

[0101] Furthermore, the proportional coefficient generating unit 63 further includes:

[0102] A historical traffic data collection unit, used to collect historical traffic data of each user, wherein the historical traffic data includes data usage, connection frequency and request mode;

[0103] A data preprocessing unit, used to construct a feature vector based on the historical traffic data to obtain an initial feature vector, and perform preprocessing and data division on the initial feature vector to obtain a training data set and a test data set;

[0104] An initialization unit, used to use a random forest algorithm model as an authorization quantity calculation model, and initialize model parameters of the authorization quantity calculation model to obtain an initialized authorization quantity calculation model;

[0105] The model training unit is used to train the initialized authorization quantity calculation model based on the training data set to obtain the pre-trained authorization quantity calculation model.

[0106] Furthermore, the model training unit includes:

[0107] A decision tree construction unit, used to randomly extract a plurality of sample subsets from the training data set to construct each decision tree of the initialized authorization quantity calculation model;

[0108] A candidate feature generating unit, used for randomly selecting the initial feature vector from the training data set as a candidate feature when constructing each node of each decision tree;

[0109] A target decision tree generating unit, configured to select a target feature from the candidate features according to a preset selection method to perform node splitting on the decision tree, so as to construct a target decision tree;

[0110] The model generation unit is used to integrate multiple target decision trees to obtain the pre-trained authorization quantity calculation model when the number of node samples is less than a preset threshold.

[0111] Further, the proportional coefficient adjustment unit 64 includes:

[0112] A monitoring data acquisition unit, used to acquire monitoring data in real time through a preset monitoring system, wherein the monitoring data includes system load data and network flow data;

[0113] A rule building unit, used for building a dynamic adjustment rule based on the monitoring data through an exponential function;

[0114] A current data acquisition unit, used to acquire the current system load and the current network traffic;

[0115] A dynamic adjustment unit is used to dynamically adjust the initial proportionality coefficient based on the current system load and the current network traffic through the dynamic adjustment rule to obtain the target proportionality coefficient.

[0116] Furthermore, the request confirmation unit 62 further includes:

[0117] A judgment result generating unit, used to judge whether the current flow remaining amount exceeds a preset flow value, and obtain a judgment result;

[0118] The first authorization unit is used to pre-authorize the small flow request if the judgment result is that the current remaining flow exceeds the preset flow value.

[0119] Further, the authorization extraction unit 65 includes:

[0120] a target request amount calculation unit, configured to multiply the target proportional coefficient by the request amount to obtain a target request amount;

[0121] A condition judgment unit, used for judging the size of the current remaining traffic amount and the target requested amount to judge whether the current remaining traffic amount and the requested amount meet the pre-authorization condition;

[0122] The second authorization unit is used to determine whether the current remaining traffic amount and the request amount meet the pre-authorization condition if the current remaining traffic amount is greater than the target request amount, and to authorize the small traffic request in advance.

[0123] In the embodiment of the present application, when a flow request is received, the flow request is parsed to obtain the current flow remaining amount and the request amount; if the request amount is within the preset flow request range, the flow request is taken as a small flow request; the ratio coefficient between the remaining predicted amount and the request predicted amount is calculated based on the current flow remaining amount and the request amount by a pre-trained authorization amount calculation model to obtain an initial ratio coefficient; the current system load and the current network traffic are obtained, and the initial ratio coefficient is dynamically adjusted based on the current system load and the current network traffic to obtain a target ratio coefficient; based on the target ratio coefficient, the current flow remaining amount and the request amount, it is determined whether the pre-authorization condition is met, and if so, the small flow request is authorized in advance. When a small flow request is received, the embodiment of the present invention can pre-authorize the small flow request before the actual billing request arrives, which reduces the processing pressure occupied by the real-time calculation of a large number of concurrent requests, reduces the load of the online billing system and the risk of system crash, and is conducive to improving the stability of the online billing system.

[0124] To solve the above technical problems, the present application embodiment also provides an Internet of Things platform. Fig. 9 , Fig. 9 This is a basic structural block diagram of the Internet of Things platform in this embodiment.

[0125] The Internet of Things platform 7 includes a memory 71, a processor 72, and a network interface 73 that are interconnected through a system bus. It should be noted that the figure only shows an Internet of Things platform 7 with three components: a memory 71, a processor 72, and a network interface 73, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the Internet of Things platform here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0126] The IoT platform can be a computing device such as a desktop computer, notebook, PDA, or cloud server. The IoT platform can interact with users through keyboard, mouse, remote control, touchpad, or voice control device.

[0127] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the Internet of Things platform 7, such as a hard disk or memory of the Internet of Things platform 7. In other embodiments, the memory 71 can also be an external storage device of the Internet of Things platform 7, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the Internet of Things platform 7. Of course, the memory 71 can also include both the internal storage unit of the Internet of Things platform 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the Internet of Things platform 7, such as the program code of the Internet of Things card online billing authorization method, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.

[0128] In some embodiments, the processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 72 is generally used to control the overall operation of the Internet of Things platform 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code of the above-mentioned Internet of Things card online charging authorization method to implement various embodiments of the Internet of Things card online charging authorization method.

[0129] The network interface 73 may include a wireless network interface or a wired network interface, and the network interface 73 is generally used to establish a communication connection between the Internet of Things platform 7 and other electronic devices.

[0130] The present application also provides another implementation, namely, providing a computer-readable storage medium, which stores a computer program, and the computer program can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned method for online billing authorization of an Internet of Things card.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0132] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An Internet of Things card online billing authorization method, characterized in that: include: When receiving a flow request, the flow request is parsed to obtain the current flow remaining amount and the requested amount; If the requested amount is within the preset flow request range, the flow request is regarded as a small flow request; Calculate the proportional coefficient between the remaining predicted amount and the requested predicted amount based on the current remaining traffic amount and the requested amount through a pre-trained authorization amount calculation model to obtain an initial proportional coefficient; Acquire the current system load and the current network traffic, and dynamically adjust the initial proportionality coefficient based on the current system load and the current network traffic to obtain a target proportionality coefficient; Multiplying the target proportionality coefficient by the request amount to obtain a target request amount; The current remaining traffic amount and the target requested amount are compared to determine whether the current remaining traffic amount and the requested amount meet the pre-authorization condition; If the current remaining traffic amount is greater than the target requested amount, determining that the current remaining traffic amount and the requested amount meet the pre-authorization condition, and authorizing the small traffic request in advance; The obtaining of the current system load and the current network traffic, and dynamically adjusting the initial proportionality coefficient based on the current system load and the current network traffic to obtain the target proportionality coefficient, includes: Acquire monitoring data in real time through a preset monitoring system, wherein the monitoring data includes system load data and network flow data; constructing a dynamic adjustment rule based on the monitoring data through an exponential function; Obtaining the current system load and the current network traffic; The initial proportionality coefficient is dynamically adjusted based on the current system load and the current network traffic through the dynamic adjustment rule to obtain the target proportionality coefficient.

2. The method for online billing authorization of Internet of Things card according to claim 1, characterized in that: The pre-trained authorization amount calculation model calculates the proportional coefficient between the remaining predicted amount and the requested predicted amount based on the current traffic remaining amount and the requested amount to obtain the initial proportional coefficient, including: Obtain the request frequency and timestamp corresponding to the low-flow request; Constructing a feature vector with the current traffic remaining amount, the request amount, the request frequency and the timestamp to obtain a target feature vector; Predicting the consumption of the requested amount and the remaining amount in the next time period based on the target feature vector by using the pre-trained authorization amount calculation model to obtain the requested predicted amount and the remaining predicted amount; The proportional coefficient between the remaining prediction amount and the requested prediction amount is calculated to generate the initial proportional coefficient.

3. The method for online billing authorization of Internet of Things card according to claim 1, characterized in that: Before obtaining the initial proportional coefficient by calculating the proportional coefficient between the remaining predicted amount and the requested predicted amount based on the current remaining traffic amount and the requested amount using the pre-trained authorized amount calculation model, the method further includes: Collecting historical traffic data for each user, wherein the historical traffic data includes data usage, connection frequency, and request pattern; Constructing a feature vector based on the historical traffic data to obtain an initial feature vector, and performing preprocessing and data division on the initial feature vector to obtain a training data set and a test data set; Using a random forest algorithm model as an authorization quantity calculation model, and initializing model parameters of the authorization quantity calculation model to obtain an initialized authorization quantity calculation model; The initialized authorization quantity calculation model is trained based on the training data set to obtain the pre-trained authorization quantity calculation model.

4. The method for online billing authorization of Internet of Things card according to claim 3, characterized in that: The step of training the initialized authorization quantity calculation model based on the training data set to obtain the pre-trained authorization quantity calculation model includes: Randomly extracting a plurality of sample subsets from the training data set to construct each decision tree of the initialized authorization quantity calculation model; When constructing each node of each decision tree, randomly selecting the initial feature vector from the training data set as a candidate feature; Selecting a target feature from the candidate features according to a preset selection method to split the nodes of the decision tree to construct a target decision tree; When the number of node samples is less than a preset threshold, multiple target decision trees are integrated to obtain the pre-trained authorization quantity calculation model.

5. The method for online billing authorization of Internet of Things card according to claim 1, characterized in that: If the requested amount is within a preset flow request range, after treating the flow request as a small flow request, the method further includes: Determine whether the current remaining flow exceeds a preset flow value, and obtain a determination result; If the judgment result is that the current remaining flow exceeds the preset flow value, the small flow request is authorized in advance.

6. An Internet of Things card online billing authorization device, characterized in that: include: A request receiving unit, configured to parse the flow request upon receiving the flow request, and obtain the current flow remaining amount and the requested amount; a request confirmation unit, configured to treat the flow request as a small flow request if the requested amount is within a preset flow request range; A proportional coefficient generating unit, configured to calculate a proportional coefficient between a remaining predicted amount and a requested predicted amount based on the current remaining traffic amount and the requested amount through a pre-trained authorized amount calculation model, to obtain an initial proportional coefficient; A proportionality coefficient adjustment unit, used to obtain a current system load and a current network flow, and dynamically adjust the initial proportionality coefficient based on the current system load and the current network flow to obtain a target proportionality coefficient; A dynamic adjustment unit, configured to multiply the target proportionality coefficient by the request amount to obtain a target request amount; A condition judgment unit, used for comparing the current remaining traffic amount with the target requested amount to determine whether the current remaining traffic amount and the requested amount meet a pre-authorization condition; A second authorization unit is used to determine that the current remaining traffic amount and the request amount meet the pre-authorization condition if the current remaining traffic amount is greater than the target request amount, and to pre-authorize the small traffic request; The proportional coefficient adjustment unit comprises: A monitoring data acquisition unit, used to acquire monitoring data in real time through a preset monitoring system, wherein the monitoring data includes system load data and network flow data; A rule building unit, used for building a dynamic adjustment rule based on the monitoring data through an exponential function; A current data acquisition unit, used to acquire the current system load and the current network traffic; A dynamic adjustment unit is used to dynamically adjust the initial proportionality coefficient based on the current system load and the current network traffic through the dynamic adjustment rule to obtain the target proportionality coefficient.

7. An Internet of Things platform, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the online billing authorization method for an Internet of Things card as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the Internet of Things card online billing authorization method according to any one of claims 1 to 5 is implemented.