Iot service monitoring method, device and storage medium

Abstract

The embodiment of the application discloses a kind of Internet of Things service monitoring method, equipment and storage medium, applied to Internet of Things technical field, can solve the problem that the accuracy of the obtained service failure reason is not high, and data is relatively scattered, reduce the efficiency and accuracy of data analysis.The method comprises: obtaining a plurality of first service data, the first data includes the service index of a plurality of service events in a preset period;According to a plurality of first service data, determine the threshold and contribution of a plurality of characteristic values;According to the threshold and contribution of a plurality of characteristic values, construct failure reason code feature library;According to the failure reason code feature library, multidimensional quality difference is converged to output delimited data, delimited data at least includes at least one of quality difference network element, quality difference terminal and quality difference area.

Description

Technical Field

[0001] This application relates to the field of the Internet of Things (IoT), and more particularly to an IoT business monitoring method, device, and storage medium. Background Technology

[0002] With the rapid development of IoT businesses, building a complete business perception, monitoring, and delineation system to ensure user experience has become paramount for the healthy development of IoT. Currently, the main approach is to rely on expert experience to delineate the causes of business failures and identify the reasons for business anomalies. However, this method yields results in low accuracy and scattered data, reducing the efficiency and accuracy of data analysis. Summary of the Invention

[0003] This application provides an IoT service monitoring method, device, and storage medium to address the problems in existing technologies where the accuracy of identifying service failure causes is low and the data is scattered, reducing the efficiency and accuracy of data analysis. To solve the above technical problems, this invention is implemented as follows:

[0004] The first aspect of this application provides an IoT business monitoring method, applied to an IoT business monitoring device, which may include: acquiring multiple first business data, wherein the first business data includes business indicators of multiple business events within a preset time period;

[0005] Based on the aforementioned multiple first business data, thresholds and contribution levels of multiple feature values ​​are determined;

[0006] A failure reason code feature library is constructed based on the thresholds and contributions of multiple feature values;

[0007] Based on the failure reason code feature library, multi-dimensional quality difference aggregation is performed to output boundary data, which includes at least one of the following: poor quality network element, poor quality terminal, and poor quality region.

[0008] As an optional implementation, in a first aspect of the present invention, after performing multi-dimensional quality difference aggregation based on the failure reason code feature library to output delimited data, the method further includes:

[0009] If the delimitation data includes the poor-quality terminal, then the IoT terminal and group customer information are aggregated, and the target terminal is determined based on the associated terminal software development kit (SDK) documents and card opening information. The target terminal is a terminal device with poor quality.

[0010] If the delineation data includes the poor-quality network element, then the cell and city information are aggregated, and the target network element is determined based on the associated wireless performance KPI indicators and measurement reports (MR). The target network element is the network element with poor quality.

[0011] If the delimitation data includes the poor quality region, then the network element MME, UGW, and Server IP information are aggregated to determine the target region, which is the region with poor quality.

[0012] As an optional implementation, in a first aspect of the present invention, determining the thresholds and contribution levels of multiple feature values ​​based on the plurality of first business data includes:

[0013] A semi-supervised learning algorithm is used to input multiple second business data into a preset model for calculation, so as to obtain the target threshold corresponding to multiple feature values ​​and the target contribution. The multiple second business data are part of the multiple first business data.

[0014] Multiple third business data are input into the preset model, and the output of the preset model is checked to see if it matches the actual data. The multiple third business data are data other than the multiple second business data among the multiple first business data.

[0015] If a match is found, the target threshold corresponding to the plurality of feature values ​​and the target contribution are output.

[0016] As an optional implementation, in a first aspect of the present invention, the step of inputting multiple second business data into a preset model using a semi-supervised learning algorithm to obtain a target threshold corresponding to multiple feature values ​​and a target contribution degree includes:

[0017] The semi-supervised learning algorithm is used to input the multiple second business data into the preset model for calculation, so as to obtain the initial threshold and initial contribution of the multiple feature values;

[0018] Delete feature values ​​whose contribution is less than a preset contribution threshold to obtain the target threshold corresponding to the plurality of feature values, and the target contribution.

[0019] As an optional implementation, in a first aspect of the present invention, the step of constructing a failure reason code feature library based on thresholds and contribution values ​​of multiple feature values ​​includes:

[0020] The base delimitation result library for obtaining failure reason codes;

[0021] Based on the correlation analysis algorithm, the first business data corresponding to the failure reason code is deeply mined;

[0022] Based on the first business data, construct a frequent pattern tree;

[0023] The failure reason code feature library is constructed based on the frequent itemsets of each failure reason code on the path from the child node to the root node in the frequent pattern tree.

[0024] As an optional implementation, in a first aspect of the present invention, the step of performing multi-dimensional quality difference aggregation based on the failure reason code feature library to output delimited data includes:

[0025] Based on the multiple first business data, determine the high-priority failure reason codes;

[0026] Based on the failure reason code, determine the coarsely defined business boundary range;

[0027] Within the defined business scope, multi-dimensional quality difference aggregation is performed to output the defined scope data.

[0028] As an optional implementation, in a first aspect of the present invention, the step of performing multi-dimensional quality difference aggregation within the business boundary to output the boundary data includes:

[0029] Within the defined service boundary, the degradation score of each first service data is determined according to the degradation contribution algorithm;

[0030] The first business data with the highest degradation score is determined as the delimiting data.

[0031] A second aspect of this application provides an Internet of Things (IoT) service monitoring device, which may include:

[0032] The acquisition module is used to acquire multiple first business data, which include business metrics of multiple business events within a preset time period.

[0033] The processing module is used to determine the thresholds and contribution of multiple feature values ​​based on the multiple first business data.

[0034] The processing module is used to construct a failure reason code feature library based on the thresholds and contributions of multiple feature values;

[0035] The processing module is used to perform multi-dimensional quality defect aggregation based on the failure reason code feature library to output boundary data, wherein the boundary data includes at least one of the following: poor quality network element, poor quality terminal, and poor quality region.

[0036] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0037] The processing module is also used to, if the delimitation data includes the poor-quality terminal, aggregate IoT terminal and group customer information, and determine the target terminal based on the associated terminal software development kit (SDK) document and card opening information, wherein the target terminal is a terminal device with poor quality.

[0038] The processing module is also used to, if the delimitation data includes the poor-quality network element, aggregate cell and city information, and determine the target network element based on the associated wireless performance KPI indicators and measurement report MR, wherein the target network element is the network element with poor quality.

[0039] The processing module is further configured to, if the delimitation data includes the poor quality region, aggregate network element MME, UGW, and Server IP information to determine the target region, wherein the target region is the region with poor quality.

[0040] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0041] The processing module is specifically used to input multiple second business data into a preset model for calculation using a semi-supervised learning algorithm, so as to obtain the target threshold corresponding to multiple feature values ​​and the target contribution, wherein the multiple second business data are part of the multiple first business data;

[0042] The processing module is specifically used to input multiple third business data into the preset model and detect whether the output result of the preset model matches the actual data. The multiple third business data are data other than the multiple second business data among the multiple first business data.

[0043] The processing module is specifically used to output the target threshold corresponding to the plurality of feature values ​​and the target contribution degree if a match is found.

[0044] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0045] The processing module is specifically used to input the multiple second business data into the preset model for calculation through the semi-supervised learning algorithm, so as to obtain the initial threshold and initial contribution of the multiple feature values;

[0046] The processing module is specifically used to delete feature values ​​whose contribution is less than a preset contribution threshold, so as to obtain the target threshold corresponding to the plurality of feature values ​​and the target contribution.

[0047] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0048] The acquisition module is specifically used to obtain the basic delimitation result library of failure reason codes;

[0049] The processing module is specifically used to perform in-depth mining of the first business data corresponding to the failure reason code based on the association analysis algorithm;

[0050] The processing module is specifically used to construct a frequent pattern tree based on the first business data;

[0051] The processing module is specifically used to construct the failure reason code feature library based on the frequent itemsets of each failure reason code on the path from the child node to the root node in the frequent pattern tree.

[0052] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0053] The processing module is specifically used to determine high-priority failure reason codes based on the multiple first business data.

[0054] The processing module is specifically used to determine the coarsely defined business boundary range based on the failure reason code;

[0055] The processing module is specifically used to perform multi-dimensional quality difference aggregation within the defined business scope in order to output the defined data.

[0056] As an optional implementation, in a second aspect of the embodiments of the present invention,

[0057] The processing module is specifically used to determine the degradation score of each first business data within the defined business boundary based on the degradation contribution algorithm.

[0058] The processing module is specifically used to determine the first business data with the largest degradation score as the delimiting data.

[0059] A third aspect of this application provides an Internet of Things (IoT) service monitoring device, which may include:

[0060] Memory containing executable program code;

[0061] A processor coupled to the memory;

[0062] The processor calls the executable program code stored in the memory to execute the IoT service monitoring method in the first aspect of the present invention.

[0063] This application also provides a computer-readable storage medium storing a computer program that causes a computer to execute the IoT service monitoring method of the first aspect of the present invention. The computer-readable storage medium includes ROM / RAM, a magnetic disk, or an optical disk, etc.

[0064] In another aspect, the present invention provides a computer program product that, when run on a computer, causes the computer to execute the Internet of Things (IoT) business monitoring method of the first aspect of the present invention.

[0065] In another aspect, the present invention provides an application publishing platform for publishing computer program products, wherein when the computer program products are run on a computer, the computer executes the Internet of Things business monitoring method of the first aspect of the present invention.

[0066] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0067] In this embodiment, the IoT service monitoring device can acquire multiple first service data, which include service indicators of multiple service events within a preset time period. Based on the multiple first service data, thresholds and contributions of multiple feature values ​​are determined. A failure reason code feature library is constructed based on the thresholds and contributions of the multiple feature values. Multi-dimensional quality difference aggregation is performed based on the failure reason code feature library to output boundary data, which includes at least one of the following: poor-quality network elements, poor-quality terminals, and poor-quality areas. This solution enables precise monitoring of changes in the perception of different IoT services. Furthermore, rapid matching based on an expert experience knowledge base helps users efficiently and accurately locate the cause of problems, greatly improving problem location efficiency and the reliability of the output results.

[0068] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0069] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 This is a flowchart illustrating an IoT service monitoring method provided in an embodiment of the present invention;

[0071] Figure 2 This is a schematic diagram of the algorithm for an IoT service monitoring method provided in an embodiment of the present invention;

[0072] Figure 3This is a schematic diagram of the structure of an IoT service monitoring device provided in an embodiment of the present invention. Figure 1 ;

[0073] Figure 4 This is a schematic diagram of the structure of an IoT service monitoring device provided in an embodiment of the present invention. Figure 2 . Detailed Implementation

[0074] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0075] The terms "first" and "second," etc., used in the specification and claims of this invention are used to distinguish different objects, not to describe a specific order of objects. For example, "first business data" and "second business data," etc., are used to distinguish different business data, not to describe a specific order of business data.

[0076] The terms “comprising” and “having” and any variations thereof in this invention are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0077] It should be noted that in the embodiments of the present invention, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0078] With the rapid development of IoT businesses, building a complete business perception, monitoring, and delineation system to ensure user experience has become paramount for the healthy development of IoT. Currently, the main approach is to rely on expert experience to delineate the causes of business failures and identify the reasons for business anomalies. However, this method yields results in low accuracy and scattered data, reducing the efficiency and accuracy of data analysis.

[0079] This application provides an IoT service monitoring method, device, and storage medium. The IoT service monitoring device can acquire multiple first service data, which include service indicators of multiple service events within a preset time period. Based on the multiple first service data, thresholds and contributions of multiple feature values ​​are determined. Based on the thresholds and contributions of the multiple feature values, a failure reason code feature library is constructed. Based on the failure reason code feature library, multi-dimensional quality difference aggregation is performed to output boundary data. The boundary data includes at least one of the following: poor-quality network elements, poor-quality terminals, and poor-quality areas. Through this scheme, accurate monitoring of changes in the perception of different IoT services can be achieved. At the same time, rapid matching based on expert experience knowledge base can help users efficiently and accurately locate the cause of problems, greatly improving the efficiency of problem location and the reliability of output results.

[0080] In this embodiment of the invention, the IoT service monitoring device can be a cloud server or a terminal device capable of executing IoT service monitoring methods.

[0081] The execution subject of the IoT service monitoring method provided in this embodiment of the invention can be the aforementioned IoT service monitoring device, or it can be a functional module and / or functional entity within the IoT service monitoring device capable of implementing the IoT service monitoring method. The specific implementation can be determined according to actual usage requirements, and this embodiment of the invention does not impose any limitations. The following uses an IoT service monitoring device as an example to executively describe the IoT service monitoring method provided in this embodiment of the invention.

[0082] Example 1

[0083] like Figure 1 As shown in the figure, an embodiment of the present invention provides an IoT service monitoring method, which may include the following steps:

[0084] Step 101: Obtain multiple first business data.

[0085] In this embodiment of the invention, the IoT service monitoring device can obtain multiple first service data from multiple user devices.

[0086] The first business data may include business metrics for multiple business events within a preset time period.

[0087] It should be noted that IoT business monitoring equipment can select multiple primary business data points within a preset time period that coincide with the time of the customer's historical complaints.

[0088] For example, suppose the preset time period is one month. If the IoT business monitoring device receives a complaint from a user that they cannot unlock their door at 3 PM, then the IoT business monitoring device can collect business data from around 3 PM every day for the month, such as the time of the complaint, the location of the complaint, and the reason for the complaint.

[0089] Optionally, business events may include: bicycle scanning services, smoke alarm services, smart door lock services, smart meter reading services, etc.

[0090] Optional business metrics may include: traffic, frequency of business access, success rate of business access, frequency of business interaction, success rate of business interaction, etc.

[0091] Step 102: Determine the thresholds and contribution of multiple feature values ​​based on multiple primary business data.

[0092] In this embodiment of the invention, the IoT business monitoring device can determine the thresholds and contribution of multiple feature values ​​based on multiple first business data.

[0093] It should be noted that the contribution level represents the probability of failure for each business event.

[0094] For example, assuming the business event is scanning a bicycle QR code, if the user cannot unlock the bicycle after scanning the code, then the system's lack of response usually contributes the most. Excessive latency causing the business to time out and fail will also contribute to some extent, but to a smaller extent.

[0095] Optionally, based on multiple first business data, thresholds and contributions of multiple feature values ​​are determined. Specifically, this may include: using a semi-supervised learning algorithm, inputting multiple second business data into a preset model to calculate the target thresholds and target contributions corresponding to the multiple feature values; inputting multiple third business data into the preset model and detecting whether the output of the preset model matches the actual data; if they match, outputting the target thresholds and target contributions corresponding to the multiple feature values.

[0096] Among them, multiple second business data are partial data from multiple first business data; multiple third business data are data from multiple first business data other than multiple second business data.

[0097] It should be noted that the IoT business monitoring device can select a portion of the data from multiple primary business data sets as training samples and input them into the semi-supervised learning algorithm model for calculation to determine the threshold and contribution of each feature value. Then, the IoT business monitoring device can use the remaining data as evaluation samples to evaluate and verify the threshold and contribution obtained from the training, ensuring a high confidence level for the threshold and contribution.

[0098] Furthermore, a semi-supervised learning algorithm is used to input multiple second business data into a preset model for calculation to obtain target thresholds and target contributions corresponding to multiple feature values. Specifically, this may include: using a semi-supervised learning algorithm to input multiple second business data into a preset model for calculation to obtain initial thresholds and initial contributions corresponding to multiple feature values; deleting feature values ​​with contributions less than a preset contribution threshold to obtain target thresholds and target contributions corresponding to multiple feature values.

[0099] In this optional implementation, the IoT business monitoring device can filter the threshold and contribution after obtaining them, delete data with a contribution less than the preset contribution threshold, and reduce the number of feature values ​​to reduce the overall computational load of the algorithm.

[0100] Optionally, IoT business monitoring devices can also set different preset contribution thresholds to filter data based on different business events.

[0101] Step 103: Construct a failure reason code feature library based on the thresholds and contributions of multiple feature values.

[0102] In this embodiment of the invention, the IoT business monitoring device can construct a failure reason code feature library based on the thresholds and contribution of multiple feature values.

[0103] Optionally, a failure reason code feature library can be constructed based on the thresholds and contributions of multiple feature values. Specifically, this may include: obtaining a basic delimitation result library of failure reason codes; performing in-depth mining on the first business data corresponding to the failure reason codes based on an association analysis algorithm; constructing a frequent pattern tree based on the first business data; and constructing a failure reason code feature library based on the frequent itemsets of each failure reason code on the path from the child node to the root node in the frequent pattern tree.

[0104] In this optional implementation, the IoT business monitoring device can first build a basic delimitation result library of failure reason codes based on historical records. Since there may be abnormal scenarios that the failure reason codes cannot cover, it is necessary to use correlation analysis algorithms to combine failure reason codes and business feature indicators for secondary modeling and mining to improve the failure reason code feature knowledge base and ensure the high confidence of each failure reason code delimitation result.

[0105] Optionally, the association analysis algorithm can be the FP-Growth algorithm.

[0106] Furthermore, IoT business monitoring equipment, through the FP-Growth algorithm, can perform a secondary scan of the basic delimitation result library built on historical records, inserting each filtered data point in descending order into a frequent pattern tree (FP-tree) with null as the root node, such as... Figure 2 As shown, at each node, the weight of that node is recorded until the entire tree is built. Based on the FP-tree, the FP-tree is mined until the root node 21 is encountered. The frequent itemsets of all failure reason codes on the path from child node 22 to root node 21 are collected. When a branch marked as a frequent failure item is mined, the entire branch is traversed first, all nodes are assigned to the failure itemset, and the confidence of each bound dimension is output.

[0107] Step 104: Based on the failure reason code feature library, perform multi-dimensional quality difference aggregation to output boundary data.

[0108] In this embodiment of the invention, the IoT business monitoring device can perform multi-dimensional quality difference aggregation based on the failure reason code feature library to output delimited data.

[0109] The delimitation data may include at least one of the following: poor-quality network elements, poor-quality terminals, and poor-quality regions.

[0110] Optionally, based on the failure reason code feature library, multi-dimensional quality difference aggregation is performed to output boundary data. Specifically, this may include: determining high-priority failure reason codes based on multiple first business data; determining the coarse boundary range of business based on the failure reason codes; and performing multi-dimensional quality difference aggregation within the business boundary range to output boundary data.

[0111] In this optional implementation, the IoT business monitoring device can determine the high-priority failure reason codes based on the frequency ratio of various failure reasons, so as to form a coarsely defined business boundary range.

[0112] For example, IoT business monitoring devices can use failure reason codes, such as failure reason codes that return values ​​corresponding to network access failures caused by unpaid fees, to roughly determine that the problem is due to the terminal and not the network.

[0113] Furthermore, IoT business monitoring equipment can perform multi-dimensional quality difference aggregation within the defined scope of the business to output defined data.

[0114] For example, suppose multiple terminals are unable to access the network at the same time. When the IoT business monitoring device aggregates data from different dimensions, it queries the problem points. For example, when aggregating by enterprise dimension, it may find that this enterprise is in arrears at the end of the month while other enterprises have no problems. Or, when aggregating by base station dimension, it may find that this base station is down, and several terminals are concentrated on this base station.

[0115] Furthermore, within the defined business scope, multi-dimensional quality difference aggregation is performed to output defined data. Specifically, this may include: within the defined business scope, determining the degradation score of each first business data based on the degradation contribution algorithm; and determining the first business data with the largest degradation score as the defined data.

[0116] The formula for calculating the degradation score based on the degradation contribution algorithm is as follows:

[0117]

[0118] Optionally, after performing multi-dimensional quality difference aggregation based on the failure reason code feature library to output bounded data, the specific implementation methods can include the following:

[0119] Implementation Method 1: If the delimitation data includes terminals with poor quality, the IoT business monitoring equipment can aggregate IoT terminal and corporate customer information, and determine the target terminal based on the associated terminal software development kit (SDK) documents and card opening information. The target terminal is the terminal device with poor quality.

[0120] Implementation Method 2: If the delineation data includes network elements with poor quality, the IoT service monitoring equipment can aggregate information from the community and the city, and determine the target network element based on the associated wireless performance KPI indicators and measurement reports (MR). The target network element is the network element with poor quality.

[0121] Implementation Method 3: If the delimitation data includes areas with poor quality, the IoT business monitoring device can aggregate network element MME, UGW, and server IP information to determine the target area, which is the area with poor quality.

[0122] This invention provides an IoT service monitoring method. The IoT service monitoring device can acquire multiple first service data sets, including service indicators for multiple service events within a preset time period. Based on the multiple first service data sets, thresholds and contribution levels of multiple feature values ​​are determined. A failure reason code feature library is constructed based on the thresholds and contribution levels of the multiple feature values. Multi-dimensional quality difference aggregation is performed based on the failure reason code feature library to output boundary data. The boundary data includes at least one of the following: poor-quality network elements, poor-quality terminals, and poor-quality areas. This solution enables precise monitoring of changes in the perception of different IoT services. Furthermore, rapid matching based on an expert experience knowledge base helps users efficiently and accurately locate the cause of problems, greatly improving problem location efficiency and the reliability of the output results.

[0123] Example 2

[0124] like Figure 3 As shown, this embodiment of the invention provides an IoT service monitoring device, which includes:

[0125] The acquisition module 301 is used to acquire multiple first business data, which include business indicators of multiple business events within a preset time period;

[0126] Processing module 302 is used to determine the thresholds and contribution of multiple feature values ​​based on the multiple first business data;

[0127] Processing module 302 is used to construct a failure reason code feature library based on the thresholds and contributions of multiple feature values;

[0128] The processing module 302 is used to perform multi-dimensional quality difference aggregation based on the failure reason code feature library to output boundary data, wherein the boundary data includes at least one of the following: poor quality network element, poor quality terminal, and poor quality region.

[0129] Optionally, the processing module 302 is further configured to, if the delimitation data includes the poor-quality terminal, aggregate IoT terminal and group customer information, and determine the target terminal based on the associated terminal software development kit (SDK) document and card opening information, wherein the target terminal is a terminal device with poor quality.

[0130] The processing module 302 is further configured to, if the delimitation data includes the poor-quality network element, aggregate cell and city information, and determine the target network element based on the associated wireless performance KPI indicators and measurement report MR, wherein the target network element is the network element with poor quality.

[0131] The processing module 302 is further configured to, if the delimitation data includes the poor quality area, aggregate network element MME, UGW and Server IP information to determine the target area, wherein the target area is the area with poor quality.

[0132] Optionally, the processing module 302 is specifically used to input multiple second business data into a preset model for calculation using a semi-supervised learning algorithm to obtain a target threshold corresponding to multiple feature values ​​and a target contribution, wherein the multiple second business data are part of the multiple first business data;

[0133] Processing module 302 is specifically used to input multiple third business data into the preset model, and detect whether the output result of the preset model matches the actual data. The multiple third business data are data other than the multiple second business data among the multiple first business data.

[0134] The processing module 302 is specifically used to output the target threshold corresponding to the plurality of feature values ​​and the target contribution degree if a match is found.

[0135] Optionally, the processing module 302 is specifically used to input the multiple second business data into the preset model for calculation through the semi-supervised learning algorithm to obtain the initial threshold and initial contribution of the multiple feature values;

[0136] The processing module 302 is specifically used to delete feature values ​​whose contribution is less than a preset contribution threshold, so as to obtain the target threshold corresponding to the plurality of feature values ​​and the target contribution.

[0137] Optionally, module 301 is used to obtain the basic delimitation result library of failure reason codes;

[0138] Processing module 302 is specifically used to perform in-depth mining on the first business data corresponding to the failure reason code according to the association analysis algorithm;

[0139] Processing module 302 is specifically used to construct a frequent pattern tree based on the first business data;

[0140] The processing module 302 is specifically used to construct the failure reason code feature library based on the frequent itemsets of each failure reason code on the path from the child node to the root node in the frequent pattern tree.

[0141] Optionally, the processing module 302 is specifically used to determine a high-priority failure reason code based on the plurality of first business data;

[0142] Processing module 302 is specifically used to determine the coarsely defined service boundary range based on the failure reason code;

[0143] The processing module 302 is specifically used to perform multi-dimensional quality difference aggregation within the business boundary range in order to output the boundary data.

[0144] Optionally, the processing module 302 is specifically used to determine the degradation score of each first business data within the business boundary range according to the degradation contribution algorithm;

[0145] The processing module 302 is specifically used to determine the first business data with the largest degradation score as the delimiting data.

[0146] In this embodiment of the invention, each module can implement the IoT business monitoring method provided in the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0147] like Figure 4 As shown, this embodiment of the invention also provides an IoT service monitoring device, which may include:

[0148] Memory 401 storing executable program code;

[0149] Processor 402 coupled to memory 401;

[0150] Specifically, the processor 402 calls the executable program code stored in the memory 401 to execute the IoT service monitoring method executed by the IoT service monitoring device in the above method embodiments.

[0151] This invention provides a computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of the methods described in the above embodiments.

[0152] This invention also provides a computer program product, wherein when the computer program product is run on a computer, the computer performs some or all of the steps of the methods described in the above method embodiments.

[0153] This invention also provides an application publishing platform, which is used to publish computer program products. When the computer program products are run on a computer, the computer performs some or all of the steps of the methods described in the above method embodiments.

[0154] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line, DSL) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk, SSD), etc.

[0155] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0156] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0157] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0158] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0159] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for monitoring Internet of Things (IoT) services, characterized in that, Applications in IoT business monitoring equipment include: Acquire multiple first business data, which include business metrics of multiple business events within a preset time period; Based on the aforementioned multiple first business data, thresholds and contribution levels of multiple feature values ​​are determined; A failure reason code feature library is constructed based on the thresholds and contributions of multiple feature values; Based on the failure reason code feature library, multi-dimensional quality difference aggregation is performed to output boundary data, which includes at least one of the following: poor quality network element, poor quality terminal, and poor quality region; The step of determining the thresholds and contribution levels of multiple feature values ​​based on the multiple first business data includes: A semi-supervised learning algorithm is used to input multiple second business data into a preset model for calculation, so as to obtain the target threshold corresponding to multiple feature values ​​and the target contribution. The multiple second business data are part of the multiple first business data. Multiple third business data are input into the preset model, and the output of the preset model is checked to see if it matches the actual data. The multiple third business data are data other than the multiple second business data among the multiple first business data. If a match is found, the target threshold corresponding to the plurality of feature values ​​and the target contribution are output.

2. The method according to claim 1, characterized in that, After performing multi-dimensional quality difference aggregation based on the failure reason code feature library to output bounded data, the method further includes: If the delimitation data includes the poor-quality terminal, then the IoT terminal and group customer information are aggregated, and the target terminal is determined based on the associated terminal software development kit (SDK) documents and card opening information. The target terminal is a terminal device with poor quality. If the delineation data includes the poor-quality network element, then the cell and city information are aggregated, and the target network element is determined based on the associated wireless performance KPI indicators and measurement reports (MR). The target network element is the network element with poor quality. If the delimitation data includes the poor quality region, then the network element MME, UGW, and Server IP information are aggregated to determine the target region, which is the region with poor quality.

3. The method according to claim 1, characterized in that, The process involves using a semi-supervised learning algorithm to input multiple second business data points into a preset model for calculation, thereby obtaining target thresholds corresponding to multiple feature values ​​and target contribution degrees, including: The semi-supervised learning algorithm is used to input the multiple second business data into the preset model for calculation, so as to obtain the initial threshold and initial contribution of the multiple feature values; Delete feature values ​​whose contribution is less than a preset contribution threshold to obtain the target threshold corresponding to the plurality of feature values, and the target contribution.

4. The method according to claim 1, characterized in that, The construction of the failure reason code feature library based on the thresholds and contributions of multiple feature values ​​includes: The base delimitation result library for obtaining failure reason codes; Based on the correlation analysis algorithm, the first business data corresponding to the failure reason code is deeply mined; Based on the first business data, construct a frequent pattern tree; The failure reason code feature library is constructed based on the frequent itemsets of each failure reason code on the path from the child node to the root node in the frequent pattern tree.

5. The method according to claim 1, characterized in that, The step of performing multi-dimensional quality difference aggregation based on the failure reason code feature library to output bounded data includes: Based on the multiple first business data, determine the high-priority failure reason codes; Based on the failure reason code, determine the coarsely defined business boundary range; Within the defined business scope, multi-dimensional quality difference aggregation is performed to output the defined scope data.

6. The method according to claim 5, characterized in that, Within the defined business scope, multi-dimensional quality difference aggregation is performed to output the defined data, including: Within the defined service boundary, the degradation score of each first service data is determined according to the degradation contribution algorithm; The first business data with the highest degradation score is determined as the delimiting data.

7. An Internet of Things (IoT) business monitoring device, characterized in that, include: The acquisition module is used to acquire multiple first business data, which include business metrics of multiple business events within a preset time period. The processing module is used to determine the thresholds and contribution of multiple feature values ​​based on the multiple first business data. The processing module is also used to construct a failure reason code feature library based on the thresholds and contribution of multiple feature values; The processing module is also used to perform multi-dimensional quality difference aggregation based on the failure reason code feature library to output boundary data, wherein the boundary data includes at least one of the following: poor quality network element, poor quality terminal, and poor quality region. Specifically, the processing module is used to: input multiple second business data into a preset model for calculation using a semi-supervised learning algorithm to obtain target thresholds corresponding to multiple feature values ​​and target contribution, wherein the multiple second business data are part of the multiple first business data; Multiple third business data are input into the preset model, and the output of the preset model is checked to see if it matches the actual data. The multiple third business data are data other than the multiple second business data among the multiple first business data. If a match is found, the target threshold corresponding to the plurality of feature values ​​and the target contribution are output.

8. An Internet of Things (IoT) business monitoring device, characterized in that, include: Memory containing executable program code; and the processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the IoT service monitoring method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, include: The computer-readable storage medium stores computer instructions, which, when executed by a processor, implement the IoT service monitoring method as described in any one of claims 1 to 6.

Images