CN114338424A - Evaluation method and evaluation device for operation health degree of Internet of things - Google Patents
Evaluation method and evaluation device for operation health degree of Internet of things Download PDFInfo
- Publication number
- CN114338424A CN114338424A CN202111643078.1A CN202111643078A CN114338424A CN 114338424 A CN114338424 A CN 114338424A CN 202111643078 A CN202111643078 A CN 202111643078A CN 114338424 A CN114338424 A CN 114338424A
- Authority
- CN
- China
- Prior art keywords
- index
- evaluation
- user
- perception
- service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 104
- 230000036541 health Effects 0.000 title claims abstract description 86
- 230000008447 perception Effects 0.000 claims abstract description 105
- 230000004927 fusion Effects 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000001364 causal effect Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000005304 joining Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003071 parasitic effect Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an assessment method for the operation health degree of the Internet of things, which comprises the following steps: acquiring operation data from multiple links of the Internet of things; performing a user perception indicator evaluation based on a first subset of data in the operational data to determine a user perception indicator; performing a quality of service awareness assessment based on a second subset of data in the operational data to determine a quality of service awareness indicator; performing a network quality aware evaluation based on a third subset of data in the operational data to determine a network quality aware indicator; performing multi-index fusion health assessment based on the user perception index, the service quality perception index and the network quality perception index to determine a health assessment index; and ascertaining at least one index anomaly of the internet of things from the multi-index fusion health assessment, and performing a root cause analysis based on a root cause propagation model for the at least one index anomaly to determine a poor root cause.
Description
Technical Field
The invention relates to the technical field of Internet of things, in particular to an evaluation method and an evaluation device for the operation health degree of the Internet of things.
Background
The Internet of Things (Internet of Things, IoT for short) is to collect any object or process needing monitoring, connection and interaction in real time and collect various required information such as sound, light, heat, electricity, mechanics, chemistry, biology and location through various devices and technologies such as various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors and laser scanners, and to realize ubiquitous connection of objects and people through various possible network accesses, and to realize intelligent sensing, identification and management of objects and processes. The internet of things is an information bearer based on the internet, a traditional telecommunication network and the like, and all common physical objects which can be independently addressed form an interconnected network.
Compared with the rapid development of the business of the Internet of things, the current guarantee evaluation means for the business of the Internet of things is far behind the industry growth level. The application scenes of the internet of things in the industry are various, including various situations such as colleges and universities, high-speed rails, commercial districts and office buildings. Under the mutual influence of various complex application scenes and user service behaviors, due to the fact that the use characteristics of user groups are different, the expressed service characteristics and network indexes are different, and great difficulty is brought to network weak coverage optimization and quality difference recognition mining work.
Currently, operators generally adopt a network index monitoring operation and maintenance mode for the operation and maintenance of the services of the internet of things, and lack of monitoring on the quality of the services, such as abnormal offline of a terminal, failed registration of the terminal, lost connection and the like; the existing means for monitoring the service quality problem is difficult, and involves a plurality of links, which affects the use experience of customers.
The Internet of things relates to multiple links such as a terminal side, a wireless side, a core network side and a platform side, each link has a corresponding monitoring evaluation index, index evaluation means are mutually independent, but each index result has strong correlation, and a set of evaluation method for the overall health degree of the business of the Internet of things is lacked.
In addition, the utilization rate of the internet of things card is low all the time, and needs to evaluate the liveness and the service value of a user urgently, so that a service department can acquire the situation of each industry in time and support service expansion and client development.
Disclosure of Invention
The invention aims to provide an evaluation method and an evaluation device for the operation health degree of the internet of things, which can overcome at least one defect in the prior art.
According to a first aspect of the invention, an evaluation method for operation health of the internet of things is provided, and the evaluation method comprises the following steps:
acquiring operation data from multiple links of the Internet of things;
performing a user perception indicator evaluation based on a first subset of data in the operational data to determine a user perception indicator;
performing a quality of service awareness assessment based on a second subset of data in the operational data to determine a quality of service awareness indicator;
performing a network quality aware evaluation based on a third subset of data in the operational data to determine a network quality aware indicator;
performing multi-index fusion health assessment based on the user perception index, the service quality perception index and the network quality perception index to determine a health assessment index; and
at least one index anomaly of the internet of things is ascertained from the multi-index fusion health assessment, and a root cause analysis based on a root cause propagation model is performed for the at least one index anomaly to determine a poor root cause.
It should be understood that in embodiments of the present invention, the data subsets from the operational data may be independent of each other or may overlap each other. According to the invention, full-process index perception can be realized and the root cause causing poor quality can be screened out favorably.
In some embodiments, "performing multi-index fusion health assessment based on user perception indicators, quality of service perception indicators, and network quality perception indicators" comprises: creating a health regression model based on a locally weighted linear regression method, the health regression model being configured to input a user perception index, a service quality perception index and a network quality perception index, and to output a health assessment index.
In some embodiments, "performing multi-index fusion health assessment based on user perception indicators, quality of service perception indicators, and network quality perception indicators" comprises: and creating a health degree regression model based on a Bayesian regression method, wherein the health degree regression model is configured to input a user perception index, a service quality perception index and a network quality perception index and is configured to output a health degree evaluation index.
In some embodiments, a root propagation model is created based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots, the root propagation model comprising a plurality of nodes and a plurality of connecting lines respectively connected between two nodes, wherein at least a part of the connecting lines are respectively assigned a correlation coefficient as a degree of correlation between two nodes.
In some embodiments, "performing a root cause analysis based on a root cause propagation model for the at least one index anomaly" comprises:
determining a plurality of initial nodes associated with the at least one index anomaly within the root cause propagation model as alarm nodes;
and counting the times of staying on each alarm node respectively finally according to the probability matrix and the forward and backward walking rule, and presuming the node with the maximum staying times as a root node.
In some embodiments, the user perception metric evaluation includes calculating a specific metric for a respective industry for an industry characteristic.
In some embodiments, the service quality aware evaluation is divided into a periodic monitoring reporting class evaluation, an anomaly detection reporting class evaluation, an interactive control class evaluation, an mqtt protocol communication class evaluation according to the service transmission characteristics.
In some embodiments, the network quality-aware evaluation includes a wireless network evaluation, a core network evaluation, and a device management platform evaluation.
In some embodiments, a user traffic operation awareness assessment is performed based on a fourth subset of data in the operation data to determine user traffic operation metrics, the user traffic operation metrics including user online rate, user activity, user decline, and/or traffic value.
In some embodiments, a user breakout model and/or a traffic prediction model is determined based on the user traffic operation awareness assessment.
In some embodiments, multi-index fusion health assessment is performed based on user awareness indicators, quality of service awareness indicators, network quality awareness indicators, and user service operation indicators.
In some embodiments, an internet of things business operation optimization scheme and a user profile are determined based on a multi-index fusion health assessment.
According to a second aspect of the present invention, there is provided an evaluation apparatus for operation health of the internet of things, the evaluation apparatus comprising:
a communication module configured to obtain operational data from a plurality of links of the internet of things;
a storage module configured to store operational data from a plurality of links of the internet of things;
a health assessment module, the health assessment module comprising:
a user perception index evaluation sub-module configured to obtain a first subset of data in the operational data and perform a user perception index evaluation to determine a user perception index;
a service quality perception evaluation sub-module configured to obtain a second subset of data in the operational data and perform a service quality perception evaluation to determine a service quality perception indicator;
a network quality awareness assessment sub-module configured to obtain a third subset of data in the operational data and perform a network quality awareness assessment to determine a network quality awareness indicator;
a multi-index fusion sub-module configured to perform multi-index fusion health assessment based on a user perception index, a service quality perception index, and a network quality perception index to determine a health assessment index;
a root cause analysis module configured to ascertain at least one index anomaly of the internet of things from the multi-index fusion health assessment performed by the multi-index fusion sub-module, and perform a root cause analysis based on a root propagation model for the at least one index anomaly to determine a root cause of the quality.
In some embodiments, the multi-index fusion sub-module is configured to create a health regression model based on a locally weighted linear regression method or a bayesian regression method, the health regression model configured to input a user perception index, a service quality perception index, and a network quality perception index, and configured to output a health assessment index.
In some embodiments, the evaluation device further comprises a root propagation model modeling module configured to create a root propagation model based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots, the root propagation model comprising a plurality of nodes and a plurality of connecting lines respectively connected between two nodes, wherein at least a part of the connecting lines are respectively assigned a correlation coefficient as a degree of correlation between two nodes.
In some embodiments, the root cause of deterioration analysis module is configured to: determining a plurality of initial nodes associated with the at least one index anomaly within the root cause propagation model as alarm nodes.
In some embodiments, according to the probability matrix and the forward and backward walking rule, the number of times of staying at each alarm node is counted, and the node with the largest staying number is estimated as the root node.
In some embodiments, the health assessment module further comprises a user service operation awareness assessment submodule configured to obtain a fourth subset of the operation data and perform a user service operation awareness assessment to determine a user service operation index, the user service operation index comprising a user online rate, a user activity, a user decline, and/or a traffic value.
In some embodiments, the user traffic awareness assessment sub-module is further configured to determine a user breakout model and/or a traffic prediction model based on the user traffic awareness assessment.
In some embodiments, the multi-index fusion sub-module is configured to perform a multi-index fusion health assessment based on the user perception index, the service quality perception index, the network quality perception index, and the user service operation index, and determine an internet of things service operation optimization scheme and a user profile based on the multi-index fusion health assessment.
According to a third aspect of the present invention, there is provided an evaluation apparatus for internet of things operation health, the evaluation apparatus comprising:
a memory configured to store a series of computer-executable instructions; and
a processor configured to execute the series of computer-executable instructions,
wherein the series of computer executable instructions, when executed by a processor, cause the processor to perform a method according to one of the embodiments of the invention.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is an exemplary flow diagram of an assessment method for internet of things operational health, according to some embodiments of the invention;
fig. 2 is an exemplary block diagram of an evaluation device for internet of things operational health in accordance with some embodiments of the present invention;
FIG. 3 presents a first embodiment of a root cause analysis of the quality difference based on a root cause propagation model;
FIG. 4 presents a second embodiment of a root cause analysis of the quality difference based on a root cause propagation model.
Note that in the embodiments described below, the same reference numerals are used in common between different drawings to denote the same portions or portions having the same functions, and a repetitive description thereof will be omitted. In some cases, similar reference numbers and letters are used to denote similar items, and thus, once an item is defined in one figure, it need not be discussed further in subsequent figures.
For convenience of understanding, the positions, sizes, ranges, and the like of the respective structures shown in the drawings and the like do not sometimes indicate actual positions, sizes, ranges, and the like. Therefore, the present invention is not limited to the positions, dimensions, ranges, and the like disclosed in the drawings and the like.
Detailed Description
The present invention will now be described with reference to the accompanying drawings, which illustrate several embodiments of the invention. It should be understood, however, that the present invention may be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein; rather, the embodiments described below are intended to provide a more complete disclosure of the present invention and to fully convey the scope of the invention to those skilled in the art. It is also to be understood that the embodiments disclosed herein can be combined in various ways to provide further additional embodiments.
It is understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to limit the scope of the present invention. All terms (including technical and scientific terms) used herein have the meaning commonly understood by one of ordinary skill in the art unless otherwise defined. Well-known functions or constructions may not be described in detail for brevity and/or clarity.
When an element is referred to herein as being "on," attached to, "" connected to, "coupled to," or "contacting" another element, etc., it can be directly on, attached to, connected to, coupled to or contacting the other element or intervening elements may be present. In contrast, when an element is referred to as being "directly on," "directly attached to," directly connected to, "directly coupled to," or "directly contacting" another element, there are no intervening elements present. In this context, one feature being disposed "adjacent" another feature may refer to one feature having a portion that overlaps or is above or below the adjacent feature.
In this document, reference may be made to elements or nodes or features being "connected" together. Unless expressly stated otherwise, "connected" means that one element/node/feature may be mechanically, electrically, logically, or otherwise joined to another element/node/feature in a direct or indirect manner to allow for interaction, even though the two features may not be directly connected. That is, "connected" is intended to include both direct and indirect joining of elements or other features, including joining using one or more intermediate elements.
Herein, the term "a or B" includes "a and B" and "a or B" rather than exclusively including only "a" or only "B" unless otherwise specifically stated.
In this document, the term "exemplary" means "serving as an example, instance, or illustration," and not as a "model" that is to be reproduced exactly. Any implementation exemplarily described herein is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, there is no intention to be bound by any expressed or implied theory presented in the preceding technical field, background, brief summary or the detailed description.
In this document, the term "substantially" is intended to encompass any minor variations due to design or manufacturing imperfections, tolerances of the devices or components, environmental influences and/or other factors. The term "substantially" also allows for differences from a perfect or ideal situation due to parasitics, noise, and other practical considerations that may exist in a practical implementation.
In addition, "first," "second," and like terms may also be used herein for reference purposes only, and thus are not intended to be limiting. For example, the terms "first," "second," and other such numerical terms referring to structures or elements do not imply a sequence or order unless clearly indicated by the context.
It will be further understood that the terms "comprises/comprising," "includes" and/or "including," when used herein, specify the presence of stated features, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, and/or components, and/or groups thereof.
Specific embodiments according to various aspects of the present invention will be described in detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 illustrates an exemplary flow diagram of an assessment method for internet of things operational health, according to some embodiments of the present invention. The method may comprise the steps of:
step S10: operation data from multiple links of the Internet of things are obtained. Step S10 relates to the collection of raw data for the internet of things. The operational data of each link may include various historical data from each link as well as current data, which may include dpi coach data, s5s8, s6a signaling data, wireless network performance data, platform connection quality data, and the like, for example.
Step S21: performing a user perception indicator evaluation based on a first subset of data in the operational data to determine a user perception indicator.
In the disclosure, the user perception index evaluation may include calculating a dedicated index of a corresponding industry with respect to an industry characteristic, and the corresponding user perception index may be obtained by performing extraction and analysis on log data collected by a platform/network. The user perception indicator may indicate that the user has usedIn the process, the indexes of good and bad services, such as data reporting or activation condition of the terminal of the internet of things, can be intuitively sensed. As an example, the user perception index may relate to meter reading type service (reporting success rate), street lamp type service (first-call street lamp lighting rate). For example, the water meter reports the data of the running words of the water meter to the platform on time, and the reporting success rate is how. For example, after the platform issues the instruction to turn on the street lamp, whether the street lamp receives the instruction and executes successfully or not is determined. Based on the step, the related index value can be obtained
Step S22: performing a quality of service awareness assessment based on a second subset of data in the operational data to determine a quality of service awareness indicator.
The service quality perception evaluation is divided into periodic monitoring reporting evaluation, abnormal detection reporting evaluation, interactive control evaluation and mqtt protocol communication evaluation according to service transmission characteristics.
As an example, the periodic monitoring reporting type evaluation may be for a gas meter terminal to evaluate, for example, an uplink coach service success rate.
As an example, the anomaly detection reporting type evaluation may be for evaluating, for example, an uplink Coap service delay or an uplink Coap service success rate for the smoke-sensitive terminal.
As an example, the interactive control class evaluation may evaluate downlink Coap traffic delay or downlink Coap traffic success rate for the street light switch, for example.
By way of example, MQTT protocol traffic class assessment may assess MQTT traffic build success rate, TCP link build success rate, or TCP build average delay.
Based on the step, the related index value can be obtained
Step S23: performing a network quality aware evaluation based on a third subset of data in the operational data to determine a network quality aware indicator.
The network quality-aware assessment may include a wireless network assessmentEstimation, core network estimation and equipment management platform estimation. In this step, the index status of the network transmission link can be counted. The wireless network may be evaluated, for example, with respect to the following parameters: the success rate of rrc establishment, the average establishment duration of rrc, the utilization rate of uplink and downlink subcarriers, the channel occupancy rate, etc. The core network may be evaluated, for example, with respect to the following parameters: attachment success rate, paging success rate, bearer utilization rate, and the like. The device management platform may be evaluated, for example, with respect to the following parameters: the success rate of northbound push, the number of uplink and downlink messages, the congestion condition and the like. Based on the step, the related index value can be obtained
Step S30: performing multi-index fusion health assessment based on the user perception index, the service quality perception index and the network quality perception index to determine a health assessment index.
A health regression model may be created based on a locally weighted linear regression method or a bayesian regression method in this step. The health regression model may be configured to input a user perception indicator, a quality of service perception indicator, and a network quality perception indicator, and to output a health assessment indicator. As an example, a weighted iterative regression equation may be used as the health regression model:
to complete the multi-index fusion calculation, which includes: user perception index
Service quality perception index
Network quality indicator
And a health score y.
Step S40: at least one index anomaly of the internet of things is ascertained from the multi-index fusion health assessment, and a root cause analysis based on a root cause propagation model is performed for the at least one index anomaly to determine a poor root cause.
In this step, in order to determine root nodes within the root cause propagation model, it is necessary to first determine a plurality of initial nodes within the root cause propagation model associated with the at least one index anomaly as alarm nodes. And then counting the times of respectively staying at each alarm node finally according to the probability matrix and the forward and backward migration rule. And finally, the node with the largest number of stay times is presumed as a root node. In an additional step S42, the quality factor may be output.
The root propagation model may be created based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots. For example, a plurality of historical roots may be collected and connected according to causal relationships, such that the root propagation model comprises a plurality of nodes V and a plurality of connecting lines E each connected between two nodes, wherein at least some of the connecting lines are each associated with a correlation coefficient as a degree of correlation between two nodes. In the root cause propagation model, also called root cause propagation graph G (V, E), for Ei，jE, calculating the Pearson correlation coefficient of two adjacent nodes i and j as the basis for evaluating the correlation degree, wherein the calculation formula is as follows
The probability matrix (which may also be referred to as a state transition matrix) and the forward-backward walking rule are introduced next. The propagation process of the quality differences can be simulated on the basis of a forward and backward propagation process. Definition of pijThe random walk process includes forward walk, backward walk, and origin stop for the probability from node i to node j. Forward propagation: if E is contained in the set Ei,jMeaning that the quality difference may propagate from node j to node i when it occurs, the correlation Si,jThe higher the probability that it propagates, the greater the probability of propagation pij＝Si,j,if ei,j∈E&i is not equal to j; backward propagation: allowing some probability in the propagation process to return to the previous node for ei,jIs E and
when the walker is located at j, the probability formula of backward walking from node j to node i is defined as
The original point stays: and allowing the wandering to stay at the current node according to a certain probability without moving. When the relevance of the node i to the parent node is higher, and the relevance to the child node is lower, the stay probability of the node i is higher, and the probability of the stay of the origin is as follows:
additionally or alternatively, the method for evaluating the operation health degree of the internet of things according to some embodiments of the present invention may further include step S50: performing user service operation perception evaluation based on a fourth data subset in the operation data to determine user service operation indexes, wherein the user service operation indexes comprise user online rate, user activity, user decline and/or flow value; and determining a user sudden drop model and/or a traffic prediction model based on the user traffic operation perception assessment.
Additionally or alternatively, performing multi-index fusion health assessment based on the user perception index, the service quality perception index, the network quality perception index and the user service operation index may also be included in step S30. Additionally or alternatively, the method for evaluating the operation health degree of the internet of things according to some embodiments of the present invention may further include step S60: and determining an Internet of things service operation optimization scheme and a user portrait based on multi-index fusion health degree evaluation.
The steps of the methods presented above are intended to be illustrative. In some embodiments, the method may be performed with one or more additional undescribed steps, and/or without one or more of the discussed steps. Further, the order in which the steps of a method are illustrated in the figures and described below is not intended to be limiting.
In some embodiments, the methods may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information). One or more processing devices may include one or more modules that perform some or all of the steps of the methods in response to instructions stored electronically on an electronic storage medium. The one or more processing modules may include one or more devices configured through hardware, firmware, and/or software designed specifically for execution of one or more steps of the method.
The method may be performed by an evaluation device according to the present disclosure, e.g. a server. Referring to fig. 2, an exemplary block diagram of an evaluation apparatus 100 for internet of things operational health is shown, according to some embodiments of the present invention. The evaluation device 100 may include a communication module 10 that may be configured to obtain operational data from multiple links of the internet of things. The evaluation device 100 may comprise a memory 21 in which the operational data may be stored, and may further be provided with a memory 22 configured to store a series of computer executable instructions; and a processor 30 configured to execute the series of computer-executable instructions, wherein the series of computer-executable instructions, when executed by the processor, cause the processor to perform the steps of the method.
With continued reference to fig. 2, the evaluation device 100, in particular the processor 30, may comprise a plurality of functional modules, which are functionally differentiated only, without strict limitations as to physical location. Some of the functional modules may constitute a single processor, while other functional modules may constitute another single processor. As shown in fig. 2, there is a health assessment module 40, which includes: a user perception index evaluation sub-module 41 configured to obtain a first subset of data in the operational data and perform a user perception index evaluation to determine a user perception index; a quality of service awareness evaluation sub-module 42 configured to obtain a second subset of data in the operational data and perform a quality of service awareness evaluation to determine a quality of service awareness indicator; a network quality aware evaluation sub-module 43 configured to obtain a third subset of data in the operational data and perform a network quality aware evaluation to determine a network quality aware indicator; a multi-index fusion sub-module 35 configured to perform a multi-index fusion health assessment based on the user perception index, the service quality perception index, and the network quality perception index to determine a health assessment index. Further, there is also a poor-quality root cause analysis module 36 configured to ascertain at least one index anomaly of the internet of things from the multi-index fusion health assessment performed by the multi-index fusion sub-module, and perform a poor-quality root cause analysis based on a root cause propagation model for the at least one index anomaly to determine a poor-quality root cause.
Additionally or alternatively, the multi-index fusion sub-module 35 is configured to create a health degree regression model based on a locally weighted linear regression method or a bayesian regression method, the health degree regression model being configured to input a user perception index, a service quality perception index and a network quality perception index, and to output a health degree evaluation index.
Additionally or alternatively, the evaluation device further comprises a root propagation model modeling module 36 configured to create a root propagation model based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots, the root propagation model comprising a plurality of nodes and a plurality of connection lines respectively connected between two nodes, wherein at least a part of the connection lines are respectively assigned correlation coefficients as a degree of correlation between two nodes.
Additionally or alternatively, the root cause of quality analysis module 36 is configured to: determining a plurality of initial nodes associated with the at least one index anomaly within the root cause propagation model as alarm nodes; and counting the times of staying on each alarm node respectively finally according to the probability matrix and the forward and backward walking rule, and presuming the node with the maximum staying times as a root node.
Additionally or alternatively, the health assessment module 40 further comprises a user service operation awareness assessment sub-module 44 configured to obtain a fourth subset of the operation data and perform a user service operation awareness assessment to determine a user service operation index, the user service operation index comprising a user online rate, a user activity, a user decline, and/or a traffic value; and is
The user traffic awareness assessment sub-module 44 is further configured to determine a user breakout model and/or a traffic prediction model based on the user traffic awareness assessment.
Additionally or alternatively, the multi-index fusion sub-module 35 is configured to perform a multi-index fusion health assessment based on the user perception index, the service quality perception index, the network quality perception index and the user service operation index, and determine an internet of things service operation optimization scheme and a user profile based on the multi-index fusion health assessment.
FIG. 3 presents a first embodiment of a root cause analysis of the quality difference based on a root cause propagation model. As shown, is a typical single-terminal poor quality case. In the current embodiment, a service scenario is that a terminal fails, a single-terminal service rate is low due to frequent failure, and service data cannot be reported to a platform, and a cell quality is poor due to the fact that the number of repeated failures is large and the success rate of cell service is reduced. In the figure, the direction of the inter-root arrow is a causal relationship summarized according to business knowledge and expert experience, and when the two nodes are connected in two directions and no arrow indicates that the two nodes are causal to each other. The numbers in the connection may represent correlation coefficients. The grey part of the graph is the node where the alarm occurs (called alarm node), and the root cause of the abnormality needs to be found from the grey part (i.e. the dark grey box is the root cause node). In the current embodiment, "randomly assign N propagators" means that N nodes are designated, and the initial positions of the nodes are randomly assigned to the alarm nodes in gray in the graph. Then, based on the probability matrix mentioned above and the forward and backward walking rule of the present disclosure, the number of the nodes on which the n nodes stay respectively is calculated, the number of times that each node stays finally is counted, and the node that stays the most is positioned as a root node.
FIG. 4 presents a second embodiment of a root cause analysis of the quality difference based on a root cause propagation model. As shown, poor quality for a typical cell network results in a group failure case. In the current embodiment, the service scenario is that the quality of the access network of the wireless network cell is poor, which causes alarms such as network access failure and service uploading failure of terminals in the cell. And in the same type as the example, n nodes are specified, and the initial positions of the nodes are randomly distributed to the alarm nodes in gray in the graph. Then, based on the probability matrix mentioned above and the forward and backward walking rule of the present disclosure, the number of the nodes on which the n nodes stay respectively is calculated, the number of times that each node stays finally is counted, and the node that stays the most is positioned as a root node.
The application has at least one of the following technical effects:
and (4) full-process index sensing, namely on the basis of the traditional network operation and maintenance indexes, a health degree evaluation algorithm not only adds a general service sensing index, but also adds a special industry-oriented sensing index by combining product characteristics.
And (3) cross-professional intelligent positioning and section fixing: and screening out the root cause of the quality difference by adopting a quality difference root cause positioning method based on multi-index abnormal propagation simulation. The link can not only effectively reduce the labor cost; and the influence level and the responsibility subject of the quality difference can be determined, and theoretical support is provided for the professional cooperative guarantee.
Although some specific embodiments of the present invention have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for the purpose of illustration and is not intended to limit the scope of the invention. The various embodiments disclosed herein may be combined in any combination without departing from the spirit and scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (14)
1. An assessment method for operation health of the Internet of things is characterized by comprising the following steps:
acquiring operation data from multiple links of the Internet of things;
performing a user perception indicator evaluation based on a first subset of data in the operational data to determine a user perception indicator;
performing a quality of service awareness assessment based on a second subset of data in the operational data to determine a quality of service awareness indicator;
performing a network quality aware evaluation based on a third subset of data in the operational data to determine a network quality aware indicator;
performing multi-index fusion health assessment based on the user perception index, the service quality perception index and the network quality perception index to determine a health assessment index; and
at least one index anomaly of the internet of things is ascertained from the multi-index fusion health assessment, and a root cause analysis based on a root cause propagation model is performed for the at least one index anomaly to determine a poor root cause.
2. The assessment method according to claim 1, wherein "performing multi-index fusion health assessment based on user perception indicators, service quality perception indicators and network quality perception indicators" comprises:
creating a health degree regression model based on a locally weighted linear regression method or a Bayesian regression method, the health degree regression model being configured to input a user perception index, a service quality perception index, and a network quality perception index, and to output a health degree evaluation index.
3. The evaluation method according to claim 1, wherein a root propagation model is created based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots, the root propagation model comprising a plurality of nodes and a plurality of connecting lines respectively connected between two nodes, wherein at least a part of the connecting lines are respectively assigned with correlation coefficients as degrees of correlation between two nodes.
4. The evaluation method according to claim 3, wherein performing a root cause analysis based on a root cause propagation model for the at least one index anomaly comprises:
determining a plurality of initial nodes associated with the at least one index anomaly within the root cause propagation model as alarm nodes;
and counting the times of staying on each alarm node respectively finally according to the probability matrix and the forward and backward walking rule, and presuming the node with the maximum staying times as a root node.
5. The evaluation method according to claim 1,
the user perception index evaluation comprises the steps of calculating special indexes of corresponding industries aiming at the characteristics of the industries;
the service quality perception evaluation is divided into periodic monitoring reporting evaluation, abnormal detection reporting evaluation, interactive control evaluation and mqtt protocol communication evaluation according to service transmission characteristics;
the network quality perception evaluation comprises wireless network evaluation, core network evaluation and equipment management platform evaluation.
6. The evaluation method according to claim 1,
performing user service operation perception evaluation based on a fourth data subset in the operation data to determine user service operation indexes, wherein the user service operation indexes comprise user online rate, user activity, user decline and/or flow value;
and determining a user sudden drop model and/or a service prediction model based on the user service operation perception evaluation.
7. The evaluation method according to claim 6,
performing multi-index fusion health assessment based on the user perception index, the service quality perception index, the network quality perception index and the user service operation index; and
and determining an Internet of things service operation optimization scheme and a user portrait based on multi-index fusion health degree evaluation.
8. An assessment device for the operation health degree of the Internet of things, which is characterized by comprising:
a communication module configured to obtain operational data from a plurality of links of the internet of things;
a storage module configured to store operational data from a plurality of links of the internet of things;
a health assessment module, the health assessment module comprising:
a user perception index evaluation sub-module configured to obtain a first subset of data in the operational data and perform a user perception index evaluation to determine a user perception index;
a service quality perception evaluation sub-module configured to obtain a second subset of data in the operational data and perform a service quality perception evaluation to determine a service quality perception indicator;
a network quality awareness assessment sub-module configured to obtain a third subset of data in the operational data and perform a network quality awareness assessment to determine a network quality awareness indicator;
a multi-index fusion sub-module configured to perform multi-index fusion health assessment based on a user perception index, a service quality perception index, and a network quality perception index to determine a health assessment index;
a root cause analysis module configured to ascertain at least one index anomaly of the internet of things from the multi-index fusion health assessment performed by the multi-index fusion sub-module, and perform a root cause analysis based on a root propagation model for the at least one index anomaly to determine a root cause of the quality.
9. The evaluation apparatus of claim 8, wherein the multi-index fusion sub-module is configured to create a health regression model based on a locally weighted linear regression method or a bayesian regression method, wherein the health regression model is configured to input a user perception index, a service quality perception index and a network quality perception index, and configured to output a health evaluation index.
10. The evaluation device of claim 8, further comprising a root propagation model modeling module configured to create a root propagation model based on a plurality of historical roots and a plurality of causal connections assigned to the plurality of historical roots, the root propagation model comprising a plurality of nodes and a plurality of connecting lines respectively connected between two nodes, wherein at least a portion of the connecting lines are respectively assigned correlation coefficients as a degree of correlation between two nodes.
11. The evaluation device of claim 10, wherein the quality factor analysis module is configured to: determining a plurality of initial nodes associated with the at least one index anomaly within the root cause propagation model as alarm nodes; and counting the times of staying on each alarm node respectively finally according to the probability matrix and the forward and backward walking rule, and presuming the node with the maximum staying times as a root node.
12. The evaluation apparatus of claim 8, wherein the health evaluation module further comprises a user service operation awareness evaluation submodule configured to obtain a fourth subset of the operation data and perform a user service operation awareness evaluation to determine a user service operation index, wherein the user service operation index comprises a user online rate, a user activity, a user decline and/or a traffic value; and is
The user service operation awareness evaluation sub-module is further configured to determine a user sudden drop model and/or a service prediction model based on the user service operation awareness evaluation.
13. The evaluation device of claim 12, wherein the multi-index fusion sub-module is configured to perform a multi-index fusion health evaluation based on a user perception index, a service quality perception index, a network quality perception index, and a user service operation index, and determine an internet of things service operation optimization scheme based on the multi-index fusion health evaluation.
14. An assessment device for the operation health degree of the Internet of things, which is characterized by comprising:
a memory configured to store a series of computer-executable instructions; and
a processor configured to execute the series of computer-executable instructions,
wherein the series of computer-executable instructions, when executed by a processor, cause the processor to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111643078.1A CN114338424A (en) | 2021-12-29 | 2021-12-29 | Evaluation method and evaluation device for operation health degree of Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111643078.1A CN114338424A (en) | 2021-12-29 | 2021-12-29 | Evaluation method and evaluation device for operation health degree of Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114338424A true CN114338424A (en) | 2022-04-12 |
Family
ID=81016677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111643078.1A Pending CN114338424A (en) | 2021-12-29 | 2021-12-29 | Evaluation method and evaluation device for operation health degree of Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114338424A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115065584A (en) * | 2022-07-05 | 2022-09-16 | 中国电信股份有限公司 | Internet of things quality difference processing method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102761889A (en) * | 2011-04-25 | 2012-10-31 | 中国移动通信集团广东有限公司 | Method and system for evaluating wireless network structure |
| US20170201897A1 (en) * | 2016-01-08 | 2017-07-13 | Futurewei Technologies, Inc. | Fingerprinting root cause analysis in cellular systems |
| CN111092786A (en) * | 2019-12-12 | 2020-05-01 | 中盈优创资讯科技有限公司 | Network equipment safety authentication service reliability enhancing system |
| CN112162907A (en) * | 2020-09-30 | 2021-01-01 | 上海新炬网络信息技术股份有限公司 | Health degree evaluation method based on monitoring index data |
| CN113766444A (en) * | 2021-09-23 | 2021-12-07 | 中国联合网络通信集团有限公司 | Fault positioning method, device and equipment |
-
2021
- 2021-12-29 CN CN202111643078.1A patent/CN114338424A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102761889A (en) * | 2011-04-25 | 2012-10-31 | 中国移动通信集团广东有限公司 | Method and system for evaluating wireless network structure |
| US20170201897A1 (en) * | 2016-01-08 | 2017-07-13 | Futurewei Technologies, Inc. | Fingerprinting root cause analysis in cellular systems |
| CN111092786A (en) * | 2019-12-12 | 2020-05-01 | 中盈优创资讯科技有限公司 | Network equipment safety authentication service reliability enhancing system |
| CN112162907A (en) * | 2020-09-30 | 2021-01-01 | 上海新炬网络信息技术股份有限公司 | Health degree evaluation method based on monitoring index data |
| CN113766444A (en) * | 2021-09-23 | 2021-12-07 | 中国联合网络通信集团有限公司 | Fault positioning method, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 王燕: "基于用户感知与业务特征的电信网络性能监控与检测模型研究", 《中国博士学位论文全文数据库 经济与管理科学辑》, 15 February 2019 (2019-02-15), pages 97 - 105 * |
| 赵龙刚等: "基于行为画像的物联网业务保障方法", 《电信科学》, no. 5, 31 May 2021 (2021-05-31), pages 52 - 63 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115065584A (en) * | 2022-07-05 | 2022-09-16 | 中国电信股份有限公司 | Internet of things quality difference processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109787817B (en) | Network fault diagnosis method, device and computer readable storage medium | |
| US10805174B2 (en) | Using machine learning to monitor link quality and predict link faults | |
| US9571334B2 (en) | Systems and methods for correlating alarms in a network | |
| CN112187514A (en) | Intelligent operation and maintenance system, method and terminal for data center network equipment | |
| CN105325023A (en) | Method and network device for cell anomaly detection | |
| CN113254254B (en) | Root cause positioning method and device of system fault, storage medium and electronic device | |
| US20230250924A1 (en) | Methods for pipeline network inspection zone generation based on smart gas and internet of things systems thereof | |
| CN101420714A (en) | Method for scheduling indicator for collecting key performance from communication network | |
| CN112953738B (en) | Root cause alarm positioning system, method and device and computer equipment | |
| CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN114338424A (en) | Evaluation method and evaluation device for operation health degree of Internet of things | |
| CN111106899B (en) | Data verification method and device in Internet of things, computer equipment and storage medium | |
| JPWO2019116418A1 (en) | Fault analyzer, fault analysis method and fault analysis program | |
| CN110647417B (en) | Energy internet abnormal data processing method, device and system | |
| US20150213415A1 (en) | System and method for providing adaptive measurement and coordinated maintenance of outdoor lighting systems | |
| Tootaghaj et al. | Network recovery from massive failures under uncertain knowledge of damages | |
| CN111078503B (en) | Abnormality monitoring method and system | |
| US20060224537A1 (en) | Device for optimizing diagnostic trees of a diagnostic tool of a communication network | |
| CN116582414A (en) | Fault root cause positioning method, device, equipment and readable storage medium | |
| JP7173273B2 (en) | Failure analysis device, failure analysis method and failure analysis program | |
| CN115903720A (en) | Fault diagnosis system and method for rail transit, and storage medium | |
| CN117880055B (en) | Network fault diagnosis method, device, equipment and medium based on transmission layer index | |
| US20220103454A1 (en) | Data inspection system for inspecting operating situations of multiple iot devices in a plurality of target iot systems | |
| EP4369674A1 (en) | Method and apparatus for anomaly detection | |
| US20240171505A1 (en) | Predicting impending change to Interior Gateway Protocol (IGP) metrics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |