CN110505196A - Internet of Things network interface card method for detecting abnormality and device - Google Patents
Internet of Things network interface card method for detecting abnormality and device Download PDFInfo
- Publication number
- CN110505196A CN110505196A CN201910591205.4A CN201910591205A CN110505196A CN 110505196 A CN110505196 A CN 110505196A CN 201910591205 A CN201910591205 A CN 201910591205A CN 110505196 A CN110505196 A CN 110505196A
- Authority
- CN
- China
- Prior art keywords
- internet
- classification results
- network interface
- interface card
- things network
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Environmental & Geological Engineering (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the present invention discloses a kind of Internet of Things network interface card method for detecting abnormality and device, is related to field of communication technology, for solving the technical problem that Internet of Things network interface card abnormality detection result accuracy is relatively low in the prior art.This method comprises: obtaining the business scenario information of Internet of Things network interface card to be detected;The corresponding behavioral data of business scenario information is obtained, and is obtained for handling the goal rule algorithm of behavioral data under business scenario information, detection Internet of Things card is treated according to goal rule algorithm and behavioral data and is classified, classification results are obtained;Wherein classification results include: normal or abnormal;Determine whether Internet of Things network interface card to be detected is abnormal according to classification results.The embodiment of the present invention is for carrying out abnormality detection Internet of Things card.
Description
Technical field
The present embodiments relate to fields of communication technology, and in particular to a kind of Internet of Things network interface card method for detecting abnormality and device.
Background technique
Internet of Things be related to life each field, such as transport and logistics field, field of industrial manufacturing, health medical treatment field,
Intelligent environment (family, office, factory) field etc..Internet of Things network interface card is the Internet of Things client that operator is only oriented to enterprise customer's offer
Identification module (subscriber identity module, SIM) card.Internet of Things network interface card is based on Internet of Things private network, using Internet of Things
Exclusive number section supports the Base communications services such as short message, wireless data communication, voice by dedicated network element device, and provides communication
The intelligent channels service such as condition managing and communication authentication, while default opens the dedicated short message access service number of Internet of Things and Internet of Things
Netcom is with access points (Access Point, AP).Since the process of exchange of Internet of Things network interface card is difficult to supervise, lead to a large amount of Internet of Things
Network interface card is illegally used, and a large amount of Internet resources are illegally occupied and wasted, and many losses is caused to operator, for above-mentioned presence
The problem of, carrying out effective abnormality detection to Internet of Things card is particularly important.
Currently, the abnormality detection of Internet of Things network interface card is determined according to the attribute information of Internet of Things network interface card and behavioural information
The Internet of Things network interface card of abnormality, however in actual conditions, that there are accuracys is inclined for the classification results obtained using above-mentioned detection mode
Low problem.
Summary of the invention
The embodiment of the present invention provides a kind of Internet of Things network interface card method for detecting abnormality and device, for solving Internet of Things in the prior art
The relatively low technical problem of network interface card anomaly classification result accuracy.
In a first aspect, providing a kind of Internet of Things network interface card method for detecting abnormality, comprising:
Obtain the business scenario information of Internet of Things network interface card to be detected;The corresponding behavioral data of business scenario information is obtained, and
It obtains for handling the goal rule algorithm of behavioral data under business scenario information, according to goal rule algorithm and behavioral data
It treats detection Internet of Things card to classify, obtains classification results;Wherein classification results include: normal or abnormal;According to classification
As a result determine whether Internet of Things network interface card to be detected is abnormal.
It, can be according to the business where Internet of Things network interface card in Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention
Scene information obtains corresponding behavioral data and goal rule algorithm, then according to goal rule algorithm and behavioral data pair
Internet of Things card to be detected carries out normal or anomaly classification, obtains classification results, finally determines object to be detected according to classification results
Whether networking card is abnormal.It can be seen that the embodiment of the present invention can by Internet of Things network interface card abnormality detection and practical business combination of shape and state,
Business datum under different business scene is selected with targetedly recognition rule, Internet of Things card is carried out abnormality detection, to have
Effect improves Internet of Things network interface card anomaly classification result accuracy.
Second aspect provides a kind of Internet of Things network interface card abnormal detector, comprising:
Module is obtained, for obtaining the business scenario information of Internet of Things network interface card to be detected;
Processing module, the corresponding behavioral data of business scenario information obtained for obtaining above-mentioned acquisition module, and obtain
It takes for handling the goal rule algorithm of behavioral data under business scenario information, according to goal rule algorithm and behavioral data pair
Internet of Things card to be detected is classified, and classification results are obtained;Wherein classification results include: normal or abnormal;
Determining module, the classification results for being obtained according to processing module determine whether Internet of Things network interface card to be detected is abnormal.
The third aspect provides a kind of Internet of Things network interface card abnormal detector, comprising: one or more processors;Processor is used
In executing the computer program code in memory, computer program code includes instruction, Internet of Things network interface card abnormality detection is filled
Set the Internet of Things network interface card method for detecting abnormality for executing above-mentioned first aspect.
Fourth aspect provides a kind of storage medium, and storage medium is stored with instruction code, and instruction code is for executing as above
State the Internet of Things network interface card method for detecting abnormality of first aspect.
5th aspect provides a kind of computer program product, and computer program product includes instruction code, and instruction code is used
In the Internet of Things network interface card method for detecting abnormality for executing such as above-mentioned first aspect.
It is to be appreciated that Internet of Things network interface card abnormal detector, storage medium and the computer product of above-mentioned offer are used for
The corresponding method of first aspect presented above is executed, therefore, the attainable beneficial effect of institute can refer to first party above
The beneficial effect of corresponding scheme in the method and following detailed description in face, details are not described herein again.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, the drawings are only for the purpose of illustrating a preferred embodiment, and is not to be construed as limiting the invention.
Fig. 1 shows a kind of method flow diagram of Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention;
Fig. 2 shows a kind of method flow diagrams of Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention;
Fig. 3 shows a kind of method flow diagram of Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention;
Fig. 4 shows a kind of method flow diagram of Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention;
Fig. 5 shows a kind of functional block diagram of Internet of Things network interface card abnormal detector provided in an embodiment of the present invention;
Fig. 6 shows a kind of functional block diagram of Internet of Things network interface card abnormal detector provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.The use of term " first " and " second " etc. does not indicate any sequence, can be by above-mentioned art
Language is construed to the title of described object.In embodiments of the present invention, " illustrative " or " such as " etc. words for indicate make
Example, illustration or explanation.Be described as in the embodiment of the present invention " illustrative " or " such as " any embodiment or design
Scheme is not necessarily to be construed as than other embodiments or design scheme more preferably or more advantage.Specifically, it uses " exemplary
" or " such as " etc. words be intended to that related notion is presented in specific ways.
Before introducing the embodiment of the present invention, simply it is situated between to Internet of Things abnormality detection mode in the prior art first
It continues.Currently, existing Internet of Things abnormality detection mode is all the attribute information and behavioural information by obtaining Internet of Things network interface card, then
Classified according to the attribute information of Internet of Things network interface card of the same trade and behavioural information to Internet of Things card, to determine normal condition Internet of Things
Card and abnormality Internet of Things network interface card.In actual conditions, since Internet of Things application scenarios are extensive, all trades and professions emerge magnanimity
Application scenarios, such as car networking, intelligent electric meter, smart city, intelligent transportation etc..To time delay, rate, stream under every kind of application scenarios
The requirement of many kinds of parameters such as amount, standby time, bandwidth is different, is both that different application scene is also possible to because of above-mentioned parameter
Difference selects different access technologies.Such as it is applied to the energy and the utility intelligent electric meter business of tap water, can preferentially selects
It is narrow to select narrowband Internet of Things (narrow band internet of things, NB-IoT) this new generation based on cellular network
Band Internet of Things transmission technology, because it has wide covering, low-power consumption, low cost, the signal outstanding features such as by force.It is particularly suitable for as remote
This low frequency of journey meter reading, the data transmission applications scene of fixed cycle;The for another example unmanned application scenarios of car networking, for when
Prolong, speed etc. has high requirement, so needing to be deployed in the net of the 5th third-generation mobile communication technology (5-generation, 5G)
Under network scene, etc..It can be seen that the business form can have significant difference when business scenario difference.At present to Internet of Things network interface card
When carrying out abnormality detection, above-mentioned business scenario difference is not considered, lead to the accuracy rate of current Internet of Things network interface card abnormal behaviour identification
It is relatively low.
Based on above-mentioned problem, the embodiment of the present invention provides a kind of Internet of Things network interface card method for detecting abnormality, referring to Fig. 1 institute
Show, includes the following steps:
Step S110: the business scenario information of Internet of Things network interface card to be detected is obtained.
Step S120: obtaining the corresponding behavioral data of business scenario information, and obtains under business scenario information for locating
The goal rule algorithm for managing behavioral data is treated detection Internet of Things card according to goal rule algorithm and behavioral data and is divided
Class obtains classification results;Wherein classification results include: normal or abnormal.
Step S130: determine whether Internet of Things network interface card to be detected is abnormal according to classification results.
It, can be according to the business where Internet of Things network interface card in Internet of Things network interface card method for detecting abnormality provided in an embodiment of the present invention
Scene information obtains behavioral data and goal rule algorithm, and the classification knot of behavioral data is then obtained according to goal rule algorithm
Fruit finally determines whether Internet of Things network interface card to be detected is abnormal according to classification results.It can be seen that the embodiment of the present invention can be by Internet of Things
Network interface card abnormality detection and practical business combination of shape and state, selecting to business datum under different business scene, there is targetedly identification to advise
Then Internet of Things card is carried out abnormality detection, to effectively improve Internet of Things network interface card anomaly classification result accuracy.
Internet of Things network interface card method for detecting abnormality provided by the invention is carried out below by following three specific embodiment detailed
It introduces.
Fig. 2 shows the embodiment of the present invention to provide a kind of Internet of Things network interface card method for detecting abnormality, shown in Figure 2, including such as
Lower step:
Step S210: the business scenario information of Internet of Things network interface card to be detected is obtained.
Specifically, business scenario information can be information relevant to the business scenario that Internet of Things network interface card is applied, such as enterprise
Mark, service identification etc..In specific implementation, the acquisition modes of business scenario information can be by those skilled in the art according to reality
Situation is configured, and this is not limited by the present invention.In specific implementation, in a preferred embodiment, business scenario information can be with
It include: enterprise's mark.
Step S220: obtaining the corresponding behavioral data of business scenario information, and obtains the corresponding use of business scenario information
In the goal rule algorithm of processing behavioral data.
Specifically, obtain behavioral data mode can there are many, such as can be disposed in the preset interface of network side
Correspondent probe is acquired network side data information relevant to business scenario information by above-mentioned probe, such as connect from S1-MME
Data relevant to signaling on mouth in terms of acquisition and recording Internet of Things signaling connection;It obtains record user from S6a interface and contracts and believe
The data of the relevant informations such as breath, roaming information;Building about carrying information is acquired from S5/S8-C interface and Gn-C interface
Vertical or modification or the related data deleted or the related data or public affairs of foundation or modification or deletion about session information
With data network (Public Data Network, PDN) establishment of connection or deletion etc. number relevant to Internet of Things network performance
According to;From data relevant to service feature index such as S5/S8-U interface, Gn-U interface acquisition security information, flow informations, from enterprise
The numbers related to user such as enterprise customers' data such as metering data, industry attribute data are obtained on the internet of things equipment of industry user
According to;Or can also from base station side obtain base station network engineering parameter (such as Location Area Code (location area code,
LAC), cell identification (Cell Identity, CI), base station longitude and base station latitude etc.);Or it can also be believed by geography
Breath system (Geographic Information System, GIS) obtains relevant geographical location information of business scenario etc..
Specifically, in embodiments of the present invention, behavioral data is divided into historical behavior data and real-time behavioral data.It is real
When the data that use online of behavioral data, that is, internet of things equipment, real-time behavioral data completes to use online on internet of things equipment
Afterwards, real-time behavioral data becomes as historical behavior data.
In the present embodiment, obtaining the corresponding behavioral data of business scenario information may include: to obtain business scenario information
Corresponding historical behavior data.Then obtain that business scenario information is corresponding can for handling the goal rule algorithm of behavioral data
To include: to obtain the corresponding goal rule function of business scenario information from preset rules function as handling historical behavior
The goal rule algorithm of data.
It describes in detail below to above-mentioned preset rules function.Specifically, preset rules function may include: at least one
Kind operating characteristic Value Types and operation rule.Wherein, above-mentioned operation rule is used for above-mentioned at least one operating characteristic value class
The characteristic value of type carries out operation, to obtain corresponding operation result.In specific implementation, above-mentioned operation result can be used to indicate that object
Networking card use state is normal or Internet of Things network interface card use state is abnormal, therefore operation result specifically may include two not
Same result value: the first result value and the second result value.Wherein the first result value presentation class result is normal,
Second result value presentation class result is abnormal.In specific implementation, the first result value and the second result value can be by these
Field technical staff is configured according to the actual situation, and this is not limited by the present invention.Wherein, in a preferred embodiment,
One result value is 0, and the second result value is 1.
In specific implementation, preset rules function can be indicated using following formula:
Y1=f (x1, x2..., xn);
Wherein, y1 is operation result, and function f is above-mentioned operation rule, xnFor the feature of n operating characteristic Value Types
Value;Wherein n is natural number and n >=1.
In embodiments of the present invention, the type of preset rules function may include following any: end message rule letter
Number, flow rule function, type of service and flow rules function and numbers match rule function.It is understood that different
At least one operating characteristic Value Types and its operation rule for including in the preset rules function of type are different.
Each type of preset rules function mentioned above is introduced below.Specifically, end message rule letter
Number can be the preset rules function formulated for the end message of internet-of-things terminal, in specific implementation, end message rule letter
Number may include following operating characteristic Value Types: terminal brand, terminal type and terminal models etc. and terminal device information phase
The information of pass;The operation rule of end message rule function can be the logical relation of above-mentioned each feature Value Types and user equipment
Function.For example: if the user of Internet of Things network interface card to be detected is enterprise A, and the terminal brand of the internet-of-things terminal equipment of enterprise A is
Brand a, terminal type is type b, if then the operation relation of end message rule function may include: the terminal of internet-of-things terminal
Brand is brand a and terminal type is type b, then normal (that is: Internet of Things network interface card use state is normal), otherwise abnormal (that is: object
Card use state of networking is abnormal).
Flow rule function can be the preset rules function for the formulation of the flow information of internet-of-things terminal.Specific implementation
In, flow rule function may include following operating characteristic Value Types: flow package upper limit value, actual flow makes in the assessment time
Relevant information is used to the flow of internet-of-things terminal with total amount, the super threshold value of flow etc.;The operation rule of flow rule function
It can be the logical relation function for above-mentioned each feature Value Types setting.If for example: the operation in flow rule function
Feature Value Types include: flow package upper limit value, actual flow is using total amount and the super threshold value of flow in the assessment time, then
The operation rule of flow rule function can be with are as follows: if in the assessment time actual flow using total amount be greater than flow package upper limit value and
Assessing actual flow in the time uses the difference of total amount and flow package upper limit value to be greater than the super threshold value of flow, then abnormal (that is: Internet of Things
Network interface card use state is abnormal), otherwise normal (that is: Internet of Things network interface card use state is normal).
Type of service and flow rules function can be for the type of service of internet-of-things terminal and presetting for process formulation
Rule function.In specific implementation, type of service and flow rules function may include following operating characteristic Value Types: user identifier
The information relevant to type of service and process such as information and type of service procedure information;Wherein, user identity information can wrap
Include enterprise's mark or internet-of-things terminal mark;Type of service procedure information may include: type of service or operation flow;Industry
The operation rule of service type and flow rules function can be the logical relation function for above-mentioned each feature Value Types setting.It lifts
Example explanation, if the enterprise of enterprise B is identified as c, it only includes intelligent electric meter meter reading business that enterprise B, which provides type of service, then enterprise B
The operation rule of type of service and flow rules function can be with are as follows: if enterprise is identified as c and type of service only includes intelligent electric meter
Meter reading business, then normal (that is: Internet of Things network interface card use state is normal), otherwise abnormal (that is: Internet of Things network interface card use state is different
Often).
Numbers match rule function can be for for internet-of-things terminal and the one-to-one binding relationship formulation of Internet of Things network interface card
Preset rules function.In specific implementation, numbers match rule function may include following operating characteristic Value Types: Internet of Things network interface card moves
Dynamic platform international member identification code (mobile subscriber international ISDN (integrated service
Digital network, ISDN)/PSTN (public switched telephone network, public friendship
Change telephone network) number, MSISDN) and terminal international mobile equipment identification number (international mobile
Equipment identity, IMEI);Then the operation rule of numbers match rule function can be for for above-mentioned each characteristic value class
The logical relation function of type setting.For example, if enterprise C when registering Internet of Things network interface card, terminal IMEI is d, Internet of Things network interface card
MSISDN is e, then the operation rule of numbers match rule function can be with are as follows: if the terminal IMEI of e binding is d, normally (i.e.:
Internet of Things network interface card use state is normal), it is otherwise abnormal (that is: Internet of Things network interface card use state is abnormal).In specific implementation, work as Internet of Things
After network interface card is sold to enterprise, the binding relationship of internet-of-things terminal and Internet of Things network interface card is stored in enterprise database, numbers match rule
Then the operation rule of function can be generated according to the binding relationship of internet-of-things terminal in enterprise database and Internet of Things network interface card.
The rule function that peels off is for the pre- of the operating characteristic Value Types formulation in internet-of-things terminal with multiple characteristic values
If rule function, wherein multiple characteristic values of above-mentioned operating characteristic Value Types include: m1, m2...mn, the rule function that peels off is used for
Whether determine in above-mentioned multiple characteristic values comprising exceptional value, and according to definitive result determine Internet of Things network interface card use state be it is normal or
Person's Internet of Things network interface card use state is abnormal.In specific implementation, the operation rule for the rule function that peels off is specifically as follows: ifThen abnormal (that is: Internet of Things network interface card use state is abnormal), otherwise normal (that is: Internet of Things network interface card use state is
Normally);Wherein, o be natural number and n >=o >=0,For m1, m2…mnAverage after removing outlier,For m1, m2…mnIt goes
Average deviation after falling outlier, wherein above-mentioned outlier can be mmaxOr mmin;mmaxFor m1, m2...mnMiddle maximum value,
mminFor m1, m2…mnMiddle minimum value.
It is, of course, understood that the operating characteristic value class that above-mentioned cited all types of preset rules functions are included
Type and operation relation are only exemplary, in specific implementation, operating characteristic value class that all types of preset rules functions include
Type and operation relation can be configured according to the actual situation by those skilled in the art, and the embodiment of the present invention does not limit this
It is fixed.
In specific implementation, the first corresponding relationship of pre-set business scene information Yu preset rules function can be preset,
It then in this step, can be according to above-mentioned first corresponding relationship in the corresponding goal rule function of acquisition business scenario information
Obtain business scenario information in the first corresponding relationship corresponding preset rules function as goal rule function.Of course, it is possible to
Understand, the mode of the above-mentioned corresponding goal rule function of acquisition business scenario information enumerated is only exemplary, and is had
During body is implemented, the present invention is not construed as limiting the mode for obtaining the corresponding goal rule function of business scenario information.
Step S230: every kind of operating characteristic Value Types corresponding spy in historical behavior data in goal rule function is obtained
Value indicative.
Specifically, the acquisition modes of features described above value can be configured according to the actual situation by those skilled in the art,
This is not limited by the present invention.
Step S240: operation is carried out to characteristic value according to operation rule, the first classification results are determined according to operation result.
Specifically, if operation result is the first result value, it is determined that the first classification results are normal, if operation result is
Second result value, it is determined that the first classification results are abnormal.
Step S250: determine whether Internet of Things network interface card to be detected is abnormal according to the first classification results.
Specifically, if the first classification results are abnormal, it is determined that Internet of Things network interface card to be detected is abnormal;If the first classification results
It is normal, it is determined that Internet of Things network interface card to be detected is positive often.
Fig. 3 shows the embodiment of the present invention and provides a kind of Internet of Things network interface card method for detecting abnormality, shown in Figure 3, including such as
Lower step:
Step S310: the business scenario information of Internet of Things network interface card to be detected is obtained.
The executive mode of this step is identical as step S210, specifically may refer to the corresponding description in step S210, herein
It repeats no more.
Step S320: obtaining the corresponding behavioral data of business scenario information, and obtains the corresponding use of business scenario information
In the goal rule algorithm of processing behavioral data.
Specifically, in the present embodiment, behavioral data may include: real-time behavioral data.Obtain business scenario information pair
That answers is used to handle the goal rule algorithm of behavioral data, comprising: it is corresponding that business scenario information is obtained from default detection model
Target detection model as the goal rule algorithm for handling real-time behavioral data.Wherein, real-time behavioral data can join
See the corresponding description in step S220, details are not described herein again.
Wherein, default detection model can be by sample of the historical behavior data of pre-set business scene information according to default
The model that machine learning algorithm obtains, the output result for presetting detection model includes third result value and the 4th number of results
Value, wherein third result value presentation class result is normal, and the 4th result value presentation class result is abnormal.Above-mentioned machine
Learning algorithm can be configured according to the actual situation by those skilled in the art, for example, by using K- means clustering algorithm etc., originally
Inventive embodiments are not construed as limiting this.Third result value and the 4th result value can be by those skilled in the art according to reality
Border situation is configured, and this is not limited by the present invention.Wherein, in a kind of preferably scheme, third result value is 0, the
Four result values are 1.It is highly preferred that third result value can be identical as the first result value, the 4th result value can be with
Second result value is identical.
It, can historical behavior data according to pre-set business scene information and default machine learning algorithm in specific implementation
The corresponding default detection model of pre-set business scene information is obtained, and between default detection model and pre-set business scene information
The second corresponding relationship is established, then in this step, business scenario information can be obtained according to above-mentioned second corresponding relationship second
Corresponding default detection model is as target detection model in corresponding relationship.It is, of course, understood that the above-mentioned acquisition enumerated
The mode of the corresponding target detection model of business scenario information is only exemplary, and in specific implementation, the present invention is to acquisition industry
The mode of the corresponding target detection model of business scene information is not construed as limiting.
Step S330: inputting target detection model for real-time behavioral data, true according to the output result of target detection model
Fixed second classification results.
Specifically, if output result is third result value, it is determined that the second classification results are normal;If operation result is
4th result value, it is determined that the second classification results are abnormal.
Step S340: determine whether Internet of Things network interface card to be detected is abnormal according to the second classification results.
Specifically, if the second classification results are abnormal, it is determined that Internet of Things network interface card to be detected is abnormal;If the second classification results
It is normal, it is determined that Internet of Things network interface card to be detected is positive often.
Wherein, in the present embodiment, in order to guarantee the accuracy of target detection model, according to pre-set business scene information
Historical behavior data and before default machine learning algorithm obtains the corresponding default detection model of pre-set business scene information,
It can also further determine that whether the sampled point quantity of historical behavior data is greater than default sampled point amount threshold, if historical behavior
The sampled point quantity of data is greater than default sampled point amount threshold, then obtains business scenario information according to above-mentioned second corresponding relationship
Corresponding default detection model is as target detection model and executes step S330 and step S340;If historical behavior data
Sampled point quantity is less than or equal to default sampled point amount threshold, it is determined that target detection model is not present, to show business
The historical behavior data of scene information do not find that Internet of Things card is abnormal, then can directly determine Internet of Things network interface card to be detected and be positive
Often, then it is normal that step S330, which can directly determine output result,.Wherein, presetting sampled point amount threshold can be by this field skill
Art personnel are configured according to the actual situation, and the embodiment of the present invention is not construed as limiting this.
Fig. 4 shows the embodiment of the present invention and provides a kind of Internet of Things network interface card method for detecting abnormality, shown in Figure 4, including such as
Lower step:
Step S410: the business scenario information of Internet of Things network interface card to be detected is obtained.
The executive mode of this step is identical as step S210, specifically may refer to the corresponding description in step S210, herein
It repeats no more.
Step S420: obtaining the corresponding behavioral data of business scenario information, and obtains the corresponding use of business scenario information
In the goal rule algorithm of processing behavioral data.
Specifically, in the present embodiment, behavioral data may include: historical behavior data and real-time behavioral data.Then
It is corresponding for handling the goal rule algorithm of behavioral data to obtain business scenario information, comprising: obtain from preset rules function
Take the corresponding goal rule function of business scenario information as goal rule algorithm, the Yi Jicong for handling historical behavior data
The corresponding target detection model of business scenario information is obtained in default detection model as the mesh for handling real-time behavioral data
Mark rule-based algorithm.
Wherein, historical behavior data, real-time behavioral data, preset rules function and its acquisition modes may refer to step
Corresponding description in S220, details are not described herein again.
Default detection model is by sample of the historical behavior data of pre-set business scene information according to default machine learning
Algorithm obtains;The output result of default detection model includes the 5th result value and the 6th result value, wherein the 5th result
Numerical value indicate classification results be it is normal, the 6th result value presentation class result for extremely.In the present embodiment, by real-time behavior
Data input target detection model, obtain the output result of target detection model as third classification results.In specific implementation, the
Five result values are equal to the third result value in S320, and the 6th result value is equal to the 4th result value in S320,
Default detection model and its acquisition modes may refer to the corresponding description in step S320, and details are not described herein again.
Step S430: detection Internet of Things card is treated according to goal rule algorithm and behavioral data and is classified, obtains and divides
Class result.
Wherein, classification results may include: normal or abnormal.In the present embodiment, when behavioral data is historical behavior
When data, goal rule algorithm corresponds to goal rule function, then in this step, obtains every kind of operation in goal rule function
Feature Value Types corresponding characteristic value in historical behavior data, then according to the operation rule of goal rule function to above-mentioned spy
Value indicative carries out operation, using operation result as the first classification results.Wherein, the acquisition modes of the first classification results may refer to
The corresponding description in step S230 and step S240 is stated, details are not described herein again.When behavioral data is real-time behavioral data, mesh
Mark rule-based algorithm corresponds to target detection model, then real-time behavioral data can be inputted target detection model, obtain target inspection
The output result of model is surveyed as third classification results.Wherein, the acquisition modes phase of third classification results and the second classification results
Together, it specifically may refer to the corresponding description of the above-mentioned acquisition modes about the second classification results, details are not described herein again.
Step S440: obtaining the corresponding first classification results operation values of the first classification results and third classification results are corresponding
Third classification results operation values.
Specifically, before executing this step, the corresponding operation values of classification results can be preset, when classification results are
Normally, the operation values that classification results are arranged are the first operation values;When classification results are exception, the operation values that classification results are arranged are
Second operation values.For example, the first operation values can be 0, the second operation values can be 1;Alternatively, the first operation values can be 1, the
Two operation values can be 0.In specific implementation, as long as can be used in distinguishing to the corresponding operation values of classification results setting different
Classification results, and operation is carried out to classification results.In this step, the is obtained according to the corresponding operation values of above-mentioned classification results
The corresponding first classification results operation values of one classification results, and third point is obtained according to the corresponding operation values of above-mentioned classification results
The corresponding third classification results operation values of class result.
Step S450: being weighted processing to the first classification results operation values and third classification results operation values, obtains
Corresponding first weighted results of first classification results operation values and corresponding second weighting of acquisition third classification results operation values
As a result.
Specifically, corresponding first weight of the first classification results and third point can be set according to business scenario information
Corresponding second weight of class result, then obtain the product of the first classification results and the first weight as the first weighted results, with
And the product of third classification results and the second weight is obtained as the second weighted results.In specific implementation, be arranged the first weight with
And second the mode of weight can be configured according to the actual situation by those skilled in the art, the embodiment of the present invention does not make this
It limits.
Step S460: summing to the first weighted results and the second weighted results, obtains summed result.
Step S470: determine whether Internet of Things network interface card to be detected is abnormal according to summed result.
Specifically, it can be determined that whether the first operation values are greater than the second operation values, if the first operation values are greater than the second operation
Value, then judge whether summed result is greater than preset threshold, if the determination result is YES, it is determined that Internet of Things network interface card to be detected is exception,
If judging result is no, it is determined that Internet of Things network interface card to be detected is positive often.If the first operation values are asked less than the second operation values, judgement
Whether it is less than or equal to preset threshold with result, if the determination result is YES, it is determined that Internet of Things network interface card to be detected is abnormal, if judging
It as a result is no, it is determined that Internet of Things network interface card to be detected is positive often.
Wherein, above-mentioned preset threshold can be configured according to the actual situation by those skilled in the art, and the present invention is to this
It is not construed as limiting.
It further, in the present embodiment, can also be according to determination after the determination result for obtaining Internet of Things network interface card to be detected
As a result goal rule algorithm is modified, such as according to definitive result re -training goal rule function and target detection mould
Type, to effectively improve the accuracy of goal rule function and target detection model.
The embodiment of the present invention also provides a kind of Internet of Things network interface card abnormal detector, it is to be understood that the embodiment of the present invention
The Internet of Things network interface card abnormal detector of offer is each it comprises executing for realizing the corresponding function in above method embodiment
The corresponding hardware configuration of function and/or software module.Those skilled in the art should be readily appreciated that, public in conjunction with institute herein
Each exemplary algorithm steps for the embodiment description opened, the present invention can be with the combining form of hardware or hardware and computer software
To realize.Some functions is executed in a manner of hardware or computer software driving hardware actually, depending on technical solution
Specific application and design constraint.Professional technician can to each specific application come using distinct methods to realize
The function of description, but such implementation should not be considered as beyond the scope of the present invention.
The embodiment of the present invention can carry out functional module to Internet of Things network interface card abnormal detector according to above method embodiment
Division two or more functions can also be integrated for example, each functional module of each function division can be corresponded to
In a processing module.Above-mentioned integrated module both can take the form of hardware realization, can also use software function mould
The form of block is realized.It should be noted that being schematical, only a kind of logic to the division of module in the embodiment of the present invention
Function division, there may be another division manner in actual implementation.
In the case where each function division of use correspondence each functional module, Fig. 5 shows in the embodiment of the present invention and relates to
And Internet of Things network interface card abnormal detector illustrative view of functional configuration, Internet of Things network interface card abnormal detector be specifically used for implement it is above-mentioned
The corresponding embodiment of the method for Fig. 1-Fig. 4, Internet of Things network interface card abnormal detector for individual equipment or can be integrated in Internet of Things
In equipment.As shown in figure 5, Internet of Things network interface card abnormal detector, comprising:
Module 51 is obtained, for obtaining the business scenario information of Internet of Things network interface card to be detected.
Processing module 52, the corresponding behavioral data of business scenario information obtained for obtaining above-mentioned acquisition module 51, with
And it obtains for handling the goal rule algorithm of behavioral data under business scenario information, according to goal rule algorithm and behavior number
Classify according to detection Internet of Things card is treated, obtains classification results;Wherein classification results include: normal or abnormal.
Determining module 53, the classification results for being obtained according to processing module 52 determine whether Internet of Things network interface card to be detected is different
Often.
Optionally, behavioral data includes: historical behavior data;Then processing module 52 is specifically used for:
The corresponding goal rule function of business scenario information is obtained from preset rules function to be used as handling history row
For the goal rule algorithm of data;Wherein preset rules function meets following formula:
Y1=f (x1, x2..., xn);
Wherein, y1 is operation result, and f is operation rule, xnFor the characteristic value of n operating characteristic Value Types;Wherein n is
Natural number and n are more than or equal to 1;
Obtain every kind of operating characteristic Value Types corresponding characteristic value in historical behavior data in goal rule function;
Operation is carried out to characteristic value according to operation rule, the first classification results are determined according to operation result;Wherein, operation knot
Fruit includes the first result value and the second result value, and the first result value presentation class result is normal, the second number of results
It is abnormal for being worth presentation class result.
Optionally it is determined that module 53 is specifically used for: determining whether Internet of Things network interface card to be detected is abnormal according to the first classification results.
Optionally, behavioral data includes: real-time behavioral data;Then processing module 52 is specifically used for:
The corresponding target detection model of business scenario information is obtained from default detection model to be used as handling real-time row
For the goal rule algorithm of data;Wherein, presetting detection model is using the historical behavior data of pre-set business scene information as sample
This basis is preset machine learning algorithm and is obtained;The output result of default detection model includes third result value and the 4th result
Numerical value, third result value presentation class result be it is normal, the 4th result value presentation class result is abnormal;By real-time behavior
Data input target detection model, obtain the output result of target detection model as the second classification results;
Then determining module 53 is specifically used for: determining whether Internet of Things network interface card to be detected is abnormal according to the second classification results.
Optionally, behavioral data includes: historical behavior data and real-time behavioral data;
Processing module 52 is further used on the basis of obtaining the first classification results:
The corresponding target detection model of business scenario information is obtained from default detection model to be used as handling real-time row
For the goal rule algorithm of data;Wherein, presetting detection model is using the historical behavior data of pre-set business scene information as sample
This basis is preset machine learning algorithm and is obtained;The output result of default detection model includes the 5th result value and the 6th result
Numerical value, the 5th result value presentation class result be it is normal, the 6th result value presentation class result is abnormal;By real-time behavior
Data input target detection model, obtain the output result of target detection model as third classification results;
Determining module 53 is specifically used for: it is first point corresponding to obtain the first classification results according to default classification results operation values
Class result operation values and the corresponding third classification results operation values of third classification results;To the first classification results operation values and
Third classification results operation values are weighted processing, obtain corresponding first weighted results of the first classification results operation values and obtain
Take corresponding second weighted results of third classification results operation values;It sums, obtains to the first weighted results and the second weighted results
Take summed result;Determine whether Internet of Things network interface card to be detected is abnormal according to summed result.
Optionally, preset rules function includes any one of following: end message rule function, flow rule function, business
Type and flow rules function, numbers match rule function and the rule function that peels off.
Optionally, Internet of Things network interface card abnormal detector further include: correction module 54 is used for:
The determination of the Internet of Things network interface card to be detected obtained in determining module 53 is obtained as a result, according to definitive result to goal rule
Algorithm is modified.
All related contents for each step that above method embodiment is related to can quote the function of corresponding function module
It can describe, details are not described herein for effect.
Using integrated module, Internet of Things network interface card abnormal detector include: storage unit, processing unit with
And interface unit.Processing unit is used for the processing movement to Internet of Things network interface card abnormal detector and carries out control management, for example, processing
Unit is for supporting Internet of Things card abnormal detector to execute each step in Fig. 1-Fig. 4.Interface unit is different for Internet of Things network interface card
The interaction of normal detection device and other devices;Storage unit, for storing Internet of Things network interface card abnormal detector code and data.
Wherein, using processing unit as processor, storage unit is memory, and interface unit is for communication interface.Wherein,
Internet of Things network interface card abnormal detector referring to fig. 6, including communication interface 601, processor 602, memory 603 and bus
604, communication interface 601, processor 602 are connected by bus 604 with memory 603.
Processor 602 can be a general central processor (Central Processing Unit, CPU), micro process
Device, application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC) or one or more
A integrated circuit executed for controlling application scheme program.
Memory 603 can be read-only memory (Read-Only Memory, ROM) or can store static information and instruction
Other kinds of static storage device, random access memory (Random Access Memory, RAM) or letter can be stored
The other kinds of dynamic memory of breath and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory (Electrically
Erasable Programmable Read-only Memory, EEPROM), CD-ROM (Compact Disc Read-
Only Memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, optical disc, digital universal
Optical disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carrying or store to have referring to
Enable or data structure form desired program code and can by any other medium of computer access, but not limited to this.
Memory, which can be, to be individually present, and is connected by bus with processor.Memory can also be integrated with processor.
Wherein, memory 603 is used to store the application code for executing application scheme, and is controlled by processor 602
System executes.Communication interface 601 is used to support the interaction of Internet of Things card abnormal detector Yu other devices.Processor 602 is used for
The application code stored in memory 603 is executed, to realize the method in the embodiment of the present invention.
The step of method in conjunction with described in the disclosure of invention or algorithm can realize in a manner of hardware, can also
It is realized in a manner of being to execute software instruction by processor.The embodiment of the present invention also provides a kind of storage medium, which is situated between
Matter may include memory, and for being stored as computer software instructions used in Internet of Things network interface card abnormal detector, it includes hold
Program code designed by row Internet of Things network interface card method for detecting abnormality.Specifically, software instruction can be by corresponding software module group
At software module can be stored on random access memory (Random Access Memory, RAM), flash memory, read-only storage
Device (Read Only Memory, ROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable ROM,
EPROM), Electrically Erasable Programmable Read-Only Memory (Electrically EPROM, EEPROM), register, hard disk, movement are hard
In the storage medium of disk, CD-ROM (CD-ROM) or any other form well known in the art.A kind of illustrative storage
Medium couples to enable a processor to from the read information, and can be written to the storage medium and believe to processor
Breath.Certainly, storage medium is also possible to the component part of processor.
The embodiment of the present invention also provides a kind of computer program, which can be loaded directly into memory, and
Containing software code, which is loaded into via computer and can be realized above-mentioned Internet of Things network interface card abnormality detection after executing
Method.
Those skilled in the art are it will be appreciated that in said one or multiple examples, function described in the invention
It can be realized with hardware, software, firmware or their any combination.It when implemented in software, can be by these functions
Storage in computer-readable medium or as on computer-readable medium one or more instructions or code transmitted.
Computer-readable medium includes computer storage media and communication media, and wherein communication media includes convenient for from a place to another
Any medium of one place transmission computer program.Storage medium can be general or specialized computer can access it is any
Usable medium.
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those skilled in the art, should all cover
Within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (16)
1. a kind of Internet of Things network interface card method for detecting abnormality characterized by comprising
Obtain the business scenario information of Internet of Things network interface card to be detected;
The corresponding behavioral data of the business scenario information is obtained, and is obtained described for handling under the business scenario information
The goal rule algorithm of behavioral data, according to the goal rule algorithm and the behavioral data to the Internet of Things to be detected
Card is classified, and classification results are obtained;Wherein the classification results include: normal or abnormal;
Determine whether the Internet of Things network interface card to be detected is abnormal according to the classification results.
2. Internet of Things network interface card method for detecting abnormality according to claim 1, which is characterized in that described to obtain the business scenario
The corresponding behavioral data of information, comprising:
Obtain the corresponding historical behavior data of the business scenario information;
It is then described to obtain the corresponding goal rule algorithm for being used to handle the behavioral data of the business scenario information, according to institute
It states goal rule algorithm and the behavioral data to classify to the Internet of Things card to be detected, obtains classification results, comprising:
The corresponding goal rule function of the business scenario information is obtained from preset rules function to be used as handling described go through
The goal rule algorithm of history behavioral data;Wherein the preset rules function meets following formula:
Y1=f (x1, x2.., xn);
Wherein, y1 is operation result, and f is operation rule, xnFor the characteristic value of n operating characteristic Value Types;Wherein n is nature
It counts and n is more than or equal to 1;
Obtain every kind of operating characteristic Value Types corresponding spy in the historical behavior data in the goal rule function
Value indicative;
Operation is carried out to the characteristic value according to the operation rule, the first classification results are determined according to operation result;Wherein, institute
Stating operation result includes the first result value and the second result value, and first result value indicates that the classification results are
Normally, second result value indicates that the classification results are abnormal.
3. Internet of Things network interface card method for detecting abnormality according to claim 2, which is characterized in that described according to the classification results
Determine whether the Internet of Things network interface card to be detected is abnormal, comprising: determine the Internet of Things to be detected according to first classification results
Whether card is abnormal.
4. Internet of Things network interface card method for detecting abnormality according to claim 1, which is characterized in that described to obtain the business scenario
The corresponding behavioral data of information, comprising:
Obtain the corresponding real-time behavioral data of the business scenario information;
It is then described to obtain the corresponding goal rule algorithm for being used to handle the behavioral data of the business scenario information, according to institute
It states goal rule algorithm and the behavioral data to classify to the Internet of Things card to be detected, obtains classification results, comprising:
The corresponding target detection model of the business scenario information is obtained from default detection model to be used as handling the reality
When behavioral data goal rule algorithm;Wherein, the default detection model is with the historical behavior of pre-set business scene information
Data are that sample is obtained according to default machine learning algorithm;The output result of the default detection model includes third result value
And the 4th result value;Wherein the third result value indicates that the classification results are normal, the 4th result value
Indicate that the classification results are abnormal;
The real-time behavioral data is inputted into the target detection model, obtains the output result conduct of the target detection model
Second classification results;
It is described to determine whether the Internet of Things network interface card to be detected is abnormal according to the classification results, comprising: according to second classification
As a result determine whether the Internet of Things network interface card to be detected is abnormal.
5. Internet of Things network interface card method for detecting abnormality according to claim 2, which is characterized in that the behavioral data further include:
Real-time behavioral data;
It is described to obtain the corresponding goal rule algorithm for being used to handle the behavioral data of the business scenario information, according to described
Goal rule algorithm and the behavioral data classify to the Internet of Things card to be detected, obtain classification results, further includes:
The corresponding target detection model of the business scenario information is obtained from default detection model to be used as handling the reality
When behavioral data goal rule algorithm;Wherein, the default detection model is with the historical behavior of pre-set business scene information
Data are that sample is obtained according to default machine learning algorithm;The output result of the default detection model includes the 5th result value
And the 6th result value, wherein the 5th result value indicates that the classification results are normal;6th result value
Indicate that the classification results are abnormal;The real-time behavioral data is inputted into the target detection model, obtains the target inspection
The output result of model is surveyed as third classification results;
It is described to determine whether the Internet of Things network interface card to be detected is abnormal according to the classification results, comprising: according to default classification results
Operation values obtain the corresponding first classification results operation values of the first classification results and the corresponding third classification of third classification results
As a result operation values;Processing is weighted to the first classification results operation values and the third classification results operation values, is obtained
It takes corresponding first weighted results of the first classification results operation values and obtains third classification results operation values corresponding second and add
Weigh result;It sums to first weighted results and second weighted results, obtains summed result;It is tied according to the summation
Fruit determines whether the Internet of Things network interface card to be detected is abnormal.
6. according to Internet of Things network interface card method for detecting abnormality described in Claims 2 or 3 or 5, which is characterized in that the preset rules letter
Number includes any one of following: end message rule function, flow rule function, type of service and flow rules function, number
With rule function and the rule function that peels off.
7. Internet of Things network interface card method for detecting abnormality according to claim 5, which is characterized in that it is characterized in that, the basis
The classification results determine the Internet of Things network interface card to be detected whether after exception, the method also includes:
The determination of the Internet of Things network interface card to be detected is obtained as a result, repairing according to the definitive result to the goal rule algorithm
Just.
8. a kind of Internet of Things network interface card abnormal detector characterized by comprising
Module is obtained, for obtaining the business scenario information of Internet of Things network interface card to be detected;
Processing module, the corresponding behavioral data of the business scenario information obtained for obtaining the acquisition module, and obtain
Take for handling the goal rule algorithm of the behavioral data under the business scenario information, according to the goal rule algorithm with
And the behavioral data classifies to the Internet of Things card to be detected, obtains classification results;Wherein the classification results include:
It is normal or abnormal;
Whether determining module, the classification results for being obtained according to the processing module determine the Internet of Things network interface card to be detected
It is abnormal.
9. Internet of Things network interface card abnormal detector according to claim 8, which is characterized in that the processing module is specifically used
In:
Obtain the corresponding historical behavior data of the business scenario information;
The corresponding goal rule function of the business scenario information is obtained from preset rules function to be used as handling described go through
The goal rule algorithm of history behavioral data;Wherein the preset rules function meets following formula:
Y1=f (x1, x2..., xn);
Wherein, y1 is operation result, and f is operation rule, xnFor the characteristic value of n operating characteristic Value Types;Wherein n is nature
Number and n >=1;
Obtain every kind of operating characteristic Value Types corresponding spy in the historical behavior data in the goal rule function
Value indicative;
Operation is carried out to the characteristic value according to the operation rule, the first classification results are determined according to operation result;Wherein, institute
Stating operation result includes the first result value and the second result value, and first result value indicates that the classification results are
Normally, second result value indicates that the classification results are abnormal.
10. Internet of Things network interface card abnormal detector according to claim 9, which is characterized in that the determining module is specifically used
In: determine whether the Internet of Things network interface card to be detected is abnormal according to first classification results.
11. Internet of Things network interface card abnormal detector according to claim 8, which is characterized in that the processing module is specifically used
In:
Obtain the corresponding real-time behavioral data of the business scenario information;
The corresponding target detection model of the business scenario information is obtained from default detection model to be used as handling the reality
When behavioral data goal rule algorithm;Wherein, the default detection model is with the historical behavior of pre-set business scene information
Data are that sample is obtained according to default machine learning algorithm;The output result of the default detection model includes third result value
And the 4th result value;The third result value indicates that the classification results are normal, the 4th result value expression
The classification results are abnormal;The real-time behavioral data is inputted into the target detection model, obtains the target detection mould
The output result of type is as the second classification results;
The determining module is specifically used for: determining whether the Internet of Things network interface card to be detected is abnormal according to second classification results.
12. Internet of Things network interface card abnormal detector according to claim 9, which is characterized in that the processing module is further
For:
Obtain the corresponding real-time behavioral data of the business scenario information;
The corresponding target detection model of the business scenario information is obtained from default detection model to be used as handling the reality
When behavioral data goal rule algorithm;Wherein, the default detection model is with the historical behavior of pre-set business scene information
Data are that sample is obtained according to default machine learning algorithm;The output result of the default detection model includes the 5th result value
And the 6th result value, the 5th result value indicate that the classification results be normal, the 6th result value expression
The classification results are abnormal;The real-time behavioral data is inputted into the target detection model, obtains the target detection mould
The output result of type is as third classification results;
The determining module is specifically used for: obtaining corresponding first classification of the first classification results according to default classification results operation values
As a result operation values and the corresponding third classification results operation values of third classification results;To the first classification results operation values with
And the third classification results operation values are weighted processing, obtain corresponding first weighted results of the first classification results operation values
And obtain corresponding second weighted results of third classification results operation values;First weighted results and described second are added
Result summation is weighed, summed result is obtained;Determine whether the Internet of Things network interface card to be detected is abnormal according to the summed result.
13. Internet of Things network interface card abnormal detector according to claim 12, which is characterized in that it is characterized in that, the dress
It sets further include: correction module is used for:
The determination for the Internet of Things network interface card to be detected that the determining module obtains is obtained as a result, according to the definitive result to the target
Rule-based algorithm is modified.
14. a kind of Internet of Things network interface card abnormal detector characterized by comprising one or more processors;The processor is used
In executing the computer program code in memory, computer program code includes instruction, terminal device is made to execute such as right
It is required that the described in any item Internet of Things network interface card method for detecting abnormality of 1-7.
15. a kind of storage medium, which is characterized in that the storage medium is stored with instruction code, and described instruction code is for holding
Row such as the described in any item Internet of Things network interface card method for detecting abnormality of claim 1-7.
16. a kind of computer program product, which is characterized in that the computer program product includes instruction code, described instruction
Code is for executing such as the described in any item Internet of Things network interface card method for detecting abnormality of claim 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910591205.4A CN110505196B (en) | 2019-07-02 | 2019-07-02 | Internet of things network card abnormality detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910591205.4A CN110505196B (en) | 2019-07-02 | 2019-07-02 | Internet of things network card abnormality detection method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110505196A true CN110505196A (en) | 2019-11-26 |
CN110505196B CN110505196B (en) | 2021-08-31 |
Family
ID=68585930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910591205.4A Active CN110505196B (en) | 2019-07-02 | 2019-07-02 | Internet of things network card abnormality detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110505196B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110933698A (en) * | 2019-11-28 | 2020-03-27 | 广州助蜂网络科技有限公司 | Monitoring management method, device and equipment for Internet of things card |
CN110995745A (en) * | 2019-12-17 | 2020-04-10 | 武汉绿色网络信息服务有限责任公司 | Method and device for separating and identifying illegal machine card of Internet of things |
CN111263349A (en) * | 2019-12-12 | 2020-06-09 | 深圳市麦谷科技有限公司 | Automatic diagnosis and recovery method and system for abnormal session of wireless networking equipment |
CN111476375A (en) * | 2020-03-30 | 2020-07-31 | 中移动信息技术有限公司 | Method and device for determining recognition model, electronic equipment and storage medium |
CN111752936A (en) * | 2020-06-30 | 2020-10-09 | 中国科学院西北生态环境资源研究院 | Data detection management method, device, server and readable storage medium |
CN113139817A (en) * | 2021-04-28 | 2021-07-20 | 北京沃东天骏信息技术有限公司 | Data classification method, data classification device, medium, and electronic apparatus |
CN113537387A (en) * | 2021-08-04 | 2021-10-22 | 北京思特奇信息技术股份有限公司 | Model design method and device for Internet online operation activities and computer equipment |
CN113536066A (en) * | 2021-07-16 | 2021-10-22 | 全球能源互联网研究院有限公司 | Data anomaly detection algorithm determination method and device and computer equipment |
CN113766462A (en) * | 2020-06-03 | 2021-12-07 | ***通信集团重庆有限公司 | Internet of things card management method and device and computing equipment |
CN113923037A (en) * | 2021-10-18 | 2022-01-11 | 北京八分量信息科技有限公司 | Credible computing-based anomaly detection optimization device, method and system |
CN114143734A (en) * | 2021-10-22 | 2022-03-04 | 广东省电信规划设计院有限公司 | Data processing method and device for 5G Internet of things network card flow acquisition |
CN114143227A (en) * | 2021-10-25 | 2022-03-04 | 国网山西省电力公司阳泉供电公司 | Internet of things card abnormal state monitoring and early warning method |
CN114168632A (en) * | 2021-12-07 | 2022-03-11 | 泰康保险集团股份有限公司 | Abnormal data identification method and device, electronic equipment and storage medium |
WO2022057501A1 (en) * | 2020-09-16 | 2022-03-24 | 中兴通讯股份有限公司 | Method for identifying abnormal terminal, analysis apparatus and device, and storage medium |
CN114422619A (en) * | 2020-10-12 | 2022-04-29 | ***通信集团广东有限公司 | Service identification method, device, equipment and storage medium |
CN114640606A (en) * | 2020-12-01 | 2022-06-17 | 中移物联网有限公司 | Abnormity processing method and controller for Internet of things card terminal |
CN115002198A (en) * | 2022-05-23 | 2022-09-02 | 支付宝(杭州)信息技术有限公司 | Information processing method, device, equipment and medium for Internet of things equipment |
CN116016230A (en) * | 2022-12-26 | 2023-04-25 | 山东有人物联网股份有限公司 | Multi-type service processing method and device for Internet of things network card, electronic equipment and medium |
CN117056594A (en) * | 2023-07-31 | 2023-11-14 | 中移互联网有限公司 | User identification method and device based on interaction relationship and electronic equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104753733A (en) * | 2013-12-31 | 2015-07-01 | 中兴通讯股份有限公司 | Method and device for detecting abnormal network traffic data |
CN107968730A (en) * | 2016-10-19 | 2018-04-27 | 中国电信股份有限公司 | The method and system that monitoring Internet of Things network interface card is stolen |
CN108270727A (en) * | 2016-12-30 | 2018-07-10 | 北京国双科技有限公司 | Abnormal data analysis method and device |
US20180232031A1 (en) * | 2017-02-15 | 2018-08-16 | Dell Products, L.P. | Safeguard and recovery of internet of things (iot) devices from power anomalies |
CN108632097A (en) * | 2018-05-14 | 2018-10-09 | 平安科技(深圳)有限公司 | Recognition methods, terminal device and the medium of abnormal behaviour object |
CN108768765A (en) * | 2018-05-11 | 2018-11-06 | 中国联合网络通信集团有限公司 | Abnormality Internet of Things network interface card checking method, device and computer readable storage medium |
CN108777866A (en) * | 2018-03-29 | 2018-11-09 | 中国联合网络通信集团有限公司 | A kind of network analysis method, server and network system |
WO2019024645A1 (en) * | 2017-08-03 | 2019-02-07 | 华为技术有限公司 | Charging method and device |
CN109842628A (en) * | 2018-12-13 | 2019-06-04 | 成都亚信网络安全产业技术研究院有限公司 | A kind of anomaly detection method and device |
CN109951491A (en) * | 2019-03-28 | 2019-06-28 | 腾讯科技(深圳)有限公司 | Network attack detecting method, device, equipment and storage medium |
-
2019
- 2019-07-02 CN CN201910591205.4A patent/CN110505196B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104753733A (en) * | 2013-12-31 | 2015-07-01 | 中兴通讯股份有限公司 | Method and device for detecting abnormal network traffic data |
CN107968730A (en) * | 2016-10-19 | 2018-04-27 | 中国电信股份有限公司 | The method and system that monitoring Internet of Things network interface card is stolen |
CN108270727A (en) * | 2016-12-30 | 2018-07-10 | 北京国双科技有限公司 | Abnormal data analysis method and device |
US20180232031A1 (en) * | 2017-02-15 | 2018-08-16 | Dell Products, L.P. | Safeguard and recovery of internet of things (iot) devices from power anomalies |
WO2019024645A1 (en) * | 2017-08-03 | 2019-02-07 | 华为技术有限公司 | Charging method and device |
CN108777866A (en) * | 2018-03-29 | 2018-11-09 | 中国联合网络通信集团有限公司 | A kind of network analysis method, server and network system |
CN108768765A (en) * | 2018-05-11 | 2018-11-06 | 中国联合网络通信集团有限公司 | Abnormality Internet of Things network interface card checking method, device and computer readable storage medium |
CN108632097A (en) * | 2018-05-14 | 2018-10-09 | 平安科技(深圳)有限公司 | Recognition methods, terminal device and the medium of abnormal behaviour object |
CN109842628A (en) * | 2018-12-13 | 2019-06-04 | 成都亚信网络安全产业技术研究院有限公司 | A kind of anomaly detection method and device |
CN109951491A (en) * | 2019-03-28 | 2019-06-28 | 腾讯科技(深圳)有限公司 | Network attack detecting method, device, equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
G. SARANYA、G. GEETHA、M. SAFA: ""E-Antenatal assistance care using decision tree analytics and cluster analytics based supervised machine learning"", 《2017 INTERNATIONAL CONFERENCE ON IOT AND APPLICATION (ICIOT)》 * |
赵俊、刘浩明、王伟杰: ""物联网卡业务运营风险监控***的研究"", 《电信工程技术与标准化》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110933698A (en) * | 2019-11-28 | 2020-03-27 | 广州助蜂网络科技有限公司 | Monitoring management method, device and equipment for Internet of things card |
CN111263349A (en) * | 2019-12-12 | 2020-06-09 | 深圳市麦谷科技有限公司 | Automatic diagnosis and recovery method and system for abnormal session of wireless networking equipment |
CN111263349B (en) * | 2019-12-12 | 2022-06-28 | 深圳市麦谷科技有限公司 | Automatic diagnosis and recovery method and system for abnormal session of wireless networking equipment |
CN110995745B (en) * | 2019-12-17 | 2021-09-21 | 武汉绿色网络信息服务有限责任公司 | Method and device for separating and identifying illegal machine card of Internet of things |
CN110995745A (en) * | 2019-12-17 | 2020-04-10 | 武汉绿色网络信息服务有限责任公司 | Method and device for separating and identifying illegal machine card of Internet of things |
CN111476375A (en) * | 2020-03-30 | 2020-07-31 | 中移动信息技术有限公司 | Method and device for determining recognition model, electronic equipment and storage medium |
CN111476375B (en) * | 2020-03-30 | 2023-09-19 | 中移动信息技术有限公司 | Method and device for determining identification model, electronic equipment and storage medium |
CN113766462A (en) * | 2020-06-03 | 2021-12-07 | ***通信集团重庆有限公司 | Internet of things card management method and device and computing equipment |
CN111752936A (en) * | 2020-06-30 | 2020-10-09 | 中国科学院西北生态环境资源研究院 | Data detection management method, device, server and readable storage medium |
CN111752936B (en) * | 2020-06-30 | 2024-04-26 | 中国科学院西北生态环境资源研究院 | Data detection management method, device, server and readable storage medium |
WO2022057501A1 (en) * | 2020-09-16 | 2022-03-24 | 中兴通讯股份有限公司 | Method for identifying abnormal terminal, analysis apparatus and device, and storage medium |
CN114422619B (en) * | 2020-10-12 | 2023-11-10 | ***通信集团广东有限公司 | Service identification method, device, equipment and storage medium |
CN114422619A (en) * | 2020-10-12 | 2022-04-29 | ***通信集团广东有限公司 | Service identification method, device, equipment and storage medium |
CN114640606A (en) * | 2020-12-01 | 2022-06-17 | 中移物联网有限公司 | Abnormity processing method and controller for Internet of things card terminal |
CN113139817A (en) * | 2021-04-28 | 2021-07-20 | 北京沃东天骏信息技术有限公司 | Data classification method, data classification device, medium, and electronic apparatus |
CN113536066A (en) * | 2021-07-16 | 2021-10-22 | 全球能源互联网研究院有限公司 | Data anomaly detection algorithm determination method and device and computer equipment |
CN113537387A (en) * | 2021-08-04 | 2021-10-22 | 北京思特奇信息技术股份有限公司 | Model design method and device for Internet online operation activities and computer equipment |
CN113923037A (en) * | 2021-10-18 | 2022-01-11 | 北京八分量信息科技有限公司 | Credible computing-based anomaly detection optimization device, method and system |
CN113923037B (en) * | 2021-10-18 | 2024-03-26 | 北京八分量信息科技有限公司 | Anomaly detection optimization device, method and system based on trusted computing |
CN114143734A (en) * | 2021-10-22 | 2022-03-04 | 广东省电信规划设计院有限公司 | Data processing method and device for 5G Internet of things network card flow acquisition |
CN114143227A (en) * | 2021-10-25 | 2022-03-04 | 国网山西省电力公司阳泉供电公司 | Internet of things card abnormal state monitoring and early warning method |
CN114168632A (en) * | 2021-12-07 | 2022-03-11 | 泰康保险集团股份有限公司 | Abnormal data identification method and device, electronic equipment and storage medium |
CN115002198A (en) * | 2022-05-23 | 2022-09-02 | 支付宝(杭州)信息技术有限公司 | Information processing method, device, equipment and medium for Internet of things equipment |
CN116016230A (en) * | 2022-12-26 | 2023-04-25 | 山东有人物联网股份有限公司 | Multi-type service processing method and device for Internet of things network card, electronic equipment and medium |
CN116016230B (en) * | 2022-12-26 | 2024-04-05 | 山东有人物联网股份有限公司 | Multi-type service processing method and device for Internet of things network card, electronic equipment and medium |
CN117056594A (en) * | 2023-07-31 | 2023-11-14 | 中移互联网有限公司 | User identification method and device based on interaction relationship and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN110505196B (en) | 2021-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110505196A (en) | Internet of Things network interface card method for detecting abnormality and device | |
CN109063966A (en) | The recognition methods of adventure account and device | |
US10637990B1 (en) | Call center load balancing and routing management | |
CN107809322A (en) | The distribution method and device of work order | |
CN106993104A (en) | Call processing method, device and terminal | |
CN110515811A (en) | Terminal artificial intelligence performance benchmark test method and device | |
US20150286949A1 (en) | Problem analysis and priority determination based on fuzzy expert systems | |
CN107818133A (en) | A kind of residential block network capabilities analysis method and system based on big data | |
CN106792992A (en) | A kind of method and apparatus for providing WAP information | |
CN109242135A (en) | A kind of model method for running, device and service server | |
CN108768765A (en) | Abnormality Internet of Things network interface card checking method, device and computer readable storage medium | |
CN112907305B (en) | Customer full-period management system based on big data analysis | |
CN107947968A (en) | The treating method and apparatus of network quality calling information | |
KR102068918B1 (en) | Router address type identification method and device | |
CN109978292B (en) | Intelligent management method and device for store | |
CN108491720A (en) | A kind of application and identification method, system and relevant device | |
CN111897705A (en) | Service state processing method, service state processing device, model training method, model training device, equipment and storage medium | |
CN108959048A (en) | The method for analyzing performance of modular environment, device and can storage medium | |
CN107679683A (en) | Software development progress method for early warning and device | |
CN105812473A (en) | Data processing method and device | |
CN109493958A (en) | A kind of follow-up ways to draw up the plan, device, server and medium | |
US7933795B2 (en) | Collaborative organization analysis | |
CN107908673A (en) | The real relationship match method, apparatus and readable storage medium storing program for executing of social platform user | |
CN109949041A (en) | A kind of active process method for limit power account | |
CN107580329A (en) | A kind of network analysis optimization method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |