CN116915630A - Network stuck prediction method, device, electronic equipment, medium and program product - Google Patents
Network stuck prediction method, device, electronic equipment, medium and program product Download PDFInfo
- Publication number
- CN116915630A CN116915630A CN202211537477.4A CN202211537477A CN116915630A CN 116915630 A CN116915630 A CN 116915630A CN 202211537477 A CN202211537477 A CN 202211537477A CN 116915630 A CN116915630 A CN 116915630A
- Authority
- CN
- China
- Prior art keywords
- network
- time period
- history
- preset time
- historical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000000903 blocking effect Effects 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000008447 perception Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000000523 sample Substances 0.000 description 5
- 238000004140 cleaning Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
- H04L43/02—Capturing of monitoring data
- H04L43/028—Capturing of monitoring data by filtering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a network katon prediction method, a network katon prediction device, electronic equipment, a medium and a program product. The network jamming prediction method comprises the following steps: acquiring historical internet surfing record data corresponding to each historical preset time period of a user; for each history preset time period, determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period based on the history internet log data corresponding to the history preset time period; taking each history label and network quality index data corresponding to each history label as training samples, and training a network katon prediction model to obtain a trained network katon prediction model; and obtaining a target label of the occurrence of the jamming in the network in the time period to be predicted based on the trained network jamming prediction model and the network quality index data in the time period to be predicted. The method can realize the effect of accurately predicting the user's stuck behavior in any time period to be predicted.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a network katon prediction method, a device, an electronic device, a medium, and a program product.
Background
In order to ensure the development of video services and the access perception of user video services, the detection and evaluation of the network quality of the video services are also an indispensable step in the development process of the video services, and in order to monitor the quality condition of the user accessing the video services, the current schemes have two kinds: one is to use dial-up detection technology, and the other is to detect based on deep packet inspection (Deep Packet Inspection, DPI) technology.
The inventor finds that although the index obtained by the dial testing technology can evaluate the perception of the user accessing the video service from the user side angle, the dial testing is always performed under specific conditions, and finally the user perception cannot be comprehensively and truly evaluated. In addition, the DPI technology cannot process and adjust related network links in advance, so that possible jamming behavior is avoided, and the user surfing experience is influenced.
Disclosure of Invention
The embodiment of the application aims to provide a network jamming prediction method, a device, electronic equipment, a medium and a program product, so as to realize the effect of comprehensively predicting whether a network is jammed.
The technical scheme of the application is as follows:
in a first aspect, a network katon prediction method is provided, and the method includes:
acquiring historical internet surfing record data corresponding to each historical preset time period of a user;
for each history preset time period, determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period based on the history internet log data corresponding to the history preset time period;
taking each history label and network quality index data corresponding to each history label as training samples, and training a network katon prediction model to obtain a trained network katon prediction model;
and obtaining a target label of the occurrence of the jamming in the network in the time period to be predicted based on the trained network jamming prediction model and the network quality index data in the time period to be predicted.
In a second aspect, a network katon prediction apparatus is provided, the apparatus comprising:
the first acquisition module is used for acquiring historical Internet surfing record data corresponding to each historical preset time period of the user;
the first determining module is used for determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period according to the history internet surfing record data corresponding to the history preset time period;
The second determining module is used for taking each history label and network quality index data corresponding to each history label as training samples, training the network katon prediction model and obtaining a trained network katon prediction model;
and the third determining module is used for obtaining a target label of the occurrence of the jamming in the network in the period to be predicted based on the trained network jamming prediction model and the network quality index data in the period to be predicted.
In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor, a memory, and a program or an instruction stored in the memory and capable of running on the processor, where the program or the instruction implements the steps of the network katon prediction method according to any one of the embodiments of the present application when executed by the processor.
In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored, where the program or the instruction implements the steps of the network katon prediction method according to any one of the embodiments of the present application when executed by a processor.
In a fifth aspect, embodiments of the present application provide a computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the steps of the network katon prediction method of any of the embodiments of the present application.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
according to the embodiment of the application, by acquiring the historical Internet surfing record data corresponding to each historical preset time period of a user, determining whether a network is blocked or not in the historical preset time period and the network quality index data in the historical preset time period based on the historical Internet surfing record data corresponding to each historical preset time period, and then training a network blocking prediction model by taking each historical label and the network quality index data corresponding to each historical label as training samples, a trained network blocking prediction model is obtained, and thus a target label of blocking in the to-be-predicted time period can be obtained based on the trained network blocking prediction model and the network quality index data in the to-be-predicted time period, and by correlating the user blocking characteristics with the network quality index data, a characteristic equation is established, the network blocking prediction model is trained, and whether the network is blocked or not is accurately predicted based on the trained network blocking prediction model, so that accurate prediction of the user blocking behavior in any to-be-predicted time period is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute a undue limitation on the application.
Fig. 1 is a flow chart of a network katon prediction method provided in an embodiment of the present application;
fig. 2 is a system architecture diagram of a network katon prediction method according to an embodiment of the present application;
fig. 3 is another implementation manner of the network katon prediction method provided in the embodiment of the present application;
fig. 4 is a schematic structural diagram of a network katon prediction apparatus according to an embodiment of the second aspect of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the third aspect of the present application.
Detailed Description
In order to enable a person skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the particular embodiments described herein are meant to be illustrative of the application only and not limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the application by showing examples of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of implementations consistent with aspects of the application as set forth in the following claims.
As in the background art, in order to guarantee the development of video services and the access perception of video services for users, the detection and evaluation of the network quality of video services are also an indispensable step in the development process of video services, and in order to monitor the quality of video services accessed by users, there are two existing schemes: one is to use dial-up detection technology, and the other is to detect based on deep packet inspection (Deep Packet Inspection, DPI) technology.
The inventor finds that although the index obtained by the dial testing technology can evaluate the perception of the user accessing the video service from the user side angle, the dial testing is always performed under specific conditions, and finally the user perception cannot be comprehensively and truly evaluated. In addition, the DPI technology cannot process and adjust related network links in advance, so that possible jamming behavior is avoided, and the user surfing experience is influenced.
In order to solve the above problems, embodiments of the present application provide a network jamming prediction method, apparatus, device, medium, and computer program product, by acquiring historical internet log data corresponding to each historical preset time period of a user, for each historical preset time period, determining, based on the historical internet log data corresponding to the historical preset time period, whether a network jamming occurs in the historical preset time period, and network quality index data in the historical preset time period, then training a network jamming prediction model by using each historical label and the network quality index data corresponding to each historical label as training samples, thereby obtaining a trained network jamming prediction model, and obtaining a target label for jamming in the network in the time period to be predicted based on the trained network jamming prediction model and the network quality index data in the time period to be predicted, so as to establish a feature equation by correlating the user jamming feature with the network quality index data, train the network jamming prediction model, and accurately predict whether the network jamming occurs based on the trained network jamming prediction model, thereby realizing accurate prediction of the network jamming behavior of the user in any time period to be predicted.
The embodiment of the application provides a network stuck prediction method, a device, equipment, a storage medium and a product. The following first describes a network katon prediction method provided by the embodiment of the present application.
Fig. 1 is a flow chart of a network katon prediction method according to an embodiment of the present application. As shown in fig. 1, the method includes:
s110, acquiring historical Internet surfing record data corresponding to each historical preset time period of the user.
The historical preset time period may be a time period during which the user accesses the resource, for example, a time period during which the user views the video, or the like.
The historical internet log data may be any one or more of data including user internet protocol (Internet Protocol, IP), resource IP, domain name information, or uniform resource locator (Universal Resource Locator, URL) information when the user accesses the resource.
The historical internet log data corresponding to each historical preset time period of the user can be obtained, specifically, the collected messages can be transmitted to a server by using a deep packet inspection technology (Deep Packet Inspection, DPI) probe, or the data can be obtained in other modes, and the method is not limited herein.
As an example, by adopting the deep packet resolution capability of the DPI probe and the synthesis function of the terminal detection and response (Extended Detection and Response, XDR) ticket, the packet is grabbed by using a network sniffing packet grabbing tool (wireshark) tool on a packet generated when a certain video website is watched by using a browser end, so that corresponding historical internet record data generated when the certain video website is watched can be obtained.
S120, determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period based on the history internet log data corresponding to the history preset time period according to each history preset time period.
The history tag may be a tag for characterizing whether network stuck occurs within a predetermined period of time of the history, and may be "stuck" or "non-stuck", for example.
In some embodiments, to more accurately determine whether a history tag of network stuck occurs within a history preset time period, the network quality indicator data may at least include: uplink speed, downlink speed, server time delay, client time delay, response time delay, uplink retransmission rate, downlink retransmission rate, access success rate, client failure rate and server failure rate.
And S130, taking each history label and network quality index data corresponding to each history label as training samples, and training a network katon prediction model to obtain a trained network katon prediction model.
The network stuck prediction model may be a model for predicting whether stuck occurs in a certain period of time, and specifically may be one of any machine learning models, or may be a prediction model preset according to actual situations, which is not limited herein.
And S140, obtaining a target label of the occurrence of the jamming in the network in the time period to be predicted based on the trained network jamming prediction model and the network quality index data in the time period to be predicted.
The target tag may be a tag for characterizing whether a jam occurs in the network within the period to be predicted, and may be, for example, "jam" or "non-jam". The label may specifically be obtained by taking network quality index data in a time period to be predicted as input of a network katon prediction model and taking a target label as output.
In this way, by acquiring the historical internet log data corresponding to each historical preset time period of the user, determining whether the network is blocked in the historical preset time period or not and the network quality index data in the historical preset time period based on the historical internet log data corresponding to each historical preset time period, then training a network blocking prediction model by taking each historical label and the network quality index data corresponding to each historical label as training samples, and obtaining a trained network blocking prediction model, the target label of blocking in the network in the time period to be predicted can be obtained based on the trained network blocking prediction model and the network quality index data in the time period to be predicted, and by correlating the user blocking characteristics with the network quality index data, a characteristic equation is established, the network blocking prediction model is trained, and whether the network is blocked or not is accurately predicted based on the trained network blocking prediction model, so that accurate prediction of the blocking behavior of the user in any time period to be predicted is realized.
In some embodiments, in order to more accurately determine whether a history tag of network blocking occurs in a history preset period of time, the history log data may include a uniform resource identifier of the user surfing the internet, and S120 may specifically include:
deleting the uniform resource identifier which does not contain preset information in the uniform resource identifier corresponding to the historical preset time period to obtain a first uniform resource identifier; the preset information at least comprises a file, path information and query parameters; the query parameters are used for representing characteristic information of network blocking;
dividing the first uniform resource identifier according to the domain name and the key value pair corresponding to the query parameter to obtain an alternative feature set;
and determining whether a history label of network blocking occurs in a history preset time period based on the alternative feature set.
In some embodiments, the uniform resource identifier (Uniform Resource Identifier, URI) may specifically be a string that identifies a certain internet resource name. Such identification allows the user to interoperate with any (including local and internet) resource via a particular protocol. The URI is one of important fields that need to be provided in an XDR ticket.
The first uniform resource identifier may be the same resource identifier obtained after deleting a uniform resource identifier that does not include preset information in the uniform resource identifiers corresponding to the historical preset time period.
The path information may be path information of network resources viewed by the user when surfing the internet.
The alternative feature set may be a set of segmented key-value pairs obtained by segmenting the first uniform resource identifier according to the domain name and the key-value pairs corresponding to the query parameter.
In some embodiments, the query parameters may be, for example, path and query parameters, and the key-value pairs may be key and value values in the parameters.
Deleting the uniform resource identifier which does not contain preset information in the uniform resource identifier corresponding to the historical preset time period to obtain a first uniform resource identifier, and specifically, deleting the URI which does not contain preset information after obtaining the multi-string URI.
In some embodiments, the first uniform resource identifier is segmented according to the domain name and the key value pair corresponding to the query parameter to obtain the alternative feature set, specifically, a specific symbol is used for segmenting each string of URI, and URIs with the same domain name and query parameter are extracted to obtain the alternative feature set.
In some embodiments, based on the alternative feature set, determining whether a history tag of network jamming occurs in a history preset time period may include taking a key value representing jamming in the set as the history tag.
As an example, based on the description of the URI above, the URI that does not contain the file, path, query parameters in the URI is filtered out first, and then the following is used: ' v ', ' v? The symbols of',', and the like divide the rest URI, and extract key and value values in the domain name, path and query parameters of the URI as shown in the following table (1):
table 1 first uniform resource identifier Fu Shili table
In one example, a method of creating a click-through when watching a video, such as an artificial speed limit, is used to watch the video and capture the video for analysis, and it is assumed that a user U generates a click-through phenomenon when watching both a video episode a and a video episode B, and 5 domain names and 5 URLs with query parameters are obtained, and 15 keys and values are obtained by splitting, where the domain names, the keys and the values are the same and different. And selecting the combination with the same domain name, key and value as an alternative feature set.
In this way, by acquiring the uniform resource identifier in the user history preset time period and filtering the identifier, the obtained uniform resource identifier is segmented according to the domain name and the key value pair corresponding to the query parameter to obtain the alternative feature set, and the obtained alternative feature set contains the feature information for representing the network blocking, so that whether the network blocking occurs in the history preset time period can be determined based on the set, and the accuracy is improved.
In some embodiments, to further improve accuracy of determining whether the network is stuck in the history preset period, determining whether the network is stuck in the history preset period based on the alternative feature set may specifically include:
respectively acquiring a first key value pair of a first domain name and a query parameter when a network is blocked in a historical preset time period and a second key value pair of a second domain name and a query parameter when the network is not blocked;
comparing the first domain name, the first key value pair, the second domain name and the second key value pair with the domain name and the key value pair in the alternative feature set, selecting a value attribute which is the same as the domain name in the alternative feature set, the key attribute which is the same as the key attribute in the key value pair in the alternative feature set and different from the value attribute in the key value pair in the alternative feature set, and determining the value attribute as a target value attribute;
and determining whether a history label of network blocking occurs in a history preset time period based on the target value attribute.
The first domain name may be a domain name when the network is blocked within a historical preset time period.
The first key-value pair may be a key-value pair of a query parameter at a network click over a historical preset period of time.
The second domain name may be a domain name when the network is not stuck within a historical preset period of time.
The second key-value pair may be a key-value pair of the query parameter when the network is not stuck within the historical preset time period.
The target value attribute may be a selected value attribute that is the same as the domain name in the alternative feature set and the key attribute in the key value pair in the alternative feature set and that is different from the value attribute in the key value pair in the alternative feature set.
As an example, in the above example, for the user U, by observing the domain name, key, and value values generated when the user U views the video episode a, the katon, and the non-katon, and the domain name, key, and value values generated when the user U views the video episode B, the domain name, key, and value values in the alternative feature set described above are compared, and combinations that are the same as the domain name, key value in the alternative feature set and are different from each other are selected as the target value attribute.
In this way, by acquiring the first key value pair of the first domain name and the query parameter when the network is blocked in the historical preset time period and the second key value pair of the second domain name and the query parameter when the network is not blocked, comparing the first key value pair with the domain name and the key value pair in the alternative feature set, selecting the value attribute which is the same as the domain name in the alternative feature set and the key attribute in the key value pair in the alternative feature set and is different from the value attribute in the key value pair in the alternative feature set, and determining the value attribute as the target value attribute, the attribute value when the network is blocked and the value in the alternative feature set can be further confirmed to be the attribute value representing blocking, the range is reduced, and the obtained historical label is more accurate.
In some embodiments, to obtain network quality indicator data more accurately within the historical preset time period, the historical internet surfing record data may further include: network characteristic information; the S120 may include:
and calculating network quality index data in the historical preset time period based on the network characteristic information corresponding to the historical preset time period.
In some embodiments, the network characteristic information may be specifically a characteristic used for calculating network quality index data, for example, information such as downloading traffic, downloading duration, uploading traffic, uploading duration, or time delay of the client initiating the synchronization sequence number (SynchronizeSequenceNumbers, SYN) to the server returning a response acknowledgement (SYN ACK).
As an example, the network quality indicator data may be a quality indicator reflecting the network surfing perception of the user, and specifically may include an uplink rate, a downlink rate, a server delay, a client delay, a response delay, an uplink retransmission rate, a downlink retransmission rate, an access success rate, a client failure rate, and a server failure rate.
For each network quality index calculation mode, the calculation modes may be as shown in table 2:
table 2 network quality index calculation mode example
In this way, the network quality index data in the historical preset time period is calculated according to the network characteristic information corresponding to the historical preset time period, and the network quality index data obtained by calculating the preset formula can contain the katon information of the user because the network characteristic information contains various index information used for representing the internet surfing of the user, so that the accuracy of the network quality index data in the historical preset time period is improved.
In some embodiments, in order to accurately obtain the network quality indicator data, the calculating the network quality indicator data in the historical preset time period based on the network feature information corresponding to the historical preset time period may specifically include:
cleaning the network characteristic information corresponding to the historical preset time period to obtain target network characteristic information;
and calculating network quality index data in a historical preset time period based on the target network characteristic information.
The target network characteristic information may be network characteristic information obtained after cleaning the network characteristic information corresponding to the historical preset time period.
In some embodiments of the present application, the cleaning of the network feature information corresponding to the historical preset time period may, but is not limited to, include performing a deduplication process, a feature encoding process, and the like on the network feature information corresponding to the historical preset time period.
In the embodiment of the application, the target network characteristic information is obtained by cleaning the network characteristic information corresponding to the historical preset time period, and then the network quality index data in the historical preset time period is calculated based on the target network characteristic information, so that the network characteristic information with better quality can be obtained, and the accurate network quality index data can be obtained based on the network characteristic information with better quality.
In some embodiments, in order to more accurately obtain the target tag of the network occurrence of the jam in the period to be predicted, the network jam prediction model may be a logistic regression model.
As an example, taking a logistic regression model as a network katon prediction model, the training process may be: obtaining user reality of recent month from big data platform distributed system infrastructure (Hadoop)Internet surfing record U 0 And m pieces of historical internet record data are contained. Processing data set U 0 Obtaining a history label of whether the user is blocked on the internet as a dependent variable y (blocked is 1; blocked is not blocked is 0), and processing a data set U 0 Acquiring network quality index data as an argument X (including X 1 、x 2 …x n N variables in total: uplink and downlink rates, client/server/response delay, retransmission rate, success/failure rate), constitute the data set U for modeling 1 . U is set to 1 M X in middle<x 1 、x 2 …x n >Taking out, and constructing a linear regression function as shown in a formula (1):
h(x)＝w 0 +w 1 x 1 +w 2 x 2 +...+w n x n (1)
wherein w is a parameter of the model, wherein w 0 Is intercept (intercept), w 1 ～w n Is a coefficient (coefficient).
It will be appreciated that the task of the linear regression function is to construct h (x) This predictive function maps the linear relationship of the input variable X and the tag value y such that h (X) =w 0 +w 1 x 1 +w 2 x 2 +...+w n x n =0 as decision boundary for whether or not a stuck occurs, then there is a function h (x)>When=0, y=1; when the function h (x)<At 0, y=0.
Due to { katon: 1, not stuck: 0 is an obvious classification problem, the value of the model is continuous, a link function (link function) is introduced, a linear regression equation h (x) is converted into g (h), the value of g (h) is distributed between (0 and 1), the label of a sample is not blocked in the category 0 when g (z) is close to 0, and the label of the sample is blocked in the category 1 when g (z) is close to 1, so that the classification model is obtained. This contact function is for logical regression a Sigmoid function, specifically as shown in equation (2):
the linear regression function, namely the formula (1), is carried into the Sigmoid function, and a final logistic regression function is obtained, specifically as shown in the formula (3):
wherein x is 1 、x 2 …x n Input data of the model, namely user internet surfing quality index data: uplink speed, downlink speed, client time delay, server time delay, response time delay, uplink retransmission rate, downlink retransmission rate, access success rate, client failure rate and server failure rate. Y (x) is the tag value returned by the logistic regression.
It can be understood that the values of y (x) are all between 0 and 1, and when y (x) tends to be 1, the user is stuck, and when y (x) tends to be 0, the user is not stuck.
Therefore, by introducing the regression model as the network jamming prediction model and taking each history label and the network quality index data corresponding to each history label as the training sample, the prediction situation of the actual network jamming can be attached, and the target label with jamming in the network in the time period to be predicted can be obtained more accurately.
In order to understand the scheme of the present application more clearly, the embodiment of the present application further provides a system architecture diagram of a network katon prediction method, and in particular, as shown in fig. 2.
In some embodiments of the present application, in order to more clearly understand the technical solutions of the present application, the technical solutions of the present application are described below in a specific scenario.
The embodiment of the application also provides another implementation manner of the network katon prediction method, as shown in fig. 3, the network katon prediction method provided by the embodiment of the application may include the following steps:
s310, capturing the package to obtain the URI, and separating the sum of domain names of the URI and query parameters.
S320, acquiring network characteristic information in the historical internet surfing data of the user.
S330, filtering key and value values in the URI to determine a target attribute value.
S340, filtering the network characteristic information and calculating network quality index data.
S350, establishing a katon prediction model.
S360, predicting the user to be stuck.
It should be noted that, in the network katon prediction method provided in the embodiment of the present application, the execution body may be a network katon prediction device, or a control module in the network katon prediction device for executing the network katon prediction method.
Based on the same application conception as the network jamming prediction method, the application also provides a network jamming prediction device. The following describes in detail the network katon prediction provided by the embodiment of the present application with reference to fig. 4.
Fig. 4 is a schematic diagram illustrating a structure of a network hitching prediction apparatus according to an exemplary embodiment.
As shown in fig. 4, the network katon prediction apparatus 400 may include:
a first obtaining module 401, configured to obtain historical internet log data corresponding to each historical preset time period of a user;
a first determining module 402, configured to determine, for each history preset time period, based on the history internet log data corresponding to the history preset time period, whether a history tag of network blocking occurs in the history preset time period, and network quality index data in the history preset time period;
a second determining module 403, configured to train the network katon prediction model by using each history tag and the network quality index data corresponding to each history tag as training samples, to obtain a trained network katon prediction model;
The third determining module 404 is configured to obtain, based on the trained network jamming prediction model and the network quality indicator data in the period to be predicted, a target tag in which jamming occurs in the network in the period to be predicted.
In this way, by acquiring the historical internet log data corresponding to each historical preset time period of the user, determining whether the network is blocked in the historical preset time period or not and the network quality index data in the historical preset time period based on the historical internet log data corresponding to each historical preset time period, then training a network blocking prediction model by taking each historical label and the network quality index data corresponding to each historical label as training samples, and obtaining a trained network blocking prediction model, the target label of blocking in the network in the time period to be predicted can be obtained based on the trained network blocking prediction model and the network quality index data in the time period to be predicted, and by correlating the user blocking characteristics with the network quality index data, a characteristic equation is established, the network blocking prediction model is trained, and whether the network is blocked or not is accurately predicted based on the trained network blocking prediction model, so that accurate prediction of the blocking behavior of the user in any time period to be predicted is realized.
In some embodiments, to more accurately determine whether a history tag of network blocking occurs within a history preset period of time, the history log data may include a uniform resource identifier of a user surfing the internet, and the first determining module 402 may specifically include the following units:
a deleting unit, configured to delete a uniform resource identifier that does not include preset information in a uniform resource identifier corresponding to a historical preset time period, so as to obtain a first uniform resource identifier; the preset information at least comprises a file, path information and query parameters; the query parameters are used for representing characteristic information of network blocking;
the segmentation unit is used for segmenting the first uniform resource identifier according to the domain name and the key value pair corresponding to the query parameter to obtain an alternative feature set;
and the determining unit is used for determining whether the history label of the network jam occurs in the history preset time period based on the alternative feature set.
In some embodiments, in order to further improve accuracy of determining whether network blocking occurs in the history preset period, the determining unit may specifically include the following sub-units:
the acquisition subunit is used for respectively acquiring a first key value pair of a first domain name and a query parameter when the network is blocked in a historical preset time period and a second key value pair of a second domain name and a query parameter when the network is not blocked;
A comparison subunit, configured to compare the first domain name, the first key value pair, the second domain name, and the second key value pair with the domain name and the key value pair in the alternative feature set, select a value attribute that is the same as the domain name in the alternative feature set, the key attribute that is the same as the key value pair in the alternative feature set, and different from the value attribute in the key value pair in the alternative feature set, and determine the value attribute as the target value attribute;
and the determining subunit is used for determining whether the history label of the network jam occurs in the history preset time period based on the target value attribute.
In some embodiments, in order to obtain the network quality index data more accurately within the historical preset time period, the historical internet access record data may further include network characteristic information, and the first determining module 402 may specifically include the following units:
the calculating unit is used for calculating network quality index data in the historical preset time period based on the network characteristic information corresponding to the historical preset time period.
The network katon prediction device provided by the embodiment of the application can be used for executing the network katon prediction method provided by the embodiments of the method, and the implementation principle and the technical effect are similar, so that the description is omitted herein for the sake of brevity.
Based on the same inventive concept, the embodiment of the application also provides electronic equipment.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 5, the electronic device may include a processor 501 and a memory 502 storing computer programs or instructions.
In particular, the processor 501 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.
Memory 502 may include mass storage for data or instructions. By way of example, and not limitation, memory 502 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. Memory 502 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 502 is a non-volatile solid state memory. The Memory may include read-only Memory (Read Only Memory image, ROM), random-Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described by the network katon prediction method provided by the above embodiments.
The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the network hitching prediction methods of the above embodiments.
In one example, the electronic device may also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected to each other by a bus 510 and perform communication with each other.
The communication interface 503 is mainly used to implement communication between each module, device, unit and/or device in the embodiments of the present invention.
Bus 510 includes hardware, software, or both that couple components of the electronic device to one another. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. Bus 510 may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
The electronic device may execute the network katon prediction method in the embodiment of the present invention, thereby implementing the network katon prediction method described in fig. 1-3.
In addition, in combination with the network katon prediction method in the above embodiment, the embodiment of the present invention may be implemented by providing a readable storage medium. The readable storage medium has program instructions stored thereon; the program instructions, when executed by a processor, implement any of the network katon prediction methods of the above embodiments.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
The functional blocks shown in the above block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.
Claims (10)
1. A method for network stuck prediction, the method comprising:
acquiring historical internet surfing record data corresponding to each historical preset time period of a user;
for each history preset time period, determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period based on history internet record data corresponding to the history preset time period;
taking each history label and the network quality index data corresponding to each history label as training samples, and training a network katon prediction model to obtain a trained network katon prediction model;
And obtaining a target label of the occurrence of the jamming in the network in the time period to be predicted based on the trained network jamming prediction model and network quality index data in the time period to be predicted.
2. The method of claim 1, wherein the historical internet log data includes a uniform resource identifier of a user's internet;
the determining whether the history label of the network is blocked in the history preset time period based on the history internet log data corresponding to the history preset time period comprises:
deleting the uniform resource identifier which does not contain preset information in the uniform resource identifier corresponding to the historical preset time period to obtain a first uniform resource identifier; the preset information at least comprises a file, path information and query parameters; the query parameters are used for representing characteristic information of network blocking;
dividing the first uniform resource identifier according to the domain name and the key value pair corresponding to the query parameter to obtain an alternative feature set;
and determining whether a history label of network blocking occurs in the history preset time period based on the alternative feature set.
3. The method of claim 2, wherein the determining whether a history tag for network stuck occurs within the history preset time period based on the alternative feature set comprises:
Respectively obtaining a first key value pair of a first domain name and a query parameter when a network is blocked in the historical preset time period and a second key value pair of a second domain name and a query parameter when the network is not blocked;
comparing the first domain name, the first key value pair, the second domain name and the second key value pair with domain names and key value pairs in the alternative feature set, selecting a value attribute which is the same as the domain name in the alternative feature set, the key attribute which is the same as the key value pair in the alternative feature set and the value attribute which is different from the value attribute in the key value pair in the alternative feature set, and determining the value attribute as a target value attribute;
and determining whether a history label of network jam occurs in the history preset time period based on the target value attribute.
4. The method of claim 1, wherein the historical internet log data further comprises: network characteristic information;
based on the historical internet surfing record data corresponding to the historical preset time period, determining the network quality index data in the historical preset time period comprises the following steps:
and calculating network quality index data in the historical preset time period based on the network characteristic information corresponding to the historical preset time period.
5. The method according to claim 1 or 4, wherein the network quality indicator data comprises at least: uplink speed, downlink speed, server time delay, client time delay, response time delay, uplink retransmission rate, downlink retransmission rate, access success rate, client failure rate and server failure rate.
6. The method of claim 1, wherein the network katon prediction model is a logistic regression model.
7. A network stuck prediction apparatus, the apparatus comprising:
the first acquisition module is used for acquiring historical Internet surfing record data corresponding to each historical preset time period of the user;
the first determining module is used for determining whether a history label of network blocking occurs in the history preset time period and network quality index data in the history preset time period according to the history internet surfing record data corresponding to the history preset time period;
the second determining module is used for taking each history label and the network quality index data corresponding to each history label as training samples, training a network katon prediction model and obtaining a trained network katon prediction model;
And the third determining module is used for obtaining a target label with the network stuck in the period to be predicted based on the trained network stuck prediction model and network quality index data in the period to be predicted.
8. An electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, the program or instruction when executed by the processor implementing the steps of the network katon prediction method of any of claims 1-6.
9. A readable storage medium, wherein a program or instructions is stored on the readable storage medium, which when executed by a processor, implements the steps of the network hitching method of any of claims 1-6.
10. A computer program product, characterized in that instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the steps of the network hitching prediction method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537477.4A CN116915630A (en) | 2022-12-02 | 2022-12-02 | Network stuck prediction method, device, electronic equipment, medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537477.4A CN116915630A (en) | 2022-12-02 | 2022-12-02 | Network stuck prediction method, device, electronic equipment, medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116915630A true CN116915630A (en) | 2023-10-20 |
Family
ID=88365461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211537477.4A Pending CN116915630A (en) | 2022-12-02 | 2022-12-02 | Network stuck prediction method, device, electronic equipment, medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116915630A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117241071A (en) * | 2023-11-15 | 2023-12-15 | 北京浩瀚深度信息技术股份有限公司 | Method for sensing video katon quality difference based on machine learning algorithm |
-
2022
- 2022-12-02 CN CN202211537477.4A patent/CN116915630A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117241071A (en) * | 2023-11-15 | 2023-12-15 | 北京浩瀚深度信息技术股份有限公司 | Method for sensing video katon quality difference based on machine learning algorithm |
| CN117241071B (en) * | 2023-11-15 | 2024-02-06 | 北京浩瀚深度信息技术股份有限公司 | Method for sensing video katon quality difference based on machine learning algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107302547B (en) | Web service anomaly detection method and device | |
| CN112200273B (en) | Data annotation method, device, equipment and computer storage medium | |
| CN105022801B (en) | A kind of hot topic video mining method and device | |
| CN111327539B (en) | Service scheduling method, device and equipment | |
| CN111107423A (en) | Video service playing card pause identification method and device | |
| CN105404631B (en) | Picture identification method and device | |
| CN107967488B (en) | Server classification method and classification system | |
| US8818927B2 (en) | Method for generating rules and parameters for assessing relevance of information derived from internet traffic | |
| CN109982068B (en) | Method, apparatus, device and medium for evaluating quality of synthesized video | |
| CN115967504A (en) | Encrypted malicious traffic detection method and device, storage medium and electronic device | |
| JP6721057B2 (en) | Communication session log analysis device and method | |
| CN116915630A (en) | Network stuck prediction method, device, electronic equipment, medium and program product | |
| CN109756358B (en) | Sampling frequency recommendation method, device, equipment and storage medium | |
| CN113453076B (en) | User video service quality evaluation method, device, computing equipment and storage medium | |
| CN106063281A (en) | Method to determine re-buffering events in video sessions | |
| WO2017159490A1 (en) | Communication analysis device, communication analysis method, and program recording medium | |
| CN116112209A (en) | Vulnerability attack flow detection method and device | |
| CN104899320A (en) | Webpage repair method, terminal, server and system | |
| Dubin et al. | Video quality representation classification of encrypted http adaptive video streaming | |
| CN115225936B (en) | Method, device, equipment and medium for determining definition index of video resource | |
| CN117241071B (en) | Method for sensing video katon quality difference based on machine learning algorithm | |
| CN114297542A (en) | Method, device, terminal and medium for recognizing traffic intention based on transfer learning | |
| CN118802621A (en) | Network quality detection method, device, equipment and storage medium | |
| CN114070819B (en) | Malicious domain name detection method, device, electronic device and storage medium | |
| CN111385136B (en) | Method and device for determining user communication identifier |
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 |