CN114221874B - Traffic analysis and scheduling method and device, computer equipment and readable storage medium - Google Patents
Traffic analysis and scheduling method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN114221874B CN114221874B CN202111526544.8A CN202111526544A CN114221874B CN 114221874 B CN114221874 B CN 114221874B CN 202111526544 A CN202111526544 A CN 202111526544A CN 114221874 B CN114221874 B CN 114221874B
- Authority
- CN
- China
- Prior art keywords
- line
- information
- external
- abnormal
- request
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000004458 analytical method Methods 0.000 title claims description 20
- 238000010801 machine learning Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005206 flow analysis Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims description 156
- 230000005856 abnormality Effects 0.000 claims description 47
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of intelligent decision making of artificial intelligence, and discloses a flow analysis and scheduling method, a device, computer equipment and a readable storage medium, wherein the method comprises the following steps: the method comprises the steps that an external circuit used by an identification server for accessing an external network is acquired, and circuit state information of the external circuit is acquired; collecting flow value and line state information of an external line in a preset collecting period and generating line characteristic information; calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period; and routing request information to the external circuit according to the optimal configuration information. The invention fully releases the processing performance of the external circuit with better performance, ensures that the external circuit with poorer performance can process the quantity of the request information to the greatest extent on the premise that the circuit state information of the external circuit meets the preset circuit state, and ensures the overall stability and the data processing efficiency of all the external circuits.
Description
Technical Field
The present invention relates to the field of intelligent decision making technology of artificial intelligence, and in particular, to a method, an apparatus, a computer device, and a readable storage medium for flow analysis and scheduling.
Background
The external circuit is an internet device for generating feedback information according to the request information, and the server is used for calling the external circuit to complete the appointed task by routing the request information to the external circuit and obtaining the feedback information returned by the external circuit. In general, a server is connected to a plurality of external lines for processing request information, and the amount of request information that can be processed is often different due to different device performance, bus performance, and processing algorithms of each external line.
However, the current server generally transmits route request information to external lines in a predetermined order alternately or transmits route request information to external lines having a low current flow value; the inventor finds that the current request information routing mode easily causes that the processing performance of the external circuit with better performance cannot be fully released, and the external circuit with worse performance often causes that the circuit is abnormal because of processing too much request information, so that the situation that the overall performance of all the external circuits connected with the server is unstable and the processing efficiency of the request information is too low occurs.
Disclosure of Invention
The invention aims to provide a flow analysis and scheduling method, a device, computer equipment and a readable storage medium, which are used for solving the problems of unstable overall performance of an external circuit and low processing efficiency of request information in the prior art.
In order to achieve the above objective, the present invention provides a traffic analysis and scheduling method, applied to a server, comprising:
the method comprises the steps that an external circuit used by an identification server for accessing an external network is acquired, and circuit state information of the external circuit is acquired; wherein the line state information includes a normal state and an abnormal state;
collecting flow value and line state information of an external line in a preset collecting period and generating line characteristic information, wherein the flow value reflects the quantity of request information received by the external line;
calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period;
and routing request information to the external circuit according to the optimal configuration information.
In the above scheme, the step of collecting the flow value and the line state information of the external line and generating the line characteristic information in a preset collection period includes:
Collecting the flow value of the external circuit in a preset time period in a preset collecting period;
generating line basic information of the external line in the time period according to the flow value of the external line in the time period and the line state information of the external line in the time period; the time period is at least one time interval obtained by dividing a preset acquisition period;
and integrating the line basic information of each time period in the acquisition period to form the line characteristic information of the acquisition period.
In the above solution, the calculating, by a preset machine learning model, the line characteristic information of at least one acquisition period to obtain optimal configuration information of the external line in the acquisition period includes:
sequentially inputting the line basic information in the line characteristic information into the machine learning model, and calculating the optimal flow value of the external line in each time period according to the line basic information;
and summarizing the time periods and the optimal flow values thereof to form a flow array for representing the optimal configuration information of the external circuit in the acquisition period.
In the above solution, after the routing request information to the external line according to the optimal configuration information, the method further includes:
when the abnormal state of the line state information of a certain external line is monitored, the request information in the external line with the abnormal state is routed to other external lines;
and identifying line state information in an abnormal state in the external line, setting the line state information as abnormal information, and generating an abnormal report according to the abnormal information.
In the above solution, the routing the request information in the external line where the abnormal state will occur to the other external lines includes:
setting an external circuit with abnormality as an abnormal circuit, and identifying the abnormal condition of the abnormal state;
if the abnormal condition is line abnormality, extracting request information in the abnormal line, and routing the request information to other external lines;
if the abnormal condition is a request abnormality, the request information of the abnormality in the abnormal line is set as an abnormal request, and the abnormal request is routed to other external lines.
In the above solution, the extracting the request information in the abnormal line, and routing the request information to other external lines includes:
Setting other external lines except the abnormal line as normal lines respectively, and identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line;
determining a switching flow value of the normal line according to the difference value, setting request information in the abnormal line as switching request information, and routing switching request information with the quantity corresponding to the switching flow value to the normal line; wherein the handover flow value characterizes an amount of routing handover request information to the normal line.
In the above solution, the setting the request information of the abnormality occurring in the abnormal line as an abnormal request, and routing the abnormal request to other external lines includes:
setting other external lines except the abnormal line as a normal line, identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line, and sequencing the normal line according to the difference value to obtain a normal sequence;
setting a normal line positioned at the first position in the normal sequence as a target line, setting abnormal request information in the abnormal line as an abnormal request route to the target line;
And if the target line is monitored to be incapable of processing the abnormal request, extracting the abnormal request from the target line, and generating an abnormal report with the content of the abnormal request.
In order to achieve the above object, the present invention further provides a traffic analysis and scheduling apparatus, installed in a server, including:
the state acquisition module is used for identifying an external circuit used by a server for accessing an external network and acquiring circuit state information of the external circuit; wherein the line state information includes a normal state and an abnormal state;
the characteristic generation module is used for collecting flow value and line state information of an external line in a preset collection period and generating line characteristic information, wherein the flow value reflects the quantity of request information received by the external line;
the optimal configuration module is used for calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period;
and the request routing module is used for routing request information to the external circuit according to the optimal configuration information.
To achieve the above object, the present invention also provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the steps of the above flow analysis and scheduling method are implemented when the processor of the computer device executes the computer program.
In order to achieve the above object, the present invention further provides a computer readable storage medium, on which a computer program is stored, the computer program stored on the readable storage medium implementing the steps of the flow analysis and scheduling method described above when executed by a processor.
The invention provides a flow analysis and scheduling method, a device, a computer device and a readable storage medium, wherein the flow value of an external circuit in a preset time period is acquired in a preset acquisition period, and circuit basic information is generated according to the flow value of the external circuit in the time period and circuit state information of the external circuit in the time period; the method and the device achieve the purpose of obtaining the flow and the state of the external circuit in each time period from the time dimension, so that the follow-up machine learning model can analyze the flow and the state of the external circuit in each time period based on the time dimension. And analyzing the flow value and the line state information of each external line by adopting a machine learning model to obtain the optimal configuration information for maximizing the flow value of the external line on the premise of ensuring that the line state information of the external line accords with the line state threshold value. By means of routing the request information to the external circuit according to the optimal configuration information, the flow value of the external circuit processing request information is guaranteed, the optimal flow value in the optimal configuration information is not exceeded, the processing performance of the external circuit with good performance is fully released, the quantity of the request information is guaranteed to be processed to the greatest extent on the premise that the circuit state information of the external circuit with poor performance meets the circuit state preset, and the overall stability and the data processing efficiency of all the external circuits are guaranteed.
Drawings
FIG. 1 is a flow chart of a first embodiment of a flow analysis and scheduling method according to the present invention;
FIG. 2 is a schematic diagram illustrating an environment application of a traffic analysis and scheduling method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a flow analysis and scheduling method according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of a program module of a third embodiment of a traffic analysis and scheduling apparatus according to the present invention;
fig. 5 is a schematic hardware structure of a computer device in a fourth embodiment of the computer device of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The flow analysis and scheduling method, the flow analysis and scheduling device, the computer equipment and the readable storage medium are suitable for the technical field of intelligent decision making of artificial intelligence, and are based on a state acquisition module, a feature generation module, an optimal configuration module and a request routing module. The method comprises the steps that an identification server accesses an external circuit used by an external network to acquire circuit state information of the external circuit; and acquiring the flow value and the line state information of the external line, generating line characteristic information, calculating the line characteristic information through a machine learning model to obtain optimal configuration information, and requesting information to the external line route according to the optimal configuration information.
Embodiment one:
referring to fig. 1, a traffic analysis and scheduling method of the present embodiment is applied to a server, and includes:
s101: the method comprises the steps that an external circuit used by an identification server for accessing an external network is acquired, and circuit state information of the external circuit is acquired; wherein the line state information includes a normal state and an abnormal state;
s102: collecting flow value and line state information of an external line in a preset collecting period and generating line characteristic information, wherein the flow value reflects the quantity of request information received by the external line;
s103: calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period;
s104: and routing request information to the external circuit according to the optimal configuration information.
In an exemplary embodiment, the normal state includes line normal and request normal; the abnormal state includes: the communication abnormality of the connectivity abnormality of the external circuit is reflected, the time delay abnormality of the time delay consumed by the external circuit for sending the request information to the external network exceeding a preset delay threshold value is reflected, the time delay abnormality of the time delay exceeding the preset delay threshold value is reflected, and the packet loss abnormality of the packet loss condition of the request information in the external circuit is represented; the communication abnormality is a line abnormality, and the delay abnormality and the packet loss abnormality are request abnormality. Acquiring the flow value of an external circuit in a preset time period in a preset acquisition period, and generating circuit basic information according to the flow value of the external circuit in the time period and the circuit state information of the external circuit in the time period; the method and the device achieve the purpose of obtaining the flow and the state of the external circuit in each time period from the time dimension, so that the follow-up machine learning model can analyze the flow and the state of the external circuit in each time period based on the time dimension. And analyzing the flow value and the line state information of each external line by adopting a machine learning model to obtain the optimal configuration information for maximizing the flow value of the external line on the premise of ensuring that the line state information of the external line accords with the line state threshold value. By means of routing the request information to the external circuit according to the optimal configuration information, the flow value of the external circuit processing request information is guaranteed, the optimal flow value in the optimal configuration information is not exceeded, the processing performance of the external circuit with good performance is fully released, the quantity of the request information is guaranteed to be processed to the greatest extent on the premise that the circuit state information of the external circuit with poor performance meets the circuit state preset, and the overall stability and the data processing efficiency of all the external circuits are guaranteed.
Embodiment two:
the present embodiment is a specific application scenario of the first embodiment, and by this embodiment, the method provided by the present application can be more clearly and specifically described.
The method provided in this embodiment will be specifically described below by taking, as an example, acquisition of flow values and line status information of an external line and calculation to obtain optimal configuration information in a server running a flow analysis and scheduling method. It should be noted that the present embodiment is only exemplary, and does not limit the scope of protection of the embodiment of the present application.
Fig. 2 schematically illustrates an environmental application diagram of a traffic analysis and scheduling method according to a second embodiment of the present application.
In the exemplary embodiment, the servers 2 where the traffic analysis and scheduling methods are located are respectively connected to the external network 4 through the external lines 3; the server 2 may be served via one or more external lines 3, which external lines 3 may comprise various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The external line 3 may comprise a physical link, such as a coaxial cable link, a twisted pair cable link, an optical fiber link, combinations thereof, and/or the like. The external line 3 may comprise a wireless link, such as a cellular link, a satellite link, a Wi-Fi link, and/or the like; the external network 4 is a network server for managing a wide area network and/or a local area network, including a web network server, and also including a local area network server for use within an enterprise or organization.
Fig. 3 is a flowchart of a method for traffic analysis and scheduling according to an embodiment of the present invention, and the method specifically includes steps S201 to S206.
S201: the method comprises the steps that an external circuit used by an identification server for accessing an external network is acquired, and circuit state information of the external circuit is acquired; wherein the line state information includes a normal state and an abnormal state.
In the step, the normal state comprises normal line and normal request; the abnormal state includes: the communication abnormality of the connectivity abnormality of the external circuit is reflected, the time delay abnormality of the time delay consumed by the external circuit for sending the request information to the external network exceeding a preset delay threshold value is reflected, the time delay abnormality of the time delay exceeding the preset delay threshold value is reflected, and the packet loss abnormality of the packet loss condition of the request information in the external circuit is represented; the communication abnormality is a line abnormality, and the delay abnormality and the packet loss abnormality are request abnormality. It should be noted that, the time delay refers to the time required for a packet or a packet to be transmitted from one end of a network to another end. It includes transmission delay, propagation delay, processing delay and queuing delay. (delay = transmit delay + propagation delay + processing delay + queuing delay).
S202: and collecting the flow value and the line state information of the external line in a preset collecting period and generating line characteristic information, wherein the flow value reflects the quantity of the request information received by the external line.
In order to refine the analysis dimension of the flow and the state of the external circuit so as to obtain the optimal flow configuration of each external circuit based on the time dimension, the step is to acquire the flow value of the external circuit in a preset time period in a preset acquisition period, and generate circuit basic information according to the flow value of the external circuit in the time period and the circuit state information of the external circuit in the time period; the method and the device achieve the purpose of obtaining the flow and the state of the external circuit in each time period from the time dimension, so that the follow-up machine learning model can analyze the flow and the state of the external circuit in each time period based on the time dimension.
In a preferred embodiment, the collecting the flow value and the line status information of the external line and generating the line characteristic information in a preset collecting period includes:
s21: collecting the flow value of the external circuit in a preset time period in a preset collecting period;
s22: generating line basic information of the external line in the time period according to the flow value of the external line in the time period and the line state information of the external line in the time period; the time period is at least one time interval obtained by dividing a preset acquisition period;
S23: and integrating the line basic information of each time period in the acquisition period to form the line characteristic information of the acquisition period.
In this embodiment, the year is taken as the collection period, and the month or every N months is taken as the time period; or taking a month as the acquisition period, and taking each day or every N days as the time period; or taking a day as a collection period, and taking each hour or every N hours as the time period; or in hours as the acquisition period, in minutes or N minutes as the time period.
Illustratively, assuming that the acquisition period is 2019, 10, 23, the line base information includes, during a 0-6 time period: the line state information of the time interval from 11 points to 12 points and 30 points is normal state-line normal, the line state information of the time interval from 4 points and 30 points to 4 points and 32 points is abnormal state-line abnormality-connected abnormality, 100 pieces of request information are received, wherein 90 pieces of the line state information of the request information are normal state-request normal, 3 pieces of the line state information of the request information are abnormal state-request abnormality-delay abnormality, and 7 pieces of the line state information of the request information are abnormal state-request abnormality-feedback abnormality. According to the above example, the line basic information integrating the 6-point to 12-point time period, the 12-point to 18-point time period, and the 18-point to 24-point time period forms the line characteristic information of 2019, 10, 23 days.
S203: calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period.
In the step, a machine learning model is adopted to analyze the flow value and the line state information of each external line, so as to obtain the optimal configuration information for maximizing the flow value of the external line on the premise of ensuring that the line state information of the external line accords with a line state threshold value.
In this embodiment, a computer model with a least square method is used as the machine learning model, and the least square method is a least square method (also called a least squares method) which is a mathematical optimization technique. It finds the best functional match for the data by minimizing the sum of squares of the errors. Unknown data can be simply obtained by using a least square method, and the square sum of errors between the obtained data and actual data is minimized; therefore, the line basic information of the target time period in the at least one acquisition period can be subjected to curve fitting through the least square method, and a functional relation between the flow value in the plurality of line basic information and the duty ratio of the time of the abnormal state in the target time period is obtained.
In a preferred embodiment, the calculating, by a preset machine learning model, the line characteristic information of at least one acquisition period to obtain optimal configuration information of the external line in the acquisition period includes:
s31: sequentially inputting the line basic information in the line characteristic information into the machine learning model, and calculating the optimal flow value of the external line in each time period according to the line basic information;
s32: and summarizing the time periods and the optimal flow values thereof to form a flow array for representing the optimal configuration information of the external circuit in the acquisition period.
Specifically, the duty ratio in the period of time at the preset time of the abnormal state is set as the line state threshold;
acquiring any time period of the out-of-line characteristic information and setting the out-of-line characteristic information as a target time period; extracting out-of-line basic information corresponding to the target time period in at least one piece of out-of-line characteristic information, and setting the out-of-line basic information as target basic information;
extracting a flow value in the target basic information, setting the flow value as a target flow value, calculating the duty ratio of the time of the abnormal state in the target basic information in the target time period, and setting the duty ratio as a target abnormal duty ratio; constructing a fitting curve according to the target flow value and the target abnormal duty ratio by the machine learning model, wherein the fitting curve represents a functional relation between the flow value in the target time period in each piece of off-line basic information and the duty ratio of the time of the abnormal state in each piece of off-line basic information in the target time period;
And calculating the out-of-line state threshold value through the fitting curve to obtain the optimal flow value.
The method is used for obtaining the optimal flow value of each time period in at least one piece of off-line characteristic information of the external circuit, and summarizing each time period and the optimal flow value thereof to form a flow array for representing the optimal configuration information of the external circuit in the acquisition period.
S204: and routing request information to the external circuit according to the optimal configuration information.
In order to ensure the quantity of the request information obtained by each external circuit, more request information is processed on the premise that the external circuit cannot be abnormal or the abnormal time is in a controllable range, the flow value of the request information is ensured to be processed by the external circuit according to the optimal configuration information in a mode of routing the request information to the external circuit, the optimal flow value in the optimal configuration information is not exceeded, the processing performance of the external circuit with better performance is fully released, and the quantity of the request information is furthest processed on the premise that the circuit state information of the external circuit with poorer performance meets the circuit state preset, so that the overall stability and the data processing efficiency of all the external circuits are ensured.
S205: when the abnormal state of the line state information of one external line is monitored, the request information in the external line with the abnormal state is routed to other external lines.
In order to monitor an abnormal line in real time and avoid the situation that the reliability of the external line route is low because feedback information cannot be generated due to the abnormal condition of the external line, when the abnormal condition of the line state information of a certain external line is monitored, the step routes the request information in the external line with the abnormal condition to other external lines to realize the flow switching of the external line, and the flow switching is realized to route the request information in the abnormal external line to the external line with the normal condition so as to ensure that the received request information can generate corresponding feedback information in time. In this embodiment, an external listening component with a listen () function is used to listen to whether an external line has a line anomaly, for example: blocking anomalies or connectivity anomalies; and for monitoring whether the external line generates feedback anomaly information with a request error code, for example: feedback anomaly information with request error code of 400-error request, 401-access denied, 504-gateway timeout, etc., which characterizes the request information in the external line as delay anomaly or feedback anomaly.
In a preferred embodiment, the routing of the request information in the external line in which the abnormal state will occur to the other external line includes:
s51: setting an external circuit with abnormality as an abnormal circuit, and identifying the abnormal condition of the abnormal state;
in the step, identifying the abnormal condition of the abnormal line; if the abnormal condition is the abnormal condition, judging the abnormal condition as line abnormality; and if the abnormal condition is feedback abnormal information with the request error code fed back by the abnormal line, judging the abnormal condition as the request abnormality.
S52: and if the abnormal condition is line abnormality, extracting request information in the abnormal line, and routing the request information to other external lines.
In the step, the request information in the abnormal line is extracted and routed to other external lines, so that the technical effect of switching the flow of the abnormal line to other normal external lines is realized; further, the line number of the abnormal line is sent to a control end, so that maintenance personnel can repair the abnormal line according to the number.
In a preferred embodiment, the extracting the request information in the abnormal line and routing the request information to other external lines includes:
S521: setting other external lines except the abnormal line as normal lines respectively, and identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line;
s522: determining a switching flow value of the normal line according to the difference value, setting request information in the abnormal line as switching request information, and routing switching request information with the quantity corresponding to the switching flow value to the normal line; wherein the handover flow value characterizes an amount of routing handover request information to the normal line.
Specifically, adding the difference values of all the normal lines to obtain a total difference value, and calculating the ratio of the difference value of the normal line in the total difference value; setting the request information in the abnormal line as switching request information, calculating a switching flow value reflecting the quantity of the switching request information, and multiplying the duty ratio by the switching flow value to obtain a line switching value; and routing switching request information with the quantity consistent with the line switching value to the normal line.
S53: if the abnormal condition is a request abnormality, the request information of the abnormality in the abnormal line is set as an abnormal request, and the abnormal request is routed to other external lines.
In this step, by routing the abnormal request in the abnormal line to the other external line, the technical effect of switching the flow of the abnormal line to the other normal external line is achieved, and at the same time, the abnormal line is restored to the external line.
In a preferred embodiment, the setting the request information of the abnormality in the abnormal line as an abnormal request, and routing the abnormal request to other external lines includes:
s531: setting other external lines except the abnormal line as a normal line, identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line, and sequencing the normal line according to the difference value to obtain a normal sequence;
s532: setting a normal line positioned at the first position in the normal sequence as a target line, setting abnormal request information in the abnormal line as an abnormal request route to the target line;
s533: and if the target line is monitored to be incapable of processing the abnormal request, extracting the abnormal request from the target line, and generating an abnormal report with the content of the abnormal request.
In this step, a target monitoring component with a listen () function is constructed to monitor whether the target line can normally process the exception request, and if the target monitoring component does not receive any feedback exception information, the target line is determined to have successfully processed the exception request; if the target monitoring component monitors feedback abnormal information sent by a target line, judging that the target line cannot process the abnormal request; the feedback anomaly information includes information requesting for an error code, for example: feedback anomaly information with request error code of 400-error request, 401-access denied, 504-gateway timeout, etc., which characterizes the request information in the target line as delay anomaly or feedback anomaly.
S206: and identifying line state information in an abnormal state in the external line, setting the line state information as abnormal information, and generating an abnormal report according to the abnormal information.
In order to ensure that the control end can timely acquire the abnormal state of each external circuit so as to facilitate the subsequent maintenance and repair of the external circuit, the step generates an abnormal report according to the abnormal information by identifying the circuit state information in the abnormal state in the external circuit and setting the circuit state information as the abnormal information; the abnormality report includes the line number of the external line in an abnormal state and the abnormal state information thereof.
Embodiment III:
referring to fig. 4, a traffic analyzing and scheduling device 1 of the present embodiment is installed in a server 2, and includes:
a state acquisition module 11, configured to identify an external line used by a server to access an external network, and acquire line state information of the external line; wherein the line state information includes a normal state and an abnormal state;
the feature generation module 12 is configured to collect a flow value and line status information of an external line in a preset collection period, and generate line feature information, where the flow value reflects the amount of request information received by the external line;
The optimal configuration module 13 is configured to calculate the line characteristic information of at least one acquisition period through a preset machine learning model, so as to obtain optimal configuration information of the external line in the acquisition period;
a request routing module 14, configured to route request information to the external line according to the optimal configuration information.
Optionally, the flow analysis and scheduling device 1 further includes:
the abnormal routing module 15 is configured to route, when it is monitored that the line state information of a certain external line has an abnormal state, request information in the external line having the abnormal state to other external lines.
Optionally, the flow analysis and scheduling device 1 further includes:
the abnormality processing module 16 is configured to identify and set, as abnormality information, line state information in an abnormal state in the external line, and generate an abnormality report based on the abnormality information.
Optionally, the feature generation module 12 further includes:
a flow collection unit 121, configured to collect, in a preset collection period, a flow value of the external line in a preset period;
an information generating unit 122 for generating line basic information of the external line in the period according to a flow value of the external line in the period and line state information of the external line in the period; the time period is at least one time interval obtained by dividing a preset acquisition period;
And an information integrating unit 123, configured to integrate the line basic information of each time period in the acquisition period to form line characteristic information of the acquisition period.
Optionally, the optimal configuration module 13 further includes:
a model input unit 131, configured to sequentially enter line basic information in the line characteristic information into the machine learning model, and calculate an optimal flow value of the external line in each time period according to the line basic information;
the array generating unit 132 is configured to aggregate the time periods and the optimal flow values thereof to form a flow array, so as to characterize the optimal configuration information of the external circuit in the acquisition period.
Optionally, the anomaly routing module 15 further includes:
an abnormality identification unit 151 for setting an external line in which abnormality occurs as an abnormal line, and identifying an abnormal condition of the abnormal state;
and a line anomaly unit 152, configured to extract request information in the anomaly line and route the request information to other external lines when the anomaly is a line anomaly.
And a request exception unit 153, configured to set, when the exception condition is a request exception, request information that an exception occurs in the exception line as an exception request, and route the exception request to another external line.
Optionally, the line anomaly unit 152 further includes:
a line difference subunit 1521, configured to set other external lines except the abnormal line as normal lines, respectively, and identify a difference between a current flow value in the normal line and an optimal flow value of the normal line;
a line routing subunit 1522, configured to determine a switching flow value of the normal line according to the difference value, set request information in the abnormal line as switching request information, and route switching request information corresponding to the switching flow value to the normal line; wherein the handover flow value characterizes an amount of routing handover request information to the normal line.
Optionally, the request exception unit 153 further includes:
a request difference subunit 1531, configured to set other external lines except for the abnormal line as a normal line, identify a difference between a current flow value in the normal line and an optimal flow value of the normal line, and sort the normal line according to the difference to obtain a normal sequence;
a request target subunit 1532, configured to set a normal line located at the first position in the normal sequence as a target line, and set request information of an abnormality occurring in the abnormal line as an abnormal request route to the target line;
A request exception subunit 1533 is configured to extract the exception request from the target line and generate an exception report whose content is the exception request when it is monitored that the target line cannot process the exception request.
The technical scheme relates to the technical field of intelligent decision making of artificial intelligence, and obtains line state information of an external line by identifying the external line used by a server for accessing the external network; and acquiring the flow value and the line state information of the external line, generating line characteristic information, calculating the line characteristic information through a machine learning model to obtain optimal configuration information, and using the optimal configuration information as a prediction model for predicting the request flow of each external line route, and requesting information to the external line route according to the optimal configuration information.
Embodiment four:
in order to achieve the above objective, the present invention further provides a computer device 5, where the components of the flow analysis and scheduling apparatus of the third embodiment may be dispersed in different computer devices, and the computer device 5 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including a separate server or a server cluster formed by multiple application servers) that execute a program, or the like. The computer device of the present embodiment includes at least, but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in fig. 5. It should be noted that fig. 5 only shows a computer device with components-but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
In the present embodiment, the memory 51 (i.e., readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 51 may also be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like. Of course, the memory 51 may also include both internal storage units of the computer device and external storage devices. In this embodiment, the memory 51 is generally used to store an operating system installed in a computer device and various application software, such as program codes of the traffic analysis and scheduling apparatus of the third embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 52 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device. In this embodiment, the processor 52 is configured to execute the program code stored in the memory 51 or process data, for example, execute the traffic analysis and scheduling device, so as to implement the traffic analysis and scheduling methods of the first embodiment and the second embodiment.
Fifth embodiment:
to achieve the above object, the present invention also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by the processor 52, performs the corresponding functions. The computer readable storage medium of the present embodiment is used for storing a computer program for implementing the flow analysis and scheduling method, and when executed by the processor 52, implements the flow analysis and scheduling methods of the first and second embodiments.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (9)
1. The traffic analysis and scheduling method is applied to a server and is characterized by comprising the following steps:
the method comprises the steps that an external circuit used by an identification server for accessing an external network is acquired, and circuit state information of the external circuit is acquired; wherein the line state information includes a normal state and an abnormal state;
collecting flow value and line state information of an external line in a preset collecting period and generating line characteristic information, wherein the flow value reflects the quantity of request information received by the external line;
Calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period;
calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain optimal configuration information of the external line in the acquisition period, wherein the method comprises the following steps:
sequentially inputting the line basic information in the line characteristic information into the machine learning model, and calculating the optimal flow value of the external line in each time period according to the line basic information;
summarizing each time period and the optimal flow value thereof to form a flow array, wherein the flow array is used for representing the optimal configuration information of the external circuit in the acquisition period; and routing request information to the external circuit according to the optimal configuration information.
2. The flow analysis and scheduling method according to claim 1, wherein the step of collecting the flow value and the line status information of the external line and generating the line characteristic information in a preset collection period includes:
collecting the flow value of the external circuit in a preset time period in a preset collecting period;
Generating line basic information of the external line in the time period according to the flow value of the external line in the time period and the line state information of the external line in the time period; the time period is at least one time interval obtained by dividing a preset acquisition period;
and integrating the line basic information of each time period in the acquisition period to form the line characteristic information of the acquisition period.
3. The traffic analysis and scheduling method according to claim 1, wherein after the request for information from the external line is routed according to the optimal configuration information, the method further comprises:
when the abnormal state of the line state information of a certain external line is monitored, the request information in the external line with the abnormal state is routed to other external lines;
and identifying line state information in an abnormal state in the external line, setting the line state information as abnormal information, and generating an abnormal report according to the abnormal information.
4. The traffic analysis and scheduling method according to claim 3, wherein routing the request information in the external line in which the abnormal state occurs to other external lines comprises:
Setting an external circuit with abnormality as an abnormal circuit, and identifying the abnormal condition of the abnormal state;
if the abnormal condition is line abnormality, extracting request information in the abnormal line, and routing the request information to other external lines;
if the abnormal condition is a request abnormality, the request information of the abnormality in the abnormal line is set as an abnormal request, and the abnormal request is routed to other external lines.
5. The traffic analysis and scheduling method according to claim 4, wherein the extracting the request information in the abnormal line and routing the request information to other external lines includes:
setting other external lines except the abnormal line as normal lines respectively, and identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line;
determining a switching flow value of the normal line according to the difference value, setting request information in the abnormal line as switching request information, and routing switching request information with the quantity corresponding to the switching flow value to the normal line; wherein the handover flow value characterizes an amount of routing handover request information to the normal line.
6. The traffic analysis and scheduling method according to claim 4, wherein the setting the abnormal request information in the abnormal line as an abnormal request, and routing the abnormal request to other external lines, includes:
setting other external lines except the abnormal line as a normal line, identifying a difference value between a current flow value in the normal line and an optimal flow value of the normal line, and sequencing the normal line according to the difference value to obtain a normal sequence;
setting a normal line positioned at the first position in the normal sequence as a target line, setting abnormal request information in the abnormal line as an abnormal request route to the target line;
and if the target line is monitored to be incapable of processing the abnormal request, extracting the abnormal request from the target line, and generating an abnormal report with the content of the abnormal request.
7. A traffic analysis and scheduling apparatus installed in a server, comprising:
the state acquisition module is used for identifying an external circuit used by a server for accessing an external network and acquiring circuit state information of the external circuit; wherein the line state information includes a normal state and an abnormal state;
The characteristic generation module is used for collecting flow value and line state information of an external line in a preset collection period and generating line characteristic information, wherein the flow value reflects the quantity of request information received by the external line;
the optimal configuration module is used for calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain the optimal configuration information of the external line in the acquisition period; calculating the line characteristic information of at least one acquisition period through a preset machine learning model to obtain optimal configuration information of the external line in the acquisition period, wherein the method comprises the following steps: sequentially inputting the line basic information in the line characteristic information into the machine learning model, and calculating the optimal flow value of the external line in each time period according to the line basic information; summarizing each time period and the optimal flow value thereof to form a flow array, wherein the flow array is used for representing the optimal configuration information of the external circuit in the acquisition period;
and the request routing module is used for routing request information to the external circuit according to the optimal configuration information.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor of the computer device implements the steps of the flow analysis and scheduling method of any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium having a computer program stored thereon, characterized in that the computer program stored on the readable storage medium, when executed by a processor, implements the steps of the flow analysis and scheduling method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111526544.8A CN114221874B (en) | 2021-12-14 | 2021-12-14 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111526544.8A CN114221874B (en) | 2021-12-14 | 2021-12-14 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114221874A CN114221874A (en) | 2022-03-22 |
| CN114221874B true CN114221874B (en) | 2023-11-14 |
Family
ID=80701799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111526544.8A Active CN114221874B (en) | 2021-12-14 | 2021-12-14 | Traffic analysis and scheduling method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114221874B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110311812A (en) * | 2019-06-24 | 2019-10-08 | 深圳市腾讯计算机系统有限公司 | A kind of network analysis method, device and storage medium |
| CN110958626A (en) * | 2019-12-06 | 2020-04-03 | 紫光云(南京)数字技术有限公司 | Link selection method based on shortest response time |
| CN112306808A (en) * | 2020-11-03 | 2021-02-02 | 平安科技（深圳）有限公司 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
| WO2021051546A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Link abnormality recognition method, server and computer-readable storage medium |
| CN112637292A (en) * | 2020-12-14 | 2021-04-09 | 中国联合网络通信集团有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113220481A (en) * | 2021-04-30 | 2021-08-06 | 平安壹钱包电子商务有限公司 | Request processing and feedback method and device, computer equipment and readable storage medium |
-
2021
- 2021-12-14 CN CN202111526544.8A patent/CN114221874B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110311812A (en) * | 2019-06-24 | 2019-10-08 | 深圳市腾讯计算机系统有限公司 | A kind of network analysis method, device and storage medium |
| WO2021051546A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Link abnormality recognition method, server and computer-readable storage medium |
| CN110958626A (en) * | 2019-12-06 | 2020-04-03 | 紫光云(南京)数字技术有限公司 | Link selection method based on shortest response time |
| CN112306808A (en) * | 2020-11-03 | 2021-02-02 | 平安科技（深圳）有限公司 | Performance monitoring and evaluating method and device, computer equipment and readable storage medium |
| CN112637292A (en) * | 2020-12-14 | 2021-04-09 | 中国联合网络通信集团有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113220481A (en) * | 2021-04-30 | 2021-08-06 | 平安壹钱包电子商务有限公司 | Request processing and feedback method and device, computer equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114221874A (en) | 2022-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109495502B (en) | Industrial control network security and health index evaluation method and device | |
| CN110198305A (en) | It attends a banquet method for detecting abnormality, system, computer equipment and the storage medium of IP | |
| CN108092836A (en) | The monitoring method and device of a kind of server | |
| US11586981B2 (en) | Failure analysis device, failure analysis method, and failure analysis program | |
| CN111258305B (en) | Wei Xingyun control center system, equipment management method, equipment and storage medium | |
| US20210226853A1 (en) | Automated network monitoring and control | |
| US11252066B2 (en) | Automated network monitoring and control | |
| CN116723136B (en) | Network data detection method applying FCM clustering algorithm | |
| CN114221874B (en) | Traffic analysis and scheduling method and device, computer equipment and readable storage medium | |
| CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
| CN112184072A (en) | Machine room equipment management method and device | |
| CN110069382B (en) | Software monitoring method, server, terminal device, computer device and medium | |
| CN115378841B (en) | Method and device for detecting state of equipment accessing cloud platform, storage medium and terminal | |
| US11329868B2 (en) | Automated network monitoring and control | |
| CN114296987A (en) | Fault processing method and device, electronic equipment and computer storage medium | |
| CN114327967A (en) | Equipment repairing method and device, storage medium and electronic device | |
| EP4336883A1 (en) | Modeling method, network element data processing method and apparatus, electronic device, and medium | |
| CN116719639A (en) | Link dynamic adjustment and data processing method, device, computer equipment and medium | |
| CN115617617A (en) | Equipment state monitoring method and device | |
| CN118012753A (en) | Test method, test equipment and test system | |
| CN114007151A (en) | Service configuration method and device for cooperation of IP network and optical network | |
| CN117421177A (en) | Method and device for monitoring running state of server | |
| CN116094908A (en) | Log file storage method, device, equipment and storage medium |
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 |