CN111290903B - Software system monitoring method and device based on user behavior and machine learning - Google Patents
Software system monitoring method and device based on user behavior and machine learning Download PDFInfo
- Publication number
- CN111290903B CN111290903B CN201811390496.2A CN201811390496A CN111290903B CN 111290903 B CN111290903 B CN 111290903B CN 201811390496 A CN201811390496 A CN 201811390496A CN 111290903 B CN111290903 B CN 111290903B
- Authority
- CN
- China
- Prior art keywords
- early warning
- current
- same time
- moment
- current moment
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
-
- 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
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the invention provides a software system monitoring method and device based on user behavior and machine learning, wherein the method comprises the following steps: acquiring the number of login users at the current moment; and if the number of the login user at the current moment is larger than the early warning threshold at the current moment, sending out early warning information. According to the software system monitoring method and device based on user behavior and machine learning, the running state of the system is monitored in real time by setting the dynamic early warning threshold, and the accuracy and timeliness of system monitoring are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of system monitoring, in particular to a software system monitoring method and device based on user behavior and machine learning.
Background
The monitoring of the software system is very important for the stability of the software system, and the abnormality of the software system can be timely found through the monitoring of the software system, and related operation and maintenance personnel can be notified through short messages, mails and the like.
In the prior art, the condition of a target software system is monitored by adding a target software system link into a dial testing system and periodically dial testing. When in dialing, a target software system is required to prepare a dial testing link in advance, add a dial testing plan, set dial testing frequency and the like. After the system is started, the dial testing system accesses the dial testing link regularly, and judges the state of the target software system according to the returned result or whether the return exists. Specifically, the target software system is determined to have abnormality when no return is performed or the return is considered to be abnormal from the perspective of the dial testing system, and at this time, relevant operation and maintenance personnel are notified in the form of short messages, mails and the like.
However, the dial testing system needs dial testing linkage, which is often old, such as a target software system homepage, if the coverage is insufficient, other links are added, the dial testing frequency is often not lower than the use frequency of a user, otherwise, the monitoring effect cannot be achieved, the use pressure of the software system is increased intangibly, meanwhile, the mechanical checking link returns a result, an alarm is sent only under the condition that the software system is abnormal, and the method plays no substantial role for the software system with high use frequency of the user.
Disclosure of Invention
It is an aim of embodiments of the present invention to provide a method and apparatus for monitoring a software system based on user behaviour and machine learning which overcomes or at least partly solves the above problems.
In order to solve the above technical problems, in one aspect, an embodiment of the present invention provides a software system monitoring method, including:
acquiring the number of login users at the current moment;
and if the number of the login user at the current moment is larger than the early warning threshold at the current moment, sending out early warning information.
In another aspect, an embodiment of the present invention provides a software system monitoring apparatus, including:
the acquisition module is used for acquiring the number of the login users at the current moment;
and the early warning module is used for sending early warning information if judging that the number of the login user at the current moment is greater than the early warning threshold at the current moment.
In still another aspect, an embodiment of the present invention provides an electronic device, including:
the device comprises a memory and a processor, wherein the processor and the memory are communicated with each other through a bus; the memory stores program instructions executable by the processor, which are called by the processor to perform the method described above.
In yet another aspect, embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method described above.
According to the software system monitoring method and device provided by the embodiment of the invention, the running state of the system is monitored in real time by setting the dynamic early warning threshold, so that the accuracy and timeliness of system monitoring are improved.
Drawings
FIG. 1 is a schematic diagram of a software system monitoring method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a software system monitoring device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present 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.
Fig. 1 is a schematic diagram of a software system monitoring method provided by an embodiment of the present invention, and as shown in fig. 1, an embodiment of the present invention provides a software system monitoring method, an execution body of which is a software system monitoring device, where the method includes:
step S101, acquiring the number of login users at the current moment;
step S102, if the number of the login users at the current moment is larger than the early warning threshold at the current moment, early warning information is sent out.
Specifically, the software system monitoring method provided by the embodiment of the invention establishes an effective method capable of continuously reflecting the use condition of the system, improves the monitoring instantaneity, and achieves the aim of monitoring work by being matched with other monitoring modes.
Because the service condition of the system is changed at any time, the monitoring method for the software system provided by the embodiment of the invention also can monitor the alarm threshold value to be changed at any time, so that the timeliness and the accuracy of the early warning can be ensured.
First, the number of registered users at the current time is acquired. In order to reflect the use condition of the system in real time, the number of users logging in the time period of the system is extracted to be key data, meanwhile, the complexity and feasibility of an algorithm are considered, the granularity of time is required to be set in a reasonable range, if the granularity is too small, huge calculation resources are consumed, and if the granularity is too large, a good real-time monitoring effect cannot be achieved. Through investigation of actual conditions and test results, granularity taking minutes as time is suitable for statistics, namely, a time interval which takes minutes as a statistics unit period is finally determined, data acquisition and calculation are carried out, and dynamic early warning of a system is carried out. The number of registered users at the current moment can be a certain sampling data in the current one minute, or can be an average value of all sampling data, and the specific situation can be combined.
After the number of the login users at the current moment is obtained, if the judgment shows that the number of the login users at the current moment is larger than the early warning threshold at the current moment, early warning information is sent out. The operation and maintenance personnel can be notified in the form of short messages or mails so as to make timely processing.
If the number of the login users at the current moment is less than or equal to the early warning threshold value at the current moment, the system is normal, and early warning information is not sent.
The early warning threshold value at the current moment is obtained through calculation according to historical data through a preset machine learning model, and the early warning threshold values at different moments are different, so that a dynamic, real-time and accurate early warning effect is achieved.
For example, if the number of registered users at the current moment is 100, if the pre-warning threshold value at the current moment obtained by calculation is 90, which indicates that the number of registered users at the current moment exceeds the pre-warning threshold value at the current moment, pre-warning information is sent, and operation and maintenance personnel are notified in a short message mode so as to make timely processing.
According to the software system monitoring method provided by the embodiment of the invention, the running state of the system is monitored in real time by setting the dynamic early warning threshold, so that the accuracy and timeliness of system monitoring are improved.
On the basis of the foregoing embodiment, further, if it is determined that the number of logged-in users at the current time is greater than the early warning threshold at the current time, before sending the early warning information, the method further includes:
acquiring historical data of a plurality of weeks, wherein the historical data comprises the number of registered users at each moment, the early warning state at each moment and the historical early warning threshold at each moment;
and inputting the historical data or part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment.
Specifically, according to the software system monitoring method provided by the embodiment of the invention, the pre-warning threshold value at the current moment is calculated and obtained by utilizing the preset machine learning model according to the historical data, and the pre-warning threshold values at different moments are different, so that a dynamic, real-time and accurate pre-warning effect is achieved.
Before early warning, firstly, historical data of a plurality of weeks are obtained, wherein the historical data comprise the number of registered users at each moment, the early warning state at each moment and the historical early warning threshold value at each moment.
And then, inputting the historical data or part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment.
The size of the acquired history data may be determined according to the actual situation, and because the usage of the system shows a periodic change with a cycle as one cycle, when calculating the early warning threshold, the actual situation is considered, and the acquired history data takes a cycle as a time length, for example, 12 cycles of history data are acquired.
The machine learning model is designed in advance, the machine learning model is used for calculating the early warning threshold, the degree of manual intervention is low, and the machine learning model has objective reference value, so that the obtained early warning threshold at the current moment is more reasonable and more accurate.
According to the software system monitoring method provided by the embodiment of the invention, the early warning threshold value at the current moment is dynamically calculated through the machine learning model, the current login user number is dynamically tracked, the running state of the system is monitored in real time, and the accuracy and timeliness of system monitoring are improved.
On the basis of the above embodiments, further, the machine learning model is specifically:
wherein Y is t Z is the maximum number of users that the system can bear and B is the early warning threshold value at the current moment t-1 A pre-warning state at the same time of the 1 st week before the current time, B t-1 The value of (1) is 0 or 1, S t-1 =0 indicates that no warning information is sent at the same time of week 1 before the current time, B t-1 =1 indicates that the same time of week 1 before the current time gives out the early warning information, B t-2 A pre-warning state at the same time of the 2 nd week before the current time, B t-2 The value of (1) is 0 or 1, B t-2 =0 indicates that no warning information is sent at the same time of the 2 nd week before the current time, B t-2 =1 indicates that the same time of week 2 before the current time gives out the early warning information, B t-m A pre-warning state at the same time of the mth week before the current time, B t-m The value of (1) is 0 or 1, B t-m =0 indicates that no warning information is sent at the same time of the mth week before the current time, B t-m =1 indicates that the same time of the mth week before the current time sends out the early warning information, Y t-1 Is the early warning threshold value of the same time of the 1 st week before the current time,
x is the average value of all historical early warning thresholds i The number of registered users at the same time of the ith week before the current time is represented, N is the number of the weeks, and N is more than m.
Specifically, for example, the granularity is set to be the time of minute, the current time is set to be 7 minutes of wednesday of 13 th week in 2018, history data of 12 weeks is acquired, i.e., n=12, and m=3 is acquired, i.e., the early warning state at the same time of 3 weeks before the current time is analyzed.
The machine learning model specifically comprises:
wherein Y is t The early warning threshold value of 7 minutes of Tuesday of 13 weeks in 2018 is Z is the maximum number of users which can be borne by the system, B t-1 Early warning state of 7 th minute of Tuesday of 12 th week of 2018, B t-1 The value of (1) is 0 or 1, B t-1 =0 indicates that no warning information is sent out at 7 minutes of wednesday at 12 th week of 2018, B t-1 =1 indicates that early warning information is sent out on 7 th minute of wednesday at 12 th week of 2018, B t-2 Early warning state of 7 th minute of Tuesday 11 in 2018, S t-2 The value of (1) is 0 or 1, B t-2 =0 indicates that no warning information is sent out on 7 th minute of wednesday at 11 th week of 2018, B t-2 =1 indicates that early warning information is sent out on 7 th minute of wednesday at 11 th week of 2018, B t-3 Early warning state of 7 th minute of Tuesday of 10 th week of 2018, B t-m The value of (1) is 0 or 1, B t-3 =0 indicates that no warning information is sent out on 7 th minute of wednesday on 10 th week of 2018, B t-3 =1 indicates that early warning information is given at 7 minutes of wednesday at 10 th week in 2018, Y t-1 An early warning threshold of 7 th minute on wednesday at week 12 in 2018,
x is the average value of all historical early warning thresholds i Indicating the number of registered users at 7 minutes of wednesday at the i-th week before week 13 in 2018, e.g., X 2 The number of registered users at 7 minutes of wednesday at 11 weeks 2018.
According to the software system monitoring method provided by the embodiment of the invention, the early warning threshold value at the current moment is dynamically calculated through the machine learning model, the current login user number is dynamically tracked, the running state of the system is monitored in real time, and the accuracy and timeliness of system monitoring are improved.
On the basis of the above embodiments, further, after the outputting the early warning threshold, the method further includes:
and generating a dynamic visual monitoring graph according to the number of the login users at the current moment and the early warning threshold value at the current moment.
Specifically, in order to facilitate the operation and maintenance personnel to intuitively monitor the operation condition of the system, a dynamic visual monitoring chart is generated according to the number of the login users at the current moment and the early warning threshold value at the current moment, namely, the number of the login users and the early warning threshold value are displayed in a dynamic curve mode, and the operation and maintenance personnel can intuitively monitor the operation condition according to the dynamic visual monitoring chart.
And storing the acquired login user number at the current moment and the early warning threshold value at the current moment into an Oracle database, wherein the obtained login user number at the current moment and the early warning threshold value at the current moment are used for supporting quick data query of the dynamic visual monitoring chart.
According to the software system monitoring method provided by the embodiment of the invention, the early warning threshold value at the current moment is dynamically calculated through the machine learning model, the current login user number is dynamically tracked, the running state of the system is monitored in real time, and the accuracy and timeliness of system monitoring are improved.
On the basis of the above embodiments, further, the obtaining the number of login users at the current time specifically includes:
acquiring system log information at the current moment;
and extracting the number of login users at the current moment from the system log information.
Specifically, an analysis program is developed through the J2EE framework to perform key data crawling from a large underlying log data store ES.
First, a system log at the current time is acquired. The system log information includes each system log and operation log.
Then, the number of registered users at the current time is extracted from the system log information.
According to the software system monitoring method provided by the embodiment of the invention, the early warning threshold value at the current moment is dynamically calculated through the machine learning model, the current login user number is dynamically tracked, the running state of the system is monitored in real time, and the accuracy and timeliness of system monitoring are improved.
Fig. 2 is a schematic diagram of a software system monitoring device according to an embodiment of the present invention, and as shown in fig. 2, the embodiment of the present invention provides a software system monitoring device for executing the method described in any of the foregoing embodiments, which specifically includes an obtaining module 201 and an early warning module 202, wherein:
the obtaining module 201 is configured to obtain a number of login users at a current moment; the early warning module 202 is configured to send early warning information if it is determined that the number of logged-in users at the current time is greater than an early warning threshold at the current time.
Specifically, the software system monitoring method provided by the embodiment of the invention establishes an effective method capable of continuously reflecting the use condition of the system, improves the monitoring instantaneity, and achieves the aim of monitoring work by being matched with other monitoring modes.
Because the service condition of the system is changed at any time, the monitoring method for the software system provided by the embodiment of the invention also can monitor the alarm threshold value to be changed at any time, so that the timeliness and the accuracy of the early warning can be ensured.
First, the number of registered users at the current time is acquired by the acquisition module 201. In order to reflect the use condition of the system in real time, the number of users logging in the time period of the system is extracted to be key data, meanwhile, the complexity and feasibility of an algorithm are considered, the granularity of time is required to be set in a reasonable range, if the granularity is too small, huge calculation resources are consumed, and if the granularity is too large, a good real-time monitoring effect cannot be achieved. Through investigation of actual conditions and test results, granularity taking minutes as time is suitable for statistics, namely, a time interval which takes minutes as a statistics unit period is finally determined, data acquisition and calculation are carried out, and dynamic early warning of a system is carried out. The number of registered users at the current moment can be a certain sampling data in the current one minute, or can be an average value of all sampling data, and the specific situation can be combined.
After the number of the login users at the current moment is obtained, if the early warning module 202 judges that the number of the login users at the current moment is greater than the early warning threshold at the current moment, early warning information is sent out. The operation and maintenance personnel can be notified in the form of short messages or mails so as to make timely processing.
If the number of the login users at the current moment is less than or equal to the early warning threshold value at the current moment, the system is normal, and early warning information is not sent.
The early warning threshold value at the current moment is obtained through calculation according to historical data through a preset machine learning model, and the early warning threshold values at different moments are different, so that a dynamic, real-time and accurate early warning effect is achieved.
For example, if the number of registered users at the current moment is 100, if the pre-warning threshold value at the current moment obtained by calculation is 90, which indicates that the number of registered users at the current moment exceeds the pre-warning threshold value at the current moment, pre-warning information is sent, and operation and maintenance personnel are notified in a short message mode so as to make timely processing.
According to the software system monitoring device provided by the embodiment of the invention, the running state of the system is monitored in real time by setting the dynamic early warning threshold, so that the accuracy and timeliness of system monitoring are improved.
On the basis of the embodiment, the device further comprises a computing module,
the calculation module is used for acquiring historical data of a plurality of weeks, wherein the historical data comprises the number of login users at each moment, the early warning state at each moment and the historical early warning threshold value at each moment;
and inputting the historical data or part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment.
Specifically, according to the software system monitoring device provided by the embodiment of the invention, the pre-warning threshold value at the current moment is calculated by utilizing the preset machine learning model according to the historical data, and the pre-warning threshold values at different moments are different, so that a dynamic, real-time and accurate pre-warning effect is achieved.
Before early warning, firstly, historical data of a plurality of weeks are obtained through a calculation module, wherein the historical data comprise the number of registered users at each moment, the early warning state at each moment and the historical early warning threshold value at each moment.
And then, inputting the historical data or part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment.
The size of the acquired history data may be determined according to the actual situation, and because the usage of the system shows a periodic change with a cycle as one cycle, when calculating the early warning threshold, the actual situation is considered, and the acquired history data takes a cycle as a time length, for example, 12 cycles of history data are acquired.
The machine learning model is designed in advance, the machine learning model is used for calculating the early warning threshold, the degree of manual intervention is low, and the machine learning model has objective reference value, so that the obtained early warning threshold at the current moment is more reasonable and more accurate.
According to the software system monitoring device provided by the embodiment of the invention, the early warning threshold value at the current moment is dynamically calculated through the machine learning model, the current login user number is dynamically tracked, the running state of the system is monitored in real time, and the accuracy and timeliness of system monitoring are improved.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 3, where the device includes: a processor 301, a memory 302, and a bus 303;
wherein the processor 301 and the memory 302 perform communication with each other through the bus 303;
the processor 301 is configured to invoke program instructions in the memory 302 to perform the methods provided by the above-described method embodiments, for example, including:
acquiring the number of login users at the current moment;
and if the number of the login user at the current moment is larger than the early warning threshold at the current moment, sending out early warning information.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the method embodiments described above, for example comprising:
acquiring the number of login users at the current moment;
and if the number of the login user at the current moment is larger than the early warning threshold at the current moment, sending out early warning information.
Embodiments of the present invention provide a non-transitory computer readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including:
acquiring the number of login users at the current moment;
and if the number of the login user at the current moment is larger than the early warning threshold at the current moment, sending out early warning information.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The embodiments of the apparatus and devices described above are merely illustrative, wherein the elements described as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for monitoring a software system, comprising:
acquiring the number of login users at the current moment;
if the number of the login users at the current moment is larger than the early warning threshold at the current moment, sending early warning information;
if the judgment that the number of the logged-in users at the current moment is larger than the early warning threshold at the current moment, before sending out the early warning information, the method further comprises the following steps:
acquiring historical data of a plurality of weeks, wherein the historical data comprises the number of registered users at each moment, the early warning state at each moment and the historical early warning threshold at each moment;
inputting the historical data or a part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment;
the machine learning model specifically comprises:
wherein Y is t Z is the maximum number of users that the system can bear and B is the early warning threshold value at the current moment t-1 A pre-warning state at the same time of the 1 st week before the current time, B t-1 The value of (1) is 0 or 1, B t-1 =0 indicates that no warning information is sent at the same time of week 1 before the current time, B t-1 =1 indicates that the same time of week 1 before the current time gives out the early warning information, B t-2 A pre-warning state at the same time of the 2 nd week before the current time, B t-2 The value of (1) is 0 or 1, B t-2 =0 indicates that no warning information is sent at the same time of the 2 nd week before the current time, B t-2 =1 indicates that the same time of week 2 before the current time gives out the early warning information, B t-m A pre-warning state at the same time of the mth week before the current time, B t-m The value of (1) is 0 or 1, B t-m =0 indicates that no warning information is sent at the same time of the mth week before the current time, B t-m =1 indicates that the same time of the mth week before the current time sends out the early warning information, Y t-1 Is the early warning threshold value of the same time of the 1 st week before the current time,
early warning threshold for all historiesAverage value of X i Indicating the number of registered users at the same time of the ith week before the current time, N being the number of the plurality of weeks, N>m。
2. The method of claim 1, wherein after outputting the early warning threshold, further comprising:
and generating a dynamic visual monitoring graph according to the number of the login users at the current moment and the early warning threshold value at the current moment.
3. The method of claim 1, wherein the obtaining the number of logged-in users at the current time specifically comprises:
acquiring system log information at the current moment;
and extracting the number of login users at the current moment from the system log information.
4. A method according to claim 3, wherein the system log information comprises respective system log and operation log.
5. A software system monitoring device, comprising:
the acquisition module is used for acquiring the number of the login users at the current moment;
the early warning module is used for sending early warning information if judging that the number of the login user at the current moment is greater than the early warning threshold at the current moment;
also included is a computing module that is configured to,
the calculation module is used for acquiring historical data of a plurality of weeks, wherein the historical data comprises the number of login users at each moment, the early warning state at each moment and the historical early warning threshold value at each moment;
inputting the historical data or a part of the historical data into a preset machine learning model, and outputting an early warning threshold value at the current moment;
the machine learning model specifically comprises:
wherein Y is t Z is the maximum number of users that the system can bear and B is the early warning threshold value at the current moment t-1 A pre-warning state at the same time of the 1 st week before the current time, B t-1 The value of (1) is 0 or 1, B t-1 =0 indicates that no warning information is sent at the same time of week 1 before the current time, B t-1 =1 indicates that the same time of week 1 before the current time gives out the early warning information, B t-2 A pre-warning state at the same time of the 2 nd week before the current time, B t-2 The value of (1) is 0 or 1, B t-2 =0 indicates that no warning information is sent at the same time of the 2 nd week before the current time, B t-2 =1 indicates that the same time of week 2 before the current time gives out the early warning information, B t-m A pre-warning state at the same time of the mth week before the current time, B t-m The value of (1) is 0 or 1, B t-m =0 indicates that no warning information is sent at the same time of the mth week before the current time, B t-m =1 indicates that the same time of the mth week before the current time sends out the early warning information, Y t-1 Is the early warning threshold value of the same time of the 1 st week before the current time,
x is the average value of all historical early warning thresholds i Indicating the number of registered users at the same time on the i-th week before the current time, N isThe number of the weeks, N>m。
6. The apparatus of claim 5, further comprising a generation module,
and generating a dynamic visual monitoring graph according to the number of the login users at the current moment and the early warning threshold value at the current moment.
7. The apparatus of claim 5, wherein the obtaining the number of logged-in users at the current time specifically comprises:
acquiring system log information at the current moment;
and extracting the number of login users at the current moment from the system log information.
8. The apparatus of claim 7, wherein the system log information comprises respective system log and operation log.
9. An electronic device, comprising:
the device comprises a memory and a processor, wherein the processor and the memory are communicated with each other through a bus; the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-4.
10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the method according to any one of claims 1 to 4 is implemented when the computer program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811390496.2A CN111290903B (en) | 2018-11-21 | 2018-11-21 | Software system monitoring method and device based on user behavior and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811390496.2A CN111290903B (en) | 2018-11-21 | 2018-11-21 | Software system monitoring method and device based on user behavior and machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111290903A CN111290903A (en) | 2020-06-16 |
| CN111290903B true CN111290903B (en) | 2023-04-25 |
Family
ID=71026557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811390496.2A Active CN111290903B (en) | 2018-11-21 | 2018-11-21 | Software system monitoring method and device based on user behavior and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111290903B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325062A (en) * | 2011-09-20 | 2012-01-18 | 北京神州绿盟信息安全科技股份有限公司 | Abnormal login detecting method and device |
| CN102752142A (en) * | 2012-07-05 | 2012-10-24 | 深圳市易聆科信息技术有限公司 | Monitoring method and system based on multidimensional modeled information system |
| CN103905229A (en) * | 2012-12-27 | 2014-07-02 | 中国移动通信集团四川有限公司 | Early-warning method and device for terminal-user loss |
| CN105743706A (en) * | 2016-03-31 | 2016-07-06 | 武汉虹信技术服务有限责任公司 | Disk array performance monitoring and early-warning method and system based on HTTP |
| CN106230849A (en) * | 2016-08-22 | 2016-12-14 | 中国科学院信息工程研究所 | A kind of smart machine machine learning safety monitoring system based on user behavior |
| CN107276982A (en) * | 2017-05-08 | 2017-10-20 | 微梦创科网络科技（中国）有限公司 | A kind of abnormal login detecting method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10776715B2 (en) * | 2017-04-28 | 2020-09-15 | Microsoft Technology Licensing, Llc | Artificial intelligent cognition threshold |
-
2018
- 2018-11-21 CN CN201811390496.2A patent/CN111290903B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102325062A (en) * | 2011-09-20 | 2012-01-18 | 北京神州绿盟信息安全科技股份有限公司 | Abnormal login detecting method and device |
| CN102752142A (en) * | 2012-07-05 | 2012-10-24 | 深圳市易聆科信息技术有限公司 | Monitoring method and system based on multidimensional modeled information system |
| CN103905229A (en) * | 2012-12-27 | 2014-07-02 | 中国移动通信集团四川有限公司 | Early-warning method and device for terminal-user loss |
| CN105743706A (en) * | 2016-03-31 | 2016-07-06 | 武汉虹信技术服务有限责任公司 | Disk array performance monitoring and early-warning method and system based on HTTP |
| CN106230849A (en) * | 2016-08-22 | 2016-12-14 | 中国科学院信息工程研究所 | A kind of smart machine machine learning safety monitoring system based on user behavior |
| CN107276982A (en) * | 2017-05-08 | 2017-10-20 | 微梦创科网络科技（中国）有限公司 | A kind of abnormal login detecting method and device |
Non-Patent Citations (2)
| Title |
|---|
| 朱黎等.基于自适应LBP人脸识别的身份验证 .《 计算机工程与科学 》.2014,第36卷(第11期),2217-2222. * |
| 陈俊 ; .基于大数据机器学习技术的IT运营分析系统建设.计算机时代.2018,(第3期),66-69. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111290903A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112162878B (en) | Database fault discovery method and device, electronic equipment and storage medium | |
| US7437281B1 (en) | System and method for monitoring and modeling system performance | |
| US7082381B1 (en) | Method for performance monitoring and modeling | |
| CN106201829B (en) | Monitor Threshold and device, monitoring alarm method, apparatus and system | |
| KR20180108446A (en) | System and method for management of ict infra | |
| US7197428B1 (en) | Method for performance monitoring and modeling | |
| US10860405B1 (en) | System operational analytics | |
| CN111314173A (en) | Monitoring information abnormity positioning method and device, computer equipment and storage medium | |
| JP2020008997A (en) | Abnormality detection system | |
| US7369967B1 (en) | System and method for monitoring and modeling system performance | |
| CN109241353B (en) | Data auditing method | |
| CN113190415A (en) | Internet hospital system monitoring method, equipment, storage medium and program product | |
| CN112650608B (en) | Abnormal root cause positioning method, related device and equipment | |
| US12039045B2 (en) | Event analysis in an electric power system | |
| CN108306997B (en) | Domain name resolution monitoring method and device | |
| CN111382494A (en) | System and method for detecting anomalies in sensory data of industrial machines | |
| CN103580924A (en) | Fault location method, device and system | |
| CN107480703B (en) | Transaction fault detection method and device | |
| CN111767193A (en) | Server data anomaly detection method and device, storage medium and equipment | |
| CN113342625A (en) | Data monitoring method and system | |
| CN112380759A (en) | Smart meter service life prediction method based on deep learning and CoxPH model | |
| CN115222181B (en) | Robot operation state monitoring system and method | |
| CN113487182B (en) | Device health state evaluation method, device, computer device and medium | |
| CN111290903B (en) | Software system monitoring method and device based on user behavior and machine learning | |
| CN113487086A (en) | Method and device for predicting remaining service life of equipment, computer equipment and 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 |