CN111078974A - Method, device and storage medium for detecting abnormal news volume in real time - Google Patents
Method, device and storage medium for detecting abnormal news volume in real time Download PDFInfo
- Publication number
- CN111078974A CN111078974A CN201911254914.XA CN201911254914A CN111078974A CN 111078974 A CN111078974 A CN 111078974A CN 201911254914 A CN201911254914 A CN 201911254914A CN 111078974 A CN111078974 A CN 111078974A
- Authority
- CN
- China
- Prior art keywords
- news
- time
- time period
- news volume
- deviation degree
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2257—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using expert systems
Abstract
The invention discloses a method, equipment and a storage medium for detecting abnormal news volume in real time, wherein the method comprises the following steps: taking the average historical news volume of a first time period as a parameter, and constructing a Poisson model of the first time period; continuously acquiring news volume per minute in a second time period as a sample, and calculating the maximum deviation degree of the sample from a Poisson model of a first time period to which the second time period belongs through KS (K-Key verification); and if the absolute value of the maximum deviation degree is larger than or equal to the absolute value of the deviation degree threshold, judging that the news volume of the second time interval is abnormal. Compared with the prior art, the method for detecting the news volume abnormity in real time can quantify the news volume abnormity, thereby detecting the abnormity of the news volume extracted by the screening system in time and finding the fault of the screening system as soon as possible.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a method, equipment and a storage medium for detecting news volume abnormity in real time.
Background
The internet generates a large amount of news at every moment, and many enterprises or individuals construct a screening system through a server to extract needed news from a large amount of internet news and further process the news. However, the abnormality of the server may cause an abnormality to occur when the screening system extracts news, for example, the server is broken down to cause that the required news cannot be acquired, or the amount of acquired news is sharply reduced due to the server congestion.
How to detect the abnormal news amount in time so as to find the fault of the screening system as early as possible is a problem to be solved at present.
Disclosure of Invention
The invention aims to provide a method, equipment and a storage medium for detecting abnormal news volume in real time.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for detecting an abnormal news volume in real time, where the method includes:
taking the average historical news volume of a first time period as a parameter, and constructing a Poisson model of the first time period;
continuously acquiring news volume per minute in a second time period as a sample, and calculating the maximum deviation degree of the sample from a Poisson model of a first time period to which the second time period belongs through KS (K-Key verification);
and if the absolute value of the maximum deviation degree is larger than or equal to the absolute value of the deviation degree threshold, judging that the news volume of the second time interval is abnormal.
As a further improvement of an embodiment of the present invention, the "calculating the maximum deviation degree of the poisson model of the first time interval to which the second time interval belongs by the KS test" specifically includes:
calculating the probability of all the samples by KS test by taking the Poisson model of the second time interval belonging to the first time interval as a reference;
and selecting a minimum value from all the probabilities, and calculating the logarithm of the minimum value to be used as the maximum deviation degree.
As a further improvement of an embodiment of the present invention, the method of determining the deviation threshold value includes:
acquiring a history news volume record from a screening system;
searching abnormal news volume when the system fails in the record;
and calculating the deviation degree of the abnormal news volume, and selecting the deviation degree with the minimum absolute value as a deviation degree threshold value.
As a further refinement of an embodiment of the invention, the duration of the second period of time is within a range of 10-30 minutes.
As a further improvement of an embodiment of the present invention, the method further comprises:
setting a corresponding deviation degree interval according to the fault type of the screening system in the historical record;
and after judging that the news volume of the time interval is abnormal, finding a corresponding deviation degree interval according to the maximum deviation degree, thereby predicting the fault type of the screening system.
As a further improvement of an embodiment of the present invention, the "taking the average historical news volume of the first time period as a parameter, and constructing the poisson model of the first time period" specifically includes:
dividing a week into a plurality of first time periods, and constructing a Poisson model of each first time period by taking the average historical news volume of each first time period as a parameter.
As a further improvement of an embodiment of the present invention, the "dividing a week into a plurality of first time periods, and constructing a poisson model of each first time period with an average historical news volume of each first time period as a parameter" specifically includes:
acquiring historical news volume records of a plurality of weeks from a screening system;
dividing one week into a plurality of first time periods, and calculating the average value of the historical news volume corresponding to each first time period in the record to obtain the average historical news volume of each first time period;
and constructing a Poisson model of each first time interval in one week according to the average historical news volume of each first time interval.
As a further improvement of an embodiment of the present invention, the "dividing one week into a plurality of first time periods" specifically includes:
with the 1 hour period as the first period, one week was divided into 168 first periods.
In order to achieve one of the above objects, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and the processor implements the steps of any one of the above methods for detecting an anomaly in news volume in real time when executing the program.
To achieve one of the above objects, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of any of the above methods for detecting newsfeed anomalies in real time.
Compared with the prior art, the method for detecting the news volume abnormity in real time can quantify the news volume abnormity, thereby detecting the abnormity of the news volume extracted by the screening system in time and finding the fault of the screening system as soon as possible.
Drawings
Fig. 1 is a schematic flow chart of the method for detecting news volume abnormality in real time according to the present invention.
FIG. 2 is a probability distribution diagram of a Poisson model of 1:00 to 2:00 on Monday according to the present invention.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
Within probability theory and statistics, the binomial distribution with parameters n and p represents the probability distribution of the number of successes for n independent trials. Only two values are taken in each independent experiment, the probability of a value representing success is p, and the probability of an experiment failing is 1-p. Such a binary test for success and failure is also called a bernoulli test.
When required news is extracted from the massive internet news, the quantity of the massive internet news is n, the process that each news in the n news is extracted by the screening system is an independent process, each news can be extracted or not extracted, the extraction probability is p (the probability is very small because the quantity of the related news is small), and therefore the probability that each news in the massive internet news is extracted by the screening system obeys binomial distribution. When n is large and p is small (when n ≧ 20, p ≦ 0.05), the binomial distribution can be approximated to a Poisson distribution.
Poisson Distribution (Poisson Distribution) is a discrete probability Distribution commonly found in statistics and probability, and is suitable for describing the number of random events occurring per unit time (or space).
The invention analyzes the history record by statistics, and finds that the news amount in the history record (the news amount extracted by the screening system in one minute) is circulated repeatedly by taking the week as a period.
Therefore, as shown in fig. 1, the present invention provides a method for detecting an anomaly in news volume in real time, which can quantify the anomaly in news volume, thereby detecting the anomaly in news volume extracted by a screening system in time and finding a fault in the screening system as soon as possible. The method comprises the following steps:
step S100: and taking the average historical news volume of the first time period as a parameter, and constructing a Poisson model of the first time period.
The first period of time is a period of time, such as 30 minutes, 1 hour, or 2 hours, etc., with 1 hour being preferred for the present invention. The poisson model of the first time period can be constructed by taking the historical average news volume of the first time period as a parameter lambda of the poisson model. The purpose of constructing a poisson model of a time interval is to facilitate the subsequent prediction of the news volume of the time interval. For example, when a Poisson model of 8: 00-9: 00 of a day is constructed, news volume of 8: 00-9: 00 of each day can be used as reference to judge whether the news volume of the day is abnormal; or when a Poisson model of 12: 00-13: 00 on Monday is constructed, the Poisson model can be referred to by news volume of 12: 00-13: 00 on every Monday.
By statistically analyzing the history, it is found that the news volume in the history is repeatedly circulated in a week period, and therefore, in order to be able to detect the abnormality of the news volume at each moment in time, it is preferable to divide one week into a plurality of first time periods, and construct a poisson model for each first time period with the average historical news volume of each first time period as a parameter.
Specifically, dividing a week into a plurality of first time periods, and constructing a poisson model of each first time period by taking the average historical news volume of each first time period as a parameter comprises the following steps:
step S110: historical news volume records are obtained from the screening system for a plurality of weeks.
Step S120: dividing one week into a plurality of first time intervals, and calculating the average value of the first corresponding historical news volume of each time interval in the record to obtain the average historical news volume of each first time interval.
The news volume in the invention refers to the quantity of news extracted by the screening system in unit time, and for convenience of calculation, the unit time is preferably one minute, namely the quantity of news extracted by the screening system in one minute, and other times such as 30 seconds and two minutes can be taken as the unit time.
And analyzing the historical news volume records to obtain the historical news volume per minute in one week (such as from 0 point of Monday to 0 point of next Monday), wherein the news volume per minute has a plurality of historical records. Dividing one week into a plurality of first time intervals, and calculating the average value of the historical news amount corresponding to each first time interval in the historical news amount record to obtain the average historical news amount of each first time interval. Preferably the first period is 1 hour, so a week can be divided into 7 x 24-168 periods.
As a simple example, all historical news volumes in the time interval of 1: 00-2: 00 on Monday, namely a plurality of historical news volumes in one minute of 1: 00-1: 01, a plurality of historical news volumes in one minute of 1: 01-1: 02 and the like are obtained from the historical news volume records, and then all the historical news volumes in the time interval are obtained, and the news volumes are averaged to obtain the average historical news volume in the time interval.
In a preferred embodiment, after obtaining the historical newsgroup records for a plurality of weeks, the abnormal newsgroup records are removed, and then the average historical newsgroup for each first time period is calculated.
Step S130: and constructing a Poisson model of each first time interval in one week according to the average historical news volume of each first time interval.
The probability function of the poisson distribution is:
the poisson model for each first time period in a week is a model with the average historical news volume for each first time period being λ. The probability distribution of the poisson model is that the news volume is taken as an X axis, the probability corresponding to the news volume is taken as a Y axis, and reference is made to fig. 2, fig. 2 is a poisson model of 1: 00-2: 00 on monday, it can be seen from the figure that the probability that the news volume per minute is 0 in the period is about 0.055, the probability that the news volume per minute is 1 is between 0.06 and 0.07, and the like.
If a period of 1 hour is used, a week can be divided into 7 × 24 segments, and 7 × 24 poisson models are required to be constructed in total.
Step S200: and continuously acquiring the news volume per minute in the second period as a sample, and calculating the maximum deviation degree of the sample from the Poisson model of the first period to which the second period belongs through the KS test.
The duration of the second time interval is less than or equal to the first time interval, and each second time interval has a corresponding first time interval, or the second time interval is referred to as belonging to a certain first time interval. For example, if the first time interval is 1 hour, the second time interval is 10 minutes, and the second time interval of 1: 00-1: 10 on Monday belongs to the first time interval of 1: 00-2: 00 on Monday.
The KS test is called Kolmogorov-Smirnov test, and is a test method for comparing a frequency distribution f (x) with a theoretical distribution g (x) or two observed value distributions. This step compares the news volume distribution frequency over a period of time with the deviation of the poisson model for the corresponding period of time by KS test. The steps specifically include:
step S210: the news volume per minute for the second period is continuously obtained as a sample.
To increase the sensitivity, it is preferred that the second period is the period closest to the sample being collected, for example, the second period is 10 minutes, and then the news volume per minute in the first 10 minutes of the current time is preferably collected as the sample. The longer the period of sampling, the more accurate the result of the calculation, but the lower the sensitivity. Conversely, the shorter the sampling period, the higher the sensitivity, but the lower the accuracy. Therefore, to balance accuracy with sensitivity, it is preferred that the duration of the second period is within 10-30 minutes.
Step S220: and calculating the probability of all the samples by KS test by taking the Poisson model corresponding to the time interval as a reference.
And calculating the D values of the probability distributions of the samples and the corresponding probability distribution in the Poisson model through KS test, and then calculating the probability of each D value, namely the probability of the corresponding sample.
Step S230: and selecting a minimum value from all the probabilities, and calculating the logarithm of the minimum value to be used as the maximum deviation degree.
According to the poisson model, when the probability that a certain news volume appears theoretically is very low, almost close to 0, but actually appears, the screening system is certainly an abnormal place, and therefore the news volume appearing with such probability is considered as an abnormal news volume.
When determining the degree of abnormality, the lower the probability of occurrence theoretically, the greater the degree of abnormality is considered. In addition, since the probability of the abnormal value is very low, such as 10^ (-12), etc., for the convenience of observation, the logarithm of the probability is taken as the deviation degree, so the minimum value is selected from all the probabilities, and the logarithm of the minimum value is taken as the maximum deviation degree. Of course, it is also possible to determine the logarithm of all the probabilities and then select the smallest logarithm as the maximum deviation.
Step S300: and if the absolute value of the maximum deviation degree is larger than or equal to the absolute value of the deviation degree threshold, judging that the news volume of the second time interval is abnormal.
For example, the maximum deviation degree is-15, the deviation degree threshold value is-10, and since 15 is greater than 10, it is determined that the news volume of the second time period in which the maximum deviation degree is-15 is abnormal.
In a preferred embodiment, the method of determining the deviation threshold comprises:
acquiring a history news volume record from a screening system, searching for abnormal news volume in the record when the system fails, calculating the deviation degree of the abnormal news volume, and selecting the deviation degree with the minimum absolute value as a deviation degree threshold value.
For example, if a plurality of abnormal news volumes are found, and the deviation of the abnormal news volumes is between-10 and-30, then-10 can be selected as the threshold of the deviation, and other values can be selected as the threshold of the deviation, so as to appropriately expand or reduce the range of the abnormal news volumes.
In a preferred embodiment, the method further comprises:
setting a corresponding deviation degree interval according to the fault type of the screening system in the historical record; and after judging that the news volume of the time interval is abnormal, finding a corresponding deviation degree interval according to the maximum deviation degree, thereby predicting the fault type of the screening system.
Types of possible failures of the screening system include, but are not limited to: the server paralysis causes that needed news can not be obtained, the server congestion causes that the obtained news volume is sharply reduced, and the problem of the screening function of the screening system causes that a lot of spam news are extracted.
The corresponding deviation degree section may be set according to the above-described fault type. And when the news volume is abnormal, judging the section in which the deviation degree (the maximum deviation degree) of the abnormal point is positioned, so as to predict the fault type of the screening system corresponding to the abnormality, inform maintenance personnel and facilitate the maintenance personnel to quickly troubleshoot faults.
It should be noted that, after it is determined that the news volume in the second time period is abnormal, the specific time when the abnormal news volume occurs can be determined according to the maximum deviation degree, which is also helpful for a maintenance worker to troubleshoot faults.
The method for detecting the news volume abnormity in real time can quantify the abnormity of the news volume, thereby detecting the abnormity of the news volume extracted by the screening system in time and finding the fault of the screening system as soon as possible.
In a specific embodiment, a total of 7 x 24 poisson models per hour over a week are constructed by analyzing historical newsgroup records per minute. News volumes per minute for 10 consecutive minutes were taken as samples, and assuming that these news volume samples obeyed the poisson model for the current time period, the maximum degree of deviation of the samples from the overall data represented by the poisson model was calculated by the KS test. And when the maximum deviation exceeds the deviation threshold, judging that the news volume is abnormal within 10 minutes, and informing related personnel to perform troubleshooting and maintenance on the screening system.
The invention further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program capable of running on the processor, and the processor implements any one of the steps of the method for detecting an anomaly in news volume in real time when executing the program, that is, implements the steps of any one of the technical solutions of the method for detecting an anomaly in news volume in real time.
The present invention also provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements any one of the steps of the above-mentioned method for detecting an anomaly in news volume in real time, that is, implements the steps of any one of the above-mentioned methods for detecting an anomaly in news volume in real time.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for detecting newscasts in real time, the method comprising:
taking the average historical news volume of a first time period as a parameter, and constructing a Poisson model of the first time period;
continuously acquiring news volume per minute in a second time period as a sample, and calculating the maximum deviation degree of the sample from a Poisson model of a first time period to which the second time period belongs through KS (K-Key verification);
and if the absolute value of the maximum deviation degree is larger than or equal to the absolute value of the deviation degree threshold, judging that the news volume of the second time interval is abnormal.
2. The method for detecting newsfeed anomalies in real time according to claim 1, wherein the step of calculating the maximum deviation degree of the poisson model of the sample from the first time interval to which the second time interval belongs through the KS test specifically includes:
calculating the probability of all the samples by KS test by taking the Poisson model of the second time interval belonging to the first time interval as a reference;
and selecting a minimum value from all the probabilities, and calculating the logarithm of the minimum value to be used as the maximum deviation degree.
3. The method for detecting newsfeed anomalies in real time as claimed in claim 1, wherein the method for determining the deviation threshold includes:
acquiring a history news volume record from a screening system;
searching abnormal news volume when the system fails in the record;
and calculating the deviation degree of the abnormal news volume, and selecting the deviation degree with the minimum absolute value as a deviation degree threshold value.
4. The method for detecting newscast abnormality in real time according to claim 1, wherein:
the duration of the second period is within 10-30 minutes.
5. The method for detecting newsgroup anomalies in real time according to claim 1, characterized in that the method further comprises:
setting a corresponding deviation degree interval according to the fault type of the screening system in the historical record;
and after judging that the news volume of the time interval is abnormal, finding a corresponding deviation degree interval according to the maximum deviation degree, thereby predicting the fault type of the screening system.
6. The method for detecting newsgroup anomaly in real time according to claim 1, wherein the "taking the average historical newsgroup of the first time period as a parameter to construct the poisson model of the first time period" specifically includes:
dividing a week into a plurality of first time periods, and constructing a Poisson model of each first time period by taking the average historical news volume of each first time period as a parameter.
7. The method for detecting newsgroup abnormality in real time according to claim 6, wherein the dividing a week into a plurality of first time periods, and constructing the poisson model for each first time period with the average historical newsgroup of each first time period as a parameter specifically comprises:
acquiring historical news volume records of a plurality of weeks from a screening system;
dividing one week into a plurality of first time periods, and calculating the average value of the historical news volume corresponding to each first time period in the record to obtain the average historical news volume of each first time period;
and constructing a Poisson model of each first time interval in one week according to the average historical news volume of each first time interval.
8. The method for detecting newscast abnormality in real time according to claim 6, wherein the "dividing one week into a plurality of first periods" specifically includes:
with the 1 hour period as the first period, one week was divided into 168 first periods.
9. An electronic device comprising a memory and a processor, the memory storing a computer program operable on the processor, wherein the processor executes the program to perform the steps of the method for detecting newsfeed anomalies in real time of any one of claims 1-8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for detecting newsfeed anomalies in real time according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911254914.XA CN111078974A (en) | 2019-12-10 | 2019-12-10 | Method, device and storage medium for detecting abnormal news volume in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911254914.XA CN111078974A (en) | 2019-12-10 | 2019-12-10 | Method, device and storage medium for detecting abnormal news volume in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111078974A true CN111078974A (en) | 2020-04-28 |
Family
ID=70313514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911254914.XA Withdrawn CN111078974A (en) | 2019-12-10 | 2019-12-10 | Method, device and storage medium for detecting abnormal news volume in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111078974A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949941A (en) * | 2020-07-03 | 2020-11-17 | 广州明珞汽车装备有限公司 | Equipment fault detection method, system, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739254B1 (en) * | 2005-09-30 | 2010-06-15 | Google Inc. | Labeling events in historic news |
| CN106803137A (en) * | 2017-01-25 | 2017-06-06 | 东南大学 | Urban track traffic AFC system enters the station volume of the flow of passengers method for detecting abnormality in real time |
| CN110086649A (en) * | 2019-03-19 | 2019-08-02 | 深圳壹账通智能科技有限公司 | Detection method, device, computer equipment and the storage medium of abnormal flow |
-
2019
- 2019-12-10 CN CN201911254914.XA patent/CN111078974A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7739254B1 (en) * | 2005-09-30 | 2010-06-15 | Google Inc. | Labeling events in historic news |
| CN106803137A (en) * | 2017-01-25 | 2017-06-06 | 东南大学 | Urban track traffic AFC system enters the station volume of the flow of passengers method for detecting abnormality in real time |
| CN110086649A (en) * | 2019-03-19 | 2019-08-02 | 深圳壹账通智能科技有限公司 | Detection method, device, computer equipment and the storage medium of abnormal flow |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949941A (en) * | 2020-07-03 | 2020-11-17 | 广州明珞汽车装备有限公司 | Equipment fault detection method, system, device and storage medium |
| CN111949941B (en) * | 2020-07-03 | 2023-03-03 | 广州明珞汽车装备有限公司 | Equipment fault detection method, system, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3557819B1 (en) | Server failure detection method and system | |
| US6973415B1 (en) | System and method for monitoring and modeling system performance | |
| US7082381B1 (en) | Method for performance monitoring and modeling | |
| EP3105644B1 (en) | Method of identifying anomalies | |
| US7636051B2 (en) | Status monitor apparatus | |
| US7197428B1 (en) | Method for performance monitoring and modeling | |
| US20160146709A1 (en) | System for preparing time series data for failure prediction | |
| CN111262750B (en) | Method and system for evaluating baseline model | |
| CN112188531A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| US7369967B1 (en) | System and method for monitoring and modeling system performance | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN114465874A (en) | Fault prediction method, device, electronic equipment and storage medium | |
| US7617313B1 (en) | Metric transport and database load | |
| CN113722134A (en) | Cluster fault processing method, device and equipment and readable storage medium | |
| CN111078974A (en) | Method, device and storage medium for detecting abnormal news volume in real time | |
| CN111879522B (en) | Steam turbine operation monitoring and fault distinguishing method and system based on time sequence probability | |
| CN116030955B (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| CN111125195A (en) | Data anomaly detection method and device | |
| CN107085544B (en) | System error positioning method and device | |
| CN114881112A (en) | System anomaly detection method, device, equipment and medium | |
| CN112732517B (en) | Disk fault alarm method, device, equipment and readable storage medium | |
| CN114531338A (en) | Monitoring alarm and tracing method and system based on call chain data | |
| CN115858606A (en) | Method, device and equipment for detecting abnormity of time series data and storage medium | |
| CN113760879A (en) | Database anomaly monitoring method, system, electronic device and medium | |
| CN113205215A (en) | Knowledge-based battlefield situation prediction method |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200428 |
|
| WW01 | Invention patent application withdrawn after publication |