CN108628721A - Method for detecting abnormality, device, storage medium and the electronic device of user data value - Google Patents
Method for detecting abnormality, device, storage medium and the electronic device of user data value Download PDFInfo
- Publication number
- CN108628721A CN108628721A CN201810411145.9A CN201810411145A CN108628721A CN 108628721 A CN108628721 A CN 108628721A CN 201810411145 A CN201810411145 A CN 201810411145A CN 108628721 A CN108628721 A CN 108628721A
- Authority
- CN
- China
- Prior art keywords
- data value
- value
- data
- user
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of method for detecting abnormality, device, storage medium and the electronic devices of user data value.Wherein, this method includes：User data value to be detected is extracted from user log files；The first data value not fallen in target data ranges is obtained from user data value to be detected；Determine the corresponding deviation value of each data value in the first data value, wherein, deviation value is used to indicate the departure degree that each data value deviates the second data value, second data value is the data value for meeting goal condition in the first data value with the distance between each data value, and deviation value is bigger, and departure degree is higher；Data value by deviation value in the first data value greater than desired value is determined as the abnormal data value in user data value.The present invention solves technical problem relatively low to the detection efficiency of abnormal user data value in the related technology.
Description
Technical field
The present invention relates to computer realm, in particular to a kind of method for detecting abnormality of user data value, device,
Storage medium and electronic device.
Background technology
The abnormality detection of traditional user data value is by modes such as Data Spot-checking, data distribution, data interval distributions
Carry out statistical data, exceptional value is judged whether there is in conjunction with network operator's experience and business meaning.Detection of this mode to exceptional value
It is less efficient.
For above-mentioned problem, currently no effective solution has been proposed.
Invention content
An embodiment of the present invention provides a kind of method for detecting abnormality of user data value, device, storage medium and electronics dresses
It sets, at least to solve technical problem relatively low to the detection efficiency of abnormal user data value in the related technology.
One side according to the ... of the embodiment of the present invention provides a kind of method for detecting abnormality of user data value, including：From
User data value to be detected is extracted in user log files；It is obtained from the user data value to be detected and does not fall within target
The first data value in data area；Determine each corresponding deviation value of data value in first data value, wherein described inclined
It is used to indicate the departure degree that each data value deviates the second data value from value, second data value is first number
According to the data value for meeting goal condition in value with the distance between each data value, the more big deviation journey of the deviation value
Degree is higher；Data value by deviation value described in first data value greater than desired value is determined as the number of users
According to the abnormal data value in value.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of abnormal detector of user data value, including：
Extraction module, for extracting user data value to be detected from user log files；First acquisition module, for being waited for from described
The first data value not fallen in target data ranges is obtained in the user data value of detection；First determining module, for determining
Each corresponding deviation value of data value in first data value, wherein the deviation value is used to indicate each data value
Deviate the departure degree of the second data value, second data value be in first data value between each data value
Distance meet the data value of goal condition, the more big departure degree of the deviation value is higher；Second determining module, being used for will
Deviation value described in first data value is determined as greater than the data value of desired value in the user data value
Abnormal data value.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of storage medium, which is characterized in that the storage is situated between
Computer program is stored in matter, wherein the computer program is arranged to execute described in any of the above-described when operation
Method.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of electronic device, including memory and processor,
It is characterized in that, computer program is stored in the memory, and the processor is arranged to hold by the computer program
Method described in row any of the above-described.
In embodiments of the present invention, using extracting user data value to be detected from user log files；From to be detected
User data value in obtain and do not fall within the first data value in target data ranges；Determine each data value in the first data value
Corresponding deviation value, wherein deviation value is used to indicate the departure degree that each data value deviates the second data value, the second data value
To meet the data value of goal condition in the first data value with the distance between each data value, the bigger departure degree of deviation value is more
It is high；Data value by deviation value in the first data value greater than desired value is determined as the abnormal data in user data value
The mode of value will not fall in target data ranges from the user data value to be detected extracted in user log files
One data value is judged to, there may be abnormal data value, tentatively reducing the range of abnormal data value screening, then determines the first number
According to the corresponding deviation value of each data value in value, determine that deviation value is greater than from the first data value according to the deviation value
The data value of desired value is abnormal data value, to accurately extract the abnormal data value in user data value, to realize
While improving the technique effect for the detection efficiency being detected to abnormal user data value, also achieve to mass users number
According to the abnormality detection of value, and then solves and the lower technology of detection efficiency of abnormal user data value is asked in the related technology
Topic.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of schematic diagram of method for detecting abnormality optionally with user data value according to the ... of the embodiment of the present invention；
Fig. 2 is that a kind of application environment of method for detecting abnormality optionally with user data value according to the ... of the embodiment of the present invention is shown
It is intended to；
Fig. 3 is the application environment of another method for detecting abnormality optionally with user data value according to the ... of the embodiment of the present invention
Schematic diagram；
Fig. 4 is showing according to optionally a kind of method for detecting abnormality optionally with user data value of embodiment of the invention
It is intended to；
Fig. 5 is a kind of schematic diagram of abnormal detector optionally with user data value according to the ... of the embodiment of the present invention；
Fig. 6 is that a kind of application scenarios of method for detecting abnormality optionally with user data value according to the ... of the embodiment of the present invention show
It is intended to one；
Fig. 7 is that a kind of application scenarios of method for detecting abnormality optionally with user data value according to the ... of the embodiment of the present invention show
It is intended to two；And
Fig. 8 is a kind of schematic diagram of optional electronic device according to the ... of the embodiment of the present invention.
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
One side according to the ... of the embodiment of the present invention provides a kind of method for detecting abnormality of user data value, such as Fig. 1 institutes
Show, this method includes：
S102 extracts user data value to be detected from user log files；
S104 obtains the first data value not fallen in target data ranges from user data value to be detected；
S106 determines the corresponding deviation value of each data value in the first data value, wherein deviation value is used to indicate every number
Deviate the departure degree of the second data value according to value, the second data value is full with the distance between each data value in the first data value
The data value of foot-eye condition, deviation value is bigger, and departure degree is higher；
S108, the data value by deviation value in the first data value greater than desired value are determined as in user data value
Abnormal data value.
Optionally, in the present embodiment, the method for detecting abnormality of above-mentioned user data value can be applied to as shown in Figure 2
In the hardware environment that server 202 is constituted.As shown in Fig. 2, server 202 extracts use to be detected from user log files
User data value obtains the first data value not fallen in target data ranges from user data value to be detected, determines first
Deviation value in first data value is greater than the data value of desired value by the corresponding deviation value of each data value in data value
The abnormal data value being determined as in user data value.
Optionally, in the present embodiment, the method for detecting abnormality of above-mentioned user data value can be applied to as shown in Figure 3
In the hardware environment that application server 302, user journal server 304 and abnormality detection server 306 are constituted.Such as Fig. 3 institutes
Show, application server 302 is reported to collected user data in log server 304.Log server 304 generates user
Journal file.Abnormality detection server 306 extracts user data value to be detected from user log files, from use to be detected
The first data value not fallen in target data ranges is obtained in user data value, determines that each data value corresponds in the first data value
Deviation value, by deviation value in the first data value greater than desired value data value be determined as it is different in user data value
Regular data value.
Optionally, in the present embodiment, the method for detecting abnormality of above-mentioned user data value can be, but not limited to be applied to pair
In the scene that user data value carries out abnormality detection.Wherein, the method for detecting abnormality of above-mentioned user data value can be, but not limited to
Applied to various types of applications, for example, online education application, instant messaging application, community space application, game application, purchase
Object application, browser application, financial application, multimedia application, live streaming application etc..Specifically, can be, but not limited to be applied to
In the scene carried out abnormality detection to user data value in above-mentioned game application, or can with but be not limited to be applied to it is above-mentioned i.e.
When communication applications in the scene that is carried out abnormality detection to user data value, abnormal user data value is detected with improving
Detection efficiency.Above-mentioned is only a kind of example, and any restriction is not done to this in the present embodiment.
Optionally, in the present embodiment, user data value can be, but not limited to the data for continuous variable.Such as：With
User data value can be, but not limited to：User's online hours, user participate in number, the user charges amount of money, the consumption of user's output
Etc..
Optionally, in the present embodiment, target data ranges can be, but not limited to be it is preset, can also but it is unlimited
Thus according to user data value automatic identification to be detected.Such as：Artificial intelligence model is trained according to history testing result, by
The target data ranges that model automatic identification after training is adapted to user data value to be detected.
Optionally, in the present embodiment, the corresponding deviation value of each data value can be, but not limited to use local outlier factor
(Local Outlier Factor, referred to as LOF) is indicated, local outlier factor is by check object relative to its neighborhood
Irrelevance (local irrelevance) detects abnormal point to judge outlier according to situation is deviateed.
Optionally, in the present embodiment, desired value can be, but not limited to be preset, can also but be not limited to root
According to user data value automatic identification to be detected.Such as：Artificial intelligence mould is trained according to the irrelevance in history detection data
Type, the desired value being adapted to user data value to be detected by the model automatic identification after training.
In an optional embodiment, for being carried out abnormality detection to the online hours in user 1 year, from
The online hours data value that user is extracted in the journal file of family, obtain from the online hours data value of user less than 1 hour or
First data value of the person more than 6570 hours is respectively user 1 corresponding 0.5 hour, user 2 corresponding 0.75 hours ... ...,
User i is 6600 hours corresponding, and user i+1 is 6659 hours corresponding ... ..., and user N is 7800 hours corresponding, determines the first number
According to the corresponding deviation value of each data value in value, such as：1 corresponding deviation value of user is 2, and 2 corresponding deviation value of user is
The corresponding deviation value of 4 ... ..., user i is 5.5, and the corresponding deviation values of user i+1 are 2.8 ... ..., the corresponding deviation values of user N
Be 7, by deviation value in the first data value greater than 4 data value be determined as it is different in the online hours data value of user
Regular data value.
As it can be seen that through the above steps, will not be fallen within from the user data value to be detected extracted in user log files
The first data value in target data ranges is determined as there may be abnormal data value, preliminary to reduce what abnormal data value was screened
Range, then determine the corresponding deviation value of each data value in the first data value, it is determined from the first data value according to the deviation value
Deviation value is abnormal data value greater than the data value of desired value, to accurately extract the exception in user data value
Data value, while to realize the technique effect for improving the detection efficiency being detected to abnormal user data value,
The abnormality detection to mass users data value is realized, and then solves the detection to abnormal user data value in the related technology
Less efficient technical problem.
As a kind of optional scheme, the not fallen in target data ranges is obtained from user data value to be detected
One data value includes：
S1, according in user data value to be detected the first maximum value and the first minimum value determine target data ranges；
The data value not fallen in target data ranges in user data value to be detected is determined as the first data by S2
Value；
S3 extracts the first data value from user data value to be detected.
Optionally, in the present embodiment, target data ranges can be, but not limited to be according to user data value to be detected
Determining.Such as：According in user data value the first maximum value and first minimum value determine target data ranges.
Such as：By taking the online hours of game user as an example, the online hours data of the game user in 1 year got
In the first maximum value be 7000 hours, the first minimum value is 3 hours, then can be that 7000 and first are minimum according to the first maximum value
Value determines target data ranges for 3.
As a kind of optional scheme, according in user data value to be detected maximum value and minimum value determine number of targets
Include according to range：
S1 determines the difference between the first maximum value and the first minimum value；
Difference between first maximum value and the first minimum value is divided into the equal portions of the first quantity by S2, is obtained number and is
The cut-point of second quantity；
S3, the difference between the second maximum value and the second minimum value in the corresponding numerical value of the cut-point of the second quantity is true
Be set to point position of user data value to be detected away from；
S4 determines target difference and first maximum value and mesh of point position of the first minimum value and target multiple away between
Mark multiple divides target and value of the position away between；
S5 will fall between target difference and target and value and be determined as falling into target data ranges.
Optionally, in the present embodiment, the first quantity can be, but not limited to as the positive integer more than or equal to 3.This reality
It applies in example so that the first quantity is 4 as an example.
Optionally, in the present embodiment, the second quantity can be, but not limited to as the positive integer more than or equal to 2.This reality
It applies in example so that the second quantity is 3 as an example.
Optionally, in the present embodiment, target multiple can be, but not limited to as positive number.In the present embodiment with target multiple
For 1.5.
In an optional embodiment, box traction substation is made to user data value.The user found out other than interior limit is corresponding
Data value, as the corresponding user data value of user that may be abnormal.Specifically, user data value is arranged simultaneously from small to large
It is divided into quarter.Three separations are followed successively by first quartile (Q1), the second quartile (Q2), third quartile
(Q3).Calculate interior limit, respectively Q1-1.5IQR and Q3+1.5IQR.It is normal data between interior limit, is located at interior limit
It is possible exceptional value (to be less than Q1-1.5IQR in addition or be more than Q3+1.5IQR).Wherein, in box traction substation 1.5 times be by
The standard that a large amount of analyses and experience accumulation are got up.With statistical significance, there is reference value.
As a kind of optional scheme, determine that the corresponding deviation value of each data value includes in the first data value：
The data value of third quantity minimum with the distance between each data value in first data value is determined as often by S1
Corresponding second data value of a data value；
S2 determines the reach distance between each second data value and each data value；
S3 determines the local reachability density between each data value and each second data value according to reach distance；
S4 determines the corresponding local outlier factor of each data value according to local reachability density, and local outlier factor is true
It is set to the corresponding deviation value of each data value.
Optionally, in the present embodiment, by by the first data value minimum with the distance between each data value the
The data value of three quantity is determined as corresponding second data value of each data value to find out the neighborhood of each data value.Such as：It is right
Data value A in the first data value, by 10 data value (data minimum with the distance between data A in the first data value
Value 1 is to data value 10) it is determined as corresponding second data values of data value A, this 10 data values (data value 1 arrives data value 10) structure
At the neighborhood of data value A.
Optionally, in the present embodiment, according between each second data value in each data value and its neighborhood can
The local reachability density in each data value and its neighborhood between each second data value is determined up to distance, it is reachable further according to part
Density determines that the corresponding local outlier factor of each data value, the local outlier factor can indicate the deviation of each data value
Value.
Such as：In above-mentioned optional embodiment, internally the user of the possibility exception other than limit makees based on the close of neighborhood
Degree method (LOF) judges whether local anomaly by local outlier factor LOF, and then finds out abnormal data value.Detailed process is such as
Under：
Each user A is calculated at a distance from m-th nearest of user, is denoted as m-distance (A).Calculating point p to A's can
Up to distance reachability-distance (p, A)=max (m-distance (A), d (p, A)).Wherein d (p, A), which is represented, to be used
The Euclidean distance of family A and p.For example, as shown in figure 4, when setting m=3, since the distance of point D to A is distant, so D to A
Reach distance can be Euclidean distance between the two, and C is close from A, so can as between the two by m-distance (A)
Up to distance.The local reachability density lrd (q) for calculating user A is the average reach distance of object A and all the points in its k- neighborhoods
Inverse.The formula of the corresponding local reachability density lrd (q) of user A is as follows：
Wherein, | Nk(A) | indicate the reach distance between k point in neighborhood.For each reach distance between user B and user A in neighborhood
Sum.
Local outlier factor LOF is calculated, judges whether it deviates neighborhood, if is abnormal.The formula of local outlier factor LOF
It is as follows：
As a kind of optional scheme, the data value by deviation value in the first data value greater than desired value determines
Include for the abnormal data value in user data value：
S1, the data value by local outlier factor greater than 4 are determined as abnormal data value.
Optionally, in the present embodiment, the data value by local outlier factor greater than 4 is determined as abnormal data
Value, can more accurately determine abnormal data value.
As a kind of optional scheme, deviation value in the first data value is true greater than the data value of desired value
It is set to after the abnormal data value in user data value, further includes：
S1, from correspondence data type and operation in obtain the target data class of user data value to be detected
The corresponding object run of type；
S2 operates the corresponding user's performance objective of abnormal data value.
Optionally, in the present embodiment, the abnormal data value determined can be, but not limited to according to user data value
Data type determine the subsequent operation that is carried out to the corresponding user of these abnormal data values.Such as：For user it is online when
Abnormal data value in long data value can be monitored the user with these abnormal data values, to determine if to deposit
In illegal operation etc..
It should be noted that for each method embodiment above-mentioned, for simple description, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the described action sequence because
According to the present invention, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
Through the above description of the embodiments, those skilled in the art can be understood that according to above-mentioned implementation
The method of example can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but it is very much
In the case of the former be more preferably embodiment.Based on this understanding, technical scheme of the present invention is substantially in other words to existing
The part that technology contributes can be expressed in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, calculate
Machine, server or network equipment etc.) execute method described in each embodiment of the present invention.
Other side according to the ... of the embodiment of the present invention additionally provides a kind of exception for implementing above-mentioned user data value
The abnormal detector of the user data value of detection method, as shown in figure 5, the device includes：
Extraction module 52, for extracting user data value to be detected from user log files；
First acquisition module 54, for obtaining do not fall in target data ranges the from user data value to be detected
One data value；
First determining module 56, for determining the corresponding deviation value of each data value in the first data value, wherein deviation value
Be used to indicate the departure degree that each data value deviates the second data value, the second data value be in the first data value with each data
The distance between value meets the data value of goal condition, and deviation value is bigger, and departure degree is higher；
Second determining module 58 is determined for the data value by deviation value in the first data value greater than desired value
For the abnormal data value in user data value.
Optionally, in the present embodiment, the abnormal detector of above-mentioned user data value can be applied to as shown in Figure 2
In the hardware environment that server 202 is constituted.As shown in Fig. 2, server 202 extracts use to be detected from user log files
User data value obtains the first data value not fallen in target data ranges from user data value to be detected, determines first
Deviation value in first data value is greater than the data value of desired value by the corresponding deviation value of each data value in data value
The abnormal data value being determined as in user data value.
Optionally, in the present embodiment, the abnormal detector of above-mentioned user data value can be applied to as shown in Figure 3
In the hardware environment that application server 302, user journal server 304 and abnormality detection server 306 are constituted.Such as Fig. 3 institutes
Show, application server 302 is reported to collected user data in log server 304.Log server 304 generates user
Journal file.Abnormality detection server 306 extracts user data value to be detected from user log files, from use to be detected
The first data value not fallen in target data ranges is obtained in user data value, determines that each data value corresponds in the first data value
Deviation value, by deviation value in the first data value greater than desired value data value be determined as it is different in user data value
Regular data value.
Optionally, in the present embodiment, the abnormal detector of above-mentioned user data value can be, but not limited to be applied to pair
In the scene that user data value carries out abnormality detection.Wherein, the method for detecting abnormality of above-mentioned user data value can be, but not limited to
Applied to various types of applications, for example, online education application, instant messaging application, community space application, game application, purchase
Object application, browser application, financial application, multimedia application, live streaming application etc..Specifically, can be, but not limited to be applied to
In the scene carried out abnormality detection to user data value in above-mentioned game application, or can with but be not limited to be applied to it is above-mentioned i.e.
When communication applications in the scene that is carried out abnormality detection to user data value, abnormal user data value is detected with improving
Detection efficiency.Above-mentioned is only a kind of example, and any restriction is not done to this in the present embodiment.
Optionally, in the present embodiment, user data value can be, but not limited to the data for continuous variable.Such as：With
User data value can be, but not limited to：User's online hours, user participate in number, the user charges amount of money, the consumption of user's output
Etc..
Optionally, in the present embodiment, target data ranges can be, but not limited to be it is preset, can also but it is unlimited
Thus according to user data value automatic identification to be detected.Such as：Artificial intelligence model is trained according to history testing result, by
The target data ranges that model automatic identification after training is adapted to user data value to be detected.
Optionally, in the present embodiment, the corresponding deviation value of each data value can be, but not limited to use local outlier factor
(Local Outlier Factor, referred to as LOF) is indicated, local outlier factor is by check object relative to its neighborhood
Irrelevance (local irrelevance) detects abnormal point to judge outlier according to situation is deviateed.
Optionally, in the present embodiment, desired value can be, but not limited to be preset, can also but be not limited to root
According to user data value automatic identification to be detected.Such as：Artificial intelligence mould is trained according to the irrelevance in history detection data
Type, the desired value being adapted to user data value to be detected by the model automatic identification after training.
In an optional embodiment, for being carried out abnormality detection to the online hours in user 1 year, from
The online hours data value that user is extracted in the journal file of family, obtain from the online hours data value of user less than 1 hour or
First data value of the person more than 6570 hours is respectively user 1 corresponding 0.5 hour, user 2 corresponding 0.75 hours ... ...,
User i is 6600 hours corresponding, and user i+1 is 6659 hours corresponding ... ..., and user N is 7800 hours corresponding, determines the first number
According to the corresponding deviation value of each data value in value, such as：1 corresponding deviation value of user is 2, and 2 corresponding deviation value of user is
The corresponding deviation value of 4 ... ..., user i is 5.5, and the corresponding deviation values of user i+1 are 2.8 ... ..., the corresponding deviation values of user N
Be 7, by deviation value in the first data value greater than 4 data value be determined as it is different in the online hours data value of user
Regular data value.
As it can be seen that by above-mentioned apparatus, will not be fallen within from the user data value to be detected extracted in user log files
The first data value in target data ranges is determined as there may be abnormal data value, preliminary to reduce what abnormal data value was screened
Range, then determine the corresponding deviation value of each data value in the first data value, it is determined from the first data value according to the deviation value
Deviation value is abnormal data value greater than the data value of desired value, to accurately extract the exception in user data value
Data value, while to realize the technique effect for improving the detection efficiency being detected to abnormal user data value,
The abnormality detection to mass users data value is realized, and then solves the detection to abnormal user data value in the related technology
Less efficient technical problem.
As a kind of optional scheme, acquisition module includes：
First determination unit, for according in user data value to be detected the first maximum value and the first minimum value determine
Target data ranges；
Second determination unit, the data value for will not be fallen in user data value to be detected in target data ranges are true
It is set to the first data value；
Extraction unit, for extracting the first data value from user data value to be detected.
Optionally, in the present embodiment, target data ranges can be, but not limited to be according to user data value to be detected
Determining.Such as：According in user data value the first maximum value and first minimum value determine target data ranges.
Such as：By taking the online hours of game user as an example, the online hours data of the game user in 1 year got
In the first maximum value be 7000 hours, the first minimum value is 3 hours, then can be that 7000 and first are minimum according to the first maximum value
Value determines target data ranges for 3.
As a kind of optional scheme, determination unit includes：
First determination subelement, for determining the difference between the first maximum value and the first minimum value；
Divide subelement, for by the difference between the first maximum value and the first minimum value be divided into the first quantity etc.
Part, obtain the cut-point that number is the second quantity；
Second determination subelement is used for the second maximum value and second in the corresponding numerical value of the cut-point of the second quantity most
Difference between small value be determined as point position of user data value to be detected away from；
Third determination subelement, for determining target difference of point position of the first minimum value and target multiple away between, with
And first maximum value and target multiple divide target and value of the position away between；
4th determination subelement is determined as falling into target data model for that will fall between target difference and target and value
It encloses.
Optionally, in the present embodiment, the first quantity can be, but not limited to as the positive integer more than or equal to 3.This reality
It applies in example so that the first quantity is 4 as an example.
Optionally, in the present embodiment, the second quantity can be, but not limited to as the positive integer more than or equal to 2.This reality
It applies in example so that the second quantity is 3 as an example.
Optionally, in the present embodiment, target multiple can be, but not limited to as positive number.In the present embodiment with target multiple
For 1.5.
In an optional embodiment, box traction substation is made to user data value.The user found out other than interior limit is corresponding
Data value, as the corresponding user data value of user that may be abnormal.Specifically, user data value is arranged simultaneously from small to large
It is divided into quarter.Three separations are followed successively by first quartile (Q1), the second quartile (Q2), third quartile
(Q3).Calculate interior limit, respectively Q1-1.5IQR and Q3+1.5IQR.It is normal data between interior limit, is located at interior limit
It is possible exceptional value (to be less than Q1-1.5IQR in addition or be more than Q3+1.5IQR).Wherein, in box traction substation 1.5 times be by
The standard that a large amount of analyses and experience accumulation are got up.With statistical significance, there is reference value.
As a kind of optional scheme, the first determining module includes：
Third determination unit, for by third quantity minimum with the distance between each data value in the first data value
Data value is determined as corresponding second data value of each data value；
4th determination unit, for determining the reach distance between each second data value and each data value；
5th determination unit, for determining the part between each data value and each second data value according to reach distance
Up to density；
6th determination unit will for determining the corresponding local outlier factor of each data value according to local reachability density
Local outlier factor is determined as the corresponding above-mentioned deviation value of each data value.
Optionally, in the present embodiment, by by the first data value minimum with the distance between each data value the
The data value of three quantity is determined as corresponding second data value of each data value to find out the neighborhood of each data value.Such as：It is right
Data value A in the first data value, by 10 data value (data minimum with the distance between data A in the first data value
Value 1 is to data value 10) it is determined as corresponding second data values of data value A, this 10 data values (data value 1 arrives data value 10) structure
At the neighborhood of data value A.
Optionally, in the present embodiment, according between each second data value in each data value and its neighborhood can
The local reachability density in each data value and its neighborhood between each second data value is determined up to distance, it is reachable further according to part
Density determines that the corresponding local outlier factor of each data value, the local outlier factor can indicate the deviation of each data value
Value.
Such as：In above-mentioned optional embodiment, internally the user of the possibility exception other than limit makees based on the close of neighborhood
Degree method (LOF) judges whether local anomaly by local outlier factor LOF, and then finds out abnormal data value.Detailed process is such as
Under：
Each user A is calculated at a distance from m-th nearest of user, is denoted as m-distance (A).Calculating point p to A's can
Up to distance reachability-distance (p, A)=max (m-distance (A), d (p, A)).Wherein d (p, A), which is represented, to be used
The Euclidean distance of family A and p.For example, as shown in figure 4, when setting m=3, since the distance of point D to A is distant, so D to A
Reach distance can be Euclidean distance between the two, and C is close from A, so can as between the two by m-distance (A)
Up to distance.The local reachability density lrd (q) for calculating user A is the average reach distance of object A and all the points in its k- neighborhoods
Inverse.The formula of the corresponding local reachability density lrd (q) of user A is as follows：
Wherein, | Nk(A) | indicate the reach distance between k point in neighborhood.For each reach distance between user B and user A in neighborhood
Sum.
Local outlier factor LOF is calculated, judges whether it deviates neighborhood, if is abnormal.The formula of local outlier factor LOF
It is as follows：
As a kind of optional scheme, the second determining module is used for：
Data value by local outlier factor greater than 4 is determined as abnormal data value.
Optionally, in the present embodiment, the data value by local outlier factor greater than 4 is determined as abnormal data
Value, can more accurately determine abnormal data value.
As a kind of optional scheme, above-mentioned apparatus further includes：
Second acquisition module, for from correspondence data type and operation in obtain user data to be detected
The corresponding object run of target data type of value；
Execution module, for being operated to the corresponding user's performance objective of abnormal data value.
Optionally, in the present embodiment, the abnormal data value determined can be, but not limited to according to user data value
Data type determine the subsequent operation that is carried out to the corresponding user of these abnormal data values.Such as：For user it is online when
Abnormal data value in long data value can be monitored the user with these abnormal data values, to determine if to deposit
In illegal operation etc..
The application environment of the embodiment of the present invention can be, but not limited to reference to the application environment in above-described embodiment, the present embodiment
In this is repeated no more.An embodiment of the present invention provides the optional tools of one kind of the connection method for implementing above-mentioned real-time Communication for Power
Body application example.
As a kind of optional embodiment, the method for detecting abnormality of above-mentioned user data value can be, but not limited to be applied to such as
Amplification shown in fig. 6 to user in game is strengthened in the scene that number index carries out abnormality detection.In this scene, such as Fig. 6
It is shown, user's achievement data is obtained, then box traction substation judgement is carried out to achievement data, judges user's achievement data in box traction substation
Within limit or except, if within, judge that user is normal, if except, carry out LOF judgements, judge each use
Whether achievement data corresponding LOF in family is bigger than normal, if less than normal, it is determined that user is normal, if bigger than normal, it is determined that user is abnormal.
In an optional embodiment, strengthen number index point for amplification of nearly 1 year of the user in ludic activity
Analysis is with the presence or absence of abnormal.It is sorted successively for the amplification reinforcing number index of all users, and box traction substation is made to it, will be arranged
Data after sequence are divided into quarter.Three cut-points are respectively Q1=2；Q2=7；Q3=34.Interquartile-range IQR is Q3-Q1=32.
Interior limit is respectively Q1-1.5IQR=-46, Q3+1.5IQR=82.Data be less than -46 and data more than 82 be abnormal number
According to A.By data A by the density method based on neighborhood, the point (k=10) based on nearest 10 neighborhoods is selected, part is calculated
Outlier factor (LOF), finds out LOF>4 point, is judged as abnormal user.As shown in fig. 7, when amplification strengthens number more than 400,000,
Data are obviously abnormal.
Another aspect according to the ... of the embodiment of the present invention additionally provides a kind of exception for implementing above-mentioned user data value
The electronic device of detection, as shown in figure 8, the electronic device includes：One or more (one is only shown in figure) processors 802,
Memory 804, sensor 806, encoder 808 and transmitting device 810 are stored with computer program in the memory, at this
Reason device is arranged to execute the step in any of the above-described embodiment of the method by computer program.
Optionally, in the present embodiment, above-mentioned electronic device can be located in multiple network equipments of computer network
At least one network equipment.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program：
S1 extracts user data value to be detected from user log files；
S2 obtains the first data value not fallen in target data ranges from user data value to be detected；
S3 determines the corresponding deviation value of each data value in the first data value, wherein deviation value is used to indicate each data
Value deviates the departure degree of the second data value, and the second data value is to meet with the distance between each data value in the first data value
The data value of goal condition, deviation value is bigger, and departure degree is higher；
S4, the data value by deviation value in the first data value greater than desired value are determined as in user data value
Abnormal data value.
Optionally, it will appreciated by the skilled person that structure shown in Fig. 8 is only to illustrate, electronic device also may be used
To be smart mobile phone (such as Android phone, iOS mobile phones), tablet computer, palm PC and mobile internet device
The terminal devices such as (Mobile Internet Devices, MID), PAD.Fig. 8 it does not cause the structure of above-mentioned electronic device
It limits.For example, electronic device may also include more than shown in Fig. 8 or less component (such as network interface, display device
Deng), or with the configuration different from shown in Fig. 8.
Wherein, memory 802 can be used for storing software program and module, such as the user data value in the embodiment of the present invention
Method for detecting abnormality and the corresponding program instruction/module of device, processor 804 by operation be stored in memory 802
Software program and module realize the control of above-mentioned target element to perform various functions application and data processing
Method.Memory 802 may include high speed random access memory, can also include nonvolatile memory, such as one or more magnetic
Property storage device, flash memory or other non-volatile solid state memories.In some instances, memory 802 can further comprise
The memory remotely located relative to processor 804, these remote memories can pass through network connection to terminal.Above-mentioned network
Example include but not limited to internet, intranet, LAN, mobile radio communication and combinations thereof.
Above-mentioned transmitting device 810 is used to receive via a network or transmission data.Above-mentioned network specific example
It may include cable network and wireless network.In an example, transmitting device 810 includes a network adapter (Network
Interface Controller, NIC), can be connected with other network equipments with router by cable so as to interconnection
Net or LAN are communicated.In an example, transmitting device 810 is radio frequency (Radio Frequency, RF) module,
For wirelessly being communicated with internet.
Wherein, specifically, memory 802 is for storing application program.
The embodiments of the present invention also provide a kind of storage medium, computer program is stored in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program：
S1 extracts user data value to be detected from user log files；
S2 obtains the first data value not fallen in target data ranges from user data value to be detected；
S3 determines the corresponding deviation value of each data value in the first data value, wherein deviation value is used to indicate each data
Value deviates the departure degree of the second data value, and the second data value is to meet with the distance between each data value in the first data value
The data value of goal condition, deviation value is bigger, and departure degree is higher；
S4, the data value by deviation value in the first data value greater than desired value are determined as in user data value
Abnormal data value.
Optionally, storage medium is also configured to store for executing step included in the method in above-described embodiment
Computer program, this is repeated no more in the present embodiment.
Optionally, in the present embodiment, one of ordinary skill in the art will appreciate that in the various methods of above-described embodiment
All or part of step be that can be completed come command terminal device-dependent hardware by program, which can be stored in
In one computer readable storage medium, storage medium may include：Flash disk, read-only memory (Read-Only Memory,
ROM), random access device (Random Access Memory, RAM), disk or CD etc..
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
If the integrated unit in above-described embodiment is realized in the form of SFU software functional unit and as independent product
Sale in use, can be stored in the storage medium that above computer can be read.Based on this understanding, skill of the invention
Substantially all or part of the part that contributes to existing technology or the technical solution can be with soft in other words for art scheme
The form of part product embodies, which is stored in a storage medium, including some instructions are used so that one
Platform or multiple stage computers equipment (can be personal computer, server or network equipment etc.) execute each embodiment institute of the present invention
State all or part of step of method.
In the above embodiment of the present invention, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed client, it can be by others side
Formula is realized.Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, only one
Kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed it is mutual it
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (14)
1. a kind of method for detecting abnormality of user data value, which is characterized in that including：
User data value to be detected is extracted from user log files；
The first data value not fallen in target data ranges is obtained from the user data value to be detected；
Determine each corresponding deviation value of data value in first data value, wherein the deviation value is used to indicate described every
A data value deviates the departure degree of the second data value, and second data value is with described in first data value per number
Meet the data value of goal condition according to the distance between value, the more big departure degree of the deviation value is higher；
Data value by deviation value described in first data value greater than desired value is determined as the user data
Abnormal data value in value.
2. according to the method described in claim 1, not fallen within it is characterized in that, being obtained from the user data value to be detected
The first data value in target data ranges includes：
According in the user data value to be detected the first maximum value and the first minimum value determine the target data ranges；
The data value not fallen in target data ranges in the user data value to be detected is determined as first data
Value；
First data value is extracted from the user data value to be detected.
3. according to the method described in claim 2, it is characterized in that, according to the maximum value in the user data value to be detected
Determine that the target data ranges include with minimum value：
Determine the difference between first maximum value and first minimum value；
Difference between first maximum value and first minimum value is divided into the equal portions of the first quantity, obtaining number is
The cut-point of second quantity；
Difference between the second maximum value and the second minimum value in the corresponding numerical value of cut-point of second quantity is determined
For the user data value to be detected divide position away from；
Determine target difference and first maximum value of the described point of position of first minimum value and target multiple away between
With divide target and value of the position away between described in the target multiple；
It will fall between the target difference and the target and value and be determined as falling into the target data ranges.
4. according to the method described in claim 1, it is characterized in that, determining that each data value is corresponding in first data value
Deviation value includes：
The data value of third quantity minimum with the distance between each data value in first data value is determined as
Corresponding second data value of each data value；
Determine each reach distance between second data value and each data value；
The local reachability density between each data value and each second data value is determined according to the reach distance；
Determine the corresponding local outlier factor of each data value according to the local reachability density, by the local anomaly because
Son is determined as the corresponding deviation value of each data value.
5. according to the method described in claim 4, it is characterized in that, deviation value described in first data value is higher than or
The abnormal data value being determined as in the user data value equal to the data value of desired value includes：
Data value by the local outlier factor greater than 4 is determined as the abnormal data value.
6. according to the method described in claim 1, it is characterized in that, deviation value described in first data value is higher than or
The data value that person is equal to desired value is determined as after the abnormal data value in the user data value, and the method further includes：
From with correspondence data type and operation in obtain the target data type of the user data value to be detected
Corresponding object run；
The object run is executed to the corresponding user of the abnormal data value.
7. a kind of abnormal detector of user data value, which is characterized in that including：
Extraction module, for extracting user data value to be detected from user log files；
First acquisition module, for obtaining do not fall in target data ranges first from the user data value to be detected
Data value；
First determining module, for determining each corresponding deviation value of data value in first data value, wherein the deviation
Value is used to indicate the departure degree that each data value deviates the second data value, and second data value is first data
Meet the data value of goal condition, the more big departure degree of the deviation value in value with the distance between each data value
It is higher；
Second determining module, for deviation value described in first data value is true greater than the data value of desired value
The abnormal data value being set in the user data value.
8. device according to claim 7, which is characterized in that the acquisition module includes：
First determination unit, for according in the user data value to be detected the first maximum value and the first minimum value determine
The target data ranges；
Second determination unit, the data value for will not be fallen in the user data value to be detected in target data ranges are true
It is set to first data value；
Extraction unit, for extracting first data value from the user data value to be detected.
9. device according to claim 8, which is characterized in that the determination unit includes：
First determination subelement, for determining the difference between first maximum value and first minimum value；
Subelement is divided, for the difference between first maximum value and first minimum value to be divided into the first quantity
Equal portions obtain the cut-point that number is the second quantity；
Second determination subelement is used for the second maximum value and second in the corresponding numerical value of cut-point of second quantity most
Difference between small value be determined as point position of the user data value to be detected away from；
Third determination subelement, for determining goal discrepancy of the described point of position of first minimum value and target multiple away between
The target and value of value and described point of position of first maximum value and the target multiple away between；
4th determination subelement is determined as falling into the target for that will fall between the target difference and the target and value
Data area.
10. device according to claim 7, which is characterized in that first determining module includes：
Third determination unit, for by third number minimum with the distance between each data value in first data value
The data value of amount is determined as corresponding second data value of each data value；
4th determination unit, for determining each reach distance between second data value and each data value；
5th determination unit, for according to the reach distance determine each data value and each second data value it
Between local reachability density；
6th determination unit, for according to the local reachability density determine the corresponding local anomaly of each data value because
The local outlier factor is determined as the corresponding deviation value of each data value by son.
11. device according to claim 10, which is characterized in that the second determining module is used for：
Data value by the local outlier factor greater than 4 is determined as the abnormal data value.
12. device according to claim 7, which is characterized in that described device further includes：
Second acquisition module, for from correspondence data type and operation in obtain the user data to be detected
The corresponding object run of target data type of value；
Execution module, for executing the object run to the corresponding user of the abnormal data value.
13. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute the method described in any one of claim 1 to 6 when operation.
14. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to execute the side described in any one of claim 1 to 6 by the computer program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810411145.9A CN108628721B (en) | 2018-05-02 | 2018-05-02 | User data value abnormality detection method, device, storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810411145.9A CN108628721B (en) | 2018-05-02 | 2018-05-02 | User data value abnormality detection method, device, storage medium, and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108628721A true CN108628721A (en) | 2018-10-09 |
| CN108628721B CN108628721B (en) | 2021-07-27 |
Family
ID=63695129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810411145.9A Active CN108628721B (en) | 2018-05-02 | 2018-05-02 | User data value abnormality detection method, device, storage medium, and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628721B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109304034A (en) * | 2018-10-25 | 2019-02-05 | 珠海市君天电子科技有限公司 | A kind of game cheat detection method and relevant device |
| CN110223102A (en) * | 2019-05-08 | 2019-09-10 | 五八有限公司 | Lead referral method, apparatus, electronic equipment and storage medium |
| CN110491106A (en) * | 2019-07-22 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Data early warning method, device and the computer equipment of knowledge based map |
| CN112532972A (en) * | 2020-11-26 | 2021-03-19 | 北京百度网讯科技有限公司 | Fault detection method and device for live broadcast service, electronic equipment and readable storage medium |
| CN113343056A (en) * | 2021-05-21 | 2021-09-03 | 北京市燃气集团有限责任公司 | Method and device for detecting abnormal gas consumption of user |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014104622A1 (en) * | 2012-12-24 | 2014-07-03 | 한국과학기술정보연구원 | System for automatically detecting abnormalities statistical data on usage, method therefor, and apparatus applied to same |
| US20160140151A1 (en) * | 2014-11-18 | 2016-05-19 | International Business Machines Corporation | Data Resource Anomaly Detection |
| CN107193824A (en) * | 2016-03-14 | 2017-09-22 | 阿里巴巴集团控股有限公司 | Abnormal deviation data examination method and device |
| CN107256237A (en) * | 2017-05-23 | 2017-10-17 | 中国电子科技集团公司第二十八研究所 | The LOF cluster datas abnormal point detecting method and detecting system optimized based on dynamic grid |
| US20170339168A1 (en) * | 2016-05-20 | 2017-11-23 | Informatica Llc | Method, apparatus, and computer-readable medium for detecting anomalous user behavior |
| CN107733921A (en) * | 2017-11-14 | 2018-02-23 | 深圳中兴网信科技有限公司 | Network flow abnormal detecting method, device, computer equipment and storage medium |
-
2018
- 2018-05-02 CN CN201810411145.9A patent/CN108628721B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014104622A1 (en) * | 2012-12-24 | 2014-07-03 | 한국과학기술정보연구원 | System for automatically detecting abnormalities statistical data on usage, method therefor, and apparatus applied to same |
| US20160140151A1 (en) * | 2014-11-18 | 2016-05-19 | International Business Machines Corporation | Data Resource Anomaly Detection |
| CN107193824A (en) * | 2016-03-14 | 2017-09-22 | 阿里巴巴集团控股有限公司 | Abnormal deviation data examination method and device |
| US20170339168A1 (en) * | 2016-05-20 | 2017-11-23 | Informatica Llc | Method, apparatus, and computer-readable medium for detecting anomalous user behavior |
| CN107256237A (en) * | 2017-05-23 | 2017-10-17 | 中国电子科技集团公司第二十八研究所 | The LOF cluster datas abnormal point detecting method and detecting system optimized based on dynamic grid |
| CN107733921A (en) * | 2017-11-14 | 2018-02-23 | 深圳中兴网信科技有限公司 | Network flow abnormal detecting method, device, computer equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| SAM-X: "异常值检测", 《HTTPS://BLOG.CSDN.NET/U010945683/ARTICLE/DETAILS/79639664》 * |
| 王茹雪等: "基于瀑布型混合技术的异常检测算法", 《吉林大学学报(信息科学版)》 * |
| 秦浩: "基于密度的局部离群点挖掘及在入侵检测中应用研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 赵新想: "基于密度的局部离群点检测算法的研究与改进", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109304034A (en) * | 2018-10-25 | 2019-02-05 | 珠海市君天电子科技有限公司 | A kind of game cheat detection method and relevant device |
| CN110223102A (en) * | 2019-05-08 | 2019-09-10 | 五八有限公司 | Lead referral method, apparatus, electronic equipment and storage medium |
| CN110491106A (en) * | 2019-07-22 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Data early warning method, device and the computer equipment of knowledge based map |
| CN110491106B (en) * | 2019-07-22 | 2022-03-18 | 深圳壹账通智能科技有限公司 | Data early warning method and device based on knowledge graph and computer equipment |
| CN112532972A (en) * | 2020-11-26 | 2021-03-19 | 北京百度网讯科技有限公司 | Fault detection method and device for live broadcast service, electronic equipment and readable storage medium |
| CN112532972B (en) * | 2020-11-26 | 2023-10-03 | 北京百度网讯科技有限公司 | Fault detection method and device for live broadcast service, electronic equipment and readable storage medium |
| CN113343056A (en) * | 2021-05-21 | 2021-09-03 | 北京市燃气集团有限责任公司 | Method and device for detecting abnormal gas consumption of user |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108628721B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108628721A (en) | Method for detecting abnormality, device, storage medium and the electronic device of user data value | |
| CN107341716A (en) | A kind of method, apparatus and electronic equipment of the identification of malice order | |
| CN107404656A (en) | Live video recommends method, apparatus and server | |
| CN107798027A (en) | A kind of heatrate Forecasting Methodology, information recommendation method and device | |
| CN108985954A (en) | A kind of method and relevant device of incidence relation that establishing each mark | |
| CN108319974A (en) | Data processing method, device, storage medium and electronic device | |
| CN108768753A (en) | Localization method, device, storage medium and the electronic device of alarm source | |
| CN112100221B (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN108121943A (en) | Method of discrimination and device and computing device based on picture | |
| CN114817425A (en) | Method, device and equipment for classifying cold and hot data and readable storage medium | |
| CN104954528B (en) | The detection method and device of the power consumption information of terminal device | |
| CN108053214A (en) | A kind of recognition methods of wash sale and device | |
| CN110196805B (en) | Data processing method, data processing apparatus, storage medium, and electronic apparatus | |
| CN109376981B (en) | Data processing mode determining method and device, server and data processing method | |
| CN106257507A (en) | The methods of risk assessment of user behavior and device | |
| CN108335008A (en) | Web information processing method and device, storage medium and electronic device | |
| CN109726808A (en) | Neural network training method and device, storage medium and electronic device | |
| CN115484112B (en) | Payment big data safety protection method, system and cloud platform | |
| CN110276283A (en) | Image identification method, Model of Target Recognition training method and device | |
| CN110020102A (en) | Object recommendation method, apparatus, storage medium, processor and system | |
| CN113435642A (en) | Edible strategy determination method and device, storage medium and electronic device | |
| CN115118447A (en) | Safety discrimination method and device for industrial control network flow, electronic device and medium | |
| CN103793764B (en) | Package optimizing system and method based on GPU and neighboring mass data rapid analysis | |
| CN108984692B (en) | The processing method and processing device of webpage, storage medium, electronic device | |
| CN110427558A (en) | The method for pushing and device of Energy Resources Service's director's part |
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 |