CN111860644A - Abnormal account identification method, device, equipment and storage medium - Google Patents
Abnormal account identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111860644A CN111860644A CN202010699003.4A CN202010699003A CN111860644A CN 111860644 A CN111860644 A CN 111860644A CN 202010699003 A CN202010699003 A CN 202010699003A CN 111860644 A CN111860644 A CN 111860644A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- historical time
- time unit
- account
- registered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 281
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012216 screening Methods 0.000 claims abstract description 42
- 230000008859 change Effects 0.000 claims abstract description 14
- 230000015654 memory Effects 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 2
- 230000006399 behavior Effects 0.000 abstract description 8
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for identifying an abnormal account, and relates to the fields of data processing, big data and cloud computing. The specific implementation scheme is as follows: screening out abnormal historical time units according to the change trend of the number of registered accounts in the continuous historical time units; acquiring at least one target account number which is registered in the abnormal historical time unit; and screening abnormal accounts meeting abnormal registration time and/or abnormal registration user name conditions from all the target accounts. According to the technical scheme, cheating judgment can be carried out only according to abnormal gathering behaviors existing among the account numbers, and cheating detection can be achieved faster and better.
Description
Technical Field
The application relates to the technical field of computers, in particular to data detection, big data and cloud computing technologies, and specifically relates to a method, a device, equipment and a storage medium for identifying an abnormal account.
Background
Currently, various applications provide many tasks that can be used by users to produce data autonomously, such as free annotation of Point of Interest (POI) data. The above task may have user cheating behavior. For example, malicious punctuation diversion, malicious business competition, or cheating actions such as toll collection agents for the above-mentioned free annotation task.
In the anti-cheating system in the prior art, a rule-class strategy is generally formulated by using expert business experience, historical report data of a single account is extracted, and if a strategy threshold value is triggered, the account is blackened or is limited to be reported.
In fact, the internet black birth completes the full link cooperation of 'automatic registration + number maintenance + account number transaction + cheating + stolen goods', the registration cost of the account number is extremely low, the anti-cheating on the single account number is usually treated as a temporary solution and not a permanent solution, and the cheating behavior can not be effectively stopped or improved.
Disclosure of Invention
The application provides a method, a device, equipment and a storage medium for identifying an abnormal account.
According to an aspect of the present application, a method for identifying an abnormal account is provided, including:
screening out abnormal historical time units according to the change trend of the number of registered accounts in the continuous historical time units;
acquiring at least one target account number which is registered in the abnormal historical time unit;
and screening abnormal accounts meeting abnormal registration time and/or abnormal registration user name conditions from all the target accounts.
According to another aspect of the present application, there is provided an apparatus for identifying an abnormal account, including:
The abnormal historical time unit screening module is used for screening the abnormal historical time unit according to the change trend of the number of the registered accounts in the continuous historical time unit;
the target account acquisition module is used for acquiring at least one target account which is registered in the abnormal historical time unit;
and the abnormal account screening module is used for screening abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registration user names from all the target accounts.
According to another aspect of the present application, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the embodiments of the present application.
According to another aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of the embodiments of the present application.
According to the technical scheme of the embodiment of the application, the abnormal historical time unit is screened out according to the variation trend of the number of the registered accounts in the continuous historical time unit, then at least one target account which is registered in the abnormal historical time unit is obtained, and finally the abnormal account meeting the abnormal registration time and/or the abnormal registered user name condition is screened out from each target account.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
fig. 1 is a schematic diagram of an identification method of an abnormal account according to an embodiment of the present application;
fig. 2a is a schematic diagram of an abnormal account identification method according to an embodiment of the present application;
FIG. 2b is a schematic diagram of an embodiment of the present application for obtaining an anomaly factor through an LOF algorithm;
fig. 3a is a schematic diagram of a method for identifying an abnormal account according to an embodiment of the present application;
FIG. 3b is a schematic diagram of a fitting curve suitable for use in embodiments of the present application;
fig. 4 is a schematic structural diagram of an abnormal account number identification apparatus according to an embodiment of the present application;
fig. 5 is a block diagram of an electronic device for implementing the abnormal account identification method according to the embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of an identification method for an abnormal account in an embodiment of the present application, where the technical solution of this embodiment is suitable for a case where cheating determination is performed according to the registered number of accounts in a historical time unit, and the method may be executed by an identification device for an abnormal account, where the identification device may be implemented in a software and/or hardware manner, and may be generally integrated in an electronic device, for example, a terminal device, and the method of this embodiment specifically includes the following steps:
And 110, screening an abnormal historical time unit according to the change trend of the number of the registered accounts in the continuous historical time unit.
The historical time unit is a standard time interval for identifying the abnormal account, that is, the abnormal account is identified in a unit time of the standard time interval, and may be 1 day, for example.
In this embodiment, in order to identify an abnormal account in a continuous historical time unit, the number of registered accounts in each historical time unit in the continuous historical time unit is first obtained, then a change trend of the number of registered accounts in the continuous historical time unit is determined according to the number of registered accounts in each historical time unit, and finally a historical time unit that does not conform to the change trend is determined as an abnormal historical time unit, that is, it is preliminarily determined that an abnormal account registration exists in the historical time unit.
For example, the number of registered accounts per day in 60 consecutive days is obtained, then the number of registered accounts per day in 60 consecutive days is fitted to obtain a fitted curve of the number of registered accounts in 60 consecutive days, the deviation amount of the number of registered accounts per day deviating from the fitted curve is further judged, and if the deviation amount exceeds a set deviation threshold, the day is determined to be an abnormal historical time unit.
And step 120, acquiring at least one target account number which is registered in the abnormal historical time unit.
In this embodiment, after the abnormal historical time unit is determined, all accounts registered in the abnormal historical time unit are acquired from the historical storage data and are used as target accounts, and the target accounts are accounts which need to be subsequently subjected to abnormal account determination. For example, after determining that the 30 th day of the continuous 60 days is an abnormal historical time unit, all accounts which are completely registered within the 30 th day are acquired as target accounts, that is, abnormal accounts may exist in the target accounts.
And step 130, screening abnormal accounts meeting the abnormal registration time and/or the abnormal registration user name condition from the target accounts.
In this embodiment, after the target account numbers included in the abnormal historical time unit are obtained, data detection is performed to screen abnormal account numbers in the target account numbers, specifically, registration time and registration user name corresponding to each target account number are extracted, then, whether the registration time corresponding to each target account number meets the abnormal registration time condition is judged, whether the registration user name of each target account number meets the abnormal registration user name condition is judged, and when the registration time or the registration user name of the target account number meets the abnormal condition, the target account number is determined to be an abnormal account number; of course, according to the actual situation, when the registration time and the registration user name of the target account satisfy the above two abnormal conditions, it is determined that the target account is an abnormal account.
Exemplarily, acquiring registration time and a registration user name of each target account, then calculating a registration time difference of each target account, determining a plurality of target accounts with the registration time difference lower than a set threshold as meeting an abnormal registration time condition, and determining the target accounts as abnormal accounts; the similarity between the registered user names of the target account numbers can be calculated, a plurality of target account numbers with the similarity between the registered user names and the registered user names of the target account numbers exceeding the set number exceeding the set similarity threshold are determined as meeting the abnormal registered user name condition, and the target account numbers are determined as abnormal account numbers. Of course, when a certain target account number simultaneously satisfies the two abnormal conditions, the target account number may be determined to be an abnormal account number.
According to the technical scheme, the abnormal historical time unit is screened out according to the variation trend of the number of registered accounts in the continuous historical time unit, at least one target account which is registered in the abnormal historical time unit is acquired, and finally, the abnormal account meeting the abnormal registration time and/or the abnormal registered user name condition is screened out from each target account.
Optionally, after screening out an abnormal account meeting the abnormal registration time and/or the abnormal registration user name condition in each target account, the method may further include:
and performing batch black drawing treatment on the screened abnormal account numbers.
In this optional embodiment, after the abnormal account numbers are screened out, all the abnormal account numbers are blackened in batches, and the server will not process any service request initiated by the blackened account numbers, so that server resources are saved, and meanwhile, malicious behaviors such as malicious upper-point diversion, malicious commercial competition or charging agency are avoided.
Fig. 2a is a schematic diagram of an abnormal account identification method in an embodiment of the present application, which is further detailed based on the above embodiment, and provides a specific step of screening out an abnormal historical time unit according to a variation trend of the number of registered accounts in a continuous historical time unit, and a specific step of screening out an abnormal account satisfying conditions of abnormal registration time and/or an abnormal registered user name in each target account. The following describes, with reference to fig. 2a, a method for identifying an abnormal account provided in an embodiment of the present application, including the following steps:
step 210, for each historical time unit, obtaining a plurality of consecutive reference historical time units located before each historical time unit along the reverse direction of the time extension direction.
In this embodiment, in order to determine whether an abnormal account registration condition exists in a certain historical time unit, a plurality of reference historical time units before the historical time unit are obtained along the direction opposite to the time extension direction, that is, a set number of consecutive historical time units before the certain historical time unit are obtained as the reference historical time units.
For example, with 1 day as 1 historical time unit, in order to determine whether there is an abnormal account registration condition on the day of 2018, 9, 16, first, 90 consecutive days before 2018, 9, 16 are acquired as a reference historical time unit.
And step 220, fitting to obtain an account number prediction curve corresponding to each historical time unit according to the registered account number in each reference historical time unit.
In this embodiment, after a plurality of consecutive reference historical time units are obtained, in order to predict the number of registered accounts of a set historical time unit according to the number of registered accounts of the plurality of reference historical time units, the number of registered accounts corresponding to each reference historical time unit needs to be fitted to obtain a prediction curve of the number of accounts corresponding to the historical time unit to be predicted, and the number of registered accounts of the set historical time unit can be predicted according to the prediction curve.
For example, in order to predict the number of registered accounts on the day of 16/9/2018, the number of registered accounts on the day of 16/9/2018 may be fitted to the number of registered accounts on 90 consecutive days before the day, so as to finally obtain an account prediction curve corresponding to the day, and the number of registered accounts on the day of 16/9/2018 may be predicted according to the curve.
And step 230, determining the account number predicted value corresponding to each historical time unit according to each account number predicted curve.
In this embodiment, after the account number prediction curve is obtained by fitting, the account number prediction value of the historical time unit corresponding to the curve is predicted according to the account number prediction curve, specifically, the horizontal axis of the coordinate system where the account number prediction curve is located is time, and the vertical axis is the registered account number, the historical time unit to be predicted may be input to the function corresponding to the account number prediction curve, and the output function value is the registered account number in the historical time unit.
And 240, verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number predicted value.
In this embodiment, after the account number prediction value of a certain historical time unit is calculated according to the account number prediction curve, in order to determine whether abnormal account registration exists in the historical time unit, a difference value between the account number prediction value and the actual registered account number of the historical time unit may be calculated, and whether the historical time unit is an abnormal historical time unit is verified according to the difference value, so that whether cheating behaviors exist or not is determined according to the registered account number in each historical time unit, and the cheating detection efficiency is improved.
For example, a difference value between the account number predicted value corresponding to the currently predicted historical time unit and the actual registered account number may be calculated, then a deviation degree of the account number predicted value from the actual registered account number may be calculated according to the difference value, and when the deviation degree is greater than a set deviation threshold, the current historical time unit may be determined to be an abnormal historical time unit.
Optionally, verifying whether each historical time unit is an abnormal historical time unit according to a difference value between the registered account number in each historical time unit and the corresponding account number prediction value comprises:
Acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number predicted value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset first threshold value, determining that the target historical time unit is an abnormal historical time unit.
In this optional embodiment, a manner is provided for verifying whether each historical time unit is an abnormal historical time unit according to a difference between the number of registered accounts in each historical time unit and a corresponding account number prediction value, specifically, an absolute value | p _ num-t _ num | of a difference between a registered account number t _ num of a current processed target historical time unit and a corresponding account number prediction value p _ num is first taken, then a ratio | p _ num-t _ num |/t _ num between the absolute difference and the registered account number of the target historical time unit is calculated, and when the ratio exceeds a preset first threshold, the current target historical time unit is determined to be an abnormal historical time unit.
And step 250, acquiring at least one target account number which is registered in the abnormal historical time unit.
And step 260, adopting a local outlier factor detection LOF algorithm, and calculating abnormal factors respectively corresponding to each target account by taking the registration time and the registered user name of each target account as characteristics.
In this embodiment, in order to determine whether at least one target account that has been registered within an abnormal historical time unit is an abnormal account, the registration time and the registered user name of each target account are extracted as features, and an LOF (Local outlier factor) algorithm is used to calculate an abnormal factor of each target account under the above two features.
The LOF algorithm is a density-based outlier detection algorithm, whose main idea is to detect the clustering of data points in a given data set, where a data point is considered to be a normal data point if the points in its local neighborhood are very dense, and an outlier if the distance between the data point and its nearest neighbor is very long.
In this embodiment, when registering an account by a machine, a large number of accounts with similar user names are often quickly registered within a period of time according to a registration rule predetermined by a cheater, for example, the user name is composed of 3 chinese characters and 4 letters, so that the account registered by the machine has two obvious characteristics, one is that the user name has a certain similarity, and the registration time is abnormally concentrated, so when detecting the account registered by the machine, it is necessary to focus on the abnormal aggregation behavior of the accounts with similar user names within a similar time interval, therefore, by using the LOF algorithm, the abnormal factor of each target account is calculated by using the registration time and the registered user name of the target account as characteristics, it can be understood that the lower the abnormal factor of the target account is, the more accounts with similar registration time and registered user name are, the target account is possibly an abnormal account registered by the machine, fig. 2b includes the abnormality factors of the target account numbers calculated by the LOF algorithm, where circles represent the abnormality factors of the target account numbers, and four horizontal lines are an aggregation of a large number of machine-registered target account numbers.
And 270, determining the target account with the abnormal factor exceeding a preset third threshold value as an outlier account.
In this embodiment, after the LOF algorithm is used to calculate the abnormal factor of each target account, whether the target account is an outlier is determined by a preset third threshold. Specifically, if the abnormal factor of a certain target account is greater than a preset third threshold, the target account is considered to belong to an outlier user, and otherwise, the target account is considered not to belong to the outlier user.
Step 280, filtering outlier accounts from the target accounts to obtain abnormal accounts.
In this embodiment, the outlier account can be regarded as a normally registered account, and the outlier accounts in the target account that have been registered in the target historical time unit are filtered out, and the remaining accounts are abnormal accounts.
According to the abnormal account detection method, the LOF algorithm can be adopted to determine the abnormal account registered by the machine in the abnormal historical time unit, so that the efficiency and accuracy of abnormal account detection are improved.
According to the technical scheme, registered account numbers corresponding to a plurality of continuous reference historical time units before each historical time unit to be processed are obtained, account number prediction curves corresponding to the historical time units are obtained through fitting, account number prediction values corresponding to the historical time units are determined according to the account number prediction curves, whether the historical time units are abnormal historical time units or not is verified according to the difference value between the registered account numbers in the historical time units and the corresponding account number prediction values, abnormal account numbers are determined through an LOF algorithm in a plurality of target account numbers which are registered in the abnormal historical time units, cheating judgment is achieved only according to abnormal gathering behaviors among the account numbers, and abnormal account number identification efficiency and accuracy are improved.
Fig. 3a is a schematic diagram of an abnormal account identification method in an embodiment of the present application, which is further detailed based on the above embodiment, and provides a specific step of screening out an abnormal historical time unit according to a variation trend of the number of registered accounts in a continuous historical time unit, and a specific step of screening out an abnormal account satisfying abnormal registration time and/or abnormal registered user name conditions in each target account. The following describes, with reference to fig. 3a, a method for identifying an abnormal account provided in an embodiment of the present application, including the following steps:
and step 310, acquiring the number of registered accounts in each historical time unit included in the set historical time interval.
In this embodiment, in order to determine whether an abnormal account exists in each historical time unit included in the set historical time interval, the number of registered accounts in each historical time unit included in the set historical time interval is first obtained, so that the historical time unit in which the abnormal account possibly exists is determined according to the number of registered accounts in the following process. For example, in order to determine whether an abnormal account exists in the time interval from 6/month 1/2018 to 9/month 1/2018, the number of registered accounts in the time interval may be first obtained, a change trend of the number of registered accounts obtained through account registration in each day may be subsequently determined, and a date corresponding to the number of registered accounts which does not conform to the change trend may be determined as a date on which the abnormal account registration exists.
And step 320, fitting to obtain an account number fitting curve matched with the historical time interval according to the number of each registered account number.
In this embodiment, after the number of registered accounts of each historical time unit is obtained, an account number fitting curve matched with the historical time interval is obtained through fitting according to the number of registered accounts and the corresponding historical time unit, and the account number fitting curve can represent the variation trend of the number of registered accounts corresponding to each historical time unit in the historical time interval.
And step 330, determining account number fitting values respectively corresponding to the historical time units according to the account number fitting curve.
In this embodiment, the fitting value of the number of accounts corresponding to each historical time unit may be calculated according to the fitting curve of the number of accounts obtained by fitting, so as to subsequently determine whether each historical time unit is an abnormal historical time unit according to the relationship between the fitting value of the number of accounts corresponding to each historical time unit and the actual number of registered accounts. Illustratively, the independent variable of the curve function corresponding to the account number fitting curve is each abnormal historical time unit, the dependent variable is the registered account number, and the user can input a certain historical time unit into the curve function to obtain the account number fitting value corresponding to the historical time unit.
And 340, verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding fitted value of the account number.
In this embodiment, after the account number fitting value of a certain historical time unit is calculated according to the account number fitting curve, in order to determine whether abnormal account registration exists in the historical time unit, a difference value between the account number fitting value and the actual registered account number of the historical time unit may be calculated, and whether the historical time unit is the abnormal historical time unit is verified according to the difference value, so that whether cheating behavior exists or not can be determined only according to the registered account number in each historical time unit, and the cheating detection efficiency is improved.
For example, a difference value between a fitting value of the number of account numbers corresponding to the current historical time unit and the actual number of registered account numbers may be calculated, then a deviation degree of the actual number of registered account numbers from the fitting value of the number of account numbers is calculated according to the difference value, and when the deviation degree is greater than a set deviation threshold value, the current historical time unit is determined to be an abnormal historical time unit.
Optionally, verifying whether each historical time unit is an abnormal historical time unit according to a difference between the number of registered accounts in each historical time unit and a fitted value of the number of corresponding accounts includes:
acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number fitting value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset second threshold value, determining the target historical time unit as an abnormal historical time unit.
In this optional embodiment, a manner is provided for verifying whether each historical time unit is an abnormal historical time unit according to a difference between the number of registered accounts in each historical time unit and a corresponding account number fitting value, specifically, an absolute value of a difference between the number of registered accounts of a currently processed target historical time unit and a corresponding account number fitting value is first taken, and then a ratio between the absolute difference and the number of registered accounts of the target historical time unit is calculated, and when the ratio exceeds a preset second threshold, the current target historical time unit is determined to be an abnormal historical time unit.
And step 350, acquiring at least one target account number which is registered in the abnormal historical time unit.
And 360, screening abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registration user names from the target accounts.
In the embodiment, in the case that abnormal account registration exists in some historical time units in the continuous historical time units, the fitting curve of the number of registered accounts obtained by fitting according to the number of registered accounts in each historical time unit may be influenced by abnormal accounts and cannot accurately reflect the change trend of the number of registered accounts in the current historical time interval, therefore, the fitted value of the number of the account corresponding to each historical time unit obtained according to the fitted curve of the number of the current account is not always capable of accurately judging whether the current historical time unit is an abnormal historical time unit or not, therefore, after each detected abnormal account number, executing abnormal account number filtering operation once, and then fitting the registered account number of each historical time unit after the abnormal account number is filtered to obtain an account number fitting curve, the determination accuracy can be improved when determining whether or not the other historical time units are abnormal historical time units.
For example, under the condition that abnormal account registration is not included, the curve fitted in a history time interval is curve 1, which is specifically shown in fig. 3b, but when the history time interval includes an abnormal history time unit, the curve fitted in the history time interval may approach curve 2 under the influence of abnormal account registration, which may cause that the abnormal history time unit indicated by arrow 1 cannot be recalled, and thus the accuracy of abnormal account identification is reduced. Therefore, after the abnormal account is detected, the abnormal account needs to be filtered in time, so that data correction is realized, and the accuracy of subsequent abnormal account identification is ensured.
According to the technical scheme of the embodiment of the application, the number of the registered accounts in each historical time unit in the set historical time interval is fitted into an account number fitting curve matched with the historical time interval, then according to the account number fitting curve, determining the account number fitting value corresponding to each historical time unit, and verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the number of registered accounts in each historical time unit and the corresponding fitting value of the number of accounts, and finally identifying and filtering abnormal accounts in the abnormal historical time unit.
Fig. 4 is a schematic structural diagram of an apparatus for identifying an abnormal account in an embodiment of the present application, where the apparatus for identifying an abnormal account includes: an abnormal historical time unit screening module 410, a target account acquisition module 420, and an abnormal account screening module 430.
An abnormal historical time unit screening module 410, configured to screen an abnormal historical time unit according to a change trend of the number of registered accounts in the continuous historical time unit;
a target account number obtaining module 420, configured to obtain at least one target account number that is registered within the abnormal historical time unit;
an abnormal account screening module 430, configured to screen out, from each target account, an abnormal account that meets the conditions of abnormal registration time and/or abnormal registration user name.
According to the technical scheme, the abnormal historical time unit is screened out according to the variation trend of the number of registered accounts in the continuous historical time unit, at least one target account which is registered in the abnormal historical time unit is acquired, and finally, the abnormal account meeting the abnormal registration time and/or the abnormal registered user name condition is screened out from each target account.
Optionally, the abnormal historical time unit filtering module 410 includes:
a reference historical time unit obtaining unit configured to obtain, for each historical time unit, a plurality of consecutive reference historical time units located before the each historical time unit in a direction opposite to a time extending direction;
the account number prediction curve fitting unit is used for fitting to obtain an account number prediction curve corresponding to each historical time unit according to the registered account number in each reference historical time unit;
the account number predicted value determining unit is used for determining the account number predicted value corresponding to each historical time unit according to each account number predicted curve;
and the first verification unit is used for verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number predicted value.
Optionally, the abnormal historical time unit filtering module 410 includes:
a registered account number obtaining unit, configured to obtain the number of registered accounts in each historical time unit included in the set historical time interval;
an account number fitting curve fitting unit, configured to fit, according to the number of each registered account, an account number fitting curve that matches the historical time interval;
An account number fitting value determining unit, configured to determine, according to the account number fitting curve, account number fitting values corresponding to the historical time units, respectively;
and the second verification unit is used for verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number fitting value.
Optionally, the first verification unit is specifically configured to:
acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number predicted value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset first threshold, determining that the target historical time unit is an abnormal historical time unit.
Optionally, the second verification unit is specifically configured to:
acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number fitting value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
And if the ratio exceeds a preset second threshold value, determining that the target historical time unit is an abnormal historical time unit.
Optionally, the abnormal account screening module 430 is specifically configured to:
calculating abnormal factors respectively corresponding to the target account numbers by adopting an LOF algorithm and taking the registration time and the registered user name of each target account number as characteristics;
determining the target account with the abnormal factor exceeding a preset third threshold value as an outlier account;
and filtering the outlier account in each target account to obtain the abnormal account.
Optionally, the device for identifying an abnormal account further includes:
and the abnormal historical time unit re-determining module is used for re-determining a new abnormal historical time unit after screening out abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registered user names from all the target accounts and filtering out all the abnormal accounts from all the registered accounts, and returning to execute the operation of acquiring at least one target account which is registered in the abnormal historical time unit until the screening of all the abnormal accounts is completed.
Optionally, the device for identifying an abnormal account further includes:
And the blackening module is used for screening abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registered user name in each target account, and then carrying out batch blackening treatment on the screened abnormal accounts.
The identification device for the abnormal account provided by the embodiment of the application can execute the identification method for the abnormal account provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 5 is a block diagram of an electronic device according to an abnormal account identification method in an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 5, the electronic apparatus includes: one or more processors 501, memory 502, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 5, one processor 501 is taken as an example.
The memory 502, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the identification method of the abnormal account number in the embodiment of the present application (for example, the abnormal historical time unit screening module 410, the target account number obtaining module 420, and the abnormal account number screening module 430 shown in fig. 4). The processor 501 executes various functional applications and data processing of the server by running non-transitory software programs, instructions and modules stored in the memory 502, that is, implements the method for identifying an abnormal account in the above method embodiment.
The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from the use of the electronic device by the identification of the abnormal account number, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 502 optionally includes memory located remotely from processor 501, which may be connected to the anomalous account's identifying electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the abnormal account identification method may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The input device 503 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of the electronic device for identification of the abnormal account number, such as an input device such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 504 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
According to the technical scheme of the embodiment of the application, the abnormal historical time unit is screened out according to the variation trend of the number of the registered accounts in the continuous historical time unit, then at least one target account which is registered in the abnormal historical time unit is obtained, and finally the abnormal account meeting the abnormal registration time and/or the abnormal registered user name condition is screened out from each target account.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (18)
1. A method for identifying an abnormal account number comprises the following steps:
screening out abnormal historical time units according to the change trend of the number of registered accounts in the continuous historical time units;
acquiring at least one target account number which is registered in the abnormal historical time unit;
and screening abnormal accounts meeting abnormal registration time and/or abnormal registration user name conditions from all the target accounts.
2. The method of claim 1, wherein the screening out abnormal historical time units according to the change trend of the number of registered accounts in the continuous historical time units comprises:
aiming at each historical time unit, acquiring a plurality of continuous reference historical time units positioned in front of each historical time unit along the reverse direction of the time extension direction;
according to the number of registered accounts in each reference historical time unit, fitting to obtain an account number prediction curve corresponding to each historical time unit;
determining account number predicted values corresponding to the historical time units according to the account number predicted curves;
and verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number predicted value.
3. The method of claim 1, wherein the screening out abnormal historical time units according to the change trend of the number of registered accounts in the continuous historical time units comprises:
acquiring the number of registered accounts in each historical time unit included in a set historical time interval;
fitting to obtain an account number fitting curve matched with the historical time interval according to the number of each registered account;
determining account number fitting values respectively corresponding to the historical time units according to the account number fitting curve;
and verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number fitting value.
4. The method of claim 2, wherein verifying whether each historical time unit is an abnormal historical time unit according to a difference value between the registered account number and the corresponding account number predicted value in each historical time unit comprises:
acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number predicted value;
Calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset first threshold, determining that the target historical time unit is an abnormal historical time unit.
5. The method of claim 3, wherein verifying whether each historical time unit is an abnormal historical time unit according to a difference between a registered account number and a corresponding account number fitting value in each historical time unit comprises:
acquiring an absolute difference value between the number of registered accounts of the currently processed target historical time unit and a corresponding account number fitting value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset second threshold value, determining that the target historical time unit is an abnormal historical time unit.
6. The method according to claim 1, wherein the screening out, from among the target account numbers, an abnormal account number that meets the conditions of abnormal registration time and/or abnormal registration user name includes:
calculating abnormal factors respectively corresponding to the target accounts by adopting a local outlier factor LOF algorithm and taking the registration time and the registered user name of each target account as characteristics;
Determining the target account with the abnormal factor exceeding a preset third threshold value as an outlier account;
and filtering the outlier account in each target account to obtain the abnormal account.
7. The method according to claim 1, further comprising, after screening out, from each target account, an abnormal account that meets an abnormal registration time and/or an abnormal registration user name condition:
and in all registered accounts, after filtering each abnormal account, re-determining a new abnormal historical time unit, and returning to execute the operation of acquiring at least one target account which is registered in the abnormal historical time unit until the screening of all abnormal accounts is completed.
8. The method according to claim 1, further comprising, after screening out, from each target account, an abnormal account that meets an abnormal registration time and/or an abnormal registration user name condition:
and performing batch black drawing treatment on the screened abnormal account numbers.
9. An abnormal account number identification device comprises:
the abnormal historical time unit screening module is used for screening the abnormal historical time unit according to the change trend of the number of the registered accounts in the continuous historical time unit;
The target account acquisition module is used for acquiring at least one target account which is registered in the abnormal historical time unit;
and the abnormal account screening module is used for screening abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registration user names from all the target accounts.
10. The apparatus of claim 9, wherein the exception history time unit filtering module comprises:
a reference historical time unit obtaining unit configured to obtain, for each historical time unit, a plurality of consecutive reference historical time units located before the each historical time unit in a direction opposite to a time extending direction;
the account number prediction curve fitting unit is used for fitting to obtain an account number prediction curve corresponding to each historical time unit according to the registered account number in each reference historical time unit;
the account number predicted value determining unit is used for determining the account number predicted value corresponding to each historical time unit according to each account number predicted curve;
and the first verification unit is used for verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number predicted value.
11. The apparatus of claim 9, wherein the exception history time unit filtering module comprises:
a registered account number obtaining unit, configured to obtain the number of registered accounts in each historical time unit included in the set historical time interval;
an account number fitting curve fitting unit, configured to fit, according to the number of each registered account, an account number fitting curve that matches the historical time interval;
an account number fitting value determining unit, configured to determine, according to the account number fitting curve, account number fitting values corresponding to the historical time units, respectively;
and the second verification unit is used for verifying whether each historical time unit is an abnormal historical time unit or not according to the difference value between the registered account number in each historical time unit and the corresponding account number fitting value.
12. The apparatus according to claim 10, wherein the first authentication unit is specifically configured to:
acquiring an absolute difference value between the number of registered accounts of a currently processed target historical time unit and a corresponding account number predicted value;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
And if the ratio exceeds a preset first threshold, determining that the target historical time unit is an abnormal historical time unit.
13. The apparatus according to claim 11, wherein the second verification unit is specifically configured to:
acquiring an absolute difference value between the number of registered accounts of a currently processed target historical time unit and a fitting value of the number of corresponding accounts;
calculating the ratio of the absolute difference value to the number of registered accounts of the target historical time unit;
and if the ratio exceeds a preset second threshold value, determining that the target historical time unit is an abnormal historical time unit.
14. The apparatus according to claim 9, wherein the abnormal account screening module is specifically configured to:
calculating abnormal factors respectively corresponding to the target accounts by adopting a local outlier factor LOF algorithm and taking the registration time and the registered user name of each target account as characteristics;
determining the target account with the abnormal factor exceeding a preset third threshold value as an outlier account;
and filtering the outlier account in each target account to obtain the abnormal account.
15. The apparatus of claim 9, the apparatus for identifying the abnormal account number further comprising:
And the abnormal historical time unit re-determining module is used for re-determining a new abnormal historical time unit after screening out abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registered user names from all the target accounts and filtering out all the abnormal accounts from all the registered accounts, and returning to execute the operation of acquiring at least one target account which is registered in the abnormal historical time unit until the screening of all the abnormal accounts is completed.
16. The apparatus of claim 9, the apparatus for identifying the abnormal account number further comprising:
and the blackening module is used for screening abnormal accounts meeting the conditions of abnormal registration time and/or abnormal registered user name in each target account, and then carrying out batch blackening treatment on the screened abnormal accounts.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699003.4A CN111860644A (en) | 2020-07-20 | 2020-07-20 | Abnormal account identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699003.4A CN111860644A (en) | 2020-07-20 | 2020-07-20 | Abnormal account identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111860644A true CN111860644A (en) | 2020-10-30 |
Family
ID=73000570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010699003.4A Pending CN111860644A (en) | 2020-07-20 | 2020-07-20 | Abnormal account identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860644A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112839027A (en) * | 2020-12-16 | 2021-05-25 | 贝壳技术有限公司 | User group identification method and device, electronic equipment and storage medium |
| CN116858854A (en) * | 2023-09-04 | 2023-10-10 | 季华实验室 | Doping concentration correction method and device, electronic equipment and storage medium |
| CN117235654A (en) * | 2023-11-15 | 2023-12-15 | 中译文娱科技(青岛)有限公司 | Artificial intelligence data intelligent processing method and system |
| CN117609974A (en) * | 2024-01-24 | 2024-02-27 | 普利泽信(滨州)科技咨询中心 | Service management system and method for technical transaction platform |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808988A (en) * | 2014-12-31 | 2016-07-27 | 阿里巴巴集团控股有限公司 | Method and device for identifying exceptional account |
| CN106339615A (en) * | 2016-08-29 | 2017-01-18 | 北京红马传媒文化发展有限公司 | Abnormal registration behavior recognition method, system and equipment |
| CN106657007A (en) * | 2016-11-18 | 2017-05-10 | 北京红马传媒文化发展有限公司 | Method for recognizing abnormal batch ticket booking behavior based on DBSCAN model |
| CN110519208A (en) * | 2018-05-22 | 2019-11-29 | 华为技术有限公司 | Method for detecting abnormality, device and computer-readable medium |
| CN110830448A (en) * | 2019-10-16 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Target event flow abnormity detection method and device, electronic equipment and medium |
| CN110995695A (en) * | 2019-11-29 | 2020-04-10 | 字节跳动有限公司 | Abnormal account detection method and device, electronic equipment and storage medium |
| WO2020073714A1 (en) * | 2018-10-12 | 2020-04-16 | 阿里巴巴集团控股有限公司 | Training sample obtaining method, account prediction method, and corresponding devices |
-
2020
- 2020-07-20 CN CN202010699003.4A patent/CN111860644A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808988A (en) * | 2014-12-31 | 2016-07-27 | 阿里巴巴集团控股有限公司 | Method and device for identifying exceptional account |
| CN106339615A (en) * | 2016-08-29 | 2017-01-18 | 北京红马传媒文化发展有限公司 | Abnormal registration behavior recognition method, system and equipment |
| CN106657007A (en) * | 2016-11-18 | 2017-05-10 | 北京红马传媒文化发展有限公司 | Method for recognizing abnormal batch ticket booking behavior based on DBSCAN model |
| CN110519208A (en) * | 2018-05-22 | 2019-11-29 | 华为技术有限公司 | Method for detecting abnormality, device and computer-readable medium |
| WO2020073714A1 (en) * | 2018-10-12 | 2020-04-16 | 阿里巴巴集团控股有限公司 | Training sample obtaining method, account prediction method, and corresponding devices |
| CN110830448A (en) * | 2019-10-16 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Target event flow abnormity detection method and device, electronic equipment and medium |
| CN110995695A (en) * | 2019-11-29 | 2020-04-10 | 字节跳动有限公司 | Abnormal account detection method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 徐金梧: "冶金生产过程质量监控理论与方法", 31 May 2015, 冶金工业出版社, pages: 137 * |
| 袁广宇: "大学物理实验 一级 第3版", 31 December 2014, 中国科学技术大学出版社, pages: 29 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112839027A (en) * | 2020-12-16 | 2021-05-25 | 贝壳技术有限公司 | User group identification method and device, electronic equipment and storage medium |
| CN116858854A (en) * | 2023-09-04 | 2023-10-10 | 季华实验室 | Doping concentration correction method and device, electronic equipment and storage medium |
| CN117235654A (en) * | 2023-11-15 | 2023-12-15 | 中译文娱科技(青岛)有限公司 | Artificial intelligence data intelligent processing method and system |
| CN117235654B (en) * | 2023-11-15 | 2024-03-22 | 中译文娱科技(青岛)有限公司 | Artificial intelligence data intelligent processing method and system |
| CN117609974A (en) * | 2024-01-24 | 2024-02-27 | 普利泽信(滨州)科技咨询中心 | Service management system and method for technical transaction platform |
| CN117609974B (en) * | 2024-01-24 | 2024-04-19 | 普利泽信(滨州)科技咨询中心 | Service management system and method for technical transaction platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860644A (en) | Abnormal account identification method, device, equipment and storage medium | |
| CN110570217B (en) | Cheating detection method and device | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| CN112507949A (en) | Target tracking method and device, road side equipment and cloud control platform | |
| CN112200167B (en) | Image recognition method, device, equipment and storage medium | |
| CN110717933B (en) | Post-processing method, device, equipment and medium for moving object missed detection | |
| CN111831512B (en) | Method and device for detecting operation and maintenance abnormality, electronic equipment and storage medium | |
| CN111724069A (en) | Method, apparatus, device and storage medium for processing data | |
| CN111241396B (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN112561053A (en) | Image processing method, training method and device of pre-training model and electronic equipment | |
| CN115688133A (en) | Data processing method, device, equipment and storage medium | |
| CN111881304B (en) | Author identification method, device, equipment and storage medium | |
| CN114781546A (en) | Method and device for determining abnormal behavior of vehicle | |
| US20230046813A1 (en) | Selecting communication schemes based on machine learning model predictions | |
| CN110995687B (en) | Cat pool equipment identification method, device, equipment and storage medium | |
| CN111460072B (en) | Lane line detection method, device, equipment and storage medium | |
| CN115222176A (en) | Risk control method, apparatus, device and medium | |
| CN112015995A (en) | Data analysis method, device, equipment and storage medium | |
| CN116431505A (en) | Regression testing method and device, electronic equipment, storage medium and product | |
| CN110889392A (en) | Method and device for processing face image | |
| CN113596011B (en) | Flow identification method and device, computing device and medium | |
| CN115333783A (en) | API call abnormity detection method, device, equipment and storage medium | |
| CN112381090A (en) | Method and device for determining telephone, electronic equipment and storage medium | |
| CN113642919A (en) | Risk control method, electronic device, and storage medium | |
| CN111177352A (en) | Complaint information processing method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |