CN115374195A - Offline wind control management method and system, storage medium and electronic equipment - Google Patents
Offline wind control management method and system, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115374195A CN115374195A CN202210877918.9A CN202210877918A CN115374195A CN 115374195 A CN115374195 A CN 115374195A CN 202210877918 A CN202210877918 A CN 202210877918A CN 115374195 A CN115374195 A CN 115374195A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- offline
- attribute data
- feature
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 39
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 96
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 abstract description 17
- 206010000117 Abnormal behaviour Diseases 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 description 13
- 230000006399 behavior Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 208000003443 Unconsciousness Diseases 0.000 description 4
- 230000003203 everyday effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 210000002268 wool Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 235000008694 Humulus lupulus Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008485 antagonism Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an off-line wind control management method, a system, a storage medium and electronic equipment, comprising the following steps: acquiring offline attribute data of a target entity, and carrying out ETL (extract transform and load) processing on the offline attribute data to obtain target attribute data; performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data; performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity; and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain and obtain the final wind control result of the target entity according to the target online portrait data of the target entity. The method adopts an off-line calculation mode to perform characteristic calculation on the mass data of the target entity, performs off-line processing on the abnormal behavior of the target entity, and combines real-time on-line data to perform wind control on the target entity with high long-period latency or disguise capability, thereby further reducing risks and reducing loss.
Description
Technical Field
The invention relates to the technical field of wind control management, in particular to an offline wind control management method, an offline wind control management system, a storage medium and electronic equipment.
Background
At present, because the business complexity and the antagonism in the wind control field, often the black grey product in society all can exist with group and high-tech form, this not only has the requirement to the real-time wind control ability of enterprise, to the black grey product that technical capability is stronger and stubborn, the wind control also is a permanent war, at this moment, long-time period's characteristic is excavated and technical wind control, can play fine recall effect, can effectively restrain the rampant of black grey product. However, due to the characteristic of real-time wind control, the processing cost and efficiency of data for a long time period are difficult to control, the living environment of the black and gray product with long-period latency or high camouflage capacity cannot be well restrained, the black and gray product cannot be effectively attacked, and loss is caused to enterprises. Therefore, it is desirable to provide the same technical solution to solve the above problems.
Disclosure of Invention
In order to solve the technical problem, the invention provides an offline wind control management method, an offline wind control management system, a storage medium and electronic equipment.
The technical scheme of the off-line wind control management method is as follows:
acquiring offline attribute data of a target entity, and carrying out ETL (extract transform and load) processing on the offline attribute data to obtain target attribute data;
performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity;
performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity;
and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain target online portrait data of the target entity, so as to obtain a final wind control result of the target entity according to the target online portrait data.
The off-line wind control management method has the following beneficial effects:
the method of the invention adopts an off-line calculation mode to carry out characteristic calculation on the mass data of the target entity, carries out off-line processing aiming at the abnormal behavior of the target entity, and combines real-time on-line data to carry out wind control on the target entity with high long-period latency or disguise capability, thereby further reducing the risk and reducing the loss. On the basis of the above scheme, the offline wind control management method of the invention can be further improved as follows.
Further, the performing ETL processing on the offline attribute data to obtain target attribute data includes:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
Further, the performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity includes:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to feature relations among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
Further, still include: and carrying out rule configuration on the feature calculation data through an offline policy platform to obtain target configuration data corresponding to the feature calculation data, and inputting the target configuration data to the preset offline rule engine.
Further, the offline attribute data includes: portrait data, business data, and device data.
The technical scheme of the off-line wind control management system is as follows:
the method comprises the following steps: the system comprises a first processing module, a second processing module, a third processing module and an operation module;
the first processing module is configured to: acquiring offline attribute data of a target entity, and carrying out ETL (extract transform and load) processing on the offline attribute data to obtain target attribute data;
the second processing module is configured to: performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity;
the third processing module is configured to: and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain the target online portrait data of the target entity, so as to obtain the final wind control result of the target entity according to the target online portrait data.
The operation module is used for: and obtaining a final wind control result of the target entity according to the offline judgment result and the current characteristic data of the target entity.
The off-line wind control management system has the following beneficial effects:
the system of the invention adopts an off-line calculation mode to carry out characteristic calculation on mass data of the target entity, carries out off-line processing on abnormal behaviors of the target entity, and combines real-time on-line data to carry out wind control on the target entity with high long-period latency or disguise capability, thereby further reducing risks and reducing loss. On the basis of the above scheme, the offline wind control management system of the invention can be further improved as follows.
Further, the first processing module is specifically configured to:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
Further, the second processing module is specifically configured to:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to the feature relationship among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
The technical scheme of the storage medium of the invention is as follows:
the storage medium stores instructions that, when read by the computer, cause the computer to perform the steps of an offline wind control management method according to the present invention.
The technical scheme of the electronic equipment is as follows:
comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, causes the computer to perform the steps of an off-line wind control management method according to the invention.
Drawings
Fig. 1 is a schematic flow chart of an offline wind control management method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an offline wind control management system according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, an offline wind control management method according to an embodiment of the present invention includes the following steps:
s1, acquiring offline attribute data of a target entity, and carrying out ETL processing on the offline attribute data to obtain target attribute data.
Wherein, the target entity is: users of either domain. The offline attribute data includes: and (3) portrait data, business data and equipment data of the user in a preset time period (such as the previous half year of the current moment). Device data includes, but is not limited to: the IP home location of the user, the account number unbinding equipment, the binding changing equipment and the like. Traffic data includes, but is not limited to: user's business registration data, login data, transaction data, etc. Portrait data includes, but is not limited to: and the occupation, the academic calendar, the gender and the like corresponding to the user account. The target attribute data is: and carrying out ETL processing on the offline attribute data to obtain data.
It should be noted that, the process of performing ETL processing on offline attribute data is prior art, and is not described herein in detail. The technical scheme of the embodiment adopts a data warehouse form to store and process the off-line data of the target entity. Specifically, portrait data, business data and equipment data of a target entity are collected, and the collected data are stored in a big data platform to form an ODS layer of a data warehouse; ETL processing is carried out on ODS layer data (offline attribute data of a target entity), and operations such as impurity removal, screening and aggregation are carried out on the offline attribute data of the target entity, so that the target attribute data of the target entity are obtained, and the availability of the data is improved; and generating the DWD layer of the data warehouse by the target attribute data after the ETL processing.
It should be noted that, according to the technical solution of this embodiment, the offline attribute data of one target entity may be collected at a time, or the offline attribute data corresponding to multiple target entities may be collected at a time, which is not limited herein.
And S2, performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
Wherein the feature types include, but are not limited to: frequency characteristics, association characteristics, risk attribute characteristics, and the like. According to different attributes of different target entities, the feature types are subdivided into: basic features (frequency features, association features), secondary features (risk attribute aggregation type features, abnormal behavior frequency features, region discrete type features, time series abnormal type features), tertiary features (mixed strong risk features, weak risk aggregation features, group features) and the like.
Specifically, data layering is performed according to the dependency relationship among each feature in the target attribute data of the target entity, a configuration file for feature calculation is written, and calculation of each feature is performed through a calculation engine Spark to obtain feature calculation data of the target entity. And performing task scheduling through an AZKABAN system, and writing the feature calculation data of the target entity into a DWS layer of the data warehouse.
It should be noted that the process of calculating each feature by using the calculation engine Spark is the prior art.
And S3, performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity.
The preset offline rule engine is a clips system (expert system clips) and is used for loading offline strategy configuration and carrying out rule judgment on data.
Specifically, the method comprises the following steps: firstly, setting an interception rule according to the actual behavior of a target entity, and importing the set interception rule into a clips system; then, taking the feature calculation data as an input source, and calling a clips system for processing; the clips system carries out rule judgment on the feature calculation data of the target entity according to the set interception rule; and for the target entities meeting the judgment conditions, judging interception by using an off-line judgment result, and otherwise, judging non-interception by using an off-line judgment result.
Specifically, a preset offline rule engine is adopted to perform data processing on feature calculation data of the target entity to obtain an offline judgment result of the target entity, and the offline judgment result is written into an ADS layer of the data warehouse.
And S4, synchronizing the offline judgment result to the original online portrait data of the target entity to obtain the target online portrait data of the target entity, so as to obtain the final wind control result of the target entity according to the target online portrait data.
Wherein, the original online portrait data is: the online image data of the offline determination result is not synchronized. The target online portrait data is: and synchronizing the online portrait data after the offline judgment result, wherein the online portrait data comprises the offline judgment result of the target entity.
Wherein, the final wind control result is as follows: and determining whether to intercept the business data of the target entity.
Specifically, the offline data and the offline judgment result of the target entity are synchronized into the original online portrait data of the target entity through a data synchronization program, when a real-time event requests an online service, the target online portrait data of the target entity is obtained, and when the online portrait data contains the offline result, the target online portrait data can be intercepted, so that the effect of online validation according to the offline data is achieved.
Preferably, the performing ETL processing on the offline attribute data to obtain target attribute data includes:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
It should be noted that the realized function of the Spark component is the prior art, and other components having the same function may also be adopted, and no limitation is set herein.
Preferably, the S2 includes:
s21, obtaining at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to feature relations among all kinds of feature types in the target attribute data.
Specifically, each feature type in the target attribute data is acquired, data layering is performed according to feature relationships (dependency relationships) among all types of feature types, and a feature calculation configuration file of the target attribute data is generated.
Wherein the relationship between different feature types is pre-constructed.
The process of generating the feature calculation configuration file of the target attribute data is realized through codes, the configuration file in a Json format is compiled, and the analysis logic is internally self-defined.
For example, the specific configuration rule is: when the duplication removing times of the ip attribution of the account in 1d are calculated, the account is used as an entity to set a function: the deduplication count distinc _ count.
The output characteristics are as follows: s _ l1_ ip _ city _ distinguint _ count _ per _ org _ token _1 d).
And S22, calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
Preferably, the method further comprises the following steps: and carrying out rule configuration on the feature calculation data through an offline policy platform to obtain target configuration data corresponding to the feature calculation data, and inputting the target configuration data to the preset offline rule engine.
The off-line strategy platform is a web platform for off-line strategy management and is mainly used for realizing functions of increasing, deleting, modifying, checking, uploading, downloading and the like of off-line strategy configuration.
According to the technical scheme, the mass data of the target entity is subjected to feature calculation in an off-line calculation mode, off-line processing is performed on abnormal behaviors of the target entity, and wind control is performed on the target entity with high long-period latency or disguise capability by combining real-time on-line data, so that risks are further reduced, and losses are reduced.
In another embodiment of the offline wind control management method of the present invention (taking number maintenance operation in a black-yielding scene as an example), the method includes the following steps:
s110, collecting offline attribute data of the number maintenance entity, and carrying out ETL processing on the offline attribute data to obtain target attribute data.
Wherein the number maintenance entity is: in a dark yield scene, the method is used for avoiding entities (users, machines, accounts and the like) pretending to be normal accounts to perform actions of singleout or wool pulling and the like for a long time when operators do marketing activities.
The offline attribute data is as follows: the device IP address, the device number, the login time period of each day, the operation behavior, the transaction behavior and the like of the number maintenance entity. The target attribute data is: and carrying out ETL processing on the offline attribute data.
And S120, performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the number maintenance entity.
Wherein the characteristic types are: frequency characteristics, association characteristics, and risk attribute characteristics. For example: the number keeping entity logs in at the same time interval every day in one month and only visits a certain activity page, does not do other behaviors and has the machine behavior of pulling wool. The frequency characteristics of the number maintenance entity are as follows: logging in at the same time period every day; the correlation characteristics are as follows: only certain active pages are accessed; risk attribute characteristics: having the behavior of a machine operation. The feature calculation data is: the data obtained by performing the feature calculation for each feature type can be calculated based on the frequency, the degree of association, and the like of the features.
S130, performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the number maintenance entity.
The method comprises the steps of presetting an interception rule in a preset offline rule engine.
S140, synchronizing the offline judgment result to the original online portrait data of the number maintenance entity to obtain target online portrait data of the number maintenance entity, so as to obtain a final wind control result of the number maintenance entity according to the target online portrait data.
Preferably, the performing ETL processing on the offline attribute data to obtain target attribute data includes:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
Preferably, the S120 includes:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to the feature relationship among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the number maintenance entity.
Preferably, the method further comprises the following steps: and carrying out rule configuration on the feature calculation data through an offline strategy platform to obtain target configuration data corresponding to the feature calculation data, and inputting the target configuration data to the preset offline rule engine.
Specifically, in this embodiment, taking number maintenance operation with a long time period, which is common in a black-out scene, as an example, such a target entity is used to avoid actions such as pretending to be a normal account, picking up a single, pulling wool, and the like when an operator makes a marketing campaign, such actions are often long in time line, large in batch, and all machine operations because they require operation with a long time period, and therefore are not suitable for online interception, in offline calculation, whether a good maintenance action exists is determined by subdividing entity data of an account corresponding to the target entity, calculating operation actions of each account entity in a long time period and every day across a long time period, for example: the number nourishing entity only logs in and prints a card at the same time period (accurate to the level of minutes or seconds, and provided with machine operation attributes) every day of a month, and does not do other actions, so that the number nourishing entity has strong risk, and is subjected to degradation processing or interception processing when participating in marketing activities of operators.
In another embodiment of the offline wind control management method of the present invention (taking the black production upstream account number Chi Cao as an example), the method includes the following steps:
s210, collecting offline attribute data of an entity used by an account pool, and carrying out ETL processing on the offline attribute data to obtain target attribute data.
The account pool using entity is as follows: and in the scenario of black products, using account pools provided upstream of other black products to perform black product behaviors. The offline attribute data is: account information, IP attribution, account unbinding and replacing binding equipment, login information and other data. The target attribute data is: and carrying out ETL processing on the offline attribute data.
S220, performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the account pool use entity.
Wherein the characteristic types are: frequency characteristics, association characteristics, risk attribute characteristics. For example: the account used by the account pool using entity is often the situation that the IP attribution of the account is continuously changed in the marketing period of the operator. The frequency characteristics of the account pool using entity are as follows: the number of changes of the IP home; the correlation characteristics are as follows: the correlation information of IP attributions of a plurality of accounts; risk attribute characteristics: risk characterization of operational behavior at non-stop hops of different IPs within a cycle.
And S230, performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the account pool use entity.
The interception rules are preset in a preset offline rule engine.
S240, synchronizing the offline judgment result to original online portrait data of the account pool using entity to obtain target online portrait data of the account pool using entity, and obtaining a final wind control result of the account pool using entity according to the target online portrait data.
Preferably, the performing ETL processing on the offline attribute data to obtain target attribute data includes:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
Preferably, the S220 includes:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to feature relations among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the account pool use entity.
Preferably, the method further comprises the following steps: and carrying out rule configuration on the feature calculation data through an offline strategy platform to obtain target configuration data corresponding to the feature calculation data, and inputting the target configuration data to the preset offline rule engine.
Specifically, in a blackout scenario, when an account pool provided by another blackout upstream is used for blackout behavior, a situation that an ip attribution of one account is constantly changed in a marketing period of an operator often exists, so that characteristics are calculated for a situation that each account entity is stable in a long period but continuously jumps during the marketing period, and such an entity has a strong risk, and when the entity participates in a marketing activity of the operator, degradation processing or interception processing is performed on an account pool using entity.
As shown in fig. 2, an offline wind control management system 200 according to an embodiment of the present invention includes: a first processing module 210 and a second processing module 220, a third processing module 230, and an execution module 240;
the first processing module 210 is configured to: the method comprises the steps of collecting off-line attribute data of a target entity, and carrying out ETL processing on the off-line attribute data to obtain target attribute data.
The second processing module 220 is configured to: and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
The third processing module 230 is configured to: and performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity.
The operation module 240 is configured to: and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain target online portrait data of the target entity, so as to obtain a final wind control result of the target entity according to the target online portrait data.
Preferably, the first processing module 210 is specifically configured to:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
Preferably, the second processing module 220 is specifically configured to:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to the feature relationship among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
According to the technical scheme, the mass data of the target entity is subjected to feature calculation in an off-line calculation mode, off-line processing is performed on abnormal behaviors of the target entity, and wind control can be well performed on the target entity with long-period latency or high disguise capability by combining real-time on-line data, so that risks are further reduced, and losses are reduced.
The above steps for realizing the corresponding functions of each parameter and each module in the offline wind control management system 200 of this embodiment may refer to each parameter and step in the above embodiment of the offline wind control management method, which are not described herein again.
An embodiment of the present invention provides a storage medium, including: the storage medium stores instructions, and when the computer reads the instructions, the computer is caused to execute the steps of the offline wind control management method, which may specifically refer to the parameters and the steps in the above embodiment of the offline wind control management method, and details are not described here.
Computer storage media such as: flash disks, portable hard disks, and the like.
An electronic device provided in an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and is characterized in that when the processor executes the computer program, the computer executes steps of an offline wind control management method, which may specifically refer to each parameter and step in the above embodiment of an offline wind control management method, and are not described herein again.
Those skilled in the art will appreciate that the present invention may be embodied as methods, systems, storage media and electronic devices.
Thus, the present invention may be embodied in the form of: may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software, and may be referred to herein generally as a "circuit," module "or" system. Furthermore, in some embodiments, the invention may also be embodied in the form of a computer program product in one or more computer-readable media having computer-readable program code embodied in the medium. Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An off-line wind control management method is characterized by comprising the following steps:
acquiring off-line attribute data of a target entity, and carrying out ETL (extract transform and load) processing on the off-line attribute data to obtain target attribute data;
performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity;
performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity;
and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain target online portrait data of the target entity, so as to obtain a final wind control result of the target entity according to the target online portrait data.
2. The offline wind control management method according to claim 1, wherein the performing ETL processing on the offline attribute data to obtain target attribute data comprises:
and carrying out ETL processing on the offline attribute data by using a Spark component to obtain the target attribute data.
3. The offline wind control management method according to claim 2, wherein the performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity includes:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to the feature relationship among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
4. The offline wind control management method according to claim 1, further comprising: and carrying out rule configuration on the feature calculation data through an offline policy platform to obtain target configuration data corresponding to the feature calculation data, and inputting the target configuration data to the preset offline rule engine.
5. The offline wind control management method according to any one of claims 1 to 4, wherein the offline attribute data comprises: portrait data, business data, and device data.
6. An offline wind management system, comprising: the system comprises a first processing module, a second processing module, a third processing module and an operation module;
the first processing module is configured to: acquiring offline attribute data of a target entity, and carrying out ETL (extract transform and load) processing on the offline attribute data to obtain target attribute data;
the second processing module is configured to: performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity;
the third processing module is configured to: performing data processing on the feature calculation data by adopting a preset offline rule engine to obtain an offline judgment result of the target entity;
the operation module is used for: and synchronizing the offline judgment result to the original online portrait data of the target entity to obtain the target online portrait data of the target entity, so as to obtain the final wind control result of the target entity according to the target online portrait data.
7. The offline wind control management system according to claim 6, wherein the first processing module is specifically configured to:
and carrying out ETL processing on the offline attribute data by utilizing a Spark component to obtain the target attribute data.
8. The offline wind control management system according to claim 7, wherein the second processing module is specifically configured to:
acquiring at least one feature type in the target attribute data, and generating a feature calculation configuration file of the target attribute data according to the feature relationship among all kinds of feature types in the target attribute data;
and calling the feature calculation configuration file by using the Spark component, and performing feature calculation on at least one feature type in the target attribute data to obtain feature calculation data of the target entity.
9. A storage medium having stored therein instructions which, when read by a computer, cause the computer to execute an offline wind management method according to any one of claims 1 to 5.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, causes the computer to perform an offline wind management method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210877918.9A CN115374195A (en) | 2022-07-25 | 2022-07-25 | Offline wind control management method and system, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210877918.9A CN115374195A (en) | 2022-07-25 | 2022-07-25 | Offline wind control management method and system, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115374195A true CN115374195A (en) | 2022-11-22 |
Family
ID=84063103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210877918.9A Pending CN115374195A (en) | 2022-07-25 | 2022-07-25 | Offline wind control management method and system, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115374195A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160292599A1 (en) * | 2015-04-06 | 2016-10-06 | Fmr Llc | Analyzing and remediating operational risks in production computing systems |
| CN108540431A (en) * | 2017-03-03 | 2018-09-14 | 阿里巴巴集团控股有限公司 | The recognition methods of account type, device and system |
| CN109858919A (en) * | 2017-11-27 | 2019-06-07 | 阿里巴巴集团控股有限公司 | Determination method and device, online ordering method and the device of abnormal account |
| CN110298601A (en) * | 2019-07-05 | 2019-10-01 | 上海观安信息技术股份有限公司 | A kind of real time business air control system of rule-based engine |
| CN110543506A (en) * | 2019-09-10 | 2019-12-06 | 百度在线网络技术（北京）有限公司 | Data analysis method and device, electronic equipment and storage medium |
| CN111414291A (en) * | 2019-01-07 | 2020-07-14 | 北京智融网络科技有限公司 | Method and system for monitoring completeness of wind control system |
-
2022
- 2022-07-25 CN CN202210877918.9A patent/CN115374195A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160292599A1 (en) * | 2015-04-06 | 2016-10-06 | Fmr Llc | Analyzing and remediating operational risks in production computing systems |
| CN108540431A (en) * | 2017-03-03 | 2018-09-14 | 阿里巴巴集团控股有限公司 | The recognition methods of account type, device and system |
| CN109858919A (en) * | 2017-11-27 | 2019-06-07 | 阿里巴巴集团控股有限公司 | Determination method and device, online ordering method and the device of abnormal account |
| CN111414291A (en) * | 2019-01-07 | 2020-07-14 | 北京智融网络科技有限公司 | Method and system for monitoring completeness of wind control system |
| CN110298601A (en) * | 2019-07-05 | 2019-10-01 | 上海观安信息技术股份有限公司 | A kind of real time business air control system of rule-based engine |
| CN110543506A (en) * | 2019-09-10 | 2019-12-06 | 百度在线网络技术（北京）有限公司 | Data analysis method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 丁世博: "基于SOA的安全风控平台研究与设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 百胜智库: "《企业中台实践指南》", 中国经济出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6878450B2 (en) | Methods and devices to prevent advertising fraud and storage media | |
| CN103023983B (en) | For the system of the process of distributed computer safe task | |
| CN110521177A (en) | Collection is captured indicator and is detected for security threat | |
| CN103593376A (en) | Method and device for collecting user behavior data | |
| CN110457223B (en) | Gray test drainage method, device, proxy server and readable storage medium | |
| CN111818066B (en) | Risk detection method and device | |
| CN107241380A (en) | For the method and apparatus of the load balancing adjusted based on the time | |
| Killer et al. | Security management and visualization in a blockchain-based collaborative defense | |
| CN105512910A (en) | Target user screening method and apparatus | |
| CN112738172A (en) | Block chain node management method and device, computer equipment and storage medium | |
| CN115374195A (en) | Offline wind control management method and system, storage medium and electronic equipment | |
| CN112651039A (en) | Electric power data differentiation desensitization method and device fusing service scenes | |
| CN115309735A (en) | Big data cleaning method and device, computer equipment and storage medium | |
| WO2012053041A1 (en) | Security monitoring device, security monitoring method and security monitoring program based on security policy | |
| CN113472825B (en) | NB-IoT terminal transaction processing method and device based on block chain | |
| CN109636389B (en) | Method, device, equipment and storage medium for determining block chaining-out time | |
| CN113343577B (en) | Parameter optimization method, device, equipment and medium based on machine learning | |
| CN108351940B (en) | System and method for high frequency heuristic data acquisition and analysis of information security events | |
| CN106846142B (en) | Information processing method and server | |
| CN112992352A (en) | Staff health early warning method, device and medium | |
| CN112685769A (en) | Data processing method and device of block chain and electronic equipment | |
| CN113905092A (en) | Method, device, terminal and storage medium for determining reusable agent queue | |
| CN112434894A (en) | Real-time risk control method, computer equipment and readable storage medium | |
| CN108268662A (en) | Social graph generation method, electronic device and storage medium based on the H5 pages | |
| CN116132528B (en) | Flight management message pushing method and device and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221122 |