CN107273411A - Business operation and the correlating method and equipment of database manipulation data - Google Patents
Business operation and the correlating method and equipment of database manipulation data Download PDFInfo
- Publication number
- CN107273411A CN107273411A CN201710305780.4A CN201710305780A CN107273411A CN 107273411 A CN107273411 A CN 107273411A CN 201710305780 A CN201710305780 A CN 201710305780A CN 107273411 A CN107273411 A CN 107273411A
- Authority
- CN
- China
- Prior art keywords
- candidate association
- association group
- business operation
- score
- database manipulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- 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
- G06F16/23—Updating
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
It is an object of the invention to provide a kind of business operation and the correlating method and equipment of database manipulation data, the application uses a kind of machine learning method, the business operation and database peration data of user is obtained under customer service application environment, real-time learning and analysis, arrange practical business operation and database manipulation data, automatically generate business operation and database manipulation data mapping ruler screen after associated group, then continuously learn and analyze in operation system running, the corresponding relation of business operation and database manipulation data can be automatically identified, it is the associated group after screening that dynamic, which updates mapping ruler,.The application is applied to the audit work of most of multilayer operation systems, can effectively recognize the incidence relation between operation and database manipulation data, and then with the incidence relation come audit operations.
Description
Technical field
The present invention relates to computer realm, more particularly to a kind of business operation and database manipulation data correlating method and
Equipment.
Background technology
As computer system application is more and more extensive, application scenarios that a large number of services system is separated with database make
With so that Data Audit is increasingly complicated.
Existing Data Audit mechanism, is generally divided into immediate operand evidence and by operation system peration data.For straight
Connect the technology that peration data audited relatively simple, primarily directed between user and used data processing chain one by one
Corresponding relation is handled；And, database then more complicated for the audit technique that operating database is carried out by operation system
Operation is isolated by operation system, and the mapping relations carried out between user's operation and database manipulation become more to feel sleepy
Difficulty, major embodiment is in the following areas：
1st, business operation and database manipulation data bulk are huge, strategy are added by the method for manual intervention, to personnel
Technical requirements are higher, and waste time and energy；
2nd, the associating policy manually formulated is more inflexible, and operation system application environment is changeable, it is difficult to makes and targetedly closing
Connection strategy, policy monitor dynamics is difficult to control；
3rd, the pure associating policy manually added, associating policy amount is big and it cannot be guaranteed that quality, when the later stage needs a large amount of artificial
Between go to safeguard so as to causing to implement relatively difficult.
The content of the invention
It is an object of the present invention to provide a kind of business operation and the correlating method and equipment of database manipulation data, energy
Enough solve existing business operation time-consuming with database manipulation data correlation, laborious and associate low-quality problem.
According to an aspect of the invention, there is provided a kind of business operation and the correlating method of database manipulation data, should
Method includes：
The business operation and database peration data of user is obtained, by the business operation and corresponding database manipulation number
According to formation candidate association group；
The occurrence number of the candidate association group is obtained, calculating the candidate according to the occurrence number of the candidate association group closes
The final confidence of joint group；
It regard candidate association group of the final confidence in preset threshold range as the associated group after screening.
Further, in the above method, the business operation and database peration data of user is obtained, by the business operation
Candidate association group is formed with corresponding database manipulation data, including：
Receive the business operation and its beginning and ending time information of user and write business information base, receive database manipulation data
And its beginning and ending time information and write data message storehouse；
The beginning and ending time information of each business operation in business information base, is intercepted in the data message storehouse
The database manipulation data of correspondence beginning and ending time information, by the business operation being truncated to and corresponding database manipulation data
Form candidate association group.
Further, in the above method, the occurrence number of the candidate association group is obtained, including：
During the one or many same candidate association groups occurred each time in business operation, by going out for the candidate association group
The increase of occurrence number is once.
Further, in the above method, the occurrence number of the candidate association group is obtained, according to the candidate association group
Occurrence number calculates the confidence level of the candidate association group, including：
Obtain the occurrence number of the candidate association group；
When the occurrence number of the candidate association group reaches preset upper limit value, by the occurrence number of the candidate association group
It is multiplied by fixed coefficient linearly to be reduced, the occurrence number formed after the reduction of the candidate association group；
The final confidence of the candidate association group is calculated according to the occurrence number after the reduction of the candidate association group.
Further, in the above method, the candidate is calculated according to the occurrence number after the reduction of the candidate association group and closed
The final confidence of joint group, including：
According to the occurrence number after the reduction of the candidate association group and default matching threshold benchmark, the candidate is obtained
Associated group be less than threshold values hits；
According to the occurrence number after the reduction of the candidate association group and less than threshold values hits, the candidate association is obtained
That organizes is higher than threshold values hits；
Threshold values hits and the default score upper limit are less than according to the candidate association group, the candidate association group is calculated
Basic confidence level；
Judge whether described be 0 higher than threshold values hits,
If described is 0 higher than threshold values hits, the basic confidence level of the candidate association group is regard as the candidate association group
Final confidence.
Further, in the above method, the threshold values hits (LOWER_MATCH_NUM) that are less than are according to equation below meter
Calculate：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matchings of MATCHES_THR
Threshold reference.
Further, in the above method, the candidate association group be higher than threshold values hits (UPPER_MATCH_NUM) root
Calculated according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).
Further, in the above method, the basic confidence level (RELIABILITY) calculates according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.
Further, in the above method, judge it is described higher than threshold values hits whether be after 0, in addition to：
If described is not 0 higher than threshold values hits, according to the default score upper limit, the default matching threshold benchmark,
Obtain the high threshold values hit ratio of the candidate association group；
After according to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than threshold values hits and reduction
Occurrence number, calculate the final confidence of the candidate association group.
Further, in the above method, the high threshold values hit ratio (UPPER_SCORE) of the candidate association group is according to such as
Lower formula is calculated:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).
Further, in the above method, final confidence (FINAL-RELIABILITY) basis of the candidate association group
Equation below is calculated：
FINALR-ELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X))。
According to another aspect of the present invention, the associate device of a kind of business operation and database manipulation data is additionally provided,
The equipment includes：
First associated apparatus, business operation and database peration data for obtaining user, by the business operation and
Corresponding database manipulation data formation candidate association group；
Computing device, the occurrence number for obtaining the candidate association group, occurrence is gone out according to the candidate association group
Number calculates the final confidence of the candidate association group；
Second associated apparatus, for regarding candidate association group of the final confidence in preset threshold range as screening
Associated group afterwards.
Further, in the said equipment, first associated apparatus, during business operation and its start-stop for receiving user
Between information and write business information base, receive database manipulation data and its beginning and ending time information and write data message storehouse；Root
According to the beginning and ending time information of each business operation in business information base, when correspondence start-stop is intercepted in the data message storehouse
Between information database manipulation data, by the business operation being truncated to and corresponding database manipulation data formation candidate close
Joint group.
Further, in the said equipment, the computing device is one or many for what is occurred in business operation each time
During same candidate association group, by the occurrence number increase of the candidate association group once.
Further, in the said equipment, the computing device, the occurrence number for obtaining the candidate association group；When
When the occurrence number of the candidate association group reaches preset upper limit value, the occurrence number of the candidate association group is multiplied by fixed system
Number is linearly reduced, the occurrence number formed after the reduction of the candidate association group；According to the reduction of the candidate association group
Occurrence number afterwards calculates the final confidence of the candidate association group.
Further, in the said equipment, the computing device, for the appearance after the reduction according to the candidate association group
Number of times and default matching threshold benchmark, obtain the candidate association group is less than threshold values hits；According to the candidate association
Occurrence number after the reduction of group and less than threshold values hits, obtain the candidate association group is higher than threshold values hits；According to
The candidate association group is less than threshold values hits and the default score upper limit, calculates the basic credible of the candidate association group
Degree；Judge whether described be 0 higher than threshold values hits, if described is 0 higher than threshold values hits, by the base of the candidate association group
Plinth confidence level as the candidate association group final confidence.
Further, in the said equipment, the threshold values hits (LOWER_MATCH_NUM) that are less than are according to equation below meter
Calculate：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matchings of MATCHES_THR
Threshold reference.
Further, in the said equipment, the candidate association group be higher than threshold values hits (UPPER_MATCH_NUM) root
Calculated according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).
Further, in the said equipment, the basic confidence level (RELIABILITY) calculates according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.
Further, in the said equipment, the computing device, be additionally operable to judge it is described higher than threshold values hits whether be
After 0, if described is not 0 higher than threshold values hits, according to the default score upper limit, the default matching threshold benchmark, obtain
High threshold values to the candidate association group hits ratio；
After according to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than threshold values hits and reduction
Occurrence number, calculate the final confidence of the candidate association group.
Further, in the said equipment, the high threshold values hit ratio (UPPER_SCORE) of the candidate association group is according to such as
Lower formula is calculated:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).
Further, in the said equipment, final confidence (FINAL-RELIABILITY) basis of the candidate association group
Equation below is calculated：
FINALR-ELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X))。
According to the another side of the application, a kind of equipment based on calculating is also provided, wherein, including：
Processor；And
It is arranged to store the memory of computer executable instructions, the executable instruction makes the place when executed
Manage device：
The business operation and database peration data of user is obtained, by the business operation and corresponding database manipulation number
According to formation candidate association group；
The occurrence number of the candidate association group is obtained, calculating the candidate according to the occurrence number of the candidate association group closes
The final confidence of joint group；
It regard candidate association group of the final confidence in preset threshold range as the associated group after screening.
Compared with prior art, the application uses a kind of machine learning method, obtains and uses under customer service application environment
The business operation and database peration data at family, real-time learning and analysis, arrange practical business operation and database manipulation data,
Automatically generate business operation and database manipulation data mapping ruler screen after associated group, then in operation system operation
During continuously learn and analyze, the corresponding relation of business operation and database manipulation data can be automatically identified,
It is the associated group after screening that dynamic, which updates mapping ruler,.The application is applied to the audit work of most of multilayer operation systems, energy
Incidence relation effectively between identification operation and database manipulation data, and then with the incidence relation come audit operations.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 shows machine learning marking figure according to an embodiment of the invention；
Fig. 2 shows the operational flowchart of one embodiment of the invention.
Same or analogous reference represents same or analogous part in accompanying drawing.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
In one typical configuration of the application, terminal, the equipment of service network and trusted party include one or more
Processor (CPU), input/output interface, network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, magnetic disk storage or other magnetic storage apparatus or
Any other non-transmission medium, the information that can be accessed by a computing device available for storage.Defined according to herein, computer
Computer-readable recording medium does not include the data-signal and carrier wave of non-temporary computer readable media (transitory media), such as modulation.
The application provides a kind of business operation and the correlating method of database manipulation data, including：
Step S1, obtains the business operation and database peration data of user, by the business operation and corresponding data
Storehouse peration data formation candidate association group；
Step S2, obtains the occurrence number of the candidate association group, is calculated according to the occurrence number of the candidate association group
The final confidence of the candidate association group；
Step S3, regard candidate association group of the final confidence in preset threshold range as the association after screening
Group.Here, the final confidence can calculate what is obtained according to according to the occurrence number of the candidate association group, it can be specific
It is a score value between 0.0-1.0.Whether confidence level score value can be used for behind determination carrying out using the mapping relations data
Audit and reference.If confidence level score value is within adjustable setting value, the mapping relations are preserved into rule model storehouse, it is no
Then abandon the relation.As shown in figure 1, final confidence is higher, final score is higher, according to the regular mould of final score real-time update
Type storehouse.
Specifically, for example：
1) user for assuming operation system is USER={ U1, U2 }；
2) assume operation system be BUSI_SYSTEM={ OS1, OS2 }, operation system mainly for the treatment of user input or
Business datum logic of the person from from Service Database, business operation action is come from user (USER), business action
Specific implementation is that in operation system (BUSI_SYSTEM), it is not that business operation, which initiates to implement the two processes with business operation,
It is visible, but the mode linked up between the two systems is usually network etc., between operation system user and operation system
The process of communication be the business operation in the model environment that builds, this system is all for user, and explanation is only to build here
Suitable environment；
3) Service Database is assumed for DATA_SYSTEM={ DS1, DS2 }, and that mainly stored in Service Database is user
Business datum be database manipulation data, database manipulation is initiated in operation system (BUSI_SYSTEM), and database is specific
Realization is that database manipulation initiation implements the two processes with database is in Service Database (DATA_SYSTEM)
It is sightless, but the mode linked up between the two systems is usually network etc., between operation system and Service Database
The process of communication is the data manipulation in the model environment that builds, and this Service Database is all for user, illustrate here be only
Build suitable environment；
4) it is RULES_MODEL_LIB={ RM1, RM2 } to assume rule model storehouse.Rule model storehouse, the inside includes built-in
Business operation and database manipulation data between rule be default associated group, it is also long-term using the method for the present embodiment
Rule between the business operation and database manipulation data that learn screen after associated group, this system be database audit
It is all, non-user environment.
4 points of the above may have following relation, and RM1 belongs to OS1, and RM2 belongs to OS2, and OS1 Service Database is DS1,
OS2 Service Database is DS2, and U1 can use OS1 or OS2, U2 to use OS1 or OS2.The shellring border built above
Only it is most basic multilayer correlation model suitable environment, rather than is suitable only for the environment, machine learning method of the invention is same
Sample is applied to complicated multilayer service environment.
The application uses a kind of machine learning method, and the business operation sum of user is obtained under customer service application environment
According to storehouse peration data, real-time learning and analysis arrange practical business operation and database manipulation data, automatically generate business operation
Mapping ruler with database manipulation data is the associated group after screening, then in operation system running continuously
Study and analysis, can automatically identify the corresponding relation of business operation and database manipulation data, and dynamic updates mapping ruler
Associated group after screening.The application is applied to the audit work of most of multilayer operation systems, can effectively recognize operation and number
According to the incidence relation between the peration data of storehouse, and then with the incidence relation come audit operations.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, step S1 obtains user
Business operation and database peration data, by the business operation and corresponding database manipulation data formation candidate association
Group, including：
Receive the business operation and its beginning and ending time information of user and write business information base (RAW_BIZ), receive data
Storehouse peration data and its beginning and ending time information simultaneously write data message storehouse (RAW_DATA)；
The beginning and ending time information of each business operation in business information base, is intercepted in the data message storehouse
The database manipulation data of correspondence beginning and ending time information, by the business operation being truncated to and corresponding database manipulation data
Candidate association group is formed, so as to accurately acquire candidate association group.
The business operation of the application is with the embodiment of correlating method one of database manipulation data, in step S2, obtaining
The occurrence number of the candidate association group, including：
During the one or many same candidate association groups occurred each time in business operation, by going out for the candidate association group
The increase of occurrence number once, so as to realize the accurate statistics of the occurrence number of candidate association group.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, step S2 obtains described
The occurrence number of candidate association group, the confidence level of the candidate association group is calculated according to the occurrence number of the candidate association group, bag
Include：
Obtain the occurrence number of the candidate association group；
When the occurrence number of the candidate association group reaches preset upper limit value, by the occurrence number of the candidate association group
It is multiplied by fixed coefficient linearly to be reduced, the occurrence number formed after the reduction of the candidate association group；Such as one integer
1000, want to allow the number to reduce, a decimal only need to be multiplied by the number, you can reduced, such as：1000*0.5=500；
The final confidence of the candidate association group is calculated according to the occurrence number after the reduction of the candidate association group.
This, when the occurrence number of the candidate association group reaches preset upper limit value, the occurrence number of the candidate association group is multiplied by
Fixed coefficient is linearly reduced, and is easy to subsequently calculate final confidence
In the business operation of the application and the embodiment of correlating method one of database manipulation data, according to the candidate association
Occurrence number after the reduction of group calculates the final confidence of the candidate association group, including：
According to the occurrence number after the reduction of the candidate association group and default matching threshold benchmark, the candidate is obtained
Associated group be less than threshold values hits；
According to the occurrence number after the reduction of the candidate association group and less than threshold values hits, the candidate association is obtained
That organizes is higher than threshold values hits；
Threshold values hits and the default score upper limit are less than according to the candidate association group, the candidate association group is calculated
Basic confidence level；
Judge whether described be 0 higher than threshold values hits,
If described is 0 higher than threshold values hits, the basic confidence level of the candidate association group is regard as the candidate association group
Final confidence.Here, if the hits higher than threshold values are equal to 0, basic confidence level now is final confidence.This reality
Apply example it is described higher than threshold values hits be 0 when, final confidence can be accurately obtained.
The business operation of the application is with the embodiment of correlating method one of database manipulation data, judging described higher than threshold values
Hits whether be after 0, in addition to：
If described is not 0 higher than threshold values hits, according to the default score upper limit, the default matching threshold benchmark
MATCH_THR, obtains the high threshold values hit ratio of the candidate association group；
After according to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than threshold values hits and reduction
Occurrence number, calculate the final confidence of the candidate association group.Here, if the hits higher than threshold values are not equal to 0, this
When final confidence be FINALRELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X)),
That is, low score value is calculated, if there is high point of matching, in addition it is also necessary to calculate high score value, the two values it
Be only final confidence.The present embodiment it is described higher than threshold values hits be 0 when, final confidence can be accurately obtained.
It is described less than threshold values hit in the business operation of the application and the embodiment of correlating method one of database manipulation data
Number LOWER_MATCH_NUM is calculated according to equation below：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matchings of MATCHES_THR
Threshold reference.Here, matching threshold benchmark (MATCH_THR), for determining matching numerical digit high threshold or Low threshold.LOWER_
MATCH_NUM, the i.e. matching number less than MATCH_THR.Such as school grade is taken to illustrate：The station left side higher than 60 points, is less than
On the right of 60 points of station, it is the coupling number higher than threshold value to stand on the left side, and what is stood at the right is the coupling number less than threshold value, and 60 points just
It is threshold value, is just above threshold value higher than 60 points, threshold value is just less than less than 60 points.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, the candidate association group
Calculated higher than threshold values hits UPPER_MATCH_NUM according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).In this UPPER_MATCH_NUM, that is, it is higher than
LOWER_MATCH_NUM matching number.Here, being higher than the number of threshold value higher than threshold values hits.Or lifted by school grade
Example：One has 60 people, and that fails has 10 people, and what that was passed just has 60-10=50 people.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, the basic confidence level
RELIABILITY is calculated according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.Here, TOP_SCORE, i.e. the score upper limit, for each
Model is that candidate association group carries out the reference upper level that marking is used.Here, RELIABILITY, for according to data above
Progress handles some the obtained model i.e. score value of the confidence level of some candidate association group.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, the candidate association group
High threshold values hit ratio UPPER_SCORE is calculated according to equation below:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).Here,
UPPER_SCORE is a ratio of the scores, i.e., using TOP_SCORE as standard, the ratio drawn.Calculate UPPER_SCORE
It is a safeguard measure, because some business only occur one for one day twice in database audit, some business occur for one day
It is tens of thousands of this, calculate UPPER_SCORE values be in order to avoid low traffic is submerged, it is to avoid heavy traffic is too high not to be limited.
In the business operation of the application and the embodiment of correlating method one of database manipulation data, the candidate association group
Final confidence FINAL-RELIABILITY is calculated according to equation below：
FINALR-ELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X))。
Detailed, it is assumed that user's mode of operation is USER<->BUSI_SYSTEM<->DATA_SYSTEM simple three number of plies
According to stream process flow；
A kind of self study based on machine that the application is learnt with analyzing primarily directed to customer service scene is associated
Model, model substantially handling process is as follows：Initial stage pre-processes to user data, and storage to RAW_BIZ (is RULES_
A RM part in MODEL_LIB, the business operation information for storing scoring model needs) and RAW_DATA (for RULES_
A RM part in MODEL_LIB, the database manipulation data message for storing scoring model needs) in, then according to industry
The time scale of business operation finds out correspondence database peration data, and it is candidate association group, Ran Houjiao to form corresponding mapping ruler
The original rule model storehouse RULES_MODEL_ of operation system OSX are updated after study is handled with analysis module, handled
LIB。
As shown in Fig. 2 operating process is as follows：
1) when initializing rule model, a total correlation model can be created, is in a model each operation system
Stored in the one relationship maps rule list of establishment of OSX (i.e. one in BUSI_SYSTEM), table each business operation with it is corresponding
Database manipulation data mapping relations be candidate association group and and each candidate association group occurrence number, here, the mapping
Relation refers to the corresponding relation between BUSI_SYSTEM and DATA_SYSTEM.
2) then, user uses operation system according to normal operational procedure and daily use habit.
3) at the same time, data processing module receives the business operation and its beginning and ending time information of user, and receives data
Storehouse peration data and its beginning and ending time information, and the business operation of user and its beginning and ending time information are write into such as business information base
(RAW_BIZ), by database manipulation data and its write-in of beginning and ending time information such as data message storehouse (RAW_DATA), according to business
The beginning and ending time information of each business operation in information bank (RAW_BIZ), in the data message storehouse (RAW_DATA)
The database manipulation data of interception correspondence beginning and ending time information, so as to form corresponding associated group.
4) next, the counting how many times SCORE_X (associated group counts) occurred according to associated group, occurs increasing every time
Plus once, be only designated as once with repeating groups in a business operation and (carry out repeatedly same operation in same business to be designated as once),
When highest, which is counted, reaches the upper limit (being a customized higher limit), each associated group and business are counted in itself and are multiplied by fixation
Coefficient is linearly reduced, and forms newest SCORE_X.
5) study and analytic function are finally entered, study passes through the number of times SCORE_X that occurs to associated group with analysis module
Handled, obtain being less than threshold values hits LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR)；Higher than threshold values
Hits UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM), and the high threshold values of setting hit ratio
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE),
Then basis confidence level RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_ are calculated
SCORE),
If the hits higher than threshold values are equal to 0, basic confidence level now is final confidence, conversely,
FINALRELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X))
6) machine learning is run always along with audit, is updated related correlation rule module and is constantly updated after OSX screening
Associated group, the moment audited with the associated group after newest screening to user environment, i.e. the mapping for each matching
Relation is stored into rule model storehouse, is used for study reference next time.
According to another aspect of the present invention, the associate device of a kind of business operation and database manipulation data is additionally provided,
The equipment includes：
First associated apparatus, business operation and database peration data for obtaining user, by the business operation and
Corresponding database manipulation data formation candidate association group；
Computing device, the occurrence number for obtaining the candidate association group, occurrence is gone out according to the candidate association group
Number calculates the final confidence of the candidate association group；
Second associated apparatus, for regarding candidate association group of the final confidence in preset threshold range as screening
Associated group afterwards.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the first association dress
Put, for receiving the business operation and its beginning and ending time information of user and writing business information base, receive database manipulation data
And its beginning and ending time information and write data message storehouse；The beginning and ending time letter of each business operation in business information base
Breath, intercepts the database manipulation data of correspondence beginning and ending time information, by the business being truncated in the data message storehouse
Operation and corresponding database manipulation data formation candidate association group.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the computing device is used
When the one or many same candidate association groups occurred in business operation each time, by the occurrence number of the candidate association group
Increase is once.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the computing device is used
In the occurrence number for obtaining the candidate association group；, will when the occurrence number of the candidate association group reaches preset upper limit value
The occurrence number of the candidate association group is multiplied by fixed coefficient and linearly reduced, after the reduction for forming the candidate association group
Occurrence number；The final confidence of the candidate association group is calculated according to the occurrence number after the reduction of the candidate association group.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the computing device is used
In the occurrence number after the reduction according to the candidate association group and default matching threshold benchmark, the candidate association group is obtained
Be less than threshold values hits；According to the occurrence number after the reduction of the candidate association group and less than threshold values hits, institute is obtained
That states candidate association group is higher than threshold values hits；According to the candidate association group less than on threshold values hits and default score
Limit, calculates the basic confidence level of the candidate association group；Judge whether described be 0 higher than threshold values hits, if described be higher than valve
Be worth hits be 0, using the basic confidence level of the candidate association group as the candidate association group final confidence.
It is described less than threshold values hit in the business operation of the application and the embodiment of associate device one of database manipulation data
Number (LOWER_MATCH_NUM) is calculated according to equation below：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matchings of MATCHES_THR
Threshold reference.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the candidate association group
Calculated higher than threshold values hits (UPPER_MATCH_NUM) according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).
In the business operation of the application and the embodiment of associate device one of database manipulation data, the basic confidence level
(RELIABILITY) calculated according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the computing device, also
For whether being after 0, if described is not 0 higher than threshold values hits, according to default judging described higher than threshold values hits
The score upper limit, the default matching threshold benchmark, obtain the high threshold values hit ratio of the candidate association group；
According to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than threshold values hit
Occurrence number after number and reduction, calculates the final confidence of the candidate association group.
In the business operation of the application and the embodiment of associate device one of database manipulation data, the candidate association group
High threshold values hit ratio (UPPER_SCORE) calculates according to equation below:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).
In the business operation of the application and the embodiment of associate device one of database manipulation data, the candidate association group
Final confidence (FINAL-RELIABILITY) is calculated according to equation below：
FINALR-ELIABILITY=(RELIABILITY+
(UP_SCORE*UPPER_MATCH_NUM/SCORE_X))。
According to the another side of the application, a kind of equipment based on calculating is also provided, wherein, including：
Processor；And
It is arranged to store the memory of computer executable instructions, the executable instruction makes the place when executed
Manage device：
The business operation and database peration data of user is obtained, by the business operation and corresponding database manipulation number
According to formation candidate association group；
The occurrence number of the candidate association group is obtained, calculating the candidate according to the occurrence number of the candidate association group closes
The final confidence of joint group；
It regard candidate association group of the final confidence in preset threshold range as the associated group after screening.
The particular content of the said equipment section Example can be found in the corresponding content of method section Example, specifically no longer go to live in the household of one's in-laws on getting married
State.
In summary, the application uses a kind of machine learning method, and the industry of user is obtained under customer service application environment
Business operation and database peration data, real-time learning and analysis, arrange practical business operation and database manipulation data, automatic raw
Mapping ruler into business operation and database manipulation data is associated group after screening, then in operation system running
Continuously learn and analyze, the corresponding relation of business operation and database manipulation data can be automatically identified, dynamic is more
Associated group after new mappings rule i.e. screening.The application is applied to the audit work of most of multilayer operation systems, can effectively know
Incidence relation that Cao Zuo be between database manipulation data, and then with the incidence relation come audit operations.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the application to the application
God and scope.So, if these modifications and variations of the application belong to the scope of the application claim and its equivalent technologies
Within, then the application is also intended to comprising including these changes and modification.
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, can adopt
Realized with application specific integrated circuit (ASIC), general purpose computer or any other similar hardware device.In one embodiment
In, software program of the invention can realize steps described above or function by computing device.Similarly, it is of the invention
Software program (including related data structure) can be stored in computer readable recording medium storing program for performing, for example, RAM memory,
Magnetically or optically driver or floppy disc and similar devices.In addition, some steps or function of the present invention can employ hardware to realize, example
Such as, as coordinating with processor so as to performing the circuit of each step or function.
In addition, the part of the present invention can be applied to computer program product, such as computer program instructions, when its quilt
When computer is performed, by the operation of the computer, the method according to the invention and/or technical scheme can be called or provided.
And the programmed instruction of the method for the present invention is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal bearing medias and be transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, including a device according to one embodiment of present invention, the device includes using
In the memory and processor for execute program instructions of storage computer program instructions, wherein, when the computer program refers to
When order is by the computing device, method and/or skill of the plant running based on foregoing multiple embodiments according to the present invention are triggered
Art scheme.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.This
Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in device claim is multiple
Unit or device can also be realized by a unit or device by software or hardware.The first, the second grade word is used for table
Show title, and be not offered as any specific order.
Claims (23)
1. a kind of business operation and the correlating method of database manipulation data, wherein, this method includes：
The business operation and database peration data of user is obtained, by the business operation and corresponding database manipulation data shape
Into candidate association group；
The occurrence number of the candidate association group is obtained, the candidate association group is calculated according to the occurrence number of the candidate association group
Final confidence；
It regard candidate association group of the final confidence in preset threshold range as the associated group after screening.
2. business operation according to claim 1 and the correlating method of database manipulation data, wherein, obtain the industry of user
Business operation and database peration data, by the business operation and corresponding database manipulation data formation candidate association group, bag
Include：
Receive user business operation and its beginning and ending time information simultaneously write business information base, receive database manipulation data and its
Beginning and ending time information simultaneously writes data message storehouse；
The beginning and ending time information of each business operation in business information base, intercepts correspondence in the data message storehouse
The database manipulation data of beginning and ending time information, the business operation being truncated to and corresponding database manipulation data are formed
Candidate association group.
3. business operation according to claim 1 and the correlating method of database manipulation data, wherein, obtain the candidate
The occurrence number of associated group, including：
During the one or many same candidate association groups occurred each time in business operation, the candidate association group is gone out into occurrence
Number increase is once.
4. business operation according to claim 1 and the correlating method of database manipulation data, wherein, obtain the candidate
The occurrence number of associated group, the confidence level of the candidate association group is calculated according to the occurrence number of the candidate association group, including：
Obtain the occurrence number of the candidate association group；
When the occurrence number of the candidate association group reaches preset upper limit value, the occurrence number of the candidate association group is multiplied by
Fixed coefficient is linearly reduced, the occurrence number formed after the reduction of the candidate association group；
The final confidence of the candidate association group is calculated according to the occurrence number after the reduction of the candidate association group.
5. business operation according to claim 4 and the correlating method of database manipulation data, wherein, according to the candidate
Occurrence number after the reduction of associated group calculates the final confidence of the candidate association group, including：
According to the occurrence number after the reduction of the candidate association group and default matching threshold benchmark, the candidate association is obtained
That organizes is less than threshold values hits；
According to the occurrence number after the reduction of the candidate association group and less than threshold values hits, the candidate association group is obtained
Higher than threshold values hits；
According to the base for being less than threshold values hits and the default score upper limit, calculating the candidate association group of the candidate association group
Plinth confidence level；
Judge whether described be 0 higher than threshold values hits,
If it is described higher than threshold values hits be 0, using the basic confidence level of the candidate association group as the candidate association group most
Whole confidence level.
6. business operation according to claim 5 and the correlating method of database manipulation data, wherein, it is described to be less than threshold values
Hits (LOWER_MATCH_NUM) are calculated according to equation below：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matching thresholds of MATCHES_THR
Benchmark.
7. business operation according to claim 6 and the correlating method of database manipulation data, wherein, the candidate association
That organizes calculates higher than threshold values hits (UPPER_MATCH_NUM) according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).
8. business operation according to claim 7 and the correlating method of database manipulation data, wherein, the basis is credible
Degree (RELIABILITY) is calculated according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.
9. business operation according to claim 8 and the correlating method of database manipulation data, wherein, it is higher than described in judgement
Threshold values hits whether be after 0, in addition to：
If described is not 0 higher than threshold values hits, according to the default score upper limit, the default matching threshold benchmark, obtain
The high threshold values hit ratio of the candidate association group；
According to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than going out after threshold values hits and reduction
Occurrence number, calculates the final confidence of the candidate association group.
10. business operation according to claim 9 and the correlating method of database manipulation data, wherein, the candidate is closed
The high threshold values hit ratio (UPPER_SCORE) of joint group is calculated according to equation below:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).
11. business operation according to claim 10 and the correlating method of database manipulation data, wherein, the candidate is closed
The final confidence (FINAL-RELIABILITY) of joint group is calculated according to equation below：
FINALR-ELIABILITY=(RELIABILITY+ (UP_SCORE*UPPER_MATCH_NUM/SCORE_X)).
12. a kind of business operation and the associate device of database manipulation data, wherein, the equipment includes：
First associated apparatus, business operation and database peration data for obtaining user, by the business operation and correspondingly
Database manipulation data formation candidate association group；
Computing device, the occurrence number for obtaining the candidate association group, according to the occurrence number meter of the candidate association group
Calculate the final confidence of the candidate association group；
Second associated apparatus, for using candidate association group of the final confidence in preset threshold range as after screening
Associated group.
13. business operation according to claim 12 and the associate device of database manipulation data, wherein, described first closes
Coupling device, for receiving the business operation and its beginning and ending time information of user and writing business information base, receives database manipulation
Data and its beginning and ending time information simultaneously write data message storehouse；During the start-stop of each business operation in business information base
Between information, the database manipulation data of correspondence beginning and ending time information are intercepted in the data message storehouse, are truncated to described
Business operation and corresponding database manipulation data formation candidate association group.
14. business operation according to claim 12 and the associate device of database manipulation data, wherein, it is described to calculate dress
Put, for occur in business operation each time one or many same candidate association groups when, by going out for the candidate association group
The increase of occurrence number is once.
15. business operation according to claim 12 and the associate device of database manipulation data, wherein, it is described to calculate dress
Put, the occurrence number for obtaining the candidate association group；When the occurrence number of the candidate association group reaches preset upper limit value
When, the occurrence number of the candidate association group is multiplied by fixed coefficient and linearly reduced, the contracting of the candidate association group is formed
Occurrence number after subtracting；The final credible of the candidate association group is calculated according to the occurrence number after the reduction of the candidate association group
Degree.
16. business operation according to claim 15 and the associate device of database manipulation data, wherein, it is described to calculate dress
Put, for the occurrence number after the reduction according to the candidate association group and default matching threshold benchmark, obtain the candidate
Associated group be less than threshold values hits；According to the occurrence number after the reduction of the candidate association group and less than threshold values hits,
Obtain the candidate association group is higher than threshold values hits；Threshold values hits are less than and default according to the candidate association group
The score upper limit, calculates the basic confidence level of the candidate association group；Judge whether described be 0 higher than threshold values hits, if described
Higher than threshold values hits be 0, using the basic confidence level of the candidate association group as the candidate association group final confidence.
17. business operation according to claim 16 and the associate device of database manipulation data, wherein, it is described to be less than valve
Value hits (LOWER_MATCH_NUM) are calculated according to equation below：
LOWER_MATCH_NUM=MIN (SCORE_X, MATCHES_THR),
Wherein, SCORE_X is the occurrence number after the reduction of the candidate association group, the default matching thresholds of MATCHES_THR
Benchmark.
18. business operation according to claim 17 and the associate device of database manipulation data, wherein, the candidate is closed
Joint group is calculated higher than threshold values hits (UPPER_MATCH_NUM) according to equation below：
UPPER_MATCH_NUM=(SCORE_X-LOWER_MATCH_NUM).
19. business operation according to claim 18 and the associate device of database manipulation data, wherein, the basis can
Reliability (RELIABILITY) is calculated according to equation below：
RELIABILITY=(LOWER_MATCH_NUM*LOWER_MATCH_NUM/TOP_SCORE),
Wherein, TOP_SCORE is the default score upper limit.
20. business operation according to claim 19 and the associate device of database manipulation data, wherein, it is described to calculate dress
Put, whether be additionally operable to judging described higher than threshold values hits is after 0, if described is not 0 higher than threshold values hits, according to pre-
If the score upper limit, the default matching threshold benchmark, obtain the candidate association group high threshold values hit ratio；
According to the basic confidence level of the candidate association group, high threshold values hit ratio, higher than going out after threshold values hits and reduction
Occurrence number, calculates the final confidence of the candidate association group.
21. business operation according to claim 20 and the associate device of database manipulation data, wherein, the candidate is closed
The high threshold values hit ratio (UPPER_SCORE) of joint group is calculated according to equation below:
UPPER_SCORE=((TOP_SCORE-MATCHES_THR*MATCHES_THR)/TOP_SCORE).
22. business operation according to claim 21 and the associate device of database manipulation data, wherein, the candidate is closed
The final confidence (FINAL-RELIABILITY) of joint group is calculated according to equation below：
FINALR-ELIABILITY=(RELIABILITY+ (UP_SCORE*UPPER_MATCH_NUM/SCORE_X)).
23. a kind of equipment based on calculating, wherein, including：
Processor；And
It is arranged to store the memory of computer executable instructions, the executable instruction makes the processing when executed
Device：
The business operation and database peration data of user is obtained, by the business operation and corresponding database manipulation data shape
Into candidate association group；
The occurrence number of the candidate association group is obtained, the candidate association group is calculated according to the occurrence number of the candidate association group
Final confidence；
It regard candidate association group of the final confidence in preset threshold range as the associated group after screening.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305780.4A CN107273411B (en) | 2017-05-03 | 2017-05-03 | Correlation method and device of business operation and database operation data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305780.4A CN107273411B (en) | 2017-05-03 | 2017-05-03 | Correlation method and device of business operation and database operation data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107273411A true CN107273411A (en) | 2017-10-20 |
| CN107273411B CN107273411B (en) | 2020-11-17 |
Family
ID=60073694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710305780.4A Active CN107273411B (en) | 2017-05-03 | 2017-05-03 | Correlation method and device of business operation and database operation data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107273411B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553487A (en) * | 2020-05-25 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Business object identification method and device |
| CN112069193A (en) * | 2020-08-27 | 2020-12-11 | 上海上讯信息技术股份有限公司 | Correlation method and device based on asynchronous correlation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639879A (en) * | 2008-07-28 | 2010-02-03 | 成都市华为赛门铁克科技有限公司 | Database security monitoring method, device and system |
| CN105138675A (en) * | 2015-09-08 | 2015-12-09 | 上海上讯信息技术股份有限公司 | Database auditing method and device |
| CN105512210A (en) * | 2015-11-27 | 2016-04-20 | 网神信息技术（北京）股份有限公司 | Correlated event type detection method and device |
| US20160171590A1 (en) * | 2014-11-10 | 2016-06-16 | 0934781 B.C. Ltd | Push-based category recommendations |
-
2017
- 2017-05-03 CN CN201710305780.4A patent/CN107273411B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639879A (en) * | 2008-07-28 | 2010-02-03 | 成都市华为赛门铁克科技有限公司 | Database security monitoring method, device and system |
| US20160171590A1 (en) * | 2014-11-10 | 2016-06-16 | 0934781 B.C. Ltd | Push-based category recommendations |
| CN105138675A (en) * | 2015-09-08 | 2015-12-09 | 上海上讯信息技术股份有限公司 | Database auditing method and device |
| CN105512210A (en) * | 2015-11-27 | 2016-04-20 | 网神信息技术（北京）股份有限公司 | Correlated event type detection method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553487A (en) * | 2020-05-25 | 2020-08-18 | 支付宝(杭州)信息技术有限公司 | Business object identification method and device |
| CN111553487B (en) * | 2020-05-25 | 2021-04-27 | 支付宝(杭州)信息技术有限公司 | Business object identification method and device |
| CN112069193A (en) * | 2020-08-27 | 2020-12-11 | 上海上讯信息技术股份有限公司 | Correlation method and device based on asynchronous correlation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107273411B (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110442516B (en) | Information processing method, apparatus, and computer-readable storage medium | |
| CA2712849A1 (en) | Claims analytics engine | |
| US8793210B2 (en) | General market prediction using position specification language | |
| CN110110092B (en) | Knowledge graph construction method and related equipment | |
| CN105373853A (en) | Stock public opinion index prediction method and device | |
| CN112184089B (en) | Training method, device and equipment of test question difficulty prediction model and storage medium | |
| CN107273411A (en) | Business operation and the correlating method and equipment of database manipulation data | |
| Özpeynirci et al. | An interactive algorithm for multiple criteria constrained sorting problem | |
| CN113723871B (en) | Multi-source information-based current situation flood consistency processing method and system | |
| CN106874286B (en) | Method and device for screening user characteristics | |
| CN104755998B (en) | Method for providing optical glass | |
| US20180101535A1 (en) | System and method for content affinity analytics | |
| CN115936003A (en) | Software function point duplicate checking method, device, equipment and medium based on neural network | |
| CN112950350B (en) | Loan product recommendation method and system based on machine learning | |
| CN112529183A (en) | Knowledge distillation-based model self-adaptive updating method | |
| CN114861984A (en) | For predicting high CO content 2 Method and processor for condensing volume of oil ring of gas reservoir | |
| CN113658173A (en) | Compression method, system and computing equipment of detection model based on knowledge distillation | |
| CN114066896A (en) | Image segmentation model training method, image segmentation method and device | |
| CN106776505B (en) | Method for comparing standard cell library by calculating characteristic value | |
| CN109726879B (en) | Data model evaluation method, device and equipment | |
| Yan et al. | The Matrix Grey Target Decision Model Based on Three Dimensional Space. | |
| CN108959485A (en) | It is a kind of for generating the data processing method and device of flow indicator data | |
| CN111008658B (en) | Police officer learning analysis system based on supervised learning | |
| CN116842960B (en) | Feature extraction model training and extracting method and device based on large model | |
| CN108073612A (en) | The method and apparatus of synchronous SQL executive plans |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |