CN110308946A - Race batch processing method, equipment, storage medium and device based on artificial intelligence - Google Patents
Race batch processing method, equipment, storage medium and device based on artificial intelligence Download PDFInfo
- Publication number
- CN110308946A CN110308946A CN201910433260.0A CN201910433260A CN110308946A CN 110308946 A CN110308946 A CN 110308946A CN 201910433260 A CN201910433260 A CN 201910433260A CN 110308946 A CN110308946 A CN 110308946A
- Authority
- CN
- China
- Prior art keywords
- batch
- target
- race
- run
- artificial intelligence
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 75
- 238000003672 processing method Methods 0.000 title claims abstract description 33
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 41
- 239000000284 extract Substances 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 65
- 230000002123 temporal effect Effects 0.000 claims description 26
- 230000005540 biological transmission Effects 0.000 claims description 18
- 235000013399 edible fruits Nutrition 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 16
- 238000004891 communication Methods 0.000 description 10
- 230000004048 modification Effects 0.000 description 10
- 238000012986 modification Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000003203 everyday effect Effects 0.000 description 8
- 230000004044 response Effects 0.000 description 7
- 238000005520 cutting process Methods 0.000 description 6
- 241000208340 Araliaceae Species 0.000 description 5
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 5
- 235000003140 Panax quinquefolius Nutrition 0.000 description 5
- 235000008434 ginseng Nutrition 0.000 description 5
- 230000002354 daily effect Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of, and race batch processing method, equipment, storage medium and device based on artificial intelligence are criticized in instruction from the race this method comprises: receiving the race batch instruction of current period and extract target service type；Corresponding target is searched by default tree according to the target service type and runs batch parameter；Batch parameter, which is run, according to the target service type and the corresponding target generates target race batch task；The target is run according to specified time and runs batch task, obtains the first operation result of current period, and the first operation result of the current period is sent to target person.The present invention runs batch parameter by intelligence configuration, without manually being configured, improves and runs batch efficiency.
Description
Technical field
The present invention relates to the technical field of artificial intelligence more particularly to a kind of race batch processing method based on artificial intelligence,
Equipment, storage medium and device.
Background technique
" run batch " also cries " batch processing " or " batch processing ", English: Batch Processing, is all kinds of IT systems now
In one of common business, according to statistics, operation in 70% operation system is completed by running batch mode." run and criticize " letter
For list, be a kind of identical business " saving bit by bit " is started at the specified time point to a certain amount (business is identical, in batch) into
Row automatically processes, and reaches simplified operation, the purpose of raising efficiency.The process of batch processing is analyzed, we are not difficult to sum up batch processing
The characteristics of business: treating capacity is big (in batch), has specific trigger timing (specified time point), can automatically process.
But the race batch task of different business still needs human configuration to run batch parameter in banking system at present, race was criticized
It reports an error in journey, requires manual intervention and location of mistake and correct mistake, the execution run batch, usually progress cross-system,
Multi-service and orderly processing, it is numerous and jumbled to may span across system, too long in a certain system residence time if you have questions and as blocked
Property problem will cause subsequent process and can not execute the execution for delaying entire race batch process；On the other hand, it is engaged in race batch work
Personnel may be non-technical developer, can not real-time perfoming investigation, need to coordinate related development colleague checked, entirely
The time-histories criticized is run to be affected.Therefore, race batch processing efficiency how is improved to be a technical problem to be solved urgently.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of race batch processing method, equipment, storage medium based on artificial intelligence
And device, it is intended to solve the technical issues of running batch processing low efficiency in the prior art.
To achieve the above object, the present invention provides a kind of race batch processing method based on artificial intelligence, described based on artificial
Intelligence race batch processing method the following steps are included:
The race batch instruction for receiving current period extracts target service type from described run in batch instruction；
Corresponding target is searched by default tree according to the target service type and runs batch parameter；
Batch parameter, which is run, according to the target service type and the corresponding target generates target race batch task；
The target is run according to specified time and runs batch task, obtains the first operation result of current period, and will be described
First operation result of current period is sent to target person.
Preferably, it includes multiple subtasks that the target, which runs batch task,；
It is described to run the target race batch task according to specified time, the first operation result of current period is obtained, and will
First operation result of the current period is sent to target person, comprising:
Race batch temporal information and the significance level information that each subtask is extracted in batch task are run from the target；
Batch temporal information and the significance level information are run according to described, the race batch of each subtask is calculated by preset formula
Sequentially；
According to batch sequence of running according to each subtask of specified time operation, the first operation result of current period is obtained,
And the first operation result of the current period is sent to target person.
Preferably, the preset formula are as follows: X=T × k+D × (1-k), wherein X is to run batch coefficient, when T is the race batch
Between information, D be the significance level information, k value be weight coefficient；
It is described to run batch temporal information and the significance level information according to described, each subtask is calculated by preset formula
Run batch sequence, comprising:
Batch temporal information and the significance level information are run according to described, the race batch of each subtask is calculated by preset formula
Coefficient；
It is ranked up from big to small according to batch coefficient that runs, obtains the race batch sequence of each subtask.
Preferably, first operation result includes the corresponding subtask operation result in multiple subtasks；
It is described that sequence is criticized according to each subtask of specified time operation according to described run, obtain the first operation knot of current period
Fruit, and the first operation result of the current period is sent to target person, comprising:
It is described that sequence is criticized according to each subtask of specified time operation according to described run, obtain multiple subtasks of current period
Operation result；
It is sent, in asynchronous transmission and unidirectional transmission according to the race batch temporal information and the significance level information from synchronous
Choose target sending method；
Multiple subtask operation results of the current period are sent to target person by the target sending method.
Preferably, described to run the target race batch task according to specified time, obtain the first operation knot of current period
Fruit, and after the first operation result of the current period is sent to target person, at the race based on artificial intelligence batch
Reason method further include:
Obtain the second operation result that preset quantity runs batch period；
It is extracted from second operation result to the private client trading amount of money and to private exchange hour；
Judge it is described whether default transaction amount range is met to the private client trading amount of money, and judge described to personal friendship Yi Shi
Between whether meet default trading rules；
If described meet default transaction amount range to the private client trading amount of money, and states and meet default friendship to private exchange hour
Easily rule, then carry out Risk-warning.
Preferably, described that corresponding target race batch ginseng is searched by default tree according to the target service type
Number, comprising:
The father node obtained in all father nodes of default tree runs batch parameter；
Batch parameter is run to the father node to segment, and obtains the first word that each father node runs batch parameter；
The first word for running batch parameter to each father node carries out part-of-speech tagging, obtains the first word of default part of speech as father
Node keyword；
The target service type is matched with the father node keyword；
If successful match, using the corresponding father node of father node keyword of successful match as target father node；
The target father node that the target father node is obtained from the default tree runs batch parameter；
Judge the target father node with the presence or absence of target descendant nodes；
If it exists, then the target descendant nodes that the target descendant nodes are obtained from the default tree run batch ginseng
Number, the target father node runs batch parameter and target descendant nodes race batch parameter constitutes target and runs batch parameter.
Preferably, described to run the target race batch task according to specified time, obtain the first operation knot of current period
Fruit, and after the first operation result of the current period is sent to target person, at the race based on artificial intelligence batch
Reason method further include:
Obtain sample error information and corresponding sample system error message；
Word segmentation processing is carried out to the sample error information and the sample system error message, the sample is obtained and reports an error
Second word of information and the third word of the sample system error message calculate the term vector of second word and described
The term vector of third word；
By the input layer of term vector input convolutional neural networks model, by convolutional layer and pond layer, the pond
Layer carries out double sampling to the output of the convolutional layer, obtains location of mistake model；
The log information generated when running the target race batch task is obtained, target report is extracted from the log information
Wrong information；
Goal systems mistake is gone out by the location of mistake model orientation according to the target error information.
In addition, to achieve the above object, the present invention also proposes a kind of race batch processing equipment based on artificial intelligence, the base
Include memory, processor in the race batch processing equipment of artificial intelligence and is stored on the memory and can be in the processor
The race batch program based on artificial intelligence of upper operation, the race batch program based on artificial intelligence be arranged for carrying out as
The step of race batch processing method based on artificial intelligence described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, it is stored with and is based on the storage medium
The race batch program of artificial intelligence is realized when the race batch program based on artificial intelligence is executed by processor as above
The step of described race batch processing method based on artificial intelligence.
In addition, to achieve the above object, the present invention also proposes a kind of race batch processing device based on artificial intelligence, the base
Include: in the race batch processing device of artificial intelligence
Receiving module extracts target service class from described run in batch instruction for receiving the race batch instruction of current period
Type；
Searching module runs batch ginseng for searching corresponding target by default tree according to the target service type
Number；
Generation module generates target race batch for running batch parameter according to the target service type and the corresponding target
Task；
Module is run, runs batch task for running the target according to specified time, obtains the first operation of current period
As a result, and the first operation result of the current period is sent to target person.
In the present invention, by receiving the race batch instruction of current period, target service class is extracted from described run in batch instruction
Type searches corresponding target by default tree according to the target service type and runs batch parameter, according to the target industry
Service type and the corresponding target run batch parameter and generate target race batch task, and intelligence configuration, which is run, criticizes parameter, carry out without artificial
Configuration improves and runs batch efficiency；The target is run according to specified time and runs batch task, obtains the first operation knot of current period
Fruit, and the first operation result of the current period is sent to target person, it runs batch result and timely feedbacks to related personnel, side
Just each related personnel understands or removes problem, improves the accuracy and efficiency for running batch traffic processing.
Detailed description of the invention
Fig. 1 is the race batch processing equipment based on artificial intelligence for the hardware running environment that the embodiment of the present invention is related to
Structural schematic diagram；
Fig. 2 is the flow diagram of the race batch processing method first embodiment the present invention is based on artificial intelligence；
Fig. 3 is the flow diagram of the race batch processing method second embodiment the present invention is based on artificial intelligence；
Fig. 4 is the flow diagram of the race batch processing method 3rd embodiment the present invention is based on artificial intelligence；
Fig. 5 is the structural block diagram of the race batch processing device first embodiment the present invention is based on artificial intelligence.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is at the race based on artificial intelligence batch for the hardware running environment that the embodiment of the present invention is related to
Manage device structure schematic diagram.
As shown in Figure 1, being somebody's turn to do the race batch processing equipment based on artificial intelligence may include: processor 1001, such as centre
It manages device (Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, storage
Device 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include showing
Display screen (Display), optional user interface 1003 can also include standard wireline interface and wireless interface, for user interface
1003 wireline interface can be USB interface in the present invention.Network interface 1004 optionally may include standard wireline interface,
Wireless interface (such as Wireless Fidelity (WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random of high speed
Memory (Random Access Memory, RAM) memory is accessed, stable memory (Non-volatile is also possible to
Memory, NVM), such as magnetic disk storage.Memory 1005 optionally can also be the storage independently of aforementioned processor 1001
Device.
It will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted at the race based on artificial intelligence batch
The restriction for managing equipment may include perhaps combining certain components or different component cloth than illustrating more or fewer components
It sets.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and the race batch program based on artificial intelligence.
In race batch processing equipment based on artificial intelligence shown in Fig. 1, network interface 1004 is mainly used for connection backstage
Server carries out data communication with the background server；User interface 1003 is mainly used for connecting user equipment；It is described to be based on
The race batch processing equipment of artificial intelligence calls the race based on artificial intelligence stored in memory 1005 batch by processor 1001
Processing routine, and execute the race batch processing method provided in an embodiment of the present invention based on artificial intelligence.
Based on above-mentioned hardware configuration, the embodiment of the race batch processing method the present invention is based on artificial intelligence is proposed.
It is the flow diagram of the race batch processing method first embodiment the present invention is based on artificial intelligence referring to Fig. 2, Fig. 2,
It is proposed that the present invention is based on the race batch processing method first embodiments of artificial intelligence.
In the first embodiment, the race batch processing method based on artificial intelligence the following steps are included:
Step S10: receiving the race batch instruction of current period, extracts target service type from described run in batch instruction.
It should be understood that the executing subject of the present embodiment is the race batch processing equipment based on artificial intelligence, wherein institute
Stating the race batch processing equipment based on artificial intelligence can be the electronic equipments such as PC or server.Batch efficiency is run in order to improve,
Can race batch traffic to system carry out basis instrument, it is described to run batch instruction and can be timing triggering, be also possible to correlation
What race batch staff or technical staff were sent by user equipment.It is generally necessary to carry out running the business of batch processing including a variety of
Type, the target service type include deposit, loan and credit card business etc. in banking system.
In the concrete realization, usually running batch processing is periodical batch processing task, and the race batch period is usually daily, described to work as
The preceding period is usually the same day；Some business may be monthly to carry out data statistics, then running batch period is the monthly current period
The usually specified times such as of that month last day or secondary month some day；Some business may be annual progress data system
Meter, then run batch period be it is annual, the current period be usually the last day of current year or some day of next year etc. it is specified when
Between, the present embodiment is without restriction to this.
Step S20: corresponding target is searched by default tree according to the target service type and runs batch parameter.
It will be appreciated that it includes that the multiple parameters such as batch date, time and data type are run in configuration that batch parameter is run in configuration.It is described
It is that corresponding run of the target service type criticizes the parameters such as date, time and data type that target, which runs batch parameter,.In order to improve effect
Rate can obtain a large amount of historical data, analyze historical data, obtain the corresponding pass between type of service and race batch parameter
System runs batch parameter and generally includes multinomial parameter relevant to batch traffic is run, each parameter includes the data of at least one level, just
Parameter is criticized in searching every run, default tree can be established according to the data of each level according to hierarchical relationship and establish institute respectively
The father node for stating default tree runs batch parameter and descendant nodes run batch parameter.It then can be according to the target service type from institute
It states and searches corresponding father node race batch parameter in default tree, and judge that the father node found runs batch parameter and whether there is
Descendant nodes run batch parameter, and if it exists, the corresponding father node of the target service type is run batch parameter and descendant nodes race batch
Parameter extracts together, runs batch parameter as the target.
In the present embodiment, the step S20, comprising:
The father node obtained in all father nodes of default tree runs batch parameter；To the father node run batch parameter into
Row participle obtains the first word that each father node runs batch parameter；The first word for running batch parameter to each father node carries out part of speech mark
Note obtains the first word of default part of speech as father node keyword；The target service type and the father node is crucial
Word is matched；If successful match, using the corresponding father node of father node keyword of successful match as target father node；From
The target father node that the target father node is obtained in the default tree runs batch parameter；Judging the target father node is
It is no that there are target descendant nodes；If it exists, then target of the target descendant nodes is obtained from the default tree
Sun Jiedian runs batch parameter, and the target father node race batch parameter and the target descendant nodes run batch parameter and constitute target race batch ginseng
Number.
In the concrete realization, the target service type includes deposit, loan and the credit card business etc. in banking system,
Batch parameter is run in order to quickly obtain the corresponding target of the target service type from the default tree, it can be preparatory
The everyday tasks information for obtaining each type of service carries out word segmentation processing to the everyday tasks information, obtains each everyday tasks letter
All words of breath carry out part-of-speech tagging to all words of each everyday tasks information, and the word for obtaining default part of speech is (such as dynamic
Word or noun) as the corresponding business keyword of each type of service.In all father nodes for obtaining the default tree
Father node run batch parameter, batch parameter is run to the father node and is segmented, the first word that each father node runs batch parameter is obtained,
The first word for running batch parameter to each father node carries out part-of-speech tagging, obtains the first word of default part of speech as father node key
Word, the default part of speech can be verb or noun.It is crucial by obtaining the corresponding target service of the target service type
Word matches the father node keyword with the target service keyword, if successful match, by the father of successful match
The corresponding father node of node keyword obtains the target father node as target father node from the default tree
Target father node runs batch parameter.In the default tree with the presence of father node descendant nodes, the descendants of each descendant nodes
It is also race needed for the target service type batch parameter that node, which runs batch parameter, then needs further to judge that the target father node is
It is no that there are target descendant nodes can return to the preamble traversal of lists of father node descendant nodes by a SQL statement, thus
Judge the target father node with the presence or absence of target descendant nodes, if the target father node there are target descendant nodes,
The target descendant nodes that the target descendant nodes are obtained from the default tree run batch parameter, the target father node
It runs batch parameter and the target descendant nodes runs batch parameter composition target and run batch parameter.
It should be noted that can also show when configuring the target race batch parameter and run batch parameter options list, and default
It chooses last time and runs the parameter used when batch processing, so that user judges whether to need to be adjusted based on the race subparameter of displaying,
If confirmation can be directly selected without adjustment, the selection that the target runs batch parameter is completed.
Step S30: batch parameter is run according to the target service type and the corresponding target and generates target race batch task.
It should be understood that different for different type of service business needs, corresponding batch task of running is different, runs batch task
The depth of processing is also different.In conjunction with business demand, batch parameter is run according to the target service type and corresponding target and generates institute
It states target and runs batch task, the target runs batch task and includes when which data which system to obtain which period from are criticized
Measure the task of processing.For example, deposit at bank business is corresponding to run batch task are as follows: after cutting time point from day, from deposit system
Middle obtain cut deposit all in the period, the data flow of withdrawal and corresponding time last day, calculates and cut last day in the period always
Deposit information.
Step S40: running the target according to specified time and run batch task, obtain the first operation result of current period,
And the first operation result of the current period is sent to target person.
It will be appreciated that the execution time that the target runs batch task is usually that after day cutting time point, can pass through setting
The specified time is timed target race batch task and is started and carried out.The operation result is to execute the target to run
The operation result, can be sent to the target person, the target person is often referred to related skill by the data that the task of criticizing obtains
Art personnel or traffic operation staff can carry out the transmission of the operation result by communication softwares such as mails.So that the mesh
Mark personnel execute follow-up business process according to the operation result.First operation result includes running batch data obtained, fortune
Row process indices and error information, so that the target person can understand in time or remove problem, to improve at race batch
Manage efficiency and data accuracy.
In the present embodiment, by receiving the race batch instruction of current period, target service is extracted from described run in batch instruction
Type searches corresponding target by default tree according to the target service type and runs batch parameter, according to the target
Type of service and the corresponding target, which run batch parameter and generate target, runs batch task, and batch parameter is run in intelligence configuration, without manually into
Row configuration, improves and runs batch efficiency；The target is run according to specified time and runs batch task, obtains the first operation knot of current period
Fruit, and the first operation result of the current period is sent to target person, it runs batch result and timely feedbacks to related personnel, side
Just each related personnel understands or removes problem, improves the accuracy and efficiency for running batch traffic processing.
It is the flow diagram of the race batch processing method second embodiment the present invention is based on artificial intelligence referring to Fig. 3, Fig. 3,
Based on above-mentioned first embodiment shown in Fig. 2, the second embodiment of the race batch processing method the present invention is based on artificial intelligence is proposed.
In a second embodiment, the step S40, comprising:
Step S401: it includes multiple subtasks that the target, which runs batch task, runs in batch task and is extracted respectively from the target
The race of subtask batch temporal information and significance level information.
It should be understood that the execution time of each subtask is usually after day cutting time point, generally according to each business department
Follow-up work required time the race batch temporal information of each subtask is set, the follow-up work required time is more urgent, corresponding
Subtask the setting of race batch time it is more forward.Usual each subtask carries out running the first operation result that batch processing obtains, and is used for
Each business department carries out follow-up work processing, and the follow-up work is more important, then corresponding subtask significance level is higher.Usually
It can be by analyzing historical data, by obtaining a large amount of sample subtask and sample significance level information to convolutional Neural
Network model is trained, and obtains subtask significance level identification model, important by the way that each subtask is inputted the subtask
Degree identification model obtains the significance level information of each subtask.
Step S402: batch temporal information and the significance level information are run according to described, each son is calculated by preset formula
The race of task batch sequence.
It will be appreciated that the preset formula are as follows: X=T × k+D × (1-k), wherein X is to run batch coefficient, and T is the race
Temporal information is criticized, D is the significance level information, and k value is weight coefficient, and k is influenced by the time-consuming of subtasking, is illustrated
For, if running taking a long time for batch processing subtasking, k should take the larger value, run batch temporal information to increase
It influences, if the time-consuming for running batch processing subtasking is shorter, k should take smaller value, run batch temporal information to reduce
It influences.The race batch coefficient X for calculating acquisition by the preset formula is bigger, and it is time-consuming longer to illustrate that corresponding subtask executes, or
Person's demand is more urgent or significance level is higher, then can be ranked up from big to small according to crowd coefficient X that runs, obtain each son
The race of task batch sequence, crowd coefficient X that runs is bigger, then the race of corresponding subtask batch sequence is more forward.In the present embodiment, institute
State step S402, comprising: run batch temporal information and the significance level information according to described, each son is calculated by preset formula and is appointed
The race of business batch coefficient；It is ranked up from big to small according to batch coefficient that runs, obtains the race batch sequence of each subtask.
Step S403: according to batch sequence of running according to each subtask of specified time operation, the first of current period is obtained
Operation result, and the first operation result of the current period is sent to target person.
It should be noted that the execution time that the target runs batch task is usually after day cutting time point, it can be by setting
The specified time is set to run batch task to the target and be timed and be started and carried out.It includes multiple sons that the target, which runs batch task,
Task starts the target in the specified time and runs batch task, is successively run to each subtask according to batch sequence of running
Batch processing, obtains the first operation result of the current period, and first operation result includes that the corresponding son in each subtask is appointed
Business operation result.First operation result can be sent to the target person, the target person is often referred to the relevant technologies
Personnel or traffic operation staff can carry out the transmission of the operation result by communication softwares such as mails.So that the target
Personnel execute follow-up business process according to first operation result.First operation result include run batch obtain data,
Operational process indices and error information are criticized so that the target person can understand in time or remove problem with improving to run
Treatment effeciency and data accuracy.
In a second embodiment, first operation result includes the corresponding subtask operation result in multiple subtasks；
The step S403, comprising:
It is described that sequence is criticized according to each subtask of specified time operation according to described run, obtain multiple subtasks of current period
Operation result；Temporal information and the significance level information are criticized from synchronous transmission, asynchronous transmission and unidirectional transmission according to the race
Middle selection target sending method；Multiple subtask operation results of the current period are sent extremely by the target sending method
Target person.
In the concrete realization, after the synchronous transmission refers to that message sender issues data, the target person can received
Member sends back to the communication modes that a data packet is just given in response later by server, and the time higher for significance level is not tight
Urgent subtask operation result usually chooses synchronous sending method as the target sending method, to ensure subtask operation knot
Fruit reliable diffusion avoids omitting significant data to the target person.After the asynchronous transmission refers to that sender issues data, no
Equal recipients send back to response, then send the communication modes of next data packet, in the multiple subtasks for executing the current period
Asynchronous transmission when, without waiting for the target person by server response can directly return, connect by callback interface
Server response is received, and the response results of server are handled, the higher son of and significance level more urgent for the time is appointed
Business, can be using the asynchronous transmission as the target sending method, so that corresponding subtask operation result can quickly be sent
To the target person, data is avoided to send delay, and have higher reliability, while ensuring accurately being sent to for data.Institute
Stating unidirectional transmission feature is only to be responsible for sending message, is not to wait for server response and triggers without call back function, i.e., only sends and ask
It asks and is not to wait for response, the process time-consuming that this mode sends message is very short, more urgent for the time and again generally in microsecond rank
The subtask for wanting degree not high can choose the unidirectional sending method as the target sending method, so that corresponding son is appointed
Business operation result can quickly be sent to the target person, and data is avoided to send delay.
In the present embodiment, it includes multiple subtasks that the target, which runs batch task, runs in batch task and extracts from the target
The race of each subtask batch temporal information and significance level information run batch temporal information and the significance level information according to described,
The race batch sequence that each subtask is calculated by preset formula runs each subtask according to specified time according to the race batch sequence,
The first operation result of current period is obtained, and the first operation result of the current period is sent to target person, so that
It is pressed for time and/or the higher priority of subtask of significance level carries out race batch processing, and the follow-up work of each business department handles energy
Enough smoothly docking.
It is the flow diagram of the race batch processing method 3rd embodiment the present invention is based on artificial intelligence referring to Fig. 4, Fig. 4,
It is proposed that the present invention is based on the race batch processing methods of artificial intelligence the based on first embodiment and second embodiment 3rd embodiment
Three embodiments in the present embodiment, are illustrated based on above-mentioned first embodiment shown in Fig. 2.
In the third embodiment, after the step S40, further includes:
Step S50: the second operation result that preset quantity runs batch period is obtained.
It should be understood that it is described run batch period be usually daily, monthly or every year, the present embodiment to be illustrated daily,
The preset quantity can be configured according to default trading rules, for example include judging that data are in the default trading rules
The no business datum needed to refer in 10 days there are risk then can set 10 for the preset quantity.The second operation knot
Fruit is that the data that batch task obtains are run in operation in the race batch period of the preset quantity, is with the first operation result of current period
Node, the preset quantity are set as 10, then obtain 9 operation results for running batch period, first operation result again forward
And current period pervious 9 operation results for running batch period constitute second operation result.
Step S60: it is extracted from second operation result to the private client trading amount of money and to private exchange hour.
It should be noted that the target service type includes deposit, loan or credit card business etc. in banking system.
Second operation result includes to the private client trading amount of money and to private exchange hour, to the public client trading amount of money and to public affairs
The data such as exchange hour.In order to avoid that need to be tied from second operation to occurring the transaction of triggering anti money washing rule in private client
It is extracted in fruit to the private client trading amount of money and to private exchange hour, according to the private client trading amount of money and to private exchange hour
Identify each couple of personal friendship in easy with the presence or absence of abnormal transaction.
Step S70: judge it is described whether default transaction amount range is met to the private client trading amount of money, and judge it is described right
Whether private exchange hour meets default trading rules.
It will be appreciated that the present count can be assessed by the default trading rules by the way that default trading rules are arranged
The second operation result that amount runs batch period whether there is risk.For example, right in 10 days including judging in the default trading rules
Whether the private client trading amount of money (same counterparty) is more than or equal to 45000 yuan and is less than or equal to 500000 yuan, and client continues three
It has transaction, if so, explanation triggers anti money washing rule.
Step S80: it if described meet default transaction amount range to the private client trading amount of money, and states and private exchange hour is accorded with
Default trading rules are closed, then carry out Risk-warning.
In the concrete realization, default transaction amount range can be carried out according to different business different scenes different institutions and is preset
The setting of trading rules, the race batch processing equipment based on artificial intelligence can also intelligence to related service scene
The accuracy for improving Risk-warning is practised, the race batch processing equipment based on artificial intelligence reserves relevant risk rule interface can
The common interface provided with the operation systems such as such as people's row or silver prison interacts, and reaches the real-time, interactive of Risk-warning rule, mentions
Rise the timeliness to Risk-warning.The Risk-warning can also be notified by communication modes such as mail or short messages.
It for example, include judging in 10 days to (the same transaction pair of the private client trading amount of money in the default trading rules
Hand) whether it is more than or equal to 45000 yuan less than or equal to 500000 yuan, and client continues to have transaction in three days, if so, illustrating to trigger
Anti money washing rule carries out Risk-warning, then the preset quantity can be set to 10, then obtains 10 operations for running batch period
As a result, extracted in the operation result for running batch period from 10 in 10 days to the private client trading amount of money (same counterparty), from
And judge whether to meet above-mentioned default trading rules, such as meet, then carry out Risk-warning, reach the real-time control of risk, is promoted
The timeliness of Risk-warning.
In the present embodiment, after the step S40, further includes:
Obtain sample error information and corresponding sample system error message；To the sample error information and the sample
System error message carry out word segmentation processing, obtain the sample error information the second word and the sample system error message
Third word, calculate the term vector of second word and the term vector of the third word；The term vector is inputted and is rolled up
The input layer of product neural network model, by convolutional layer and pond layer, the pond layer carries out two to the output of the convolutional layer
Secondary sampling obtains location of mistake model；The log information generated when running the target race batch task is obtained, is believed from the log
Target error information is extracted in breath；Goal systems is gone out by the location of mistake model orientation according to the target error information
Mistake.
It should be noted that can also obtain a large amount of sample error information and corresponding sample system error message, pass through
Word segmentation processing is carried out to the sample error information and the corresponding sample system error message, obtains the sample report
Second word of wrong information and the third word of the sample system error message, calculate second word TF-IDF value and
The sample error information is expressed as with second word and second word by the TF-IDF value of the third word
The term vector of TF-IDF value composition, the sample system error message is expressed as with the third word and the third word
TF-IDF value composition term vector.TF-IDF is actually: TF*IDF, TF word frequency (Term Frequency), IDF is inversely literary
Part frequency (Inverse Document Frequency).TF indicates the frequency that entry occurs in a document.
In the concrete realization, convolutional neural networks model generally includes input layer, convolutional layer, pond layer and full articulamentum,
The term vector is carried out to the input layer of input convolutional neural networks model after mathematicization, the input layer of convolutional neural networks model
For by n*a two-dimensional data matrix, the output data of input layer passes through convolutional layer, the input of convolutional layer by preceding layer partial zones
Domain and weight decision, input of each layer of the output as next layer of neuron, with multilayer convolution algorithm, to each layer of volume
Product operation result carries out nonlinear transformation, and input of the output of the convolutional layer as neuron passes through multilayer convolution algorithm pair
The output of the convolutional layer carries out nonlinear transformation, and pond layer carries out double sampling to the output result of nonlinear transformation, passing through
It crosses after the maximum pondization operation of pond layer, having extracted influences maximum first quantity (such as 300 to system mistake identification
It is a) local optimum feature, then system mistake classification is mapped to by full articulamentum, to obtain location of mistake model.
It should be understood that the implementation procedure that can run batch task to the target is monitored, records and run batch task every time
Treatment process and processing time, corresponding log information can all be generated by being run when batch task is handled every time, can be to the log information
It is analyzed, the target error information in the log information is identified by special field, and to the target error information
It extracts.
It will be appreciated that can learn to the treatment process and processing time for running batch task every time, at each race time
The operation result of reason is analyzed, and a large amount of sample error information and corresponding sample system mistake is obtained, according to the sample
Error information and corresponding sample system mistake are trained convolutional neural networks model, obtain the location of mistake model,
Goal systems mistake is quickly then oriented by the location of mistake model according to the target error information, it can also be by described
Location of mistake model exports target modification information.Usually running batch middle mistake occurred is much the mistake occurred in the past, described
Location of mistake model learns the previous error information and corresponding solution, so as to be accurately located out
Goal systems mistake simultaneously exports the target modification information.
It should be noted that the target modification information is correct business datum, according to the target modification information pair
The target error information is modified, and generates relevant change record.It can also be according to previous legacy system mistake and right
The history modification information answered is learnt, and establishes the corresponding relationship between system mistake and corresponding modification information, then can be from
The corresponding target modification information of the goal systems mistake is searched in the corresponding relationship, at the race based on artificial intelligence batch
Reason equipment has the ability of self-regeneration and intelligence learning as an intelligent platform, for the system mistake oriented every time and repairs
It converts to breath to be learnt, so as to be subsequently encountered same error, can quickly be positioned by the location of mistake model, and defeated
Modification information out improves to solve a problem promptly and runs batch processing efficiency and data processing accuracy.It is described in the present embodiment
Gone out after goal systems mistake according to the target error information by the location of mistake model orientation, further includes: according to institute
State goal systems mistake and search corresponding target modification information, according to the target modification information to the goal systems mistake into
Row amendment.
In the present embodiment, second operation result in batch period is run by obtaining preset quantity, from second operation result
In extract to the private client trading amount of money and to private exchange hour, judge described whether default friendship is met to the private client trading amount of money
Easy amount of money range, and judge it is described whether default trading rules are met to private exchange hour, if described to the private client trading amount of money
Meet default transaction amount range, and state and default trading rules are met to private exchange hour, then carries out Risk-warning, reach risk
Real-time control, promote the timeliness of Risk-warning.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is stored on the storage medium based on artificial intelligence
Race batch program, the race batch program based on artificial intelligence realizes base as described above when being executed by processor
In the race batch processing method of artificial intelligence the step of.
In addition, the embodiment of the present invention also proposes a kind of race batch processing device based on artificial intelligence, the base referring to Fig. 5
Include: in the race batch processing device of artificial intelligence
Receiving module 10 extracts target service from described run in batch instruction for receiving the race batch instruction of current period
Type.
It should be understood that run batch efficiency to improve, can the race batch traffic to system carry out basis instrument, described run batch refers to
It enables and can be timing triggering, be also possible to related race batch staff or technical staff is sent by user equipment
's.It is generally necessary to carry out running the business of batch processing including multiple types, the target service type includes depositing in banking system
Money, loan and credit card business etc..
In the concrete realization, usually running batch processing is periodical batch processing task, and the race batch period is usually daily, described to work as
The preceding period is usually the same day；Some business may be monthly to carry out data statistics, then running batch period is the monthly current period
The usually specified times such as of that month last day or secondary month some day；Some business may be annual progress data system
Meter, then run batch period be it is annual, the current period be usually the last day of current year or some day of next year etc. it is specified when
Between, the present embodiment is without restriction to this.
Searching module 20, for searching corresponding target race batch by default tree according to the target service type
Parameter.
It will be appreciated that it includes that the multiple parameters such as batch date, time and data type are run in configuration that batch parameter is run in configuration.It is described
It is that corresponding run of the target service type criticizes the parameters such as date, time and data type that target, which runs batch parameter,.In order to improve effect
Rate can obtain a large amount of historical data, analyze historical data, obtain the corresponding pass between type of service and race batch parameter
System runs batch parameter and generally includes multinomial parameter relevant to batch traffic is run, each parameter includes the data of at least one level, just
Parameter is criticized in searching every run, default tree can be established according to the data of each level according to hierarchical relationship and establish institute respectively
The father node for stating default tree runs batch parameter and descendant nodes run batch parameter.It then can be according to the target service type from institute
It states and searches corresponding father node race batch parameter in default tree, and judge that the father node found runs batch parameter and whether there is
Descendant nodes run batch parameter, and if it exists, the corresponding father node of the target service type is run batch parameter and descendant nodes race batch
Parameter extracts together, runs batch parameter as the target.
In the present embodiment, described that corresponding target race is searched by default tree according to the target service type
Criticize parameter, comprising:
The father node obtained in all father nodes of default tree runs batch parameter；To the father node run batch parameter into
Row participle obtains the first word that each father node runs batch parameter；The first word for running batch parameter to each father node carries out part of speech mark
Note obtains the first word of default part of speech as father node keyword；The target service type and the father node is crucial
Word is matched；If successful match, using the corresponding father node of father node keyword of successful match as target father node；From
The target father node that the target father node is obtained in the default tree runs batch parameter；Judging the target father node is
It is no that there are target descendant nodes；If it exists, then target of the target descendant nodes is obtained from the default tree
Sun Jiedian runs batch parameter, and the target father node race batch parameter and the target descendant nodes run batch parameter and constitute target race batch ginseng
Number.
In the concrete realization, the target service type includes deposit, loan and the credit card business etc. in banking system,
Batch parameter is run in order to quickly obtain the corresponding target of the target service type from the default tree, it can be preparatory
The everyday tasks information for obtaining each type of service carries out word segmentation processing to the everyday tasks information, obtains each everyday tasks letter
All words of breath carry out part-of-speech tagging to all words of each everyday tasks information, and the word for obtaining default part of speech is (such as dynamic
Word or noun) as the corresponding business keyword of each type of service.In all father nodes for obtaining the default tree
Father node run batch parameter, batch parameter is run to the father node and is segmented, the first word that each father node runs batch parameter is obtained,
The first word for running batch parameter to each father node carries out part-of-speech tagging, obtains the first word of default part of speech as father node key
Word, the default part of speech can be verb or noun.It is crucial by obtaining the corresponding target service of the target service type
Word matches the father node keyword with the target service keyword, if successful match, by the father of successful match
The corresponding father node of node keyword obtains the target father node as target father node from the default tree
Target father node runs batch parameter.In the default tree with the presence of father node descendant nodes, the descendants of each descendant nodes
It is also race needed for the target service type batch parameter that node, which runs batch parameter, then needs further to judge that the target father node is
It is no that there are target descendant nodes can return to the preamble traversal of lists of father node descendant nodes by a SQL statement, thus
Judge the target father node with the presence or absence of target descendant nodes, if the target father node there are target descendant nodes,
The target descendant nodes that the target descendant nodes are obtained from the default tree run batch parameter, the target father node
It runs batch parameter and the target descendant nodes runs batch parameter composition target and run batch parameter.
It should be noted that can also show when configuring the target race batch parameter and run batch parameter options list, and default
It chooses last time and runs the parameter used when batch processing, so that user judges whether to need to be adjusted based on the race subparameter of displaying,
If confirmation can be directly selected without adjustment, the selection that the target runs batch parameter is completed.
Generation module 30 generates target race for running batch parameter according to the target service type and the corresponding target
The task of criticizing.
It should be understood that different for different type of service business needs, corresponding batch task of running is different, runs batch task
The depth of processing is also different.In conjunction with business demand, batch parameter is run according to the target service type and corresponding target and generates institute
It states target and runs batch task, the target runs batch task and includes when which data which system to obtain which period from are criticized
Measure the task of processing.For example, deposit at bank business is corresponding to run batch task are as follows: after cutting time point from day, from deposit system
Middle obtain cut deposit all in the period, the data flow of withdrawal and corresponding time last day, calculates and cut last day in the period always
Deposit information.
Module 40 is run, runs batch task for running the target according to specified time, obtains the first fortune of current period
Row is as a result, and be sent to target person for the first operation result of the current period.
It will be appreciated that the execution time that the target runs batch task is usually that after day cutting time point, can pass through setting
The specified time is timed target race batch task and is started and carried out.The operation result is to execute the target to run
The operation result, can be sent to the target person, the target person is often referred to related skill by the data that the task of criticizing obtains
Art personnel or traffic operation staff can carry out the transmission of the operation result by communication softwares such as mails.So that the mesh
Mark personnel execute follow-up business process according to the operation result.First operation result includes running batch data obtained, fortune
Row process indices and error information, so that the target person can understand in time or remove problem, to improve at race batch
Manage efficiency and data accuracy.
In the present embodiment, by receiving the race batch instruction of current period, target service is extracted from described run in batch instruction
Type searches corresponding target by default tree according to the target service type and runs batch parameter, according to the target
Type of service and the corresponding target, which run batch parameter and generate target, runs batch task, and batch parameter is run in intelligence configuration, without manually into
Row configuration, improves and runs batch efficiency；The target is run according to specified time and runs batch task, obtains the first operation knot of current period
Fruit, and the first operation result of the current period is sent to target person, it runs batch result and timely feedbacks to related personnel, side
Just each related personnel understands or removes problem, improves the accuracy and efficiency for running batch traffic processing.
In one embodiment, it includes multiple subtasks that the target, which runs batch task,；
The operation module 40 is also used to run the race batch temporal information for extracting each subtask in batch task from the target
And significance level information；Batch temporal information and the significance level information are run according to described, each son is calculated by preset formula and is appointed
The race of business batch sequence；According to batch sequence of running according to each subtask of specified time operation, the first operation of current period is obtained
As a result, and the first operation result of the current period is sent to target person.
In one embodiment, the preset formula are as follows: X=T × k+D × (1-k), wherein X is to run batch coefficient, and T is described
Batch temporal information is run, D is the significance level information, and k value is weight coefficient；
The race batch processing device based on artificial intelligence further include:
Computing module is calculated for running batch temporal information and the significance level information according to described by preset formula
The race of each subtask batch coefficient；
Sorting module obtains the race batch sequence of each subtask for being ranked up from big to small according to batch coefficient that runs.
In one embodiment, first operation result includes the corresponding subtask operation result in multiple subtasks；
The operation module 40 is also used to described criticize according to the race and sequentially runs each subtask according to specified time, obtains
Obtain multiple subtask operation results of current period；According to batch temporal information and the significance level information of running from synchronous hair
It send, choose target sending method in asynchronous transmission and unidirectional transmission；The current period is sent by the target sending method
Multiple subtask operation results to target person.
In one embodiment, the race batch processing device based on artificial intelligence further include:
Module is obtained, second operation result in batch period is run for obtaining preset quantity；
Extraction module, for extracting from second operation result to the private client trading amount of money and to personal friendship Yi Shi
Between；
Judgment module, for judge it is described whether default transaction amount range is met to the private client trading amount of money, and judge
It is described that whether default trading rules are met to private exchange hour；
Warning module if meeting default transaction amount range to the private client trading amount of money for described, and is stated easy to personal friendship
Time meets default trading rules, then carries out Risk-warning.
In one embodiment, the searching module 20, is also used to obtain the father in all father nodes of default tree
Node runs batch parameter；Batch parameter is run to the father node to segment, and obtains the first word that each father node runs batch parameter；To each
The first word that father node runs batch parameter carries out part-of-speech tagging, obtains the first word of default part of speech as father node keyword；
The target service type is matched with the father node keyword；If successful match, by the father node of successful match
The corresponding father node of keyword is as target father node；The target of the target father node is obtained from the default tree
Father node runs batch parameter；Judge the target father node with the presence or absence of target descendant nodes；If it exists, then from it is described preset it is tree-shaped
The target descendant nodes that the target descendant nodes are obtained in structure run batch parameter, and the target father node runs batch parameter and described
Target descendant nodes run batch parameter and constitute target race batch parameter.
In one embodiment, the acquisition module is also used to obtain sample error information and corresponding sample system mistake
Information；
The computing module is also used to carry out at participle the sample error information and the sample system error message
Reason, obtains the second word of the sample error information and the third word of the sample system error message, calculates described the
The term vector of the term vector of two words and the third word；
The race batch processing device based on artificial intelligence further include:
Module is constructed, for the term vector to be inputted to the input layer of convolutional neural networks model, by convolutional layer and pond
Change layer, the pond layer carries out double sampling to the output of the convolutional layer, obtains location of mistake model；
The extraction module is also used to obtain the log information generated when running the target race batch task, from the day
Target error information is extracted in will information；
Locating module, for going out goal systems mistake by the location of mistake model orientation according to the target error information
Accidentally.
The other embodiments or specific implementation of race batch processing device of the present invention based on artificial intelligence can refer to
Above-mentioned each method embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.If listing equipment for drying
Unit claim in, several in these devices, which can be, to be embodied by the same item of hardware.Word first,
Second and the use of third etc. do not indicate any sequence, can be mark by these word explanations.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
(such as read-only memory mirror image (Read Only Memory image, ROM)/random access memory (Random Access
Memory, RAM), magnetic disk, CD) in, including some instructions are used so that terminal device (can be mobile phone, computer,
Server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of race batch processing method based on artificial intelligence, which is characterized in that the race batch processing side based on artificial intelligence
Method the following steps are included:
The race batch instruction for receiving current period extracts target service type from described run in batch instruction；
Corresponding target is searched by default tree according to the target service type and runs batch parameter；
Batch parameter, which is run, according to the target service type and the corresponding target generates target race batch task；
The target is run according to specified time and runs batch task, obtains the first operation result of current period, and will be described current
First operation result in period is sent to target person.
2. the race batch processing method based on artificial intelligence as described in claim 1, which is characterized in that the target runs batch task
Including multiple subtasks；
It is described to run the target race batch task according to specified time, the first operation result of current period is obtained, and will be described
First operation result of current period is sent to target person, comprising:
Race batch temporal information and the significance level information that each subtask is extracted in batch task are run from the target；
Batch temporal information and the significance level information are run according to described, the race batch for calculating each subtask by preset formula is suitable
Sequence；
According to batch sequence of running according to each subtask of specified time operation, the first operation result of current period is obtained, and will
First operation result of the current period is sent to target person.
3. the race batch processing method based on artificial intelligence as claimed in claim 2, which is characterized in that the preset formula are as follows: X
=T × k+D × (1-k), wherein X is to run batch coefficient, and T is the race batch temporal information, and D is the significance level information, k value
For weight coefficient；
It is described to run batch temporal information and the significance level information according to described, the race batch of each subtask is calculated by preset formula
Sequentially, comprising:
Batch temporal information and the significance level information are run according to described, is by the race batch that preset formula calculates each subtask
Number；
It is ranked up from big to small according to batch coefficient that runs, obtains the race batch sequence of each subtask.
4. the race batch processing method based on artificial intelligence as claimed in claim 2, which is characterized in that first operation result
Including the corresponding subtask operation result in multiple subtasks；
It is described that sequence is criticized according to each subtask of specified time operation according to described run, the first operation result of current period is obtained,
And the first operation result of the current period is sent to target person, comprising:
It is described that sequence is criticized according to each subtask of specified time operation according to described run, obtain multiple subtasks operation of current period
As a result；
It is chosen from synchronous transmission, asynchronous transmission and unidirectional transmission according to the race batch temporal information and the significance level information
Target sending method；
Multiple subtask operation results of the current period are sent to target person by the target sending method.
5. the race batch processing method based on artificial intelligence as described in claim 1, which is characterized in that described according to specified time
It runs the target and runs batch task, obtain the first operation result of current period, and the first operation of the current period is tied
Fruit is sent to after target person, the race batch processing method based on artificial intelligence further include:
Obtain the second operation result that preset quantity runs batch period；
It is extracted from second operation result to the private client trading amount of money and to private exchange hour；
Judge it is described whether default transaction amount range is met to the private client trading amount of money, and judge described be to private exchange hour
It is no to meet default trading rules；
If described meet default transaction amount range to the private client trading amount of money, and states and meet default transaction rule to private exchange hour
Then, then Risk-warning is carried out.
6. the race batch processing method based on artificial intelligence as described in claim 1, which is characterized in that described according to the target
Type of service searches corresponding target by default tree and runs batch parameter, comprising:
The father node obtained in all father nodes of default tree runs batch parameter；
Batch parameter is run to the father node to segment, and obtains the first word that each father node runs batch parameter；
The first word for running batch parameter to each father node carries out part-of-speech tagging, obtains the first word of default part of speech as father node
Keyword；
The target service type is matched with the father node keyword；
If successful match, using the corresponding father node of father node keyword of successful match as target father node；
The target father node that the target father node is obtained from the default tree runs batch parameter；
Judge the target father node with the presence or absence of target descendant nodes；
If it exists, then the target descendant nodes that the target descendant nodes are obtained from the default tree run batch parameter,
The target father node runs batch parameter and the target descendant nodes run batch parameter composition target and run batch parameter.
7. such as the race batch processing method of any of claims 1-6 based on artificial intelligence, which is characterized in that described to press
The target is run according to specified time and runs batch task, obtains the first operation result of current period, and by the current period
First operation result is sent to after target person, the race batch processing method based on artificial intelligence further include:
Obtain sample error information and corresponding sample system error message；
Word segmentation processing is carried out to the sample error information and the sample system error message, obtains the sample error information
The second word and the sample system error message third word, calculate second word term vector and the third
The term vector of word；
By the input layer of term vector input convolutional neural networks model, by convolutional layer and pond layer, the pond layer is right
The output of the convolutional layer carries out double sampling, obtains location of mistake model；
It obtains and runs the target and run the log information generated when batch task, target is extracted from the log information and is reported an error letter
Breath；
Goal systems mistake is gone out by the location of mistake model orientation according to the target error information.
8. a kind of race batch processing equipment based on artificial intelligence, which is characterized in that the race batch processing based on artificial intelligence is set
It is standby include: memory, processor and be stored on the memory and can run on the processor based on artificial intelligence
Race batch program, realize when the race batch program based on artificial intelligence is executed by the processor such as claim
The step of race batch processing method described in any one of 1 to 7 based on artificial intelligence.
9. a kind of storage medium, which is characterized in that the race batch program based on artificial intelligence is stored on the storage medium,
It is realized as described in any one of claims 1 to 7 when the race batch program based on artificial intelligence is executed by processor
The step of race batch processing method based on artificial intelligence.
10. a kind of race batch processing device based on artificial intelligence, which is characterized in that the race batch processing dress based on artificial intelligence
It sets and includes:
Receiving module extracts target service type from described run in batch instruction for receiving the race batch instruction of current period；
Searching module runs batch parameter for searching corresponding target by default tree according to the target service type；
Generation module is appointed for running batch parameter generation target race batch according to the target service type and the corresponding target
Business；
Module is run, batch task is run for running the target according to specified time, obtains the first operation result of current period,
And the first operation result of the current period is sent to target person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433260.0A CN110308946A (en) | 2019-05-21 | 2019-05-21 | Race batch processing method, equipment, storage medium and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910433260.0A CN110308946A (en) | 2019-05-21 | 2019-05-21 | Race batch processing method, equipment, storage medium and device based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110308946A true CN110308946A (en) | 2019-10-08 |
Family
ID=68074925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910433260.0A Pending CN110308946A (en) | 2019-05-21 | 2019-05-21 | Race batch processing method, equipment, storage medium and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110308946A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111078268A (en) * | 2019-12-20 | 2020-04-28 | 中国建设银行股份有限公司 | Bank system business processing method, device, equipment and storage medium |
| CN111124491A (en) * | 2019-12-12 | 2020-05-08 | 浪潮(北京)电子信息产业有限公司 | Batch processing method, device, equipment and storage medium |
| CN111275122A (en) * | 2020-02-03 | 2020-06-12 | 腾讯医疗健康(深圳)有限公司 | Label labeling method, device, equipment and readable storage medium |
| CN111340147A (en) * | 2020-05-22 | 2020-06-26 | 四川新网银行股份有限公司 | Decision behavior generation method and system based on decision tree |
| CN111414376A (en) * | 2020-03-02 | 2020-07-14 | 中国建设银行股份有限公司 | Data early warning method and device |
| CN111858542A (en) * | 2020-06-22 | 2020-10-30 | 中国平安财产保险股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN112686557A (en) * | 2021-01-04 | 2021-04-20 | 北京金风慧能技术有限公司 | Wind generating set cumulant determination method, device, equipment, system and medium |
| CN114240109A (en) * | 2021-12-06 | 2022-03-25 | 中电金信软件有限公司 | Method, device and system for cross-region processing batch running task |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7894918B2 (en) * | 2006-07-27 | 2011-02-22 | Abb Research Ltd. | System for analyzing batch processes |
| CN105303324A (en) * | 2015-11-10 | 2016-02-03 | 中国建设银行股份有限公司 | Information system parameter management method and device |
| WO2017181587A1 (en) * | 2016-04-20 | 2017-10-26 | 乐视控股（北京）有限公司 | Method and electronic equipment for managing nodes in cdn |
| CN108509344A (en) * | 2018-04-04 | 2018-09-07 | 深圳前海微众银行股份有限公司 | Cut race batch test method, equipment and readable storage medium storing program for executing day |
-
2019
- 2019-05-21 CN CN201910433260.0A patent/CN110308946A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7894918B2 (en) * | 2006-07-27 | 2011-02-22 | Abb Research Ltd. | System for analyzing batch processes |
| CN105303324A (en) * | 2015-11-10 | 2016-02-03 | 中国建设银行股份有限公司 | Information system parameter management method and device |
| WO2017181587A1 (en) * | 2016-04-20 | 2017-10-26 | 乐视控股（北京）有限公司 | Method and electronic equipment for managing nodes in cdn |
| CN108509344A (en) * | 2018-04-04 | 2018-09-07 | 深圳前海微众银行股份有限公司 | Cut race batch test method, equipment and readable storage medium storing program for executing day |
Non-Patent Citations (1)
| Title |
|---|
| 赵威;李明皓;唐远明;王彬;: "辽宁省气象网络计算应用***的设计与实现", 气象, no. 12, 21 December 2009 (2009-12-21) * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124491A (en) * | 2019-12-12 | 2020-05-08 | 浪潮(北京)电子信息产业有限公司 | Batch processing method, device, equipment and storage medium |
| CN111078268A (en) * | 2019-12-20 | 2020-04-28 | 中国建设银行股份有限公司 | Bank system business processing method, device, equipment and storage medium |
| CN111078268B (en) * | 2019-12-20 | 2023-06-06 | 中国建设银行股份有限公司 | Bank system business processing method, device, equipment and storage medium |
| CN111275122A (en) * | 2020-02-03 | 2020-06-12 | 腾讯医疗健康(深圳)有限公司 | Label labeling method, device, equipment and readable storage medium |
| CN111275122B (en) * | 2020-02-03 | 2023-08-11 | 腾讯医疗健康(深圳)有限公司 | Label labeling method, device, equipment and readable storage medium |
| CN111414376A (en) * | 2020-03-02 | 2020-07-14 | 中国建设银行股份有限公司 | Data early warning method and device |
| CN111340147A (en) * | 2020-05-22 | 2020-06-26 | 四川新网银行股份有限公司 | Decision behavior generation method and system based on decision tree |
| CN111858542A (en) * | 2020-06-22 | 2020-10-30 | 中国平安财产保险股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN111858542B (en) * | 2020-06-22 | 2023-10-27 | 中国平安财产保险股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN112686557A (en) * | 2021-01-04 | 2021-04-20 | 北京金风慧能技术有限公司 | Wind generating set cumulant determination method, device, equipment, system and medium |
| CN114240109A (en) * | 2021-12-06 | 2022-03-25 | 中电金信软件有限公司 | Method, device and system for cross-region processing batch running task |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110308946A (en) | Race batch processing method, equipment, storage medium and device based on artificial intelligence | |
| US10162884B2 (en) | System and method for auto-suggesting responses based on social conversational contents in customer care services | |
| CN109543925A (en) | Risk Forecast Method, device, computer equipment and storage medium based on machine learning | |
| CN107612893A (en) | The auditing system and method and structure short message examination ＆ verification model method of short message | |
| CN107809331A (en) | The method and apparatus for identifying abnormal flow | |
| WO2020005895A1 (en) | Systems and methods of windowing time series data for pattern detection | |
| CN113157947A (en) | Knowledge graph construction method, tool, device and server | |
| CN112925911B (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
| CN111371673A (en) | Notes mail automatic processing method and device | |
| US20160283876A1 (en) | System and method for providing automomous contextual information life cycle management | |
| CN112149838A (en) | Method, device, electronic equipment and storage medium for realizing automatic model building | |
| CN112529477A (en) | Credit evaluation variable screening method, device, computer equipment and storage medium | |
| CN110175272A (en) | One kind realizing the convergent control method of work order and control device based on feature modeling | |
| CN115114439A (en) | Method and device for multi-task model reasoning and multi-task information processing | |
| CN107256231B (en) | Team member identification device, method and system | |
| CN115202847A (en) | Task scheduling method and device | |
| CN115082203A (en) | Method and device for pushing living scheme, electronic equipment and storage medium | |
| CN112995155A (en) | Financial abnormal message identification method and device | |
| CN115794545A (en) | Automatic processing method of operation and maintenance data and related equipment thereof | |
| CN115495587A (en) | Alarm analysis method and device based on knowledge graph | |
| Prasad et al. | Using Natural Language Processing and Blockchain for Employee Performance Evaluation | |
| CN113590604A (en) | Service data processing method and device and server | |
| CN112328812A (en) | Domain knowledge extraction method and system based on self-adjusting parameters and electronic equipment | |
| Shu et al. | A social sensing approach for quality changes of real-world services | |
| CN109635074A (en) | A kind of entity relationship analysis method and terminal device based on public feelings information |
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 |