CN110347583A - A kind of data analysis system consultation of doctors method and relevant apparatus - Google Patents
A kind of data analysis system consultation of doctors method and relevant apparatus Download PDFInfo
- Publication number
- CN110347583A CN110347583A CN201910436034.8A CN201910436034A CN110347583A CN 110347583 A CN110347583 A CN 110347583A CN 201910436034 A CN201910436034 A CN 201910436034A CN 110347583 A CN110347583 A CN 110347583A
- Authority
- CN
- China
- Prior art keywords
- test result
- target
- limit value
- machine learning
- learning model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3692—Test management for test results analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The disclosure is directed to a kind of data analysis system consultation of doctors method and relevant apparatus, belong to machine learning applied technical field, this method comprises: carrying out real-time testing to the data analysis system, and output test result when the test for receiving data analysis system is instructed；Judge whether the test result passes through；If the test result is not pass through, the test result is obtained not by the difference of target limit value and the test result beyond the target limit value in the corresponding predetermined upper limit value and the upper limit value；The data of the target indicator, the test result, the difference and the target limit value are inputted into preparatory trained machine learning model together, export testing and debugging scheme.For the disclosure by training machine learning model, according to holding a consultation, element is automatic, is accurately and rapidly held a consultation to obtain consultation of doctors scheme, and then effectively improves the regulated efficiency of system.
Description
Technical field
This disclosure relates to machine learning applied technical field, in particular to a kind of data analysis system consultation of doctors method
And device.
Background technique
Data analysis system is to be processed, arranged by data information of the data analysis system to various indexs, is calculated
Various analysis indexes are obtained, are changed into the message form for being easy to be accepted by people, and can will treated that information is store
The system deposited.Data analysis system is from developing to coming into operation, or the processes such as upgrading require to be tested, and find these
The problem of system；This test process is carried out generally by test macro, and test macro is surveyed to software systems
Corresponding test result can be obtained when examination.Then, if the test result of test macro passes through, tester's progress is not needed
Adjust data analysis system；But if the test result of test macro is not over needing tester to carry out by not
Disconnected modification, retrieval, how lookup adjusts so that the scheme that test result passes through, the efficiency of adjustment are very low.
So needing one kind that can hold a consultation automatically according to the test result of test macro, how to be adjusted so that surveying
The method for the scheme that test result passes through；Can accurate, quick predict output adjustment scheme, and then effectively improve regulated efficiency.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of data analysis system consultation of doctors scheme, and then at least to a certain extent in reality
It is now automatic, accurately and rapidly the test result of test macro is held a consultation to obtain consultation of doctors scheme, and then effectively improve system
Regulated efficiency.
According to one aspect of the disclosure, a kind of data analysis system consultation of doctors method is provided, comprising:
When the test for receiving the data analysis system analyzed for the data to target indicator instructs, to described
Data analysis system carries out real-time testing, and outputs test result；
Judge whether the test result passes through, wherein if the test result is in predetermined upper limit value and predetermined lower bound value
Except, then test result is not pass through；
If the test result is not pass through, obtaining the test result is corresponding predetermined upper limit value when not passing through
And the target limit value in the predetermined lower bound value, calculate the difference that the test result exceeds the target limit value；
The data of the target indicator, the test result, the difference and the target limit value are inputted in advance together
First trained machine learning model exports testing and debugging scheme, wherein the testing and debugging scheme is for indicate how adjustment
So that test result is to pass through.
In a kind of exemplary embodiment of the disclosure, it has been respectively trained according to different types of target indicator and has corresponded to difference
The machine learning model of the target indicator of type, then it is described by the data of the target indicator, the test result, the difference
And the target limit value inputs preparatory trained machine learning model together and is trained, and exports testing and debugging scheme, packet
It includes:
Obtain the corresponding trained machine learning model in advance of type of the target indicator；
The data of the target indicator, the test result, the difference and the target limit value are inputted into institute together
The corresponding trained machine learning model in advance of type for stating target indicator, exports testing and debugging scheme.
In a kind of exemplary embodiment of the disclosure, the training method of the machine learning model includes:
Collect in advance be marked how to adjust so that test result be by testing and debugging scheme include target indicator
Data, the test result, the difference and the target limit value sample set；
Sample each in the set of the sample is inputted into machine learning model respectively, adjustment machine learning model output is every
The corresponding testing and debugging scheme of a sample；
After having the sample input machine learning model, the output of machine learning model is corresponding with the sample
Testing and debugging scheme it is inconsistent, then adjust the coefficient of machine learning model until consistent；
After all samples input machine learning model, the output of machine learning model is corresponding with the sample
Testing and debugging scheme is consistent, and the training of machine learning model terminates.
It is described to judge whether the test result passes through in a kind of exemplary embodiment of the disclosure, wherein if the survey
Then test result is not pass through to test result except predetermined upper limit value and predetermined lower bound value, comprising:
From pre-set limit table, the data for obtaining the corresponding target indicator of the test result are corresponding described predetermined
Upper limit value and the predetermined lower bound value；
According to the predetermined upper limit value and the predetermined lower bound value, judge whether the test result passes through, wherein if institute
Stating test result, then test result is not pass through except predetermined upper limit value and predetermined lower bound value.
In a kind of exemplary embodiment of the disclosure, the method also includes:
From Adjusted Option record sheet, each possible sub- tune in the testing and debugging scheme of machine learning model output is obtained
The history selection rate of perfect square case；
Multiple sub- Adjusted Options that history selection rate is more than predetermined threshold are exported to user.
In a kind of exemplary embodiment of the disclosure, the method also includes:
The current version for obtaining the data analysis system is adjusted for first of the last revision before the current version
Whole target；
Obtain the second adjustment target of the testing and debugging scheme；
It is general according to the correctness of testing and debugging scheme described in the first adjustment target and the second adjustment Target Acquisition
Rate.
It is described according to the first adjustment target and the second adjustment target in a kind of exemplary embodiment of the disclosure
Obtain the probability of correctness of the testing and debugging scheme, comprising:
Obtain the corresponding adjustment influence function of the first adjustment target；
According to the regulation coefficient of adjustment variable each in Tuning function described in the second adjustment Target Acquisition；
According to the regulation coefficient and the adjustment influence function, the probability of correctness of the testing and debugging scheme is obtained.
According to one aspect of the disclosure, a kind of data analysis system consultation of doctors device is provided characterized by comprising
Test module, for when the test for receiving the data analysis system analyzed for the data to target indicator
When instruction, real-time testing is carried out to the data analysis system, and output test result；
Judgment module, for judging whether the test result passes through, wherein if the test result is in predetermined upper limit value
Except predetermined lower bound value, then test result is not pass through；
Module is obtained, if being not pass through for the test result, it is corresponding when not passing through for obtaining the test result
Target limit value in the predetermined upper limit value and the predetermined lower bound value calculates the test result beyond the target limit value
Difference；
Output module, for limiting the data of the target indicator, the test result, the difference and the target
Value inputs trained machine learning model in advance together, exports testing and debugging scheme, wherein the testing and debugging scheme is used for
Adjustment is indicated how so that test result is to pass through.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, data analysis system is stored thereon with
System consultation of doctors program, which is characterized in that the data analysis system consultation of doctors program realizes any of the above-described institute when being executed by processor
The method stated.
According to one aspect of the disclosure, a kind of electronic equipment is provided characterized by comprising
Processor；And
Memory, for storing the data analysis system consultation of doctors program of the processor；Wherein, the processor is configured to
Method described in any of the above embodiments is executed via the data analysis system consultation of doctors program is executed.
A kind of data analysis system consultation of doctors method and device of the disclosure, firstly, when receiving in the data to target indicator
The test for the data analysis system analyzed instructs, and carries out real-time testing to the data analysis system, and exports test knot
Fruit；Data analysis system analyzes the data of a type of index to obtain processing result, and test macro is in treatment process
Real-time testing obtains test result according to the calculating difference of processing result and scheduled benchmark result, realizes real-time testing.Judgement
Whether test result passes through, wherein test result is not lead to if test result is except predetermined upper limit value and predetermined lower bound value
It crosses；If test result illustrates occur inside data analysis system in this way beyond previously given reasonable predetermined threshold range
Problem, normal processing are will not to obtain the index value beyond the preset range.If test result is not pass through, test knot is obtained
Fruit does not pass through the difference of target limit value and test result beyond target limit value in corresponding predetermined upper limit value and predetermined lower bound value
Value；Test result is not by illustrating to need to hold a consultation to test result there are mistake inside data analysis system, test result
The case where beyond predetermined threshold range, can accurately guide different internal errors, by be more than described include predetermined upper limit value and
The predetermined upper limit value of the preset limit value range of predetermined lower bound value or the difference of predetermined lower bound value, can be accurate in conjunction with other data
Analyzed for the index, improve the accuracy rate of the consultation of doctors.By the data of target indicator, test result, difference and target
Limit value inputs preparatory trained machine learning model together, exports testing and debugging scheme, wherein testing and debugging scheme is for referring to
Show how to adjust so that test result is to pass through；By inputting the above-mentioned factor for being used to hold a consultation according to consultation of doctors factor sample training
How good machine learning model, can be automatic, accurate and be efficiently adjusted so that the scheme that test result passes through, effectively
Improve the efficiency solved the problems, such as.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of flow chart of data analysis system consultation of doctors method.
Fig. 2 schematically shows a kind of Application Scenarios-Example figure of data analysis system consultation of doctors method.
Fig. 3 schematically shows a kind of testing and debugging scheme accuracy acquisition methods flow chart.
Fig. 4 schematically shows a kind of block diagram of data analysis system consultation of doctors device.
Fig. 5 schematically shows a kind of electronic equipment example block diagram for realizing above-mentioned data analysis system consultation of doctors method.
Fig. 6 schematically shows a kind of computer-readable storage medium for realizing above-mentioned data analysis system consultation of doctors method
Matter.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Data analysis system consultation of doctors method, data analysis system consultation of doctors method are provided firstly in this example embodiment
Server can be run on, server cluster or Cloud Server etc. can also be run on, certainly, those skilled in the art can also be with
Method of the invention is run in other platforms according to demand, does not do particular determination to this in the present exemplary embodiment.With reference to Fig. 1 institute
Show, data analysis system consultation of doctors method may comprise steps of:
Step S110, when the test for receiving the data analysis system analyzed for the data to target indicator instructs
When, real-time testing is carried out to the data analysis system, and output test result；
Step S120, judges whether the test result passes through, wherein if the test result is in predetermined upper limit value and in advance
Except lower limit value, then test result is not pass through；
Step S130, if the test result is not pass through, it is corresponding described when not passing through for obtaining the test result
Target limit value in predetermined upper limit value and the predetermined lower bound value calculates the difference that the test result exceeds the target limit value
Value.
Step S140. is by the data of the target indicator, the test result, the difference and the target limit value one
It rises and inputs trained machine learning model in advance, export testing and debugging scheme, wherein the testing and debugging scheme is used to indicate
How to adjust so that test result is to pass through.
In above-mentioned data analysis system consultation of doctors method, firstly, being analyzed when receive in the data to target indicator
The test of data analysis system instructs, and carries out real-time testing to the data analysis system, and output test result；Data analysis
System analyzes the data of a type of index to obtain processing result, and test macro is in treatment process real-time testing, root
Test result is obtained according to the calculating difference of processing result and scheduled benchmark result, realizes real-time testing.Judging test result is
It is no to pass through, wherein test result is not pass through if test result is except predetermined upper limit value and predetermined lower bound value；Test result
If illustrating to there is a problem inside data analysis system in this way beyond previously given reasonable predetermined threshold range, normally
Processing is will not to obtain the index value beyond the preset range.If test result is not pass through, obtains test result and do not pass through pair
The difference of target limit value and test result beyond target limit value in predetermined upper limit value and predetermined lower bound value answered；Test knot
Fruit is not by illustrating to need to hold a consultation to test result there are mistake inside data analysis system, and test result is beyond predetermined
The case where threshold range, can accurately guide different internal errors, include predetermined upper limit value and predetermined lower bound by being more than described
The predetermined upper limit value of the preset limit value range of value or the difference of predetermined lower bound value can accurately be directed to this in conjunction with other data
Index is analyzed, and the accuracy rate of the consultation of doctors is improved.Together by the data of target indicator, test result, difference and target limit value
Trained machine learning model in advance is inputted, testing and debugging scheme is exported, wherein testing and debugging scheme is for indicate how adjust
It is whole so that test result be pass through；Pass through the machine that the above-mentioned factor input for being used to hold a consultation is good according to consultation of doctors factor sample training
How learning model, can be automatic, accurate and be efficiently adjusted so that the scheme that test result passes through, effectively improves solution
The efficiency of problem.
In the following, by conjunction with attached drawing to each step in data analysis system consultation of doctors method above-mentioned in this example embodiment into
The detailed explanation of row and explanation.
In step s 110, when the test for receiving the data analysis system analyzed for the data to target indicator
When instruction, real-time testing is carried out to the data analysis system, and output test result.
In this exemplary embodiment, refering to what is shown in Fig. 2, server 201 receives referring to target for the sending of server 202
The test for the data analysis system that target data are analyzed instructs, and then the test macro in server 201 analyzes data
System carries out real-time testing, outputs test result.Wherein, server 201 can be any equipment with processing capacity, example
Such as, computer, microprocessor etc., do not do particular determination herein, and server 202 can be any equipment with ability of issuing an order, example
Such as mobile phone, computer, do not do particular determination herein.
Data analysis system is analyzed and processed a kind of data of index, obtains processing result, is exactly entire data point
The process of analysis；Data analysis system is tested in entire treatment process using test macro, data analysis system can be obtained
The test result united to a kind of data of index in analysis treatment process；Test results system analyzes data
The processing result and a reference value of system are asked difference to obtain difference and are determined, data analysis system is logical to a kind of processing result of the data of index
Be often there are a reference value that one can characterize this results change situation, and while changing maintain it is a certain range of, in this way
The consultation of doctors of data analysis system internal problem can be carried out in the next steps using the test result.
Step S120, judges whether the test result passes through, wherein if the test result is in predetermined upper limit value and in advance
Except lower limit value, then test result is not pass through.
In this exemplary embodiment, whether what it is using test result is more than that predetermined upper limit value and the judgement of predetermined lower bound value are surveyed
Whether test result passes through；Carry out data analysis when would generally be directed to different indexs, such as a product core be concerned with it is assorted
? does is for another example it sales growth rate, occupation rate of market? sales growth rate, occupation rate of market are exactly a kind of index；When data are analyzed
By the data input data analysis system of the index of one of index, it is analyzed and processed to obtain one according to scheduled algorithm
It is a as a result, and this result is that in a certain range, that is, in certain threshold range, test macro is logical under normal circumstances
Real-time testing is crossed, result and the normality threshold of test macro output are compared according to scheduled rule, such as seek difference etc., such as
Fruit output result differ larger with certain threshold range, judge that test result does not pass through, it is on the contrary then by, for example, number
It is 50 to the result obtained after a kind of data analysis of index according to analysis system, a reference value 60, difference 10, and give predetermined
Threshold range is -2-5, then test result is more than upper limit value 5, and going beyond the scope is 5, and test result is not by illustrating data analysis system
There are mistakes for internal system of uniting, and cause processing result beyond preset range.
In step s 130, if the test result is not pass through, it is corresponding when not passing through for obtaining the test result
Target limit value in the predetermined upper limit value and the predetermined lower bound value calculates the test result beyond the target limit value
Difference.
In this exemplary embodiment, test macro is not pass through to the test result of data analysis system, illustrates data
There are problem inside analysis system, leading to test result is not pass through, and under normal conditions, a kind of data of index are by data point
When analysis system analysis processing, executed inside data analysis system by corresponding module or the program of corresponding part,
So the test result of different indexs is by with corresponding solution, and specific test result is more than described predetermined
The predetermined upper limit value of threshold range perhaps the difference of predetermined lower bound value the case where can reflect out further function or public affairs
Problem inside formula, for example, the excessive test result that may cause of some coefficient is more than upper limit value, and coefficient is too small is likely to result in
Test result is lower than lower limit value；Meanwhile test result is more than that the size of the difference of the limitation can accurately reflect and go wrong
Severity, for example, the coefficient of some function will lead to the difference more than corresponding threshold value when being more than certain threshold value.Institute
It is more than the predetermined threshold model including predetermined upper limit value and predetermined lower bound value to obtain specific test result by this step
The predetermined upper limit value enclosed or the difference for making a reservation for offline value can accurately guide detailed solution, effectively improve the consultation of doctors
Accuracy.
In step S140, the data of the target indicator, the test result, the difference and the target are limited
Value inputs trained machine learning model in advance together, exports testing and debugging scheme, wherein the testing and debugging scheme is used for
Adjustment is indicated how so that test result is to pass through.
In this exemplary embodiment, by one machine learning model of precondition, which is basis
Expert is in history according to the data of target indicator, test result, the difference and the corresponding preset limit value of the difference
How what (target limit value) was found adjusts so that the scheme training that test result passes through obtained；So by the number of target indicator
According to, the test result, the difference and the target as consultation of doctors factor input machine learning model, Ke Yizhun together
Really, it efficiently predicts and how to adjust so that test result scheme.It in this way can be inefficient, low accurate to avoid artificial lookup bring
Rate problem.
In a kind of originally exemplary embodiment, it has been respectively trained according to different types of target indicator corresponding to inhomogeneity
The machine learning model of the target indicator of type, then it is described by the data of the target indicator, the test result, the difference with
And the target limit value inputs preparatory trained machine learning model together and is trained, and exports testing and debugging scheme, comprising:
Obtain the corresponding trained machine learning model in advance of type of the target indicator；
The data of the target indicator, the test result, the difference and the target limit value are inputted into institute together
The corresponding trained machine learning model in advance of type for stating target indicator, exports testing and debugging scheme.
According to different types of target indicator, the machine learning mould of the multiple target indicators corresponding to different types of training
Type, such training can make machine learning model have specific aim, and how output adjusts so that the side that test result passes through
Case is more accurate, training machine learning model it is more efficient.
In a kind of originally exemplary embodiment, have according to the training of all types of target indicators corresponding to all types of
The machine learning model of target indicator, then it is described by the data of the target indicator, the test result, the difference and institute
It states target limit value and inputs preparatory trained machine learning model together and be trained, export testing and debugging scheme, comprising:
Obtain the machine learning model for corresponding to all types of target indicators；
The data of the target indicator, the test result, the difference and the target limit value are inputted into institute together
The corresponding trained machine learning model in advance of type for stating target indicator, exports testing and debugging scheme.
It is suitable for the machine learning model of all types of target indicators by training, it, can when test result is obstructed out-of-date
With directly by the data of target indicator, the index value, the difference and the corresponding predetermined upper limit value of the difference or under
Limit value inputs machine learning model, and how output adjusts so that the scheme that test result passes through, can effectively save cost in this way,
Only with a machine learning model.
In a kind of originally exemplary embodiment, the training method of the machine learning model includes:
Collect in advance be marked how to adjust so that test result be by testing and debugging scheme include target indicator
Data, the test result, the difference and the target limit value sample set；
Sample each in the set of the sample is inputted into machine learning model respectively, adjustment machine learning model output is every
The corresponding testing and debugging scheme of a sample；
After having the sample input machine learning model, the output of machine learning model is corresponding with the sample
Testing and debugging scheme it is inconsistent, then adjust the coefficient of machine learning model until consistent；
After all samples input machine learning model, the output of machine learning model is corresponding with the sample
Testing and debugging scheme is consistent, and the training of machine learning model terminates.
The data of target indicator, the test result, the difference and target limit value can be accurate as consultation of doctors element
Guidance system internal data handle the problem, by history according to these consultation of doctors elements as input sample,
The scheme of corresponding solution accurately exports sample labeling according to the sample of input as sample labeling, training machine learning model,
The accuracy of machine mould can be effectively ensured.
It is described to judge whether the test result passes through, wherein if the test in a kind of originally exemplary embodiment
As a result then test result is not pass through except predetermined upper limit value and predetermined lower bound value, comprising:
From pre-set limit table, the data for obtaining the corresponding target indicator of the test result are corresponding described predetermined
Upper limit value and the predetermined lower bound value；
According to the predetermined upper limit value and the predetermined lower bound value, judge whether the test result passes through, wherein if institute
Stating test result, then test result is not pass through except predetermined upper limit value and predetermined lower bound value.
Had recorded in pre-set limit table the data of all indexs data area and it is corresponding with data area it is predetermined on
Limit value and predetermined lower bound value.It in this way can be with according to the data area where the size of the data of the corresponding target indicator of test result
The corresponding predetermined upper limit value of data and predetermined lower bound value of target indicator are accurately found from pre-set limit table.Then, root
According to predetermined upper limit value and the predetermined lower bound value, judge whether test result is located at predetermined upper limit value and the predetermined lower bound value
Except range, and then when test result then can be to test result with accurate judgement except predetermined upper limit value and predetermined lower bound value
Do not pass through.It can be convenient, accurately adjust in limit value table predetermined upper limit value and predetermined as the case may be by pre-set limit table
The size of the data such as lower limit value.
In a kind of originally exemplary embodiment, the method also includes:
From Adjusted Option record sheet, each possible sub- tune in the testing and debugging scheme of machine learning model output is obtained
The history selection rate of perfect square case；
Multiple sub- Adjusted Options that history selection rate is more than predetermined threshold are exported to user.
The data such as the number that each testing and debugging scheme is easily selected by a user are had recorded in Adjusted Option record sheet.Machine learning
The testing and debugging scheme of model output can be at least one, such as output includes the test tune of 5 possible sub- Adjusted Options
Perfect square case.Then, it is chosen by the number that each possible sub- Adjusted Option is selected divided by all possible sub- Adjusted Option
The number selected obtains the history selection rate of every sub- Adjusted Option.Selection rate height illustrates that the frequency that the solution is adopted is high,
The high scheme of selection rate is exported, can effectively help user quickly to position and ask by the namely high solution of customer acceptance rate
Topic improves testing efficiency.
In a kind of originally exemplary embodiment, refering to what is shown in Fig. 3, the method also includes:
Step 310, the current version of the data analysis system is obtained for the last revision before the current version
The first adjustment target；
Step 320, the second adjustment target of the testing and debugging scheme is obtained；
Step 330, according to the first adjustment target and second adjustment Target Acquisition testing and debugging scheme
Probability of correctness.
Current version is exactly the data point of current version for the first adjustment target of the last revision before current version
The effect of promotion or change that analysis system needs to obtain after improvement relative to last revision.The effect is usually by multiple sons
What change collectively constituted, so the first adjustment target may include multiple first son adjustment targets.Meanwhile testing and debugging scheme
It is the scheme improved to data analysis system, can also obtains improved effect, that is, second adjustment target.In this way,
According to, to the degree for deviating from or promoting, can reflect out testing and debugging scheme between the first adjustment target and second adjustment target
Probability of correctness.In a kind of example, can by can represent adjustment target in advance for the first adjustment target designation first
Target fractional, while the second target fractional of adjustment target can be represented for second adjustment target designation in advance, then by the
The ratio of difference and the sum of first object score and the second target fractional between one target fractional and the second target fractional carries out
The numerical value between 1 to 10 is normalized to, the probability of correctness of testing and debugging scheme is obtained.All how to adjust so that testing exported
As a result how output adjusts the probability of correctness so that the scheme that test result passes through while the scheme passed through, in this way can be clear
The help tester of Chu understands the accuracy situation of all scheme and scheme, user can according to accuracy combination experience into
Row selection solution.
It is described to be obtained according to the first adjustment target and the second adjustment target in a kind of originally exemplary embodiment
Take the probability of correctness of the testing and debugging scheme, comprising:
Obtain the corresponding adjustment influence function of the first adjustment target；
According to the regulation coefficient of adjustment variable each in Tuning function described in the second adjustment Target Acquisition；
According to the regulation coefficient and the adjustment influence function, the probability of correctness of the testing and debugging scheme is obtained.
The corresponding adjustment influence function of the first adjustment target is exactly the data analysis system of current version relative to upper one edition
This needs represents the adjustment shadow of the adjustment variable of each improvement or variation and the unknowm coefficient composition of each variable when improving
Ring function.The adjustment variable for representing each improvement or variation can change according to preset each of the data analysis system that is stored with
It is obtained in the corresponding adjustment argument table of dynamic influence.The unknowm coefficient of each variable then can be according to second adjustment target, from depositing
It contains when being changed to obtain second adjustment target to the part in the first adjustment target, the secondary change of generation becomes first time
It is obtained in dynamic influence coefficient table, that is, to the regulation coefficient of Partial Variable.Then, by by regulation coefficient assignment to adjustment
Corresponding variable part in influence function, can be accurately obtained the probability of correctness of testing and debugging scheme.
The disclosure additionally provides a kind of data analysis system consultation of doctors device.Refering to what is shown in Fig. 4, the data analysis system is held a consultation
Device may include test module 410, judgment module 420, obtain module 430 and output module 440.Wherein:
Test module 410, which can be used for working as, receives the data analysis system analyzed for the data to target indicator
Test instruction when, real-time testing is carried out to the data analysis system, and is outputed test result；
Judgment module 420 can be used for judging whether the test result passes through, wherein if the test result is predetermined
Except upper limit value and predetermined lower bound value, then test result is not pass through；
If obtaining module 430 to can be used for the test result is not pass through, obtaining the test result is when not passing through
Target limit value in the corresponding predetermined upper limit value and the predetermined lower bound value calculates the test result beyond the target
The difference of limit value；
Output module 440 can be used for the data of the target indicator, the test result, the difference and described
Target limit value inputs preparatory trained machine learning model together, exports testing and debugging scheme, wherein the testing and debugging side
Case is for indicate how adjust so that test result is to pass through.
The detail of each module is in corresponding data analysis system meeting in above-mentioned data analysis system consultation of doctors device
It examines in method and is described in detail, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Fig. 5.The electronics that Fig. 5 is shown
Equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in fig. 1: working as reception
To the data analysis system analyzed for the data to target indicator test instruction when, to the data analysis system into
Row real-time testing, and output test result；S120: judge whether the test result passes through, wherein if the test result exists
Except predetermined upper limit value and predetermined lower bound value, then test result is not pass through；Step S130: if the test result is not lead to
Cross, obtain the test result be not by when the corresponding predetermined upper limit value and the predetermined lower bound value in target limit
Value calculates the difference that the test result exceeds the target limit value；Step S140: by data of the target indicator, described
Test result, the difference and the target limit value input preparatory trained machine learning model together, and output test is adjusted
Perfect square case, wherein the testing and debugging scheme is for indicate how adjust so that test result is to pass through.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment that also client can be enabled interact with the electronic equipment 500 with one or more communicates, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 6, describing the program product for realizing the above method of embodiment according to the present invention
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in client
It calculates and executes in equipment, partly executes on the client device, being executed as an independent software package, partially in client's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to client computing device, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
- A kind of method 1. data analysis system is held a consultation characterized by comprisingWhen the test for receiving the data analysis system analyzed for the data to target indicator instructs, to the data Analysis system carries out real-time testing, and outputs test result；Judge whether the test result passes through, wherein if the test result except predetermined upper limit value and predetermined lower bound value, Then test result is not pass through；If the test result is not pass through, the corresponding predetermined upper limit value and institute when obtaining the test result not pass through The target limit value in predetermined lower bound value is stated, the difference that the test result exceeds the target limit value is calculated；The data of the target indicator, the test result, the difference and the target limit value are inputted into preparatory instruction together The machine learning model perfected, export testing and debugging scheme, wherein the testing and debugging scheme for indicate how adjustment so that Test result is to pass through.
- 2. the method according to claim 1, wherein correspondence has been respectively trained according to different types of target indicator It is in the machine learning model of different types of target indicator, then described by the data of the target indicator, the test result, institute It states difference and the target limit value inputs preparatory trained machine learning model together and is trained, export testing and debugging side Case, comprising:Obtain the corresponding trained machine learning model in advance of type of the target indicator；The data of the target indicator, the test result, the difference and the target limit value are inputted into the mesh together The corresponding trained machine learning model in advance of type for marking index, exports testing and debugging scheme.
- 3. the method according to claim 1, wherein the training method of the machine learning model includes:Collect in advance be marked how to adjust so that test result be by testing and debugging scheme the number including target indicator According to the set of the, sample of the test result, the difference and the target limit value；Sample each in the set of the sample is inputted into machine learning model respectively, adjustment machine learning model exports each institute State the corresponding testing and debugging scheme of sample；After having the sample input machine learning model, the output of machine learning model survey corresponding with the sample It is inconsistent to try Adjusted Option, then adjusts the coefficient of machine learning model until consistent；After all samples input machine learning model, the output of machine learning model test corresponding with the sample Adjusted Option is consistent, and the training of machine learning model terminates.
- 4. judging whether the test result passes through the method according to claim 1, wherein described, wherein if The test result is except predetermined upper limit value and predetermined lower bound value, then test result is not pass through, comprising:From pre-set limit table, the corresponding predetermined upper limit of data of the corresponding target indicator of the test result is obtained Value and the predetermined lower bound value；According to the predetermined upper limit value and the predetermined lower bound value, judge whether the test result passes through, wherein if the survey Test result is except predetermined upper limit value and predetermined lower bound value, then test result is not pass through.
- 5. the method according to claim 1, wherein the method also includes:From Adjusted Option record sheet, every a sub- Adjusted Option is gone through in the testing and debugging scheme of acquisition machine learning model output History selection rate；Multiple sub- Adjusted Options that history selection rate is more than predetermined threshold are exported to user.
- 6. the method according to claim 1, wherein the method also includes:Obtain the first adjustment mesh of the current version for the last revision before the current version of the data analysis system Mark；Obtain the second adjustment target of the testing and debugging scheme；According to the probability of correctness of testing and debugging scheme described in the first adjustment target and the second adjustment Target Acquisition.
- 7. according to the method described in claim 6, it is characterized in that, it is described according to the first adjustment target and it is described second adjust The probability of correctness of testing and debugging scheme described in whole Target Acquisition, comprising:Obtain the corresponding adjustment influence function of the first adjustment target；According to the regulation coefficient of adjustment variable each in Tuning function described in the second adjustment Target Acquisition；According to the regulation coefficient and the adjustment influence function, the probability of correctness of the testing and debugging scheme is obtained.
- The device 8. a kind of data analysis system is held a consultation characterized by comprisingTest module, for when the test instruction for receiving the data analysis system analyzed for the data to target indicator When, real-time testing is carried out to the data analysis system, and output test result；Judgment module, for judging whether the test result passes through, wherein if the test result is in predetermined upper limit value and in advance Then test result is not pass through except lower limit value；Obtain module, if being not pass through for the test result, obtain the test result do not pass through it is corresponding described predetermined Upper limit value and the difference of target limit value and the test result beyond the target limit value in the predetermined lower bound value；Output module, for by the data of the target indicator, the test result, the difference and the target limit value one It rises and inputs trained machine learning model in advance, export testing and debugging scheme, wherein the testing and debugging scheme is used to indicate How to adjust so that test result is to pass through.
- 9. a kind of computer readable storage medium is stored thereon with data analysis system consultation of doctors program, which is characterized in that the number The described in any item methods of claim 1-7 are realized when being executed by processor according to analysis system consultation of doctors program.
- 10. a kind of electronic equipment characterized by comprisingProcessor；AndMemory, for storing the data analysis system consultation of doctors program of the processor；Wherein, the processor be configured to via It executes the data analysis system consultation of doctors program and carrys out the perform claim requirement described in any item methods of 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436034.8A CN110347583A (en) | 2019-05-23 | 2019-05-23 | A kind of data analysis system consultation of doctors method and relevant apparatus |
| PCT/CN2019/103442 WO2020232899A1 (en) | 2019-05-23 | 2019-08-29 | Troubleshooting method for data analysis system, and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436034.8A CN110347583A (en) | 2019-05-23 | 2019-05-23 | A kind of data analysis system consultation of doctors method and relevant apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110347583A true CN110347583A (en) | 2019-10-18 |
Family
ID=68174261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910436034.8A Pending CN110347583A (en) | 2019-05-23 | 2019-05-23 | A kind of data analysis system consultation of doctors method and relevant apparatus |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110347583A (en) |
| WO (1) | WO2020232899A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114817064A (en) * | 2022-05-20 | 2022-07-29 | 国网数字科技控股有限公司 | Automatic judgment method and device for safety test result |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893256A (en) * | 2016-03-30 | 2016-08-24 | 西北工业大学 | Software failure positioning method based on machine learning algorithm |
| CN107195186A (en) * | 2017-06-07 | 2017-09-22 | 千寻位置网络有限公司 | The method and system of Automatic Optimal crossing vehicle pass-through speed |
| CN107822617A (en) * | 2017-10-23 | 2018-03-23 | 上海百芝龙网络科技有限公司 | A kind of heart rate method for detecting abnormality based on WiFi signal |
| CN107885503A (en) * | 2017-11-11 | 2018-04-06 | 湖南大学 | A kind of iteration based on performance of program analysis compiles optimization method |
| US20180150742A1 (en) * | 2016-11-28 | 2018-05-31 | Microsoft Technology Licensing, Llc. | Source code bug prediction |
| CN108494602A (en) * | 2018-04-08 | 2018-09-04 | 上海鸿洛通信电子有限公司 | Method of adjustment, device and the intelligent terminal of OTA parameters |
| CN109222208A (en) * | 2018-10-30 | 2019-01-18 | 杭州安脉盛智能技术有限公司 | Technology for making tobacco threds analysis optimization method and system towards production of cigarettes norm controlling |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7533369B2 (en) * | 2004-03-15 | 2009-05-12 | Ramco Systems Limited | Method and system for providing documentation and training in a software development activity |
| CN102841835B (en) * | 2012-06-07 | 2015-09-30 | 腾讯科技（深圳）有限公司 | The method and system of hardware performance evaluation and test |
| CN105045713B (en) * | 2015-07-14 | 2018-02-13 | 腾讯科技（深圳）有限公司 | Data processing method and mobile terminal |
| CN109426700B (en) * | 2017-08-28 | 2023-04-25 | 腾讯科技（北京）有限公司 | Data processing method, data processing device, storage medium and electronic device |
| CN107766299B (en) * | 2017-10-24 | 2021-05-18 | 携程旅游信息技术（上海）有限公司 | Data index abnormity monitoring method and system, storage medium and electronic equipment |
| CN109389329A (en) * | 2018-11-13 | 2019-02-26 | 平安科技（深圳）有限公司 | Test performance prediction technique, device, medium and the electronic equipment of test macro |
| CN109783332B (en) * | 2018-12-12 | 2022-05-17 | 平安科技（深圳）有限公司 | Server warning method and system based on data modeling |
| CN110083452A (en) * | 2019-04-26 | 2019-08-02 | 深信服科技股份有限公司 | A kind of method for managing resource, system and electronic equipment and storage medium |
-
2019
- 2019-05-23 CN CN201910436034.8A patent/CN110347583A/en active Pending
- 2019-08-29 WO PCT/CN2019/103442 patent/WO2020232899A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893256A (en) * | 2016-03-30 | 2016-08-24 | 西北工业大学 | Software failure positioning method based on machine learning algorithm |
| US20180150742A1 (en) * | 2016-11-28 | 2018-05-31 | Microsoft Technology Licensing, Llc. | Source code bug prediction |
| CN107195186A (en) * | 2017-06-07 | 2017-09-22 | 千寻位置网络有限公司 | The method and system of Automatic Optimal crossing vehicle pass-through speed |
| CN107822617A (en) * | 2017-10-23 | 2018-03-23 | 上海百芝龙网络科技有限公司 | A kind of heart rate method for detecting abnormality based on WiFi signal |
| CN107885503A (en) * | 2017-11-11 | 2018-04-06 | 湖南大学 | A kind of iteration based on performance of program analysis compiles optimization method |
| CN108494602A (en) * | 2018-04-08 | 2018-09-04 | 上海鸿洛通信电子有限公司 | Method of adjustment, device and the intelligent terminal of OTA parameters |
| CN109222208A (en) * | 2018-10-30 | 2019-01-18 | 杭州安脉盛智能技术有限公司 | Technology for making tobacco threds analysis optimization method and system towards production of cigarettes norm controlling |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020232899A1 (en) | 2020-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409533B (en) | Method, device, equipment and storage medium for generating machine learning model | |
| CN109241418A (en) | Abnormal user recognition methods and device, equipment, medium based on random forest | |
| CN109446071A (en) | Interface test method, interface test device, electronic equipment and storage medium | |
| CN109669853A (en) | Test report generation method and device, storage medium, electric terminal | |
| EP3441891A1 (en) | Data source-based service customisation apparatus, method, system, and storage medium | |
| CN103309793B (en) | The method and system of ranking analysis instrument | |
| CN109523752A (en) | A kind of equipment fault early-warning method, apparatus, electronic equipment and medium | |
| CN110147317A (en) | Code test method and device, electronic equipment and storage medium | |
| CN109871315A (en) | The diagnostic method and device of system upgrade failure based on machine learning | |
| CN109871311A (en) | A kind of method and apparatus for recommending test case | |
| CN109857431A (en) | Code revision method and device, computer-readable medium and electronic equipment | |
| CN110109824A (en) | Big data automatic regression test method, apparatus, computer equipment and storage medium | |
| CN111383100A (en) | Risk model-based full life cycle management and control method and device | |
| CN115086148B (en) | Optical network alarm processing method, system, equipment and storage medium | |
| CN110473098A (en) | Company's equity data processing method and device | |
| CN109684172A (en) | Log method for pushing, system, equipment and storage medium based on access frequency | |
| CN114638442A (en) | Flight training scheme generation system, method and equipment for individual difference | |
| CN110347583A (en) | A kind of data analysis system consultation of doctors method and relevant apparatus | |
| CN114360581A (en) | Method and device for identifying equipment fault and electronic equipment | |
| CN108629355A (en) | Method and apparatus for generating workload information | |
| CN109389329A (en) | Test performance prediction technique, device, medium and the electronic equipment of test macro | |
| CN110717315B (en) | System data batch modification method and device, storage medium and electronic equipment | |
| CN112785111A (en) | Production efficiency prediction method, device, storage medium and electronic equipment | |
| CN116301916A (en) | Service deployment method, device, electronic equipment and storage medium | |
| CN113590484B (en) | Algorithm model service testing method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |