CN110096391A - A kind of life forecast method, apparatus and equipment - Google Patents
A kind of life forecast method, apparatus and equipment Download PDFInfo
- Publication number
- CN110096391A CN110096391A CN201810082569.5A CN201810082569A CN110096391A CN 110096391 A CN110096391 A CN 110096391A CN 201810082569 A CN201810082569 A CN 201810082569A CN 110096391 A CN110096391 A CN 110096391A
- Authority
- CN
- China
- Prior art keywords
- data
- relationship
- time
- point
- writing
- 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
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2268—Logging of test results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
Abstract
The application provides a kind of life forecast method, apparatus and equipment, this method comprises: according to multiple use times of certain device, corresponding life parameter of the multiple use time, construct the first data relationship, wherein first data relationship includes multiple data points;The selection target data point from multiple data points of first data relationship;Life parameter is determined using the number of targets strong point and using the corresponding relationship of time;The service life of the certain device is predicted using determining corresponding relationship.By the technical solution of the application, the service life end time can be just perceived before the service life of certain device terminates, then carry out the operation such as Data Migration in advance, avoid loss of data or unavailable.
Description
Technical field
This application involves Internet technical field, especially a kind of life forecast method, apparatus and equipment.
Background technique
The performance of SSD (Solid State Drives, solid state hard disk) be significantly better than HDD (Hard Disk Drive, firmly
Disk drive), if IOPS (Input/Output Operations Per Second, the number of read-write I/O per second) is HDD
Hundred times, therefore be used widely, especially DB (Database, database)/RDS (Relational Database
Service, relevant database service) etc. application scenarios, largely use SSD.
With the increase of data writing, the service life of SSD is reduced, and at the end of service life, is stored in the number of SSD
According to can lose or unavailable.Therefore, it is necessary to before the useful life is complete, just perceive the service life end time, then
The operation such as Data Migration is carried out in advance, avoids loss of data or unavailable.
Summary of the invention
The application provides a kind of life forecast method, which comprises
According to multiple use times of certain device, corresponding life parameter of the multiple use time, the first number of construction
According to relationship, wherein first data relationship includes multiple data points;
The selection target data point from multiple data points of first data relationship;
Life parameter is determined using the number of targets strong point and using the corresponding relationship of time;
The service life of the certain device is predicted using determining corresponding relationship.
The application provides a kind of life forecast device, and described device includes:
Module is obtained, for joining according to multiple use times, the multiple use time in the corresponding service life of certain device
Number constructs the first data relationship, wherein first data relationship includes multiple data points;
Selecting module, for the selection target data point from multiple data points of first data relationship;
Determining module, for determining life parameter using number of targets strong point and using the corresponding relationship of time;
Prediction module, for predicting the service life of the certain device using determining corresponding relationship.
The application provides a kind of life forecast equipment, and the life forecast equipment includes:
Processor, for using times, corresponding life parameter of the multiple use time according to the multiple of certain device,
Construct the first data relationship, wherein first data relationship includes multiple data points;
The selection target data point from multiple data points of first data relationship;
Life parameter is determined using the number of targets strong point and using the corresponding relationship of time;
The service life of the certain device is predicted using determining corresponding relationship.
It based on the above-mentioned technical proposal, can be corresponding according to multiple use times, multiple use times in the embodiment of the present application
Life parameter (such as attrition value or writing) construct the first data relationship, and from multiple data points of the first data relationship
Selection target data point is determined life parameter using number of targets strong point and is closed using the corresponding relationship of time, and using the correspondence
The service life of system's prediction certain device.In this way, can just perceive before the service life of certain device terminates using the longevity
The end time is ordered, the operation such as Data Migration is then carried out in advance, avoids loss of data or unavailable.Moreover, not being to utilize institute
There are data to predict service life, but utilize target data point prediction service life, in this way, can be based on meeting recent business field
The data of scape predict service life, and the prediction error of service life is smaller, and prediction result is accurate and reliable.
Detailed description of the invention
It, below will be to the application in order to clearly illustrate the embodiment of the present application or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is only some embodiments as described in this application, for those of ordinary skill in the art, can also be according to this Shen
Please these attached drawings of embodiment obtain other attached drawings.
Fig. 1 is the flow chart of the life forecast method in a kind of embodiment of the application;
Fig. 2A-Fig. 2 C is the training relation schematic diagram in a kind of embodiment of the application;
Fig. 3 is the flow chart of the life forecast method in the application another embodiment;
Fig. 4 is the flow chart of the life forecast method in the application another embodiment;
Fig. 5 is the structure chart of the life forecast device in a kind of embodiment of the application.
Specific embodiment
In term used in this application merely for the sake of for the purpose of describing particular embodiments, rather than limit the application.This Shen
Please it is also intended to the "an" of singular used in claims, " described " and "the" including most forms, unless
Context clearly shows that other meanings.It is also understood that term "and/or" used herein refers to comprising one or more
Associated any or all of project listed may combine.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, in addition, used word " if " can be construed to " ... when " or " when ... "
Or " in response to determination ".
The embodiment of the present application proposes that a kind of life forecast method, this method can be applied to life forecast and set
Standby, which can be server, PC (Personal Computer, personal computer), notebook electricity
Brain, mobile terminal etc., with no restrictions to the type of this life forecast equipment.
Wherein, which is used to predict that the service life of certain device, the certain device to may include
But it is not limited to: solid state hard disk (i.e. SSD).Certainly, the certain device can also (Hybrid Hard Drive be mixed for HDD, HHD
Close hard disk), CPU (Central Processing Unit, central processing unit), memory etc., the type of this certain device is not done
Limitation, is illustrated by taking solid state hard disk as an example herein.
Before introducing the life forecast method, following concept related with the embodiment of the present application is first introduced:
1, attrition value, when needing to predict the service life of solid state hard disk, attrition value is solid state hard disk attrition value.
When data are written into solid state hard disk, a degree of abrasion, the data volume of write-in can be caused to solid state hard disk
Bigger, then higher to the degree of wear of solid state hard disk, the service life of solid state hard disk is also shorter.Therefore, it is possible to use attrition value
It indicates the degree of wear of solid state hard disk, then assesses the service life of solid state hard disk.
For example, the attrition value of completely new solid state hard disk is 100 (such as 100%), indicates that solid state hard disk does not generate abrasion, wear journey
Degree is 0.With the use of solid state hard disk, after data are written into solid state hard disk, if the attrition value of solid state hard disk is reduced to 60
(such as 60%) indicates that solid state hard disk has generated abrasion, the degree of wear 40.With continuing to use for solid state hard disk, to admittedly
After data are written in state hard disk, if the attrition value of solid state hard disk is reduced to 0 (such as 0%), indicate that solid state hard disk is unavailable, Gu
Data in state hard disk can lose.
In one example, it is operated to carry out Data Migration etc. in advance, avoids the loss of data in solid state hard disk, it will not
After the attrition value of solid state hard disk is reduced to 0, migrating data is just gone.Based on this, a default attrition value can be set, it is pre- to this
If attrition value is with no restrictions, can rule of thumb it be configured, such as default attrition value can be 1 (such as 1%), 3,5,8.Solid
After the attrition value of state hard disk is reduced to default attrition value, data are no longer written into solid state hard disk, to the data in solid state hard disk
It carries out the operation such as migrating.That is, solid state hard disk uses the longevity after the attrition value of solid state hard disk is reduced to default attrition value
Life terminates.
2, service life, by taking the service life for predicting solid state hard disk as an example, then service life indicates that solid state hard disk can be with
Using how long, i.e., always use time and currently used time difference.For example, solid state hard disk attrition value be reduced to it is default
When attrition value, solid state hard disk can also use how long.Assuming that when the attrition value of solid state hard disk is reduced to default attrition value, Gu
The total of state hard disk using the time is 2000 hours, and the currently used time of solid state hard disk is 1500 hours, then solid state hard disk
Service life can be 500 hours.That is, the attrition value of the solid state hard disk reduces after solid state hard disk reuses 500 hours
To default attrition value.
3, writing (i.e. data writing), when needing to predict the service life of solid state hard disk, then writing is solid-state
The writing of hard disk, i.e. writing can be the total quantity that data are written into solid state hard disk.
When data are written into solid state hard disk, a degree of abrasion can be caused to solid state hard disk, solid state hard disk is write
Enter that amount is bigger, then higher to the degree of wear of solid state hard disk, the service life of solid state hard disk is also shorter.
In general, the writing of solid state hard disk and the attrition value of solid state hard disk are in a linear relationship, for example, every to solid
The data of 1000M are written in state hard disk, and when leading to the attrition value of solid state hard disk reduces by 1, then writing 0 is corresponding with attrition value 100, writes
Enter amount 1000M corresponding with attrition value 99, writing 2000M and attrition value 98 correspond to, writing 3000M and attrition value 97 are corresponded to,
And so on, details are not described herein.
4, inflection point, the i.e. splice point of the different straight line of two slope over 10.For example, in sequence, successively there is point 1- point 5,
3 groups in alignment 1 of postulated point 1- point, 5 groups in alignment 2 of point 3- point, and the slope of straight line 1 is different from the slope of straight line 2,
The splice point (putting 3) of this two straight lines is exactly an inflection point.
It is shown in Figure 1 based on above-mentioned application scenarios, it is the process of the life forecast method in the embodiment of the present application
Figure, this method are used to predict that the service life of certain device, this method to may include:
Step 101, according to multiple use times of certain device, corresponding life parameter of the multiple use time, structure
Make the first data relationship, wherein first data relationship includes multiple data points.
Step 102, the selection target data point from multiple data points of first data relationship.
Step 103, life parameter is determined using number of targets strong point and use the corresponding relationship of time.
Step 104, the service life of the certain device is predicted using determining corresponding relationship.
In one example, above-mentioned execution sequence is intended merely to facilitate description to provide example, in practical applications,
Sequence is executed between can also changing the step, with no restrictions to this execution sequence.Moreover, in other embodiments, and it is different
The fixed sequence for showing and describing according to this specification is come the step of executing correlation method, step included by method can be than this
It is more or less described in specification.In addition, single step described in this specification, it in other embodiments may quilt
Multiple steps are decomposed into be described;Multiple steps described in this specification may also be merged into other embodiments
Single step is described.
In one example, life parameter (such as attrition value or writing) can be constructed to close with using the corresponding of time
System, the service life based on this corresponding relationship prediction certain device.It is Fixed disk with certain device, life parameter is abrasion
It is attrition value and the corresponding relationship using the time referring to fig. 2 shown in A for value.
In fig. 2, the attrition value of each data point can be known based on historical data and using the time, is based on each data point
Straight line shown in Fig. 2A can be simulated, the slope based on this straight line, so that it may determine attrition value and pair using the time
It should be related to.For example, attrition value from 100 be reduced to 5 when, the use of the time is 1300 hours, therefore, attrition value is every to reduce by 1, when use
Between increase by 13.7 hours.Based on this, attrition value and the corresponding relationship using the time can be determined, such as attrition value 100 and use
Time 0 is corresponding, and attrition value 99 is corresponding with using 13.7 hours time, and attrition value 98 is corresponding with using 27.4 hours time, with this
Analogize.
It as can be seen from Figure 2A, always the use of the time is 1300 hours when attrition value is reduced to default attrition value 5 from 100,
The currently used time is 1000 hours, and therefore, the service life of solid state hard disk is 300 hours.
In the above-described embodiments, be go out straight line shown in Fig. 2A using all digital simulations, with the proviso that attrition value with make
Be linear relationship with the time, still, from Fig. 2A as can be seen that attrition value with the use of the time is not linear relationship, therefore, base
It is inaccurate in the service life (i.e. 300 hours) that aforesaid way determines.
Wherein, attrition value is with the reason of not being linear relationship using the time: assuming that business A was executed at 0-300 hours,
Speed to solid state hard disk write-in data is slower, and at -375 hours 300 hours, business B is executed, data are written to solid state hard disk
Fast speed, therefore, 0-300 hours attrition values and the corresponding relationship using the time, the abrasion with -375 hours 300 hours
For value with using the corresponding relationship of time, the two is not linear relationship.Similarly, -375 hours 300 hours attrition values and use
The corresponding relationship of time and -500 hours 375 hours attrition values and the corresponding relationship using the time, the two is not linearly to close
System, and so on.
In conclusion since the premise of aforesaid way is attrition value and uses the time for linear relationship, but business on line
Variation and load variation, will lead to attrition value and the use of the time be not linear relationship, it is therefore, pre- using aforesaid way
When surveying the service life of solid state hard disk, prediction result can be deviated.
For above-mentioned discovery, in the embodiment of the present application, propose that a kind of linear model based on inflection point (attrition value and uses
The linear relationship of time), the data for meeting recent business scenario can be obtained from historical data, and use meets recent business
The data building linear model of scene is (it is of course also possible to be other types of model, as long as can provide attrition value and use
Between corresponding relationship, without limitation, be illustrated by taking linear model as an example), rather than use all historical datas
It constructs linear model (shown in Fig. 2A).
Wherein it is possible to meet the data of recent business scenario based on inflection point discovery, i.e., the last one inflection point (its from it is current when
Carve a nearest inflection point) after data, be the data for meeting recent business scenario, therefore, can be by the last one inflection point
Data later are as training sample, to construct attrition value and using the linear relationship of time, and using this attrition value with make
With the linear relationship of time, the service life of solid state hard disk is predicted.
Wherein, by service impact, attrition value with using that can have multiple inflection points in the relationship of time, as time goes by and
The variation of business write-in characteristic, certainly will will appear new inflection point, and that one piece of data after inflection point, be within the scope of certain time
Therefore existing linear relationship can capture the last one inflection point, then using the data after the last one inflection point as training sample
This, to construct attrition value and using the linear relationship of time.
Referring to fig. 2 shown in B, the attrition value of each data point can be known based on historical data and using time, each data
Point means that an attrition value and the corresponding relationship using the time.In fig. 2b, the slope based on straight line between each data point, can
To find inflection point from all data points, such as data point 3, data point 4, data point 5, data point 6, data point 7, then from these
The last one inflection point, i.e. data point 7 are found in inflection point.
It is then possible to using the data (such as data point 7, data point 8, data point 9, data point 10) after data point 7, simulation
Straight line shown in Fig. 2 B (straight line being made of data point 7, data point 8, data point 9, data point 10) out, this straight line and number
All data points before strong point 7 are not related.
Slope based on this straight line, can determine attrition value with using the time corresponding relationship (i.e. attrition value with make
With the linear relationship of time).For example, attrition value from 35 be reduced to 5 when, using the time be 300 hours, therefore, the every drop of attrition value
Low 1, increased by 10 hours using the time.Based on this, attrition value and the corresponding relationship using the time can be determined, such as attrition value 35
Corresponding with 850 hours time is used, attrition value 34 is corresponding with the 860 hours time of use, attrition value 33 and the use time 870 hours
It is corresponding, and so on.
It as can be seen from Figure 2B, always the use of the time is 1150 hours when attrition value is reduced to default attrition value 5 from 100,
The currently used time is 1000 hours, and therefore, the service life of solid state hard disk is 150 hours.
In the above-described embodiments, it is to go out straight line shown in Fig. 2 B using the digital simulation after the last one inflection point, is based on
The error range for the service life (i.e. 150 hours) that aforesaid way determines is lower, meets business demand.
It based on the above-mentioned technical proposal, can be corresponding according to multiple use times, multiple use times in the embodiment of the present application
Life parameter (such as attrition value or writing) construct the first data relationship, and from multiple data points of the first data relationship
Selection target data point is determined life parameter using number of targets strong point and is closed using the corresponding relationship of time, and using the correspondence
The service life of system's prediction certain device.In this way, can just perceive before the service life of certain device terminates using the longevity
The end time is ordered, the operation such as Data Migration is then carried out in advance, avoids loss of data or unavailable.Moreover, not being to utilize institute
There are data to predict service life, but utilize target data point prediction service life, in this way, can be based on meeting recent business field
The data of scape predict service life, and the prediction error of service life is smaller, and prediction result is accurate and reliable.
Below in conjunction with application scenarios shown in Fig. 2 B, above-mentioned steps 101- step 104 is illustrated.
For step 101, in one example, for " multiple according to certain device use time, the multiple use
The process of time corresponding life parameter, the first data relationship of construction ", can include but is not limited to such as under type: from history number
Multiple use times, corresponding life parameter of multiple use times are chosen according to middle;Then, according to multiple using the times, multiple make
With time corresponding life parameter, construction includes the first data relationship of multiple data points, and when the expression use of each data point
Between corresponding relationship with life parameter.
Further, for " according to multiple use times of certain device, corresponding service life ginseng of the multiple use time
Number, construct the first data relationship " process, can include but is not limited to: establishing coordinate system, the coordinate system may include horizontal axis and
The longitudinal axis;According to multiple use times, corresponding life parameter of the multiple use time, multiple data are added in the coordinate system
Point, the abscissa of each data point are using the time, and ordinate is that this uses time corresponding life parameter;Utilize multiple data points
Construct the first data relationship.
In the above-described embodiments, the first data relationship can include but is not limited to the first entity relationship diagram, i.e., with relational graph
The first data relationship of representation, certainly, the first data relationship may be other structures, it is not limited to the knot of relational graph
Structure, it is without limitation as long as may include multiple data points.
By taking life parameter is attrition value as an example, then the first data relationship may refer to shown in Fig. 2 B.When life parameter is to write
When entering amount, then corresponding first data relationship is similar with Fig. 2 B, the difference is that, ordinate is writing, rather than is worn
Value, for the convenience of description, subsequent be illustrated by taking Fig. 2 B as an example.
For each solid state hard disk, a large amount of historical datas are stored in database, these historical datas indicate to use the time
With the corresponding relationship of attrition value, and such as attrition value 100 and using the corresponding relationship of time 0, attrition value 99 use the time 20 hours
Corresponding relationship, attrition value 98 and using the time 40 hours corresponding relationships, and so on, attrition value 85 and use the time 300
The corresponding relationship of hour, attrition value 70 and the corresponding relationship using the time 375 hours, and so on, when attrition value 20 is with using
Between 1000 hours corresponding relationships.
Wherein, attrition value 99 and the corresponding relationship expression using the time 20 hours: what it is in solid state hard disk is 20 using the time
When hour, detect that the attrition value of solid state hard disk is 99, it is corresponding with use the time 20 hours in data-base recording attrition value 99
Relationship, other corresponding relationships are similar.It, can be in database by constantly detecting use time and the attrition value of solid state hard disk
It is middle to constantly update the corresponding relationship for using time and attrition value.
Wherein, since " using the corresponding relationship of time and attrition value " in database is constantly updated, when different
Between, the historical data in database is not identical, and the data point determined based on these historical datas is not also identical, and including these
First data relationship of data point is not also identical.For example, it is assumed that current time is using the 375 hours time corresponding time, then
From all data points that the historical data got in database includes between data point 1- data point 4, it is assumed that current time is
Using the 1000 hours time corresponding time, then the historical data got from database include data point 1- data point 10 it
Between all data points.
In conclusion due to being constantly updated using the corresponding relationship of time and attrition value in database, Ke Yizhou
Phase property executes step 101- step 104, such as executes every 24 hours primary.When executing step 101- step 104 every time, the first number
It changes according to relationship, and the inflection point in the first data relationship can also change, once inflection point changes, just finds again
Number of targets strong point, and the service life of solid state hard disk is predicted using number of targets strong point again, dynamic adjusts the use of solid state hard disk
Service life improves forecasting accuracy.
Based on the historical data stored in database, can be chosen from these historical datas it is multiple using the times, it is multiple
Use time corresponding attrition value;Coordinate system is established, adds multiple data points in the coordinate system, it, should for each data point
The abscissa of data point is using the time, and the ordinate of the data point is that this uses time corresponding attrition value.B institute referring to fig. 2
Show, after choosing attrition value 100 in historical data and using the corresponding relationship of time 0, add data point 1 in a coordinate system,
I.e. the abscissa of data point 1 is using the time 0, and ordinate is attrition value 100.It is choosing attrition value 85 from historical data and is making
After the time 300 hours corresponding relationships, data point 3 is added in a coordinate system, i.e. the abscissa of data point 3 is to use the time
300, ordinate is attrition value 85, and so on.Finally, referring to fig. 2 shown in B, data point 1- number can be added in a coordinate system
All data points between strong point 10, these data points just form the first data relationship.
For step 102, in one example, for " from multiple data points of first data relationship selection target
The process of data point " can include but is not limited to such as under type: the slope information of data point (such as each data point) is utilized, from
Inflection point is determined in multiple data points of above-mentioned first data relationship, and selects a target inflection point from determining inflection point, by institute
It states target inflection point and is determined as number of targets strong point.Wherein, target inflection point includes: the inflection point nearest apart from current time, that is, the
The last one inflection point of one data relationship.
Further, for " using the slope information of data point, determination is turned from multiple data points of the first data relationship
The process of point ", can include but is not limited to: for data point (i.e. each of first data relationship in the first data relationship
Data point), if determining that the data point is scope discontinuity using the slope information of the data point, it is determined that the data point is to turn
Point;Otherwise, it determines the data point is not inflection point.
First data relationship shown in B referring to fig. 2 does not have left-hand digit strong point for data point 1, therefore data point 1 is not
Inflection point.For data point 2, the slope and data point 2 and right side data point of data point 2 and left-hand digit strong point composition straight line are formed
The slope of straight line is identical, and therefore, data point 2 is not inflection point.For data point 3, data point 3 and left-hand digit strong point form straight line
Slope and data point 3 are different from the right side data point composition slope of straight line, and therefore, data point 3 is scope discontinuity, i.e. data
Point 3 is inflection point.
And so on, after carrying out above-mentioned processing to each data point in the first data relationship, determine that inflection point includes number
Strong point 3, data point 4, data point 5, data point 6, data point 7.Then, it determines from these inflection points and (is counted apart from current time
Strong point 10 corresponds to the time) a nearest inflection point, i.e. data point 7.
For step 103, in one example, for " determining life parameter using number of targets strong point and using the time
The process of corresponding relationship " can include but is not limited to such as under type: determining using first data relationship to be with number of targets strong point
The slope information of starting point;Then, life parameter is determined using the slope information and using the corresponding relationship of time, i.e. the service life joins
Number and the linear relationship for using the time.Wherein, if life parameter is attrition value, it is determined that attrition value is closed with using the corresponding of time
System, if life parameter is writing, it is determined that writing and the corresponding relationship using the time.For the convenience of description, subsequent with mill
For damage value.
Referring to fig. 2 shown in B, after determining that number of targets strong point is data point 7, based on the data point after data point 7, with data
Point 7 constructs straight line for starting point, i.e., the straight line being made of data point 7, data point 8, data point 9, data point 10 utilizes this
The slope information of straight line determines attrition value and the corresponding relationship using the time, i.e. attrition value and the linear relationship using the time.Example
Such as, attrition value from 35 be reduced to 20 when, the use of the time is 150 hours, therefore attrition value is every reduces by 1, is increased using the time 10 small
When, determine therefrom that out attrition value and the corresponding relationship using the time, if attrition value 35 is corresponding with using 850 hours time, abrasion
Value 34 is corresponding with using 860 hours time, and attrition value 33 is corresponding with using 870 hours time, and so on.
For step 104, in one example, for " predicting that the certain device is (such as above-mentioned using determining corresponding relationship
Solid state hard disk) service life " process, can include but is not limited to such as under type:
If mode one, the life parameter are attrition value, it can use attrition value and (walked with using the corresponding relationship of time
Rapid 103 definitive result), it is corresponding using the time to predict default attrition value.Then, the corresponding use of default attrition value is utilized
Time and currently used time, predict the service life of certain device.
For example, with reference to shown in Fig. 2 B, based on attrition value and using the corresponding relationship of time, (attrition value is every to reduce by 1, when use
Between increase by 10 hours), so that it may predicting default attrition value 5, corresponding (i.e. attrition value is reduced to default mill from 100 using the time
When damage value 5 it is total use the time) be 1150 hours, it is assumed that the currently used time is 1000 hours, then it is hard to predict solid-state
The service life of disk is 150 hours.
If mode two, the life parameter are writing, can be according to the second data relationship of attrition value and writing, really
Surely the corresponding writing of attrition value is preset.Using writing and using the time corresponding relationship (i.e. the definitive result of step 103),
It is corresponding using the time to predict the corresponding writing of default attrition value, and corresponding using the time and current using the writing
Using the time, the service life of certain device is predicted.
In one example, multiple writing, the multiple writing pair of certain device can be first chosen from historical data
The attrition value answered;Then, according to multiple writing, the corresponding attrition value of multiple writing, the second data relationship is constructed, this second
Data relationship includes multiple data points, and each data point indicates the corresponding relationship of attrition value and writing.Further, for
The process of " according to multiple writing, the corresponding attrition value of multiple writing, constructing the second data relationship " may include but unlimited
In such as under type: establishing a coordinate system, which may include horizontally and vertically;Then, according to multiple writing, multiple
The corresponding attrition value of writing adds multiple data points in the coordinate system, and the abscissa of each data point is writing, and is indulged
Coordinate is the corresponding attrition value of the writing;The second data relationship is constructed using multiple data points.
In the above-described embodiments, the second data relationship can include but is not limited to the second entity relationship diagram, i.e., with relational graph
The second data relationship of representation, certainly, the second data relationship may be other structures, it is not limited to the knot of relational graph
Structure, it is without limitation as long as may include multiple data points.
For each solid state hard disk, a large amount of historical datas are stored in database, these historical datas indicate writing with
The corresponding relationship of attrition value.In general, writing and attrition value are in a linear relationship, for example, in the history number of database
In, the corresponding relationship of corresponding relationship, writing 1000M and attrition value 99 including writing 0 and attrition value 100, writing
The corresponding relationship of 2000M and attrition value 98, and so on.
Wherein, writing 1000M and the corresponding relationship of attrition value 99 can indicate: be in the writing of solid state hard disk
When 1000M, detects that the attrition value of solid state hard disk is 99, it is corresponding with attrition value 99 to record writing 1000M in the database
Relationship, other corresponding relationships are similar.It, can be in database by constantly detecting the writing and attrition value of solid state hard disk
The middle corresponding relationship for constantly updating writing and attrition value.
Based on the historical data stored in database, multiple writing can be chosen from these historical datas, multiple are write
Enter the corresponding attrition value of amount;Coordinate system is established, adds multiple data points in the coordinate system, for each data point, the data
The abscissa of point is writing, and the ordinate of the data point is the corresponding attrition value of the writing.Referring to fig. 2 shown in C, from going through
After the corresponding relationship for choosing attrition value 100 and writing 0 in history data, add data point 1 in a coordinate system, i.e. data point 1
Abscissa is writing 0, and ordinate is attrition value 100.Choosing attrition value 85 and writing 15000M's from historical data
After corresponding relationship, data point 2 is added in a coordinate system, i.e. the abscissa of data point 2 is writing 15000M, and ordinate is abrasion
Value 85, and so on.Finally, referring to fig. 2 shown in C, these group of data points are at the second data relationship.
The second data relationship based on attrition value shown in fig. 2 C and writing can then determine that default attrition value 5 is corresponding
Writing be 95000M.It is then possible to based on writing and use the corresponding relationship of time (with attrition value and using the time
Corresponding relationship is similar, no longer repeats again), can determining writing 95000M, corresponding using the time, (i.e. attrition value is from 100
Total when being reduced to default attrition value 5 uses the time) it is 1150 hours, if the currently used time is 1000 hours, prediction is solid
The service life of state hard disk is 150 hours.
Below in conjunction with two specific embodiments, aforesaid way one and mode two are further detailed.
It is shown in Figure 3, it is another flow chart of life forecast method, this method may include:
Step 301, according to multiple use times of solid state hard disk, corresponding attrition value of the multiple use time, construction
First data relationship, wherein first data relationship includes multiple data points.
Step 302, the selection target data point from multiple data points of first data relationship.
Step 303, attrition value is determined using number of targets strong point and use the corresponding relationship of time.
Step 304, it predicts that default attrition value is corresponding using determining corresponding relationship and uses the time.
Step 305, the service life of the solid state hard disk is predicted using time and currently used time using this.
Wherein, the processing of step 301- step 305, process shown in Figure 1, it is no longer repeated.
It is shown in Figure 4, it is another flow chart of life forecast method, this method may include:
Step 401, according to multiple use times of solid state hard disk, corresponding writing of the multiple use time, construction
First data relationship, wherein first data relationship may include multiple data points.
Step 402, according to multiple writing of solid state hard disk, the corresponding attrition value of the multiple writing, construction second
Data relationship, wherein second data relationship may include multiple data points.
Wherein, each data point in the first data relationship, indicates the corresponding relationship for using time and writing, and second
Each data point in data relationship indicates the corresponding relationship of writing and attrition value.
Step 403, according to second data relationship, the default corresponding writing of attrition value is determined.
Step 404, the selection target data point from multiple data points of first data relationship.
Step 405, writing is determined using number of targets strong point and use the corresponding relationship of time.
Step 406, it predicts that the default corresponding writing of attrition value is corresponding using the corresponding relationship and uses the time.
Step 407, the service life of the solid state hard disk is predicted using time and currently used time using this.
Wherein, the processing of step 401- step 407, process shown in Figure 1, it is no longer repeated.
Based on similarly applying conceiving with the above method, the embodiment of the present application also provides a kind of life forecast device,
As shown in figure 5, being the structure chart of the life forecast device, described device includes:
Module 501 is obtained, for multiple use times, the multiple use time in the corresponding service life according to certain device
Parameter constructs the first data relationship, and first data relationship includes multiple data points;
Selecting module 502, for the selection target data point from multiple data points of the first data relationship;
Determining module 503, for determining life parameter using the inflection point and using the corresponding relationship of time;
Prediction module 504, for predicting the service life of the certain device using determining corresponding relationship.
The acquisition module 501, specifically for choosing multiple use times from historical data, multiple use times correspond to
Life parameter;According to it is multiple using the times, it is multiple using time corresponding life parameter, construction includes the of multiple data points
One data relationship, data point indicate to use the corresponding relationship of time and life parameter;Root according to it is multiple using the times, multiple make
With time corresponding life parameter, when construction includes the first data relationship of multiple data points, according to it is multiple using the times, it is multiple
Using time corresponding life parameter, multiple data points are added in coordinate system, the abscissa of the data point is to indulge using the time
Coordinate is that this uses time corresponding life parameter;The first data relationship is constructed using the multiple data point.
The selecting module 502, specifically for the slope information using data point, from multiple data of the first data relationship
Inflection point is determined in point, and selects a target inflection point from determining inflection point, and the target inflection point is determined as number of targets strong point;
Wherein, the target inflection point includes: the inflection point nearest apart from current time;
In the slope information using data point, when determining inflection point from multiple data points of first data relationship, needle
To the data point in the first data relationship, if determining that the data point is scope discontinuity using the slope information of the data point,
Determine that the data point is inflection point;Otherwise, it determines the data point is not inflection point.
The determining module 503 is specifically used for determining using the first data relationship using the number of targets strong point as starting point
Slope information;Life parameter is determined using the slope information and using the corresponding relationship of time.
The prediction module 504 is specifically used for when the life parameter is attrition value, using attrition value and uses the time
Corresponding relationship, predict that default attrition value is corresponding and use the time, and is corresponding using the time and current using default attrition value
Using the time, the service life of certain device is predicted.When the life parameter is writing, according to attrition value and writing
Second data relationship determines the default corresponding writing of attrition value, and using writing and uses the corresponding relationship of time, prediction
Said write amount is corresponding to use the time, and uses time and currently used time using said write amount is corresponding, and prediction is special
Determine the service life of device.
Based on similarly applying conceiving with the above method, the embodiment of the present application also provides a kind of life forecast equipment,
The life forecast equipment can include but is not limited to: processor, for using time, institute according to the multiple of certain device
It states multiple using time corresponding life parameter, the first data relationship of construction, wherein first data relationship includes multiple numbers
Strong point;The selection target data point from multiple data points of first data relationship;The longevity is determined using the number of targets strong point
Order parameter and the corresponding relationship using the time;The service life of the certain device is predicted using determining corresponding relationship.
Based on similarly applying conceiving with the above method, the embodiment of the present application also provides a kind of machine readable storage medium,
Be stored with several computer instructions, the computer instruction, which is performed, to be handled as follows: multiple according to certain device make
With time, corresponding life parameter of the multiple use time, the first data relationship is constructed, wherein first data relationship
Including multiple data points;The selection target data point from multiple data points of first data relationship;Utilize the number of targets
Strong point determines life parameter and the corresponding relationship using the time;The use of the certain device is predicted using determining corresponding relationship
Service life.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.A kind of typically to realize that equipment is computer, the concrete form of computer can
To be personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
In device, navigation equipment, E-mail receiver/send equipment, game console, tablet computer, wearable device or these equipment
The combination of any several equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes computer usable program code that the embodiment of the present application, which can be used in one or more,
The computer implemented in computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of program product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It is generally understood that being realized by computer program instructions each in flowchart and/or the block diagram
The combination of process and/or box in process and/or box and flowchart and/or the block diagram.It can provide these computer journeys
Sequence instruct to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor with
A machine is generated, so that the instruction generation executed by computer or the processor of other programmable data processing devices is used for
Realize the dress for the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
Moreover, these computer program instructions also can store be able to guide computer or other programmable datas processing set
In standby computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates
Manufacture including command device, the command device are realized in one process of flow chart or multiple processes and/or block diagram one
The function of being specified in a box or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing devices, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer
Or the instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram
The step of function of being specified in one box or multiple boxes.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (18)
1. a kind of life forecast method, which is characterized in that the described method includes:
According to multiple use times of certain device, corresponding life parameter of the multiple use time, the first data of construction are closed
System, wherein first data relationship includes multiple data points;
The selection target data point from multiple data points of first data relationship;
Life parameter is determined using the number of targets strong point and using the corresponding relationship of time;
The service life of the certain device is predicted using determining corresponding relationship.
2. the method according to claim 1, wherein described use times, described according to the multiple of certain device
It is multiple to use time corresponding life parameter, the first data relationship of construction, comprising:
Multiple use times are chosen from historical data, the multiple using time corresponding life parameter;
According to multiple use times, corresponding life parameter of the multiple use time, construction includes the first of multiple data points
Data relationship, and data point indicates to use the corresponding relationship of time and life parameter.
3. method according to claim 1 or 2, which is characterized in that described to use time, institute according to the multiple of certain device
It states multiple using time corresponding life parameter, the first data relationship of construction, comprising:
According to multiple use times, corresponding life parameter of multiple use times, multiple data points, data point are added in coordinate system
Abscissa be using the time, ordinate is that this uses time corresponding life parameter;
The first data relationship is constructed using the multiple data point.
4. the method according to claim 1, wherein
The process of selection target data point from multiple data points of first data relationship, specifically includes:
Using the slope information of data point, inflection point is determined from multiple data points of first data relationship;
A target inflection point is selected from determining inflection point, and the target inflection point is determined as number of targets strong point.
5. according to the method described in claim 4, it is characterized in that,
The target inflection point includes: the inflection point nearest apart from current time.
6. according to the method described in claim 4, it is characterized in that, the slope information using data point, from described first
The process that inflection point is determined in multiple data points of data relationship, specifically includes:
For the data point in the first data relationship, if determining that the data point is that slope is mutated using the slope information of the data point
Point, it is determined that the data point is inflection point;Otherwise, it determines the data point is not inflection point.
7. the method according to claim 1, wherein it is described using the number of targets strong point determine life parameter with
Using the process of the corresponding relationship of time, specifically include:
It is determined using first data relationship using the number of targets strong point as the slope information of starting point;
Life parameter is determined using the slope information and using the corresponding relationship of time.
8. method according to claim 1 or claim 7, which is characterized in that described using true if the life parameter is attrition value
Fixed corresponding relationship predicts the process of the service life of the certain device, comprising:
Using attrition value and using the corresponding relationship of time, predicts that default attrition value is corresponding and use the time, and utilize default mill
Damage value is corresponding to use time and currently used time, predicts the service life of certain device.
9. method according to claim 1 or claim 7, which is characterized in that described using true if the life parameter is writing
Fixed corresponding relationship predicts the process of the service life of the certain device, comprising:
According to the second data relationship of attrition value and writing, the default corresponding writing of attrition value is determined;
Using writing and using the corresponding relationship of time, prediction said write amount is corresponding to use the time, and writes described in utilization
Enter amount corresponding use time and currently used time, predicts the service life of certain device.
10. according to the method described in claim 9, it is characterized in that, the method also includes:
Multiple writing, the corresponding attrition value of the multiple writing of certain device are chosen from historical data;
According to multiple writing, the corresponding attrition value of multiple writing, the second data relationship is constructed, second data relationship is more
A data point, data point indicate the corresponding relationship of attrition value and writing.
11. according to the method described in claim 10, it is characterized in that, described corresponding according to multiple writing, multiple writing
Attrition value, construct the second data relationship process, specifically include:
According to multiple writing, the corresponding attrition value of the multiple writing, multiple data points, data point are added in a coordinate system
Abscissa be writing, ordinate be the corresponding attrition value of the writing;
Second data relationship is constructed using the multiple data point.
12. the method according to claim 1, wherein
The certain device specifically includes: solid state hard disk.
13. a kind of life forecast device, which is characterized in that described device includes:
Module is obtained, for multiple use times according to certain device, corresponding life parameter of the multiple use time, structure
Make the first data relationship, wherein first data relationship includes multiple data points;
Selecting module, for the selection target data point from multiple data points of first data relationship;
Determining module, for determining life parameter using number of targets strong point and using the corresponding relationship of time;
Prediction module, for predicting the service life of the certain device using determining corresponding relationship.
14. device according to claim 13, which is characterized in that
The acquisition module, specifically for choosing multiple use times, multiple use times in corresponding service life from historical data
Parameter;According to multiple use times, corresponding life parameter of multiple use times, construction includes the first data of multiple data points
Relationship, data point indicate to use the corresponding relationship of time and life parameter;
In root according to multiple use times, corresponding life parameter of multiple use times, construction includes the first of multiple data points
When data relationship, according to multiple use times, corresponding life parameter of multiple use times, multiple data are added in coordinate system
Point, the abscissa of the data point are using the time, and ordinate is that this uses time corresponding life parameter;Using the multiple
Data point constructs the first data relationship.
15. device according to claim 13, which is characterized in that
The selecting module, specifically for the slope information using data point, from multiple data points of the first data relationship really
Determine inflection point, and select a target inflection point from determining inflection point, the target inflection point is determined as number of targets strong point;Wherein,
The target inflection point includes: the inflection point nearest apart from current time;
In the slope information using data point, when determining inflection point from multiple data points of first data relationship, for the
Data point in one data relationship, if determining that the data point is scope discontinuity using the slope information of the data point, it is determined that
The data point is inflection point;Otherwise, it determines the data point is not inflection point.
16. device according to claim 13, which is characterized in that
The determining module is believed specifically for being determined using the first data relationship by the slope of starting point of the number of targets strong point
Breath;Life parameter is determined using the slope information and using the corresponding relationship of time.
17. device described in 3 or 16 according to claim 1, which is characterized in that
The prediction module is specifically used for when the life parameter is attrition value, corresponding with the use time using attrition value
Relationship predicts that default attrition value is corresponding and uses the time, and using default attrition value it is corresponding using the time and it is currently used when
Between, predict the service life of certain device.When the life parameter is writing, according to the second number of attrition value and writing
According to relationship, the default corresponding writing of attrition value is determined, and utilize writing and the corresponding relationship using the time, write described in prediction
It is corresponding using the time to enter amount, and uses time and currently used time using said write amount is corresponding, predicts certain device
Service life.
18. a kind of life forecast equipment, which is characterized in that the life forecast equipment includes:
Processor, for multiple use times according to certain device, corresponding life parameter of the multiple use time, construction
First data relationship, wherein first data relationship includes multiple data points;
The selection target data point from multiple data points of first data relationship;
Life parameter is determined using the number of targets strong point and using the corresponding relationship of time;
The service life of the certain device is predicted using determining corresponding relationship.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810082569.5A CN110096391A (en) | 2018-01-29 | 2018-01-29 | A kind of life forecast method, apparatus and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810082569.5A CN110096391A (en) | 2018-01-29 | 2018-01-29 | A kind of life forecast method, apparatus and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110096391A true CN110096391A (en) | 2019-08-06 |
Family
ID=67442681
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810082569.5A Pending CN110096391A (en) | 2018-01-29 | 2018-01-29 | A kind of life forecast method, apparatus and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110096391A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105893168A (en) * | 2016-03-29 | 2016-08-24 | 深圳市硅格半导体股份有限公司 | Health condition analysis method and device for hard disk |
CN106909482A (en) * | 2017-03-01 | 2017-06-30 | 郑州云海信息技术有限公司 | A kind of method and device of solid-state disk service life detection |
US20170193373A1 (en) * | 2015-08-25 | 2017-07-06 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Disk capacity predicting method, apparatus, equipment and non-volatile computer storage medium |
-
2018
- 2018-01-29 CN CN201810082569.5A patent/CN110096391A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170193373A1 (en) * | 2015-08-25 | 2017-07-06 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Disk capacity predicting method, apparatus, equipment and non-volatile computer storage medium |
CN105893168A (en) * | 2016-03-29 | 2016-08-24 | 深圳市硅格半导体股份有限公司 | Health condition analysis method and device for hard disk |
CN106909482A (en) * | 2017-03-01 | 2017-06-30 | 郑州云海信息技术有限公司 | A kind of method and device of solid-state disk service life detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108701252B (en) | Training neural networks using prioritized empirical memories | |
CN104778127B (en) | The method and apparatus that a kind of NAND FLASH write data | |
CN104731896B (en) | A kind of data processing method and system | |
CN108089814A (en) | A kind of date storage method and device | |
CN104159113A (en) | Method and device for selecting video coding mode for Android system | |
CN106802772B (en) | Data recovery method and device and solid state disk | |
CN106775474A (en) | A kind of Nand Flash abrasion equilibrium methods, device and memory | |
CN108897492A (en) | A kind of method for writing data and device | |
CN103077184B (en) | The method obtained for rule-based sight | |
CN110221959A (en) | Test method, equipment and the computer-readable medium of application program | |
CN112000893B (en) | Resident region prediction method, device, equipment and storage medium | |
CN111736772A (en) | Storage space data processing method and device of distributed file system | |
CN109871181A (en) | A kind of Object Access method and device | |
CN107291392A (en) | A kind of solid state hard disc and its reading/writing method | |
CN115907222A (en) | Carbon emission prediction method and system | |
CN104021226A (en) | Method and device for updating prefetch rule | |
CN110674397B (en) | Method, device, equipment and readable medium for training age point prediction model | |
CN105528178B (en) | Date storage method and solid state disk | |
CN108170824A (en) | A kind of date storage method based on SQL, device, equipment and storage medium | |
CN109902821A (en) | A kind of data processing method, device and associated component | |
CN116728419B (en) | Continuous playing action planning method, system, equipment and medium for playing robot | |
CN110096391A (en) | A kind of life forecast method, apparatus and equipment | |
CN105224305A (en) | Function call path decoding method, Apparatus and system | |
WO2019179252A1 (en) | Sample playback data access method and device | |
CN109993338A (en) | A kind of link prediction method and device |
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 |