CN108829883A - Periodicity extraction method, apparatus, equipment and the storage medium of data sequence - Google Patents
Periodicity extraction method, apparatus, equipment and the storage medium of data sequence Download PDFInfo
- Publication number
- CN108829883A CN108829883A CN201810679840.3A CN201810679840A CN108829883A CN 108829883 A CN108829883 A CN 108829883A CN 201810679840 A CN201810679840 A CN 201810679840A CN 108829883 A CN108829883 A CN 108829883A
- Authority
- CN
- China
- Prior art keywords
- value
- setting
- window
- minimum
- long
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses periodicity extraction method, apparatus, equipment and the storage mediums of a kind of data sequence.This method includes：The period of target data sequence is estimated, periodic regime is estimated in acquisition；Estimate that at least one window is obtained in periodic regime is long described according to setting means；In the case where each window is long, the extreme value pair for meeting setting condition in the target data sequence is obtained；It will include meeting that the extreme value to impose a condition is long to most window to be determined as that target window is long, and extract the long lower data met between the extreme value pair and extreme point of setting condition of the target window, and obtain the period of the target data sequence.The periodicity extraction method of data sequence provided in an embodiment of the present invention, the long lower extreme value pair for meeting setting condition of different window is obtained respectively, extreme value pair under growing including the extreme value for meeting setting condition to most windows and extreme value extract data before, in the period for obtaining target data sequence, the accuracy of periodicity extraction can be improved.
Description
Technical field
The present embodiments relate to a kind of periodicity extraction method of data mining technology field more particularly to data sequence,
Device, equipment and storage medium.
Background technique
Time series data is prevalent in many important applied fields, such as DNA sequence dna, finance data, sensor network prison
Measured data, mobile object tracking data and mechanical disorder data etc..Since time series data and time correlation join, because of its data volume
Be usually quite it is huge, then to time series data carry out data mining be particularly important.Wherein, is carried out to time series data the period
Extraction is one of important link of data mining.This is because, after the periodicity extraction of time series data is come out, so that it may needle
Data in 1 or several periods are analyzed, the workload of data analysis can be significantly reduced.
In the prior art, when extracting in the period to time series data, time series data is usually transformed into frequency domain, it is right
The data of frequency domain obtain the period of time series data, this kind of method data more complicated for the period, accuracy into analysis
It is lower.
Summary of the invention
The embodiment of the present invention provides periodicity extraction method, apparatus, equipment and the storage medium of a kind of data sequence, to realize
The accuracy of periodicity extraction can be improved in extraction to the data period.
In a first aspect, the embodiment of the invention provides a kind of periodicity extraction method of data sequence, this method includes：
The period of target data sequence is estimated, periodic regime is estimated in acquisition, and the target data ordered series of numbers is from number
According to the data sequence with setting length intercepted in sequence；
Estimate that at least one window is obtained in periodic regime is long described according to setting means；
In the case where each window is long, the extreme value pair for meeting setting condition in the target data sequence, the extreme value pair are obtained
Including maximum pair or minimum pair；
To include meet the extreme value that imposes a condition it is long to most window to be determined as target window long, and it is long to extract the target window
Under satisfaction impose a condition extreme value pair and extreme point between data, obtain the period of the target data sequence.
Further, according to setting means it is described estimate obtained in periodic regime at least one window it is long after, also wrap
It includes：
Obtain the maximum point and minimum point of the target data sequence；
Obtain the minimum value of the maximum value and the minimum point in the maximum point；
If the maximum value is greater than institute multiplied by the quantity for the maximum point for including between the first setting value and the maximum value
Minimum value and the minimum value are stated multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to being minimum
Value pair；
If the maximum value is less than institute multiplied by the quantity for the maximum point for including between the first setting value and the maximum value
Minimum value and the minimum value are stated multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to for greatly
Value pair.
Further, when the extreme value obtains the target data sequence in the case where each window is long to for minimum clock synchronization
The middle extreme value to impose a condition that meets is to including：
Obtain all minimums pair of the minimum point composition in the target data sequence；
To each minimum to verifying, obtains and meet the first subconditional minimum pair of setting；Wherein, it first sets
Stator condition includes：Value of the value of two minimum points of minimum pair less than the minimum point among two minimum points, pole
The index distance of two minimum points of small value pair is less than when front window is long and is greater than when front window is long multiplied by third setting value, minimum
Pair the differences of value of two minimum points be less than the first setting ratio；
Meet the first value averageds for setting subconditional minimum centering minimum point for all under front window is long,
The difference of the minimum point and average value of rejecting the subconditional minimum centering of the first setting of satisfaction is more than the second setting ratio
Minimum pair obtains the minimum pair for meeting and imposing a condition.
Further, when the extreme value obtains the target data sequence in the case where each window is long to for maximum clock synchronization
The middle extreme value to impose a condition that meets is to including：
Obtain all maximum pair of the maximum point composition in the target data sequence；
To each maximum to verifying, obtains and meet the second subconditional maximum pair of setting；Wherein, it second sets
Stator condition includes：The value of two maximum points of maximum pair is greater than the value of the maximum point among two maximum points, pole
The index distance of two maximum points of big value pair is less than when front window is long and is greater than when front window is long multiplied by the 4th setting value, maximum
Pair the differences of value of two maximum points be less than third setting ratio；
Meet the second value averageds for setting subconditional maximum centering maximum point for all under front window is long,
The difference of the maximum point and average value of rejecting the subconditional maximum centering of the second setting of satisfaction is more than the 4th setting ratio
Maximum pair obtains the maximum pair for meeting and imposing a condition.
Further, described to estimate that obtain at least one window in periodic regime long described according to setting means, including：
It estimates the corresponding minimum value of periodic regime by described to be determined as initial window long, since the initial window is long and with the
The Rate Index of five setting values increases, at least one window estimated in periodic regime described in acquisition is long；Wherein, the 5th setting
Value is respectively with third setting value and the 4th setting value at reciprocal relation.
Further, before target window length being determined as to most window length including meeting the extreme value to impose a condition, including：
It obtains under each window length, meets the connection of the extreme value pair of setting condition situation；
It is long to reject the window for being unsatisfactory for setting condition of contact；Wherein, set condition of contact as：The connection number of extreme value pair be greater than and
Equal to minimum logarithm multiplied by the 6th setting value.
Further, it in the case where each window is long, obtains and meets the extreme value of setting condition in the target data sequence to it
Afterwards, further include：
In the case where each window is long, using similarity algorithm to the extreme value of satisfaction setting condition to progress similarity detection；
Reject the extreme value pair for being unsatisfactory for similarity condition.
Second aspect, the embodiment of the invention also provides a kind of periodicity extraction device of data sequence, which includes：
Periodic regime obtains module, estimates for the period to target data sequence, and periodic regime is estimated in acquisition, institute
Stating target data ordered series of numbers is the data sequence with setting length intercepted from data sequence；
Window is long to obtain module, for estimating that obtain at least one window in periodic regime long described according to setting means；
Extreme value imposes a condition to module is obtained in the case where each window is long, obtaining to meet in the target data sequence
Extreme value pair, the extreme value to include maximum pair or minimum pair；
Period obtains module, and the extreme value target window that is determined as long to most windows for that will include satisfaction setting condition is long,
And the data between the extreme value pair and extreme point that the satisfaction under the target window length imposes a condition are extracted, obtain the number of targets
According to the period of sequence.
The third aspect the embodiment of the invention also provides a kind of computer equipment, including memory, processor and is stored in
On memory and the computer program that can run on a processor, the processor are realized when executing described program as the present invention is real
Apply method described in example.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, the program realize method as described in the embodiments of the present invention when being executed by processor.
The embodiment of the present invention first estimates the period of target data sequence, and periodic regime is estimated in acquisition, then presses
According to setting means, to obtain at least one window in periodic regime long estimating, and subsequently in the case where each window is long, obtains target data
Meet the extreme value pair of setting condition in sequence, finally will include meeting the extreme value to impose a condition to be determined as target to most window length
Window is long, and extracts the data between the extreme value pair and extreme point that the satisfaction under target window length imposes a condition, and obtains target data
The period of sequence.The periodicity extraction method of data sequence provided in an embodiment of the present invention obtains the long lower satisfaction of different window respectively and sets
The extreme value pair of fixed condition will include meeting the extreme value that imposes a condition to extreme value pair under long of most window and extreme value to before
Data extract, and obtain the period of target data sequence, the accuracy of periodicity extraction can be improved.
Detailed description of the invention
Fig. 1 is the flow chart of the periodicity extraction method of one of the embodiment of the present invention one data sequence；
Fig. 2 is the flow chart of the periodicity extraction method of another data sequence in the embodiment of the present invention one；
Fig. 3 is the structural schematic diagram of the periodicity extraction device of one of the embodiment of the present invention two data sequence；
Fig. 4 is the structural schematic diagram of one of the embodiment of the present invention three computer equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart of the periodicity extraction method for data sequence that the embodiment of the present invention one provides, the present embodiment
It is applicable to the case where extracting to the period of data sequence, this method can be held by the periodicity extraction device of data sequence
Row, which can be made of hardware and/or software, and can generally be integrated in computer, server and all comprising data sequence
Periodicity extraction function terminal in.As shown in Figure 1, this method specifically comprises the following steps.
Step 110, the period of target data sequence is estimated, periodic regime is estimated in acquisition.
Wherein, target data ordered series of numbers is the data sequence with setting length intercepted from data sequence.Target data
Sequence can be discrete data sequence, and setting length can be the number for the data point that data sequence includes, such as：Setting length
Degree can be set to the arbitrary value between 100-500.Periodic regime can be the range comprising data point number.
Specifically, the mode estimated to the period of target data sequence can be, include to target data sequence
The value of data point is analyzed, and is estimated with the period to target data sequence, estimates periodic regime to obtain.Alternatively,
Periodic regime can be determined directly as 3-length/3, wherein " 3 " indicate that the data point number for including in a cycle is 3,
Length is the length of target data sequence.Illustratively, it is assumed that the length of target data sequence is 150, then periodic regime can
To be determined as 3-50.
Step 120, according to setting means, that at least one window is obtained in periodic regime is long estimating.
Wherein, window length can be to obtain extreme value in following step to providing foundation.Optionally, it is being estimated according to setting means
At least one window length is obtained in periodic regime to be implemented by following manner：The corresponding minimum value of periodic regime will be estimated to be determined as
Initial window is long, increases since initial window is long and with the Rate Index of the 5th setting value, acquisition is estimated in periodic regime at least
One window is long.
Wherein, the 5th setting value can be greater than 1 arbitrary value.Illustratively, it is assumed that estimating periodic regime is 3-50, the 5th
Setting value is set as 5/4, long for initial window with 3, the Rate Index since 3 ing with 5/4 increase the window that obtains it is long respectively 3,
3.95、5.57、8.55、14.62、28.58。
Step 130, in the case where each window is long, the extreme value pair for meeting setting condition in target data sequence is obtained.
Wherein, extreme value is to including maximum pair or minimum pair.
Optionally, when extreme value obtains in the case where each window is long to for minimum clock synchronization and meets setting in target data sequence
The extreme value of condition by following manner to can be implemented：Obtain all minimums of the minimum point composition in target data sequence
It is right；To each minimum to verifying, obtains and meet the first subconditional minimum pair of setting；Wherein, the first setting
Condition includes：Value, minimum of the value of two minimum points of minimum pair less than the minimum point among two minimum points
Pair the index distances of two minimum points be less than when front window is long and is greater than when front window is long multiplied by third setting value, minimum pair
The difference of the value of two minimum points is less than the first setting ratio；It is subconditional that all the first settings of satisfaction under front window length will be worked as
The value averaged of minimum centering minimum point rejects the minimum point for meeting the first subconditional minimum centering of setting
Difference with average value is more than the minimum pair of the second setting ratio, obtains the minimum pair for meeting and imposing a condition.
Wherein, minimum is formed to can be any two minimum in target data sequence, for example, it is assumed that target data
It include 10 minimums in sequence, then 45 minimums pair can be formed.Third setting value can be any between 0-1
Number.Preferably, under this application scene, third setting value and the 5th setting value at reciprocal relation, such as：The setting of 5th setting value
It is 5/4, then third setting value is then 4/5.First setting ratio can be the absolute value of the value of difference and two minimum points
The ratio of middle smaller value can be set to the arbitrary value between 0.1-0.2, it is preferred that be set as 0.2.Second setting ratio can
Be difference and average value and minimum point value absolute value in smaller value ratio, can be set between 0.1-0.2
Arbitrary value, it is preferred that be set as 0.2.
Optionally, when extreme value obtains in the case where each window is long to for maximum clock synchronization and meets setting in target data sequence
The extreme value of condition by following manner to can be implemented：Obtain all maximum of the maximum point composition in target data sequence
It is right；To each maximum to verifying, obtains and meet the second subconditional maximum pair of setting；Wherein, the second setting
Condition includes：The value of two maximum points of maximum pair is greater than value, the maximum of the maximum point among two maximum points
Pair the index distances of two maximum points be less than when front window is long and is greater than when front window is long multiplied by the 4th setting value, maximum pair
The difference of the value of two maximum points is less than third setting ratio；It is subconditional that all the second settings of satisfaction under front window length will be worked as
The value averaged of maximum centering maximum point rejects the maximum point for meeting the second subconditional maximum centering of setting
Difference with average value is more than the maximum pair of the 4th setting ratio, obtains the maximum pair for meeting and imposing a condition.
Wherein, wherein maximum is formed to can be any two maximum in target data sequence, for example, it is assumed that mesh
Marking in data sequence includes 10 maximum, then 45 maximum pair can be formed.4th setting value can be between 0-1
Arbitrary number.Preferably, under this application scene, the 4th setting value and the 5th setting value at reciprocal relation, such as：5th setting value
It is set as 5/4, then the 4th setting value is then 4/5.Third setting ratio can be the exhausted of difference and the value of two maximum points
To the ratio of smaller value in value, the arbitrary value between 0.1-0.2 can be set to, it is preferred that be set as 0.2.4th setting ratio
Example can be difference and average value and maximum point value absolute value in smaller value ratio, can be set to 0.1-0.2 it
Between arbitrary value, it is preferred that be set as 0.2.
Step 140, will include meet the extreme value that imposes a condition it is long to most window to be determined as target window long, and extract target
The data between extreme value pair and extreme point that satisfaction under window is long imposes a condition, obtain the period of target data sequence.
Specifically, the extreme value for meeting setting condition in the case where obtaining each window length respectively will set item including meeting to later
The extreme value of part is long to most window to be determined as that target window is long, and extract the long lower extreme value pair for meeting setting condition of target window and
Data between extreme point obtain the period of target data sequence.Illustratively, it is respectively 3 that window is long, 3.95,5.57,8.55,
14.62,28.58, window it is a length of 8.55 when, the extreme value that the satisfaction of acquisition imposes a condition is to most, then by expiring under window long 8.55
Data between the extreme value pair and extreme point of sufficient condition extract, to obtain the period of target data ordered series of numbers.
The technical solution of the present embodiment first estimates the period of target data sequence, and periodic regime is estimated in acquisition,
Then according to setting means, to obtain at least one window in periodic regime long estimating, and subsequently in the case where each window is long, obtains mesh
Meet the extreme value pair of setting condition in mark data sequence, finally will include meeting the extreme value to impose a condition to determine most window length
It is long for target window, and the data between the extreme value pair and extreme point that the satisfaction under target window length imposes a condition are extracted, obtain mesh
Mark the period of data sequence.The periodicity extraction method of data sequence provided in an embodiment of the present invention is obtained respectively under different window length
Meet the extreme value pair to impose a condition, will include the extreme value pair and extreme value pair for meeting the extreme value to impose a condition to most windows under long
Data before extract, and obtain the period of target data sequence, the accuracy of periodicity extraction can be improved.
Optionally, according to setting means estimate obtained in periodic regime at least one window it is long after, further include as follows
Step：Obtain the maximum point and minimum point of target data sequence；Obtain the maximum value and minimum point in maximum point
Minimum value；If maximum value is greater than minimum value and minimum multiplied by the quantity for the maximum point for including between the first setting value and maximum value
Value is multiplied by the quantity for the minimum point for including between the second setting value, then extreme value is to for minimum pair；If maximum value is multiplied by first
The quantity for the maximum point for including between setting value and maximum value is less than minimum value and minimum value is wrapped multiplied by between the second setting value
The quantity of the minimum point contained, then extreme value is to for maximum pair.
Wherein, the first setting value can be the arbitrary value between 0-1, for example, being set as 3/4.Second setting value can be
Arbitrary value greater than 1, for example, can be set to 5/4.Maximum value is multiplied by the maximum for including between the first setting value and maximum value
Point can be greater than maximum value multiplied by the first setting value with value and be less than the maximum point of maximum value.Minimum value and minimum value are multiplied by
The minimum point for including between two setting values can be value greater than minimum value and be less than minimum value multiplied by the pole of the second setting value
Small value point.The scheme of the present embodiment, the foundation using the lesser extreme point of the frequency of occurrences as extracting cycle, can be improved the period
The reliability of extraction.
Optionally, it before the extreme value that will include satisfaction setting condition is determined as target window length to most window length, also wraps
Include following steps：It obtains under each window length, meets the connection of the extreme value pair of setting condition situation；Rejecting is unsatisfactory for setting
The window of condition of contact is long；Wherein, set condition of contact as：The connection number of extreme value pair is greater than and is equal to minimum logarithm multiplied by the 6th
Setting value.
Wherein, connection can be adjacent extreme value to whether being connected, if the maximum value of extreme value pair is next extreme value
Pair minimum value, then the two extreme values to be connected.Wherein, the 6th setting value can be the arbitrary value between 0-1, it is preferred that set
It is set to 0.3.The connection number of extreme value pair can be adjacent extreme value to the quantity of shared extreme value.Illustratively, under a certain window is long, there is 5
It is a to meet the extreme value pair to impose a condition, and the connection number of extreme value pair is 3,3 greater than 5*0.3, meets setting condition of contact.Another
Under window is long, there are 6 to meet the extreme value pair to impose a condition, and the connection number of extreme value pair is 1,1 less than 6*0.3, then it is long to reject the window.
Optionally, in the case where each window is long, the extreme value for meeting setting condition in target data sequence is obtained to later, is also wrapped
Include following steps：In the case where each window is long, using similarity algorithm to the extreme value of satisfaction setting condition to progress similarity detection；
Reject the extreme value pair for being unsatisfactory for similarity condition.
Wherein, similarity algorithm can be Euclidean distance algorithm or cosine similarity algorithm.In the present embodiment, it will be discontented with
The accuracy of periodicity extraction can be improved to weeding out in the extreme value of sufficient similarity condition.
Fig. 2 is the flow chart of the periodicity extraction method for another data sequence that the embodiment of the present invention one provides.As right
Above-described embodiment is explained further, as shown in Fig. 2, this method comprises the following steps.
Step 201, the period of target data sequence is estimated, periodic regime is estimated in acquisition.
Step 202, estimating the corresponding minimum value of periodic regime, to be determined as initial window long, since initial window is long and with 5/
4 Rate Index increases, and it is long to obtain at least one window estimated in periodic regime.
Step 203, obtain target data sequence maximum point and minimum point, obtain maximum point in maximum value and
The minimum value of minimum point.
Step 204, when determine maximum value multiplied by the maximum point for including between 3/4 and maximum value quantity be greater than minimum value
With minimum value multiplied by the minimum point for including between 5/4 quantity when, execute step 205.
Step 205, all minimums pair of the minimum point composition in target data sequence are obtained.
Step 206, it to each minimum to verifying, obtains and meets the first subconditional minimum pair of setting,
In, the first sub- condition of setting includes：The value of two minimum points of minimum pair is less than the minimum among two minimum points
The value of point, the index distance of two minimum points of minimum pair be less than when front window is long and be greater than when front window it is long multiplied by 4/5, it is minimum
The difference of the value of two minimum points of value pair is less than 0.2.
Step 207, the values for meeting the first subconditional minimum centering minimum point of setting all under front window is long are asked
It is averaged, the difference of the minimum point and average value of rejecting the subconditional minimum centering of the first setting of satisfaction is more than 0.2
Minimum pair obtains the minimum pair for meeting and imposing a condition.
Step 208, it obtains under each window length, meets the connection of the extreme value pair of setting condition situation, reject discontented
The window of foot setting condition of contact is long；Wherein, set condition of contact as：The connection number of extreme value pair is greater than and is equal to minimum logarithm and multiplies
With 0.3.
Step 209, in the case where each window is long, using similarity algorithm to the extreme value of satisfaction setting condition to progress similarity
Detection；Reject the extreme value pair for being unsatisfactory for similarity condition.
Step 210, will include meet the extreme value that imposes a condition it is long to most window to be determined as target window long, and extract target
The data between extreme value pair and extreme point that satisfaction under window is long imposes a condition, obtain the period of target data sequence.
Embodiment two
Fig. 3 is a kind of structural schematic diagram of the periodicity extraction device of data sequence provided by Embodiment 2 of the present invention.Such as Fig. 3
Shown, which includes：Periodic regime obtains module 301, and window is long to obtain module 302, and extreme value obtains acquisition module 303 and period
Modulus block 304.
Periodic regime obtains module 301, estimates for the period to target data sequence, and period model is estimated in acquisition
It encloses, the target data ordered series of numbers is the data sequence with setting length intercepted from data sequence；
Window is long to obtain module 302, for estimating that obtain at least one window in periodic regime long described according to setting means；
Extreme value meets setting item to module 303 is obtained, for obtaining in the case where each window is long in the target data sequence
The extreme value pair of part, the extreme value is to including maximum pair or minimum pair；
Period obtains module 304, for will include meeting the extreme value to impose a condition to be determined as target window to most window length
It is long, and the data between the extreme value pair and extreme point that the satisfaction under the target window length imposes a condition are extracted, obtain the mesh
Mark the period of data sequence.
Can sequence, further include：
Extreme point obtains module, for obtaining the maximum point and minimum point of the target data sequence；
Most value point obtains module, for obtaining the minimum in maximum value and the minimum point in the maximum point
Value；
If the maximum value is greater than institute multiplied by the quantity for the maximum point for including between the first setting value and the maximum value
Minimum value and the minimum value are stated multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to being minimum
Value pair；
If the maximum value is less than institute multiplied by the quantity for the maximum point for including between the first setting value and the maximum value
Minimum value and the minimum value are stated multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to for greatly
Value pair.
Optionally, extreme value No. 303 is used for module is obtained：
Obtain all minimums pair of the minimum point composition in the target data sequence；
To each minimum to verifying, obtains and meet the first subconditional minimum pair of setting；Wherein, it first sets
Stator condition includes：Value of the value of two minimum points of minimum pair less than the minimum point among two minimum points, pole
The index distance of two minimum points of small value pair is less than when front window is long and is greater than when front window is long multiplied by third setting value, minimum
Pair the differences of value of two minimum points be less than the first setting ratio；
Meet the first value averageds for setting subconditional minimum centering minimum point for all under front window is long,
The difference of the minimum point and average value of rejecting the subconditional minimum centering of the first setting of satisfaction is more than the second setting ratio
Minimum pair obtains the minimum pair for meeting and imposing a condition.
Optionally, extreme value is also used to module 303 is obtained：
Obtain all maximum pair of the maximum point composition in the target data sequence；
To each maximum to verifying, obtains and meet the second subconditional maximum pair of setting；Wherein, it second sets
Stator condition includes：The value of two maximum points of maximum pair is greater than the value of the maximum point among two maximum points, pole
The index distance of two maximum points of big value pair is less than when front window is long and is greater than when front window is long multiplied by the 4th setting value, maximum
Pair the differences of value of two maximum points be less than third setting ratio；
Meet the second value averageds for setting subconditional maximum centering maximum point for all under front window is long,
The difference of the maximum point and average value of rejecting the subconditional maximum centering of the second setting of satisfaction is more than the 4th setting ratio
Maximum pair obtains the maximum pair for meeting and imposing a condition.
Optionally, window is long obtains module 302, is also used to：
It estimates the corresponding minimum value of periodic regime by described to be determined as initial window long, since the initial window is long and with the
The Rate Index of five setting values increases, at least one window estimated in periodic regime described in acquisition is long；Wherein, the 5th setting
Value is respectively with third setting value and the 4th setting value at reciprocal relation.
Optionally, further include：
Connection obtains module, for obtaining under each window length, meets the connection of the extreme value pair of setting condition situation
Situation；
Window is long to reject module, long for rejecting the window for being unsatisfactory for setting condition of contact；Wherein, set condition of contact as：Pole
The connection number of value pair is greater than and is equal to minimum logarithm multiplied by the 6th setting value.
Optionally, further include：
Similarity detection module, the extreme value for being imposed a condition to satisfaction using similarity algorithm in the case where each window is long
To progress similarity detection；
Extreme value is to module is rejected, for rejecting the extreme value pair for being unsatisfactory for similarity condition.
Method provided by the executable aforementioned all embodiments of the present invention of above-mentioned apparatus, it is corresponding to have the execution above method
Functional module and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the aforementioned all implementations of the present invention
Method provided by example.
Embodiment three
Fig. 4 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention three provides, as shown in figure 4, this implementation
A kind of computer equipment that example provides, including：Processor 41 and memory 42.Processor in the computer equipment can be one
A or multiple, in Fig. 4 by taking a processor 41 as an example, processor 41 and memory 42 in the computer equipment can pass through
Bus or other modes connect, in Fig. 4 for being connected by bus.
The period of data sequence provided by the above embodiment is integrated in the processor 41 of computer equipment in the present embodiment
Extraction element.In addition, the memory 42 in the computer equipment is used as a kind of computer readable storage medium, can be used for storing one
A or multiple programs, described program can be software program, computer executable program and module, in the embodiment of the present invention
Corresponding program instruction/the module of the periodicity extraction method of data sequence.Processor 41 is stored in memory 42 by operation
Software program, instruction and module, thereby executing the various function application and data processing of equipment, i.e. the realization above method is real
Apply the periodicity extraction method of data sequence in example.
Memory 42 may include storing program area and storage data area, wherein storing program area can storage program area, extremely
Application program needed for a few function；Storage data area, which can be stored, uses created data etc. according to equipment.In addition, depositing
Reservoir 42 may include high-speed random access memory, can also include nonvolatile memory, and a for example, at least disk is deposited
Memory device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 42 can further comprise
The memory remotely located relative to processor 41, these remote memories can pass through network connection to equipment.Above-mentioned network
Example include but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
The program that processor 41 is stored in memory 42 by operation, at various function application and data
Reason realizes the periodicity extraction method of example data sequence provided in an embodiment of the present invention.
Example IV
The computer storage medium of the embodiment of the present invention, is stored thereon with computer program, which is filled by data backup
Set the periodicity extraction method realized when execution such as data sequence provided in an embodiment of the present invention.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer can
Reading storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device
Or device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：
Electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only storage with one or more conducting wires
Device (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.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of periodicity extraction method of data sequence, which is characterized in that including：
The period of target data sequence is estimated, periodic regime is estimated in acquisition, and the target data ordered series of numbers is from data sequence
What is intercepted in column has the data sequence of setting length；
Estimate that at least one window is obtained in periodic regime is long described according to setting means；
In the case where each window is long, the extreme value pair for meeting setting condition in the target data sequence is obtained, the extreme value is to including
Maximum pair or minimum pair；
To include meet the extreme value to impose a condition it is long to most window to be determined as target window long, and extract the target window it is long under
Meet the data between the extreme value pair to impose a condition and extreme point, obtains the period of the target data sequence.
2. the method according to claim 1, wherein being obtained according to setting means in described estimate in periodic regime
After taking at least one window long, further include：
Obtain the maximum point and minimum point of the target data sequence；
Obtain the minimum value in the maximum value and the minimum point in the maximum point；
If the maximum value multiplied by the quantity for the maximum point for including between the first setting value and the maximum value be greater than it is described most
Small value and the minimum value are multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to for minimum
It is right；
If the maximum value multiplied by the quantity for the maximum point for including between the first setting value and the maximum value be less than it is described most
Small value and the minimum value are multiplied by the quantity for the minimum point for including between the second setting value, then the extreme value is to for maximum
It is right.
3. according to the method described in claim 2, it is characterized in that, when the extreme value is to for minimum clock synchronization, in each window
Under length, the extreme value pair for meeting setting condition in the target data sequence is obtained, including：
Obtain all minimums pair of the minimum point composition in the target data sequence；
To each minimum to verifying, obtains and meet the first subconditional minimum pair of setting；Wherein, the first setting
Condition includes：Value, minimum of the value of two minimum points of minimum pair less than the minimum point among two minimum points
Pair the index distances of two minimum points be less than when front window is long and is greater than when front window is long multiplied by third setting value, minimum pair
The difference of the value of two minimum points is less than the first setting ratio；
By the value averageds for meeting the first subconditional minimum centering minimum point of setting all under front window is long, reject
The difference of the minimum point and average value that meet the first subconditional minimum centering of setting is more than the minimum of the second setting ratio
Value pair obtains the minimum pair for meeting and imposing a condition.
4. according to the method described in claim 2, it is characterized in that, when the extreme value is to for maximum clock synchronization, in each window
Under length, the extreme value pair for meeting setting condition in the target data sequence is obtained, including：
Obtain all maximum pair of the maximum point composition in the target data sequence；
To each maximum to verifying, obtains and meet the second subconditional maximum pair of setting；Wherein, the second setting
Condition includes：The value of two maximum points of maximum pair is greater than value, the maximum of the maximum point among two maximum points
Pair the index distances of two maximum points be less than when front window is long and is greater than when front window is long multiplied by the 4th setting value, maximum pair
The difference of the value of two maximum points is less than third setting ratio；
By the value averageds for meeting the second subconditional maximum centering maximum point of setting all under front window is long, reject
The difference of the maximum point and average value that meet the second subconditional maximum centering of setting is more than the very big of the 4th setting ratio
Value pair obtains the maximum pair for meeting and imposing a condition.
5. the method according to claim 3 or 4, which is characterized in that described to estimate period model described according to setting means
It is long to enclose interior at least one window of acquisition, further includes：
It estimates the corresponding minimum value of periodic regime by described to be determined as initial window long, set since the initial window is long and with the 5th
The Rate Index of definite value increases, at least one window estimated in periodic regime described in acquisition is long；Wherein, the 5th setting value point
Not with third setting value and the 4th setting value at reciprocal relation.
6. the method according to claim 1, wherein that will include meeting the extreme value to impose a condition to most windows
It is long to be determined as before target window length, including：
It obtains under each window length, meets the connection of the extreme value pair of setting condition situation；
It is long to reject the window for being unsatisfactory for setting condition of contact；Wherein, set condition of contact as：The connection number of extreme value pair is greater than and is equal to
Minimum logarithm is multiplied by the 6th setting value.
7. the method according to claim 1, wherein obtaining the target data sequence in the case where each window is long
It is middle meet impose a condition extreme value to later, further include：
In the case where each window is long, using similarity algorithm to the extreme value of satisfaction setting condition to progress similarity detection；
Reject the extreme value pair for being unsatisfactory for similarity condition.
8. a kind of periodicity extraction device of data sequence, which is characterized in that including：
Periodic regime obtains module, estimates for the period to target data sequence, and periodic regime, the mesh are estimated in acquisition
Mark data ordered series of numbers is the data sequence with setting length intercepted from data sequence；
Window is long to obtain module, for estimating that obtain at least one window in periodic regime long described according to setting means；
Extreme value is to module is obtained, for obtaining the pole for meeting setting condition in the target data sequence in the case where each window is long
Value pair, the extreme value is to including maximum pair or minimum pair；
Period obtains module, for will include meet the extreme value to impose a condition it is long to most window to be determined as target window long, and mention
The data between extreme value pair and extreme point that satisfaction under taking the target window long imposes a condition, obtain the target data sequence
The period of column.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes the side as described in any in claim 1-7 when executing described program
Method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810679840.3A CN108829883A (en) | 2018-06-27 | 2018-06-27 | Periodicity extraction method, apparatus, equipment and the storage medium of data sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810679840.3A CN108829883A (en) | 2018-06-27 | 2018-06-27 | Periodicity extraction method, apparatus, equipment and the storage medium of data sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108829883A true CN108829883A (en) | 2018-11-16 |
Family
ID=64139298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810679840.3A Pending CN108829883A (en) | 2018-06-27 | 2018-06-27 | Periodicity extraction method, apparatus, equipment and the storage medium of data sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108829883A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112204605A (en) * | 2019-08-29 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Extreme point extraction method, extreme point extraction device, and computer-readable storage medium |
| CN112380249A (en) * | 2020-11-24 | 2021-02-19 | 中国矿业大学(北京) | Coal face period pressure analysis method and device and electronic equipment |
| WO2021042250A1 (en) * | 2019-09-02 | 2021-03-11 | 西门子（中国）有限公司 | Method and device for determining production cycles of production equipment |
| CN112530579A (en) * | 2020-12-03 | 2021-03-19 | 上海工程技术大学 | Method for calculating vertical relative displacement of breast in Python environment |
| CN115661919A (en) * | 2022-09-26 | 2023-01-31 | 珠海视熙科技有限公司 | Repeated action cycle statistical method and device, fitness equipment and storage medium |
| CN114033369B (en) * | 2021-11-10 | 2023-11-28 | 中煤科工开采研究院有限公司 | Bidirectional coal cutting cycle analysis method based on coal cutter position and frame number |
-
2018
- 2018-06-27 CN CN201810679840.3A patent/CN108829883A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112204605A (en) * | 2019-08-29 | 2021-01-08 | 深圳市大疆创新科技有限公司 | Extreme point extraction method, extreme point extraction device, and computer-readable storage medium |
| WO2021042250A1 (en) * | 2019-09-02 | 2021-03-11 | 西门子（中国）有限公司 | Method and device for determining production cycles of production equipment |
| CN113811908A (en) * | 2019-09-02 | 2021-12-17 | 西门子（中国）有限公司 | Method and device for determining production cycle of production facility |
| CN112380249A (en) * | 2020-11-24 | 2021-02-19 | 中国矿业大学(北京) | Coal face period pressure analysis method and device and electronic equipment |
| CN112380249B (en) * | 2020-11-24 | 2023-05-30 | 中国矿业大学(北京) | Coal face period pressure analysis method and device and electronic equipment |
| CN112530579A (en) * | 2020-12-03 | 2021-03-19 | 上海工程技术大学 | Method for calculating vertical relative displacement of breast in Python environment |
| CN112530579B (en) * | 2020-12-03 | 2022-02-11 | 上海工程技术大学 | Method for calculating vertical relative displacement of breast in Python environment |
| CN114033369B (en) * | 2021-11-10 | 2023-11-28 | 中煤科工开采研究院有限公司 | Bidirectional coal cutting cycle analysis method based on coal cutter position and frame number |
| CN115661919A (en) * | 2022-09-26 | 2023-01-31 | 珠海视熙科技有限公司 | Repeated action cycle statistical method and device, fitness equipment and storage medium |
| CN115661919B (en) * | 2022-09-26 | 2023-08-29 | 珠海视熙科技有限公司 | Repeated action period statistics method and device, body-building equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829883A (en) | Periodicity extraction method, apparatus, equipment and the storage medium of data sequence | |
| CN105227626B (en) | Content pushing method and device and terminal | |
| CN104461903B (en) | The method and apparatus of test client based on browser | |
| CN109657107B (en) | Terminal matching method and device based on third-party application | |
| CN109492128A (en) | Method and apparatus for generating model | |
| CN109376267A (en) | Method and apparatus for generating model | |
| CN103634316A (en) | Account login method and electronic equipment | |
| CN105302727A (en) | Testing method, device and system | |
| CN108563571A (en) | Software interface test approach and system, computer readable storage medium, terminal | |
| CN111552633A (en) | Interface abnormal call testing method and device, computer equipment and storage medium | |
| CN106649120A (en) | Data acquisition method, and data analysis method and system | |
| CN108459964A (en) | Test cases selection method, apparatus, equipment and computer readable storage medium | |
| CN109618236A (en) | Video comments treating method and apparatus | |
| CN105701153B (en) | Method and device for reading webpage resources and electronic equipment | |
| CN106506249B (en) | Collecting method and device | |
| CN107562426B (en) | Method and system for collecting and analyzing Trace of browser in non-embedded cloud | |
| CN103108033A (en) | File uploading method and system | |
| CN109118291A (en) | User authen method, device and computer equipment in advertisement tasks popularization | |
| CN108334516A (en) | Information-pushing method and device | |
| CN109558297A (en) | EMS memory management process and device | |
| CN109271929A (en) | Detection method and device | |
| CN114757229A (en) | Signal processing method, signal processing device, electronic apparatus, and medium | |
| CN105677730B (en) | Method and device for reading webpage resources and electronic equipment | |
| CN108763050A (en) | A kind of detection method and device of application memory leakage | |
| CN115705190A (en) | Method and device for determining dependence degree |
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: 20181116 |