CN105956164A - Data storage method and device as well as corresponding system - Google Patents
Data storage method and device as well as corresponding system Download PDFInfo
- Publication number
- CN105956164A CN105956164A CN201610334343.0A CN201610334343A CN105956164A CN 105956164 A CN105956164 A CN 105956164A CN 201610334343 A CN201610334343 A CN 201610334343A CN 105956164 A CN105956164 A CN 105956164A
- Authority
- CN
- China
- Prior art keywords
- value
- data
- key
- key value
- stored
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2272—Management thereof
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data storage method and device as well as a corresponding system. The method comprises the following steps: in a key-value rapid storage system, determining a characteristic value of a key value corresponding to each to-be-stored data according to a predetermined algorithm; and merging the key value with the to-be-stored data and storing the merged data into a storage space corresponding to the characteristic value. According to the method, the characteristic value of the key value corresponding to each to-be-stored data is determined according to the predetermined algorithm, the quantity of the characteristic values is less than the quantity of the key values, the characteristic values of the same class and with same or similar characteristics can be stored in one storage space, and the stored data is a result after the merging of the key values and the to-be-stored data, so that the subsequent search of the data is convenient, and the problem of consuming relatively much time and being low in search efficiency as search is carried out by inputting the key values one by one when much data with similar conditions are searched are solved.
Description
Technical field
The present invention relates to field of data storage, particularly relate to a kind of store the method for data, device and right
The system answered.
Background technology
For distributed key-value quick storage system, its data according to key value (key assignments) to
Form carries out organizing, index and storing, and uses internal memory to realize data storage, can effectively reduce read-write magnetic simultaneously
The number of times of dish, has more preferable readwrite performance than SQL database storage.
Use key-value quick storage system storage data, need to specify concrete key value to access number
According to, access procedure is quick.When storing the data of key value correspondence, each data store under a key value,
The number of the key value of storage is more.When retrieving data, can only individually search each data according to key value,
If during the most similar multiple data of search criterion, it is also desirable to input key value is searched one by one, consuming
More time, recall precision is low.
Summary of the invention
The present invention provides a kind of system storing the method for data, device and correspondence thereof, in order to solve existing
During key-value quick storage system retrieval data, can only individually search each data according to key value, look into
When looking for the most similar multiple data of condition, also can only input key value one by one and search, when expending more
Between, the problem that recall precision is low.
For solving above-mentioned technical problem, on the one hand, the present invention provides a kind of method storing data, including:
In key-value quick storage system, determine, according to pre-defined algorithm, the key that each data to be stored are corresponding
The eigenvalue of value;Described key value is merged with described data to be stored, and will merge after data be deposited into
In the memory space that described eigenvalue is corresponding.
Further, determine the eigenvalue of key value corresponding to each data to be stored according to pre-defined algorithm, including:
In the case of described pre-defined algorithm is built-in interval method, using predetermined amount of time as in described predetermined amount of time
All key value characteristic of correspondence values;Or, in the case of described pre-defined algorithm is remainder numerical method,
Using key value corresponding for each data to be stored divided by the remainder obtained after predetermined number as described key value
Eigenvalue.
Further, described key value is merged with described data to be stored, and will merge after data be deposited into
In the memory space that described eigenvalue is corresponding, including: using the described eigenvalue that determines as described key-value
Key value new in quick storage system;Described key value is merged with described data to be stored, and determines conjunction
Data after and are value part;The storage that described value part is stored in described new key value corresponding is empty
In.
Further, described key value is merged with described data to be stored, including: by separator by described
Key value is separated with described data to be stored, and the data after separating merge;Or, arrange from
Predetermined the byte that storage section start starts store a described key value, arrange after described predetermined individual byte its
He stores described data to be stored at byte.
Further, described method also includes: receive the index value for searching data, wherein, described index
Value includes: eigenvalue, or, key value;According to described index value in described key-value quick storage system
System is searched data.
Further, in described key-value quick storage system, search data according to described index value, bag
Include: in the case of described index value is characterized value, search in described key-value quick storage system
Total data in the memory space that described eigenvalue is corresponding;In the case of described index value is key value,
Calculate described key value characteristic of correspondence value, and find institute in described key-value quick storage system
State the total data in the memory space that eigenvalue is corresponding, then in described total data, search described key value
Corresponding data.
On the other hand, the present invention provides a kind of device storing data, comprises determining that module, is used for
In key-value quick storage system, determine key value corresponding to each data to be stored according to pre-defined algorithm
Eigenvalue;Memory module, for described key value is merged with described data to be stored, and will be after merging
Data are deposited in the memory space that described eigenvalue is corresponding.
Further, described determine module, be additionally operable in the case of described pre-defined algorithm is built-in interval method,
Using predetermined amount of time as all key value characteristic of correspondence values in described predetermined amount of time;Described predetermined
In the case of algorithm is remainder numerical method, by key value corresponding for each data to be stored divided by predetermined number after
The remainder obtained is as the eigenvalue of described key value.
Further, described memory module includes: first determines unit, makees for the described eigenvalue that will determine
For key value new in described key-value quick storage system;Second determines unit, for by described key
Value merges with described data to be stored, and determines that the data after merging are value part;Memory element, uses
In described value part is stored in the memory space that described new key value is corresponding.
Further, described second determines unit, is additionally operable to described key value be deposited with described waiting by separator
Storage data are separated, and the data after separating merge;Or, arrange from storing what section start started
Predetermined byte store a described key value, described predetermined byte is set after other bytes store described in treat
Storage data.
Further, described device also includes: receiver module, for receiving the index value for searching data,
Wherein, described index value includes: eigenvalue, or, key value;Search module, for according to described rope
Draw value in described key-value quick storage system, search data.
Further, described lookup module, it is additionally operable in the case of described index value is characterized value, described
Key-value quick storage system is searched the total data in the memory space that described eigenvalue is corresponding;Institute
State in the case of index value is key value, calculate described key value characteristic of correspondence value, and at described key-value
Quick storage system finds the total data in the memory space that described eigenvalue is corresponding, then described entirely
Portion's data are searched the data that described key value is corresponding.
Another aspect, the present invention provides a kind of key-value quick storage system, including: above-mentioned storage
The device of data.
The present invention determines the eigenvalue of key value corresponding to each data to be stored, eigenvalue according to pre-defined algorithm
Quantity store less than the quantity of key value, the key value that a class the most just can be had same or similar feature
In a memory space, facilitate follow-up according to eigenvalue search data, and storage data be key value and
Result after data to be stored merging, also saves the corresponding relation of key value and data to be stored, after convenience
Continuous lookup data, solve existing when key-value quick storage system retrieval data, can only be according to key
Value individually searches each data, when multiple data that search criterion is the most similar, also can only input one by one
Key value is searched, and expends more time, the problem that recall precision is low.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method storing data in the embodiment of the present invention;
Fig. 2 is the structural representation of the device storing data in the embodiment of the present invention;
Fig. 3 is the structural representation of the device memory module storing data in the embodiment of the present invention;
Fig. 4 is the preferred structure schematic diagram of the device storing data in the embodiment of the present invention;
Fig. 5 is the data store organisation schematic diagram of key-value quick storage system in prior art;
Fig. 6 is the data store organisation signal of key-value quick storage system in the preferred embodiment of the present invention
Figure.
Detailed description of the invention
Existing when key-value quick storage system retrieval data in order to solve, can only be single according to key value
Solely search each data, when multiple data that search criterion is the most similar, also can only input key one by one
Value is searched, and expends more time, the problem that recall precision is low, the invention provides a kind of storage data
The system of method, device and correspondence thereof, below in conjunction with accompanying drawing and embodiment, the present invention is entered one
Step describes in detail.Should be appreciated that specific embodiment described herein only in order to explain the present invention, not
Limit the present invention.
Embodiments providing a kind of method storing data, the flow process of the method is as it is shown in figure 1, wrap
Include step S102 to S104:
S102, in key-value quick storage system, determines each data to be stored according to pre-defined algorithm
The eigenvalue of corresponding key value;
S104, merges key value with data to be stored, and the data after merging to be deposited into eigenvalue corresponding
Memory space in.
The embodiment of the present invention determines the eigenvalue of key value corresponding to each data to be stored according to pre-defined algorithm,
One class, less than the quantity of key value, the most just can be had the key of same or similar feature by the quantity of eigenvalue
Value is stored in a memory space, facilitates follow-up according to eigenvalue lookup data, and the data of storage are key
It is worth the result after merging with data to be stored, also saves the corresponding relation of key value and data to be stored, side
Continuous lookup data after an action of the bowels, solve existing when key-value quick storage system retrieval data, Zhi Nenggen
Each data are individually searched according to key value, when multiple data that search criterion is the most similar, also can only one
Individual input key value is searched, and expends more time, the problem that recall precision is low.
When realizing, when determining the eigenvalue of key value corresponding to each data to be stored according to pre-defined algorithm, can
To use multiple pre-defined algorithm, the most commonly used built-in interval method and remainder numerical method.At pre-defined algorithm
In the case of built-in interval method, using predetermined amount of time as all key values correspondence in predetermined amount of time
Eigenvalue, such as, arranges an eigenvalue, then within this time period by 10:00 to the 10:20 time period
Data are stored in the memory space that this feature value is corresponding.In the case of pre-defined algorithm is remainder numerical method,
Using key value corresponding for each data to be stored divided by the remainder obtained after predetermined number as the feature of key value
Value, such as, in the case of there are 10 station servers, can use the method, thus can search
The data of storage on every station server.
Data after key value is merged with data to be stored and will be merged are deposited into the storage that eigenvalue is corresponding
Time in space, specifically can include following process: using the eigenvalue that determines as key-value quick storage
Key value new in system;Key value is merged with data to be stored, and determines that the data after merging are value
Part;Value part is stored in the memory space that new key value is corresponding.Original data store organisation
Including key value part and value part, original key value is exactly the serial number that storage generates, this sequence
Number it is discontinuous discrete series under normal circumstances, but, the embodiment of the present invention is according to key value generation one
Individual eigenvalue, this feature value substitutes the key value part of various discrete originally, again by key value and value originally
Part is stored along, also will not lose data message, it is possible to more convenient later retrieval process.
When key value is merged with data to be stored, by separator, key value can be entered with data to be stored
Row separate, then will separate after data merge;It is, of course, also possible to arrange from storing what section start started
Make a reservation for a byte storage key value, other bytes storage data to be stored after predetermined byte are set, then
Front predetermined byte is just used to store key value, avoids the need for making a distinction with separator.By key
When value merges with data to be stored, it is also possible to after original key value is stored in data to be stored, ability
Field technique personnel can be configured according to the actual requirements, above-mentioned key value is stored in data to be stored it
Front mode, more convenient can check and find data.
After storing data, if need to search data, and data can be retrieved, now, receive
For searching the index value of data, wherein, index value can be eigenvalue, it is also possible to be key value;Subsequently,
In key-value quick storage system, data are searched further according to index value.If using eigenvalue to carry out
Retrieval, then that retrieves is frequently not individual data, it may be possible to more one group of data with certain series of features,
If using key value to retrieve, then retrieve is single data, when retrieval, and first basis
The key value received, to determine eigenvalue, finds the data of storage further according to eigenvalue, at this point it is possible to
In the data of storage, the data of key value correspondence are directly found according to above-mentioned key value, it is of course also possible to hands
Dynamic lookup.
The embodiment of the present invention additionally provides a kind of device storing data, the structural representation of this device such as Fig. 2 institute
Show, comprise determining that module 10, in key-value quick storage system, true according to pre-defined algorithm
The eigenvalue of the key value that fixed each data to be stored are corresponding;Memory module 20, and determines that module 10 couples,
For key value is merged with data to be stored, and will merge after data be deposited into the storage that eigenvalue is corresponding
In space.
During realization, determine module 10, be additionally operable in the case of pre-defined algorithm is built-in interval method, will
Predetermined amount of time is as all key value characteristic of correspondence values in predetermined amount of time;It is remainder at pre-defined algorithm
In the case of numerical method, by key value corresponding for each data to be stored divided by the remainder obtained after predetermined number
Eigenvalue as key value.
Fig. 3 shows the structural representation of memory module 20, comprising: first determines unit 201, is used for
Using the eigenvalue that determines as key value new in key-value quick storage system;Second determines unit 202,
For key value being merged with data to be stored, and determine that the data after merging are value part;Storage is single
Unit 203, determines that with first unit 201 and second determines that unit 202 couples, for value part being deposited
Enter in the memory space that new key value is corresponding.
Wherein, second determines unit 202, is additionally operable to key value be carried out with data to be stored by separator
Separating, the data after separating merge;Or, predetermined the byte started from storage section start is set
Store key value, other bytes storage data to be stored after predetermined byte are set.
Further, Fig. 4 shows the preferred structure schematic diagram of said apparatus, and said apparatus can also include:
Receiver module 30, couples with memory module 20, for receiving the index value for searching data, wherein,
Index value includes: eigenvalue, or, key value;Search module 40, couple with receiver module 30, use
In searching data in key-value quick storage system according to index value.
Wherein, above-mentioned lookup module 40, specifically can be also used in the case of index value is characterized value,
Key-value quick storage system is searched the total data in the memory space that eigenvalue is corresponding;At index value
In the case of key value, calculate key value characteristic of correspondence value, and at key-value quick storage system
In find the total data in the memory space that eigenvalue is corresponding, then it is right to search key value in total data
The data answered.
The embodiment of the present invention also provides for a kind of key-value quick storage system, and this system includes above-mentioned depositing
The device of storage data.Those skilled in the art, according to above-mentioned record, know how to be arranged on said apparatus
In key-value quick storage system, here is omitted.
Preferred embodiment
Embodiments provide a kind of method storing data, apply in key-value quick storage system
In system, scheme is as follows: according to pre-defined algorithm, key value is carried out pretreatment, to calculate eigenvalue, due to
Algorithm is predetermined in order to can be by data corresponding to extensive search multiple key value, therefore,
Multiple key values can calculate same eigenvalue, uses eigenvalue storage data, can reduce in a large number and deposit
The quantity of storage key;Wherein, pre-defined algorithm can include multiple, such as, and built-in interval method or remainder number
Value method, certainly, in the conceived case, it is also possible to use the methods such as the Hash method through converting to realize mesh
's.On the data store, actual key value merges storage with data to be stored, therefore, it is possible to reduce cache layer
Secondary and accelerate recall precision.When retrieval, it is possible to realize by interval (a certain feature) retrieval data.
Below in conjunction with the accompanying drawings the embodiment of the present invention is further described.
As it is shown in figure 5, be the data store organisation signal of key-value quick storage system in prior art
Figure, wherein, key part stores actual key value, the data that value part storage is actual.Fig. 6 shows
After the method for storage data of embodiment of the present invention offer is provided, in key-value quick storage system
Data store organisation schematic diagram, wherein, when key-value quick storage system is stored in data, key part
For calculating the eigenvalue of gained, value part storage data list, after actual key value merges with data
The list of data item, during storage, front 4 storages key length (byte number of key, examples can be set
" 9 " as in Fig. 6), the actual key of sequential storage and real data afterwards, form data item.
The present embodiment also provides for a kind of device storing data, when realizing, and can be by this device with computer
The form of program realizes, and to form independent application, it is quick that this application may reside in key-value
In storage system.
During using application to store, according to actual key value (such as: 20151215134406.356)
Can directly calculate eigenvalue (such as: 20151215134400);Use eigenvalue be key part from
Key-value caching gets value (list of data items);Actual key value and real data are combined,
Form data item;Data item to be stored is merged in value part (can be appended to list of data items afterbody);
By in key-value caching corresponding for value part storage to eigenvalue.
During using application to retrieve, directly calculate eigenvalue according to key value, or directly input
Eigenvalue;Eigenvalue is used to obtain multi-group data item list;Merging data item list;Decompose each data item,
Form retrieval result.
The embodiment of the present invention possesses advantages below: extend the range of key-value quick storage system;
Can be with flexible expansion for different business data;Key value continuous print data can be stored;Can examine by interval
Rope key value continuous print data;Compression memory space.
Although being example purpose, having been disclosed for the preferred embodiments of the present invention, those skilled in the art will
It is also possible for recognizing various improvement, increasing and replace, therefore, on the scope of the present invention should be not limited to
State embodiment.
Claims (13)
1. the method storing data, it is characterised in that including:
In key-value quick storage system, determine that each data to be stored are corresponding according to pre-defined algorithm
The eigenvalue of key value;
Described key value is merged with described data to be stored, and will merge after data be deposited into described feature
In the memory space that value is corresponding.
2. the method for claim 1, it is characterised in that determine that each waiting is deposited according to pre-defined algorithm
The eigenvalue of the key value that storage data are corresponding, including:
In the case of described pre-defined algorithm is built-in interval method, using predetermined amount of time as the described scheduled time
All key value characteristic of correspondence values in Duan;Or,
In the case of described pre-defined algorithm is remainder numerical method, by key value corresponding for each data to be stored
Divided by the remainder obtained after predetermined number as the eigenvalue of described key value.
3. the method for claim 1, it is characterised in that described key value is to be stored with described
Data merge, and will merge after data be deposited in the memory space that described eigenvalue is corresponding, including:
Using the described eigenvalue that determines as key value new in described key-value quick storage system;
Described key value is merged with described data to be stored, and determines that the data after merging are value part;
Described value part is stored in the memory space that described new key value is corresponding.
4. method as claimed in claim 3, it is characterised in that described key value is to be stored with described
Data merge, including:
Described key value being separated with described data to be stored by separator, the data after separating are entered
Row merges;Or,
Arrange predetermined the byte started from storage section start to store described key value, arrange described predetermined word
Other bytes after joint store described data to be stored.
5. the method as according to any one of Claims 1-4, it is characterised in that described method is also wrapped
Include:
Receiving the index value for searching data, wherein, described index value includes: eigenvalue, or, key
Value;
In described key-value quick storage system, data are searched according to described index value.
6. method as claimed in claim 5, it is characterised in that according to described index value described
Key-value quick storage system is searched data, including:
In the case of described index value is characterized value, search in described key-value quick storage system
Total data in the memory space that described eigenvalue is corresponding;
In the case of described index value is key value, calculate described key value characteristic of correspondence value, and in institute
State and key-value quick storage system find the total data in the memory space that described eigenvalue is corresponding,
The data that described key value is corresponding are searched again in described total data.
7. the device storing data, it is characterised in that including:
Determine module, in key-value quick storage system, determine each treating according to pre-defined algorithm
The eigenvalue of the key value that storage data are corresponding;
Memory module, for merging described key value with described data to be stored, and by the data after merging
It is deposited in the memory space that described eigenvalue is corresponding.
8. the device stated such as claim 7, it is characterised in that
Described determine module, be additionally operable in the case of described pre-defined algorithm is built-in interval method, will timing in advance
Between section as all key value characteristic of correspondence values in described predetermined amount of time;At described pre-defined algorithm for taking
In the case of remainder values method, by key value corresponding for each data to be stored divided by more than obtaining after predetermined number
Number is as the eigenvalue of described key value.
9. device as claimed in claim 7, it is characterised in that described memory module includes:
First determines unit, for will the described eigenvalue that determine as described key-value quick storage system
Key value new in system;
Second determines unit, for described key value being merged with described data to be stored, and after determining merging
Data be value part;
Memory element, for being stored in described value part in the memory space that described new key value is corresponding.
10. device as claimed in claim 9, it is characterised in that
Described second determines unit, is additionally operable to described key value be entered with described data to be stored by separator
Row separates, and the data after separating merge;Or, predetermined the word started from storage section start is set
Joint stores described key value, arranges other bytes described data to be stored of storage after described predetermined byte.
11. devices as according to any one of claim 7 to 10, it is characterised in that described device is also
Including:
Receiver module, for receiving the index value for searching data, wherein, described index value includes: special
Value indicative, or, key value;
Search module, for searching number in described key-value quick storage system according to described index value
According to.
12. devices as claimed in claim 11, it is characterised in that
Described lookup module, is additionally operable in the case of described index value is characterized value, at described key-value
Quick storage system is searched the total data in the memory space that described eigenvalue is corresponding;At described index value
In the case of key value, calculate described key value characteristic of correspondence value, and quick at described key-value
Storage system finds the total data in the memory space that described eigenvalue is corresponding, then at described whole numbers
According to the data that middle lookup described key value is corresponding.
13. 1 kinds of key-value quick storage systems, it is characterised in that including: claim 7 to 12
According to any one of the device of storage data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610334343.0A CN105956164A (en) | 2016-05-19 | 2016-05-19 | Data storage method and device as well as corresponding system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610334343.0A CN105956164A (en) | 2016-05-19 | 2016-05-19 | Data storage method and device as well as corresponding system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105956164A true CN105956164A (en) | 2016-09-21 |
Family
ID=56912862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610334343.0A Pending CN105956164A (en) | 2016-05-19 | 2016-05-19 | Data storage method and device as well as corresponding system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105956164A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799628A (en) * | 2012-06-21 | 2012-11-28 | 新浪网技术(中国)有限公司 | Method and device for data partitioning in key-value database |
CN103370113A (en) * | 2012-12-12 | 2013-10-23 | 华为技术有限公司 | Data storage method and data storage system |
CN104731864A (en) * | 2015-02-26 | 2015-06-24 | 国家计算机网络与信息安全管理中心 | Data storage method for mass unstructured data |
CN105260464A (en) * | 2015-10-16 | 2016-01-20 | 北京奇虎科技有限公司 | Data storage structure conversion method and apparatus |
CN105320775A (en) * | 2015-11-11 | 2016-02-10 | 中科曙光信息技术无锡有限公司 | Data access method and apparatus |
-
2016
- 2016-05-19 CN CN201610334343.0A patent/CN105956164A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102799628A (en) * | 2012-06-21 | 2012-11-28 | 新浪网技术(中国)有限公司 | Method and device for data partitioning in key-value database |
CN103370113A (en) * | 2012-12-12 | 2013-10-23 | 华为技术有限公司 | Data storage method and data storage system |
CN104731864A (en) * | 2015-02-26 | 2015-06-24 | 国家计算机网络与信息安全管理中心 | Data storage method for mass unstructured data |
CN105260464A (en) * | 2015-10-16 | 2016-01-20 | 北京奇虎科技有限公司 | Data storage structure conversion method and apparatus |
CN105320775A (en) * | 2015-11-11 | 2016-02-10 | 中科曙光信息技术无锡有限公司 | Data access method and apparatus |
Non-Patent Citations (1)
Title |
---|
陈敏 等: "《大数据浪潮 大数据整体解决方案及关键技术探索》", 31 October 2015, 华中科技大学出版社 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180011861A1 (en) | Managing storage of individually accessible data units | |
EP2729884B1 (en) | Managing storage of data for range-based searching | |
US7853770B2 (en) | Storage system, data relocation method thereof, and recording medium that records data relocation program | |
CN102521406B (en) | Distributed query method and system for complex task of querying massive structured data | |
US7885932B2 (en) | Managing storage of individually accessible data units | |
CN106959963A (en) | A kind of data query method, apparatus and system | |
CN101867607A (en) | Distributed data access method, device and system | |
CN105302840B (en) | A kind of buffer memory management method and equipment | |
EP3289484B1 (en) | Method and database computer system for performing a database query using a bitmap index | |
CN105956123A (en) | Local updating software-based data processing method and apparatus | |
CN104424219B (en) | A kind of management method and device of data file | |
KR20130036094A (en) | Managing storage of individually accessible data units | |
CN110245134B (en) | Increment synchronization method applied to search service | |
CN114281819A (en) | Data query method, device, equipment and storage medium | |
US20130007394A1 (en) | Reorganization of a fragmented directory of a storage data structure comprised of the fragmented directory and members | |
CN105956164A (en) | Data storage method and device as well as corresponding system | |
CN109241098B (en) | Query optimization method for distributed database | |
CN113127717A (en) | Key retrieval method and system | |
CN111949439B (en) | Database-based data file updating method and device | |
CN111651475B (en) | Information generation method and device, electronic equipment and computer readable medium | |
AU2015258326B2 (en) | Managing storage of individually accessible data units | |
US20150324408A1 (en) | Hybrid storage method and apparatus | |
CN113971238A (en) | Data retrieval method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20160921 |