CN112148213B - Annotated data storage server allocation method based on evolution optimization - Google Patents
Annotated data storage server allocation method based on evolution optimization Download PDFInfo
- Publication number
- CN112148213B CN112148213B CN202010842865.8A CN202010842865A CN112148213B CN 112148213 B CN112148213 B CN 112148213B CN 202010842865 A CN202010842865 A CN 202010842865A CN 112148213 B CN112148213 B CN 112148213B
- Authority
- CN
- China
- Prior art keywords
- individual
- population
- data storage
- storage server
- nps
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0629—Configuration or reconfiguration of storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a labeled data storage server distribution method based on evolution optimization. The invention solves the allocation problem of the storage server of the marked data by adopting an improved sine and cosine algorithm. In the improved sine and cosine algorithm, firstly generating random population and setting survival time of individuals; then comprehensively considering the priority and the survival time of the individual to generate a guiding probability; selecting leading individuals based on the leading probability, executing sine and cosine operation operators based on the leading individuals, selecting excellent individuals to enter a new generation of population, and updating the survival time of the individuals; the search process is repeatedly performed until a termination condition is satisfied. The invention comprehensively considers the individual priority and the survival time to select the searching guide direction, reduces the probability of being trapped in local optimum and can improve the comprehensive storage efficiency of the distributed annotation data storage server.
Description
Technical Field
The invention relates to the field of cloud computing, in particular to an annotated data storage server allocation method based on evolution optimization.
Background
Artificial intelligence is a hot technology in modern information society. Artificial intelligence techniques have been widely applied to various industries of society, such as: intelligent video monitoring, fingerprint identification, handwriting identification, voice identification and the like. The support foundation of artificial intelligence is mass marking data. The accuracy and the usability of the artificial intelligence system can be improved well only if the system has massive marking data.
Facing to massive marking data, technicians often need to construct a cloud computing system to store the massive marking data. In a cloud computing system storing annotation data, technicians often need to solveAn annotation data storage server allocation problem: ND station annotation data storage servers are arranged in a cloud computing system, wherein each annotation data storage server has an external storage space SV dt Internal memory volume MV dt And energy consumption per unit time value PE dt Wherein the dimension subscript dt =1,2, ·, ND; for a given annotation data storage task, a server needs to be selected from ND annotation data storage servers to store annotation data, the sum of external storage of the selected annotation data storage servers is required to be maximized, the sum of internal storage of the selected annotation data storage servers is required to be greater than the lower limit LM of the internal storage, and the sum of energy consumption values per unit time of the selected annotation data storage servers is required to be less than the upper limit SE of energy consumption. The annotation data storage server allocation problem is an NP-completeness problem. When the scale of the annotation data storage server is large, the traditional method has difficulty in obtaining a better annotation data storage server allocation scheme within an acceptable time. To this end, many researchers have proposed evolutionary optimization algorithms that use natural law simulations to solve.
The sine and cosine algorithm is an evolutionary optimization algorithm which is proposed in recent years, and achieves certain effect in optimizing a plurality of practical engineering problems [ Kun, jiao Qingliang, liu Zilong, jiang Yiqin, zhang Qiaoxiang, liu Yufang, spectral characteristic peak positioning method [ J ] optical science based on improved sine and cosine algorithm, 2019,39 (09): 411-417 ]. However, the sine and cosine algorithm is easy to fall into the local optimum when solving the problem of the allocation of the storage server of the labeled data, so that the comprehensive storage efficiency of the allocated storage server of the labeled data is not high.
Disclosure of Invention
The invention provides a marked data storage server distribution method based on evolution optimization. The method can overcome the defect that the traditional sine and cosine algorithm is easy to fall into local optimum when solving the problem of allocation of the label data storage server to a certain extent, and can improve the comprehensive storage efficiency of the allocated label data storage server.
The technical scheme of the invention is as follows: a method for allocating an annotation data storage server based on evolution optimization comprises the following steps:
step 1, inputting the number ND of the labeled data storage servers;
step 2, inputting external storage space SV of ND station mark data storage server dt Internal memory MV dt And energy consumption per unit time value PE dt Wherein the dimension subscript dt =1,2, ·, ND;
step 3, inputting a lower limit LM and an upper limit SE of energy consumption of the internal memory;
step 4, setting a population size NPS, a maximum iteration number MIT and a maximum survival time MSL;
step 5, setting the current iteration times it =0;
step 6, randomly generating NPS individual composition population RP = { RA = { (RA) } 1 ,RA 2 ,...,RA ki ,...,RA NPS In which RA is ki ＝[RA ki,1 ,RA ki,2 ,...,RA ki,dt ,...,RA ki,ND ]Is the ki individual in the population, and individual RA ki Storing the responsiveness of the ND station annotation data storage server; RA ki,dt Representing individual RA ki The dt th station stored in (1) annotates the responsiveness of the data storage server; wherein the individual subscripts ki =1,2.., NPS, and the dimension subscripts dt =1,2.., ND;
step 7, calculating the adaptive values of the NPS individuals in the population; for individual RA ki Adaptation value PFit ki The calculation process of (2) is as follows: first, RA is given to the individual ki Stored ND tag data storage server responsiveness decodes into a state pool RT ki Then calculating individual RA according to equation (1) ki Adapted value PFit of ki ：
Wherein the status pool RT ki Storing the allocation status of the ND tag data storage server, and RT ki,dt Denotes RT ki The dt th station stored in (1) marks the distribution state of the data storage server; aw1 is a memory penalty factor; aw2 is an energy consumption penalty factor; wmv is the memory difference; wpe is energy consumption excess; max is a function of taking the maximum value;
step 8, setting the survival period SL of each individual in the population ki =1, wherein the individual subscript ki =1,2, ·, NPS;
step 9, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 10, calculating the integration coefficient kw according to the formula (2)
Step 11, calculating the guiding probability LP of each individual in the population according to the formula (3) ki ：
Among them, APFit ki Representing individual RA ki Individual subscript ki =1,2.., NPS;
step 12, according to the guiding probability LP of each individual in the population ki Selecting leading individual EA from population by roulette selection method ki ；
Step 13, executing sine and cosine operation operators based on the guide individuals according to the formula (4):
wherein
r2 and r4 are randomly generated, r2 is [0,2 × π]Random real number in between, and pi is the circumferential ratio; r3 is [0,2]Random real numbers in between; r4 is [0,1]Random real numbers in between; sin is a sine function; cos is a cosine function; RU (RU) ki Is a newborn individual;
step 14, calculating the new individual RU according to the formula (1) ki Adaptive value of UFit ki ；
Step 15, if newborn individual RU ki Is less than the individual RA ki The adaptation value of (a) is then to use the newly born individual RU in the population ki Replacement of individual RA ki Otherwise, individual RA is maintained in the population ki The change is not changed;
step 16, updating the survival time SL according to the formula (5) ki ：
Step 17, if SL ki If it is larger than MSL, an individual NA is randomly generated ki Then using individual NA in the population ki Replacement of individual RA ki And is provided with SL ki =1, otherwise keep individual RA in population ki The change is not changed;
step 18, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 19, setting the current iteration time it = it +1;
step 20, if the current iteration time it is greater than MIT, go to step 21, otherwise go to step 10;
and step 21, decoding the optimal individual GRA into the distribution state of the marked data storage server, and obtaining the distribution result of the marked data storage server.
The invention has the beneficial effects that: when the distribution problem of the storage server of the optimization labeling data is solved by the traditional sine and cosine algorithm, the optimal individuals in the population are directly used as search guide directions in the sine search strategy and the cosine search strategy, so that the optimization search shows larger greedy, the population is often lack of diversity, and the defect of trapping in local optimization easily occurs. In order to improve the defects of the traditional method, the invention adopts an improved sine and cosine algorithm to optimize the allocation problem of the annotation data storage server. In the modified sine-cosine algorithm, the adaptation value of an individual is set as a priority for selecting a search guidance direction, while the survival time of the individual in the population is also set as another criterion for selecting a search guidance direction. The improved sine and cosine algorithm integrates the priority and the survival time of the individual to select the search guide direction of the individual, so that the diversity of the population is kept, the probability of being trapped into local optimum is reduced, and the integrated storage efficiency of the distributed labeled data storage server can be improved.
Drawings
FIG. 1 is a flow chart of an annotated data storage server allocation method based on evolutionary optimization.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b):
in this embodiment, with reference to the accompanying drawings, the specific implementation steps of the present invention are as follows:
step 1, inputting the number ND =150 of the label data storage servers;
step 2, inputting external storage space SV of ND station mark data storage server dt Internal memory volume MV dt And energy consumption per unit time value PE dt Wherein the subscript dt =1,2,.
The annotation data storage server refers to a server for storing annotation data; wherein, the marking data refers to data which is washed and labeled; the external storage capacity refers to the size of the free space of the hard disk of the label data storage server; the internal storage refers to the size of the memory of the label data storage server; the energy consumption value in unit time refers to the power consumption of the label data storage server working for 1 hour;
step 3, inputting a lower limit LM =2600 of the internal memory space and an upper limit SE =68000 of energy consumption;
step 4, setting a population size NPS =100, a maximum iteration number MIT =3000 and a maximum survival time MSL =160;
step 5, setting the current iteration times it =0;
step 6, randomly generating NPS individual composition population RP = { RA = { (RA) } 1 ,RA 2 ,...,RA ki ,...,RA NPS In which RA is ki ＝[RA ki,1 ,RA ki,2 ,...,RA ki,dt ,...,RA ki,ND ]Is the ki individual in the population, and individual RA ki Storing the responsiveness of the ND station annotation data storage server; RA ki,dt Representing individual RA ki The dt th station stored in (1) annotates the responsiveness of the data storage server; wherein the individual subscripts ki =1,2.., NPS, and the dimension subscripts dt =1,2.., ND; the responsiveness of the annotation data storage server is [0,1]Real numbers in between;
step 7, calculating the adaptive values of NPS individuals in the population; for individual RA ki Adaptation value PFit ki The calculation process of (2) is as follows: first, RA is given to the individual ki Stored ND tag data storage server responsiveness decodes into a state pool RT ki Then calculating individual RA according to equation (1) ki Adapted value PFit of ki ：
Wherein the status pool RT ki Storing the allocation status of the ND tag data storage server, and RT ki,dt Represents RT ki The dt th station mark data storage clothes stored inThe distribution status of the server; aw1 is a memory penalty factor; aw2 is an energy consumption penalty factor; wmv is the memory difference; wpe is energy consumption excess; max is a function of taking the maximum value;
the individual RA ki Stored ND tag data storage server responsiveness decodes into a state pool RT ki The specific process is as follows: first RA is performed on an individual ki The responsiveness of the stored ND station annotation data storage server is subjected to four-round-five-in integer processing to obtain an integer with the ND value of 0 or 1, and then the obtained integer with the ND value of 0 or 1 is sequentially stored in a state pool RT ki Performing the following steps; state pool RT ki The integer with the ND value of 0 or 1 stored in the ND table is the distribution state of the ND station marking data storage server; wherein the status pool RT ki The value of 1 in the index table indicates that the corresponding label data storage server is allocated to complete the given storage task; state pool RT ki The value of 0 indicates that the corresponding label data storage server is not allocated to complete the given storage task;
step 8, setting the survival period SL of each individual in the population ki =1, where individual subscript ki =1,2, · NPS;
step 9, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 10, calculating the integration coefficient kw according to the formula (2)
Step 11, calculating the guiding probability LP of each individual in the population according to the formula (3) ki ：
Among them, APFit ki Representing individual RA ki Individual subscript ki =1,2.., NPS;
step 12, according to the guide probability LP of each individual in the population ki Using roulette wheel selectionMethod for selecting leading individual EA from population ki ；
Step 13, executing sine and cosine operation operators based on the guide individuals according to the formula (4):
wherein
r2 is [0,2 x pi ]]Random real number in between, and pi is the circumferential ratio; r3 is [0,2]Random real numbers in between; r4 is [0,1]Random real numbers in between; sin is a sine function; cos is a cosine function; RU (RU) ki Is a newborn individual;
step 14, calculating the new individual RU according to the formula (1) ki Adapted value of UFit ki ；
Step 15, if newborn individual RU ki Is less than the individual RA ki The adaptation value of (a) is then to use the newly born individual RU in the population ki Replacement of individual RA ki Otherwise, individual RA is maintained in the population ki The change is not changed;
step 16, updating the survival period SL according to the formula (5) ki ：
Step 17, if SL ki If it is larger than MSL, an individual NA is randomly generated ki Then using individual NA in the population ki Replacement of individual RA ki And is provided with SL ki =1, otherwise keep individual RA in population ki The change is not changed;
step 18, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 19, setting the current iteration time it = it +1;
step 20, if the current iteration time it is greater than MIT, go to step 21, otherwise go to step 10;
and step 21, decoding the optimal individual GRA into the distribution state of the marked data storage server, and obtaining the distribution result of the marked data storage server.
Claims (1)
1. The method for allocating the annotated data storage servers based on evolution optimization is characterized by comprising the following steps:
step 1, inputting the number ND of the labeled data storage servers;
step 2, inputting external storage space SV of ND station mark data storage server dt Internal memory volume MV dt And energy consumption per unit time value PE dt Wherein the dimension subscript dt =1,2, ·, ND;
step 3, inputting a lower limit LM and an upper limit SE of energy consumption of the internal memory;
step 4, setting a population size NPS, a maximum iteration number MIT and a maximum survival time MSL;
step 5, setting the current iteration times it =0;
step 6, randomly generating NPS individual composition population RP = { RA = { (RA) } 1 ,RA 2 ,...,RA ki ,...,RA NPS In which RA is ki ＝[RA ki,1 ,RA ki,2 ,...,RA ki,dt ,...,RA ki,ND ]Is the ki individual in the population, and individual RA ki Storing the responsiveness of the ND station annotation data storage server; RA ki,dt Representing individual RA ki The dt th station stored in (1) annotates the responsiveness of the data storage server; wherein the individual subscript ki =1,2.., NPS;
step 7, calculating the adaptive values of the NPS individuals in the population; for individual RA ki Its adaptive value PFit ki The calculation process of (2) is as follows: first, RA is given to the individual ki Stored ND tag data storage server responsiveness decodes into a state pool RT ki Then calculating individual RA according to equation (1) ki Adapted value PFit of ki ：
Wherein the status pool RT ki Storing the allocation status of the ND tag data storage server, and RT ki,dt Represents RT ki The dt th station stored in (1) marks the distribution state of the data storage server; aw1 is a memory penalty factor; aw2 is an energy consumption penalty factor; wmv is the memory difference; wpe is energy consumption excess; max is a function of taking the maximum value;
step 8, setting the survival period SL of each individual in the population ki =1, where individual subscript ki =1,2, · NPS;
step 9, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 10, calculating an integration coefficient kw according to a formula (2):
step 11, calculating the guiding probability LP of each individual in the population according to the formula (3) ki ：
Among them, APFit ki Representing individual RA ki Individual subscript ki =1,2.., NPS;
step 12, according to the guiding probability LP of each individual in the population ki Selecting leading individual EA from population by roulette selection method ki ；
Step 13, executing sine and cosine operation operators based on the guide individuals according to the formula (4):
wherein
r2 is [0,2 x pi]Random real number in between, and pi is the circumferential ratio; r3 is [0,2]Random real numbers in between; r4 is [0,1]Random real numbers in between; sin is a sine function; cos is a cosine function; RU (RU) ki Is a newborn individual;
step 14, calculating the new individual RU ki Adaptive value of UFit ki ；
Step 15, if newborn individual RU ki Is less than the individual RA ki Using the newly born individual RU in the population ki Replacement of individual RA ki Otherwise, individual RA is maintained in the population ki The change is not changed;
step 16, updating the survival time SL according to the formula (5) ki ：
Step 17, if SL ki If it is larger than MSL, an individual NA is randomly generated ki Then utilizing individual NA in the population ki Replacement of individual RA ki And set up SL ki =1, otherwise keep individual RA in population ki The change is not changed;
step 18, finding out the individual with the minimum adaptive value from the population and storing the individual with the minimum adaptive value into the optimal individual GRA;
step 19, setting the current iteration time it = it +1;
step 20, if the current iteration time it is greater than MIT, go to step 21, otherwise go to step 10;
and step 21, decoding the optimal individual GRA into the distribution state of the marked data storage server, and obtaining the distribution result of the marked data storage server.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010842865.8A CN112148213B (en) | 2020-08-20 | 2020-08-20 | Annotated data storage server allocation method based on evolution optimization |
| PCT/CN2021/096124 WO2022037164A1 (en) | 2020-08-20 | 2021-05-26 | Labeled data storage server allocation method based on evolutionary optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010842865.8A CN112148213B (en) | 2020-08-20 | 2020-08-20 | Annotated data storage server allocation method based on evolution optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112148213A CN112148213A (en) | 2020-12-29 |
| CN112148213B true CN112148213B (en) | 2022-11-29 |
Family
ID=73888596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010842865.8A Active CN112148213B (en) | 2020-08-20 | 2020-08-20 | Annotated data storage server allocation method based on evolution optimization |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112148213B (en) |
| WO (1) | WO2022037164A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148213B (en) * | 2020-08-20 | 2022-11-29 | 广东奥博信息产业股份有限公司 | Annotated data storage server allocation method based on evolution optimization |
| CN114626498B (en) * | 2022-03-02 | 2024-05-28 | 中国电建集团江西省电力建设有限公司 | Photovoltaic operation and maintenance data reconstruction method based on evolution optimization |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104023088A (en) * | 2014-06-28 | 2014-09-03 | 山东大学 | Storage server selection method applied to distributed file system |
| USRE46310E1 (en) * | 1991-12-23 | 2017-02-14 | Blanding Hovenweep, Llc | Ergonomic man-machine interface incorporating adaptive pattern recognition based control system |
| CN108694227A (en) * | 2017-04-07 | 2018-10-23 | 埃森哲环球解决方案有限公司 | Label for the supply of automatic cloud resource |
| CN109189578A (en) * | 2018-09-06 | 2019-01-11 | 北京京东尚科信息技术有限公司 | Storage server distribution method, device, management server and storage system |
| CN110472046A (en) * | 2019-07-11 | 2019-11-19 | 广东奥博信息产业股份有限公司 | A kind of government and enterprises' service Text Clustering Method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8856483B1 (en) * | 2010-09-21 | 2014-10-07 | Amazon Technologies, Inc. | Virtual data storage service with sparse provisioning |
| CN112148213B (en) * | 2020-08-20 | 2022-11-29 | 广东奥博信息产业股份有限公司 | Annotated data storage server allocation method based on evolution optimization |
-
2020
- 2020-08-20 CN CN202010842865.8A patent/CN112148213B/en active Active
-
2021
- 2021-05-26 WO PCT/CN2021/096124 patent/WO2022037164A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| USRE46310E1 (en) * | 1991-12-23 | 2017-02-14 | Blanding Hovenweep, Llc | Ergonomic man-machine interface incorporating adaptive pattern recognition based control system |
| CN104023088A (en) * | 2014-06-28 | 2014-09-03 | 山东大学 | Storage server selection method applied to distributed file system |
| CN108694227A (en) * | 2017-04-07 | 2018-10-23 | 埃森哲环球解决方案有限公司 | Label for the supply of automatic cloud resource |
| CN109189578A (en) * | 2018-09-06 | 2019-01-11 | 北京京东尚科信息技术有限公司 | Storage server distribution method, device, management server and storage system |
| CN110472046A (en) * | 2019-07-11 | 2019-11-19 | 广东奥博信息产业股份有限公司 | A kind of government and enterprises' service Text Clustering Method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112148213A (en) | 2020-12-29 |
| WO2022037164A1 (en) | 2022-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148213B (en) | Annotated data storage server allocation method based on evolution optimization | |
| CN109918532A (en) | Image search method, device, equipment and computer readable storage medium | |
| CN104199827B (en) | The high dimensional indexing method of large scale multimedia data based on local sensitivity Hash | |
| Groh et al. | Ggnn: Graph-based gpu nearest neighbor search | |
| CN112732864B (en) | Document retrieval method based on dense pseudo query vector representation | |
| CN110059875B (en) | Public bicycle demand prediction method based on distributed whale optimization algorithm | |
| CN116028838B (en) | Clustering algorithm-based energy data processing method and device and terminal equipment | |
| Cheng et al. | Select and optimize: Learning to solve large-scale tsp instances | |
| CN104731847A (en) | Search method, search program, and search device | |
| CN113836341B (en) | Remote sensing image retrieval method based on unsupervised converter balanced hash | |
| CN115048539B (en) | Social media data online retrieval method and system based on dynamic memory | |
| CN115659175A (en) | Multi-mode data analysis method, device and medium for micro-service resources | |
| CN112766400A (en) | Semi-supervised classification integration method for high-dimensional data based on multiple data transformation spaces | |
| CN112231076B (en) | Data annotation task scheduling method based on intelligent optimization | |
| CN115203378B (en) | Retrieval enhancement method, system and storage medium based on pre-training language model | |
| CN115099309A (en) | Method for designing cost evaluation model for storage and index of graph data | |
| CN111523230B (en) | Self-adaptive clustering method for wind-light load composite typical scene | |
| CN104484418B (en) | A kind of characteristic quantification method and system based on dual resolution design | |
| Elkinton et al. | Optimization algorithms for offshore wind farm micrositing | |
| CN114399152B (en) | Method and device for optimizing comprehensive energy scheduling of industrial park | |
| CN112422712B (en) | Distributed domain name storage method and system | |
| CN112084665B (en) | Modeling method and system for transformer substation and storage medium | |
| CN106777131A (en) | A kind of querying method of High dimensional space data, device and computer-readable medium | |
| CN118228812A (en) | Intelligent water conservancy-oriented AI knowledge base construction method and system | |
| CN115408571A (en) | Neighbor graph vector retrieval-oriented vector coding learning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |