CN107341126A - Mobile object inquiry unit - Google Patents
Mobile object inquiry unit Download PDFInfo
- Publication number
- CN107341126A CN107341126A CN201710446556.7A CN201710446556A CN107341126A CN 107341126 A CN107341126 A CN 107341126A CN 201710446556 A CN201710446556 A CN 201710446556A CN 107341126 A CN107341126 A CN 107341126A
- Authority
- CN
- China
- Prior art keywords
- mobile object
- data
- module
- inquiry
- communicated
- 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
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/02—Digital computers in general; Data processing equipment in general manually operated with input through keyboard and computation using a built-in program, e.g. pocket calculators
- G06F15/025—Digital computers in general; Data processing equipment in general manually operated with input through keyboard and computation using a built-in program, e.g. pocket calculators adapted to a specific application
- G06F15/0283—Digital computers in general; Data processing equipment in general manually operated with input through keyboard and computation using a built-in program, e.g. pocket calculators adapted to a specific application for data storage and retrieval
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of mobile object inquiry unit, belongs to high-performance computing sector and database field.The mobile object inquiry unit includes：Pretreatment module, the mobile object for being detected in real time by buffer update the data the inquiry data with user's input；And execution module, communicated with the pretreatment module, updated the data and the inquiry data for obtaining the mobile object from the pretreatment module, and the mobile object is updated the data by multi-core CPU and rebuilds index with the inquiry data, the index structure built is calculated by GPU again, to obtain Query Result.The embodiment of the present invention is proposed based on the high-throughput mobile object query processing framework under new hardware environment, the characteristics of big internal memory, multi-core CPU, GPU can be given full play to, so as to improve the query processing efficiency of mobile object, it can more meet user's query demand based on location-based service under big data.
Description
Technical field
The present invention relates to high-performance computing sector and database field, more particularly to a kind of mobile object inquiry unit.
Background technology
With the rapid development of global positioning system, wireless communication technology, mobile calculation technique, network technology etc., largely
Mobile device (such as mobile phone, tablet personal computer and various mobile units) progresses into daily life, location Based service
(Location based Service, LBS) gradually rises and is used widely.It is various fixed that LBS refers to that mobile device utilizes
Position technology obtains current location information, then obtains a certain service by wireless network, such as：User can carry out intelligent transportation
Control, the diffusion monitoring of pollutant, the mobile route of hurricane and coverage monitoring etc..
At present, the research on LBS is principally dedicated to the quick renewal for solving the problems, such as mobile object and inquiry real-time response.
But present inventor has found that this kind of scheme has the disadvantage that during the present invention is realized：
1) such scheme needs to build complicated index structure, and constantly safeguards index structure with the arrival subsequently updated.
2) with the swift and violent growth of number of users and enriching constantly for application scenarios, its algorithm process framework can not be good
Tackle the new demand of location-based service under big data.
Therefore, it is necessary to new mobile object query scheme be found, to meet the query demand of location-based service under big data.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of mobile object inquiry unit, and the mobile object inquiry unit is used for real
Now meet the mobile object query scheme of the query demand of location-based service under big data.
To achieve these goals, the embodiment of the present invention provides a kind of mobile object inquiry unit, and the mobile object is looked into
Asking device includes：Pretreatment module, the mobile object for being detected in real time by buffer updates the data to be inputted with user
Inquiry data；And execution module, communicated with the pretreatment module, for obtaining the movement from the pretreatment module
Object update the data with the inquiry data, and the mobile object is updated the data and the inquiry data by multi-core CPU
Index is rebuild, then the index structure built is calculated by GPU, to obtain Query Result.
Alternatively, the pretreatment module is configured with multiple snapshot spaces, and in each snapshot space, passes through
The mobile object that buffer detects in real time updates the data the inquiry data with user's input.
Alternatively, the execution module includes：Receiving submodule, communicated with the pretreatment module, for from described pre-
Processing module obtains the mobile object and updated the data and the inquiry data；First implementation sub-module, with the reception submodule
Block is communicated, and index is rebuild with the inquiry data for being updated the data by multi-core CPU to the mobile object；And the
Two implementation sub-modules, communicated with first implementation sub-module, for being calculated by GPU the index structure built,
To obtain Query Result.
Alternatively, the execution module is configured as updating the data the mobile object by a multi-core CPU and institute
State inquiry data and rebuild index, and the index structure built is calculated by several GPU.
Alternatively, the mobile object inquiry unit also includes：Scheduler module, communicated with the execution module, for obtaining
The Query Result is taken, and the Query Result is distributed to user.
Alternatively, the scheduler module includes：Distribute submodule, communicated with the execution module, for obtaining described look into
Ask result and the Query Result is distributed to user；And submodule is deleted, communicated with the execution module, for obtaining simultaneously
Delete caused intermediate result during the execution module is calculated.
Pass through above-mentioned technical proposal, beneficial effect possessed by the embodiment of the present invention are：The movement pair of the embodiment of the present invention
, can be with as inquiry unit and method propose one based on the high-throughput mobile object query processing framework under new hardware environment
The characteristics of having given full play to big internal memory, multi-core CPU, GPU, so as to improve the query processing efficiency of mobile object, it can more meet
User's query demand based on location-based service under big data.
The further feature and advantage of the embodiment of the present invention will be described in detail in subsequent specific embodiment part.
Brief description of the drawings
Accompanying drawing is that the embodiment of the present invention is further understood for providing, and a part for constitution instruction, with
The embodiment in face is used to explain the embodiment of the present invention together, but does not form the limitation to the embodiment of the present invention.Attached
In figure：
Fig. 1 is the structural representation of mobile object inquiry unit according to embodiments of the present invention；
Fig. 2 is the configuration diagram of GPGPU model according to embodiments of the present invention；
Fig. 3 is the structural representation of execution module according to embodiments of the present invention；
Fig. 4 is the structural representation of scheduler module according to embodiments of the present invention；And
Fig. 5 is the schematic diagram of query processing framework according to embodiments of the present invention.
Description of reference numerals
The execution module of 100 pretreatment module 200
The receiving submodule of 300 scheduler module 201
The implementation sub-module of 202 first implementation sub-module 203 second
301 distribution submodules 302 delete submodule
Embodiment
The embodiment of the embodiment of the present invention is described in detail below in conjunction with accompanying drawing.It should be appreciated that this
The embodiment of place description is merely to illustrate and explain the present invention embodiment, is not intended to limit the invention embodiment.
Present inventor has found handling up in many big datas are applied system by the investigation to many LBS technologies
Amount is key factor, and optimizes the processing time of single query, it is impossible to as the key of lifting whole system handling capacity.For big
For certain applications, as long as the response time of single query reaches second level can meet demand, it is not necessary to deliberately pursue single
The response time of inquiry, such as typical application (APP) of calling a taxi, as long as most of user can meet with a response in seconds
With regard to that can meet to require, for faster query responding time, the service experience of user does not have significant change.For whole system,
When a large amount of inquiries pour in, inquiry needs to be lined up with wait-for-response, the queue waiting time of inquiry, it will influences obtaining for user
The time of response.Therefore, the handling capacity of system is improved, reduces the queue waiting time of user, the service experience to increasing user
It is most important.
Based on this thinking, the embodiment of the present invention proposes a kind of mobile object inquiry unit, as shown in figure 1, the movement
Object Query device includes：Pretreatment module 100, for the shifting detected in real time by buffer (hereinafter referred to as Buffer) caching
Dynamic object updates the data the inquiry data with user's input；And execution module 200, communicate, use with the pretreatment module 100
In from the pretreatment module 100 obtain the mobile object update the data with the inquiry data, and by multi-core CPU to institute
State mobile object and update the data and rebuild index with the inquiry data, then pass through GPU (Graphics Processing
Unit, graphics processing unit) index structure built is calculated, to obtain Query Result.
Wherein, mobile object updates the data the change of the real time position for the vehicle being related in e.g. typical application of calling a taxi,
Inquiry data are, for example, inquiry of the user being related in typical application of calling a taxi to the taxi in neighbouring two kilometers.
Wherein, it is known that the execution module 200 has fully used multi-core CPU and GPU characteristic, for being arrived in Buffer
Mobile object renewal inquiry, by way of rebuilding index, given full play to the characteristic of multi-core CPU；For building
Index structure, be skillful in the feature of high-speed data computing using GPU, improve the performance of algorithm queries.
In addition, the execution module 200 also uses Large Copacity memory techniques, i.e., by workload, (i.e. Buffer is cached
Inquiry data and mobile object update the data) be all placed in multi-core CPU and handled, so as to take full advantage of the sky of data
Between locality, the hit rate of cache is added, so as to be advantageous to the follow-up execution efficiency for improving related algorithm.
Therefore, it is known that the mobile object inquiry unit of the embodiment of the present invention be configured with based on Large Copacity internal memory, multi-core CPU and
The inquiry framework of GPU new hardware environment, the concrete configuration of the inquiry framework can be such as：Configuring every can provide in 12TB
Some 8 road servers deposited, maximum reachable 18 server of configuration CPU core number, and be configured to do on a large scale
The GPU of concurrent operation.Wherein, it is data cached by Buffer, it is responsible for performing the discomforts such as complex logic processing and transaction management by CPU
The calculating of data parallel is closed, is responsible for the Large-scale parallel computing of computation-intensive by GPU.
Further, multi-core CPU and GPU cooperation constitute GPGPU (General Purpose GPU, general purpose
GPU) model.As shown in Fig. 2 in GPGPU model, CPU is as main frame (Host), and GPU is as coprocessor or equipment
(Device).There may be a main frame and several equipment in a system, you can be interpreted as：The execution module 200
It is configured as updating the data the mobile object by a multi-core CPU and rebuilds index with the inquiry data, passes through
Several GPU are calculated the index structure built.
In addition, multi-core CPU is that the data for building the Grid indexes completed are delivered into GPU ends in units of cell, such as
Shown in Fig. 2, GPU ends remain the data storage scheme of the cell based on Grid indexes at multi-core CPU end, and GPU is to identical list
Mobile object in first lattice updates the data and inquired about data and calculated, and, can be parallel. between unit lattice independently of each other
Perform.Wherein, the cell (2,0) such as in Fig. 2 refers to the cell that two-dimentional theorem in Euclid space coordinate is (2,0), and GPU is to the list
Data in first lattice, which carry out calculating, can obtain relevant query result.
In this GPGPU model, CPU and GPU cooperates, and Each performs its own functions, and CPU is responsible for carrying out the strong things of logicality
Processing and serial computing, GPU, which is then absorbed in, performs highly threading parallel processing task.Therefore once it is determined that program and
Row part, it is possible to consider this part evaluation work to give GPU.
It should be noted that CPU, GPU each possess separate memory address space, i.e.,：The internal memory of host side and
The video memory of equipment end.
Based on GPGPU model framework, as shown in figure 3, the execution module 200 is preferably to include：Receiving submodule
201, communicated with the pretreatment module 100, for from the pretreatment module 100 obtain the mobile object update the data and
The inquiry data；First implementation sub-module 202, communicated with the receiving submodule 201, for by multi-core CPU to described
Mobile object updates the data rebuilds index with the inquiry data；And second implementation sub-module 203, held with described first
Row submodule 202 communicates, for being calculated by GPU the index structure built, to obtain Query Result.
Understanding, receiving submodule 201 is used to realize the information exchange between execution module 200 and pretreatment module 100, and
First implementation sub-module 202 and the second implementation sub-module are engaged the information processing framework to be formed based on GPGPU model.
In addition, in the present embodiment, the pretreatment module 100 is preferably to be configured with multiple snapshot spaces, and
In each snapshot space, the mobile object detected in real time by Buffer cachings updates the data the inquiry number inputted with user
According to.In this way, subsequently in execution module 200, the mobile object in snapshot can be updated the data and be inquired about data structure index, have
Beneficial to the hardware performance for playing multi-core CPU.
Wherein, the principle and specific method on snapshot, refers to existing pertinent literature, and the embodiment of the present invention is herein no longer
Repeat.
Further, the mobile object inquiry unit of the embodiment of the present invention preferably also includes：Scheduler module 300, with institute
State execution module 200 to communicate, user is distributed to for obtaining the Query Result, and by the Query Result.
In addition to Query Result is distributed, the scheduler module 300 of the present embodiment is also preferably that can delete some intermediate results, i.e.,
As shown in figure 4, the scheduler module 300 can be configured as including：Distribute submodule 301, it is logical with the execution module 200
Letter, for obtaining the Query Result and the Query Result being distributed into user；And submodule 302 is deleted, held with described
Row module 200 communicates, for obtaining and deleting caused intermediate result during the execution module is calculated.
On the premise of scheduler module 300 is considered, what the mobile object inquiry unit of the present embodiment was established utilizes imperial palace
Deposit, the query processing framework of multi-core CPU and GPU feature is as shown in figure 5, mainly include three phases：Pretreatment
(Preprocessing) stage, execution (Execute) stage and scheduling (Dispatch) stage, these three phase sequences perform.
In the Preprocessing stages, mainly by Buffer be cached to come mobile object update the data and inquire about number
According to.Simultaneously data-pushing to next stage.Wherein, the Preprocessing stages by query window (Query window)-
The pattern of object window (Object window), query caching (Query buffer)-target cache (Object buffer)
Data are cached by snap shot.
In the Execute stages, first by multi-core CPU, index is rebuild to the data to arrive on last stage, passes through weight
The mode of new structure index, the complicated updating maintenance operation to index in traditional approach is avoided, has given full play to multi-core CPU
Characteristic.Wherein, the mode of index search index (Index query)-index object (Index as illustrated in the drawing is rebuild
Object mode).
Secondly, for the index structure built, GPU ends is pushed to and carry out computing, be i.e. GPU performs query processing
(Process Queries), gives full play to the characteristics of GPU parallel efficiency calculations are high, improves the execution efficiency of computing.When completion is transported
After calculation, result is pushed to next stage.
In the Dispatch stages, the result that inquiry is obtained is distributed to user, while deletes the middle knot in calculating process
Fruit.
In summary, the mobile object inquiry unit of the embodiment of the present invention proposes one based on the height under new hardware environment
Handling capacity mobile object query processing framework, the characteristics of big internal memory, multi-core CPU, GPU can be given full play to, moved so as to improve
The query processing efficiency of dynamic object, can more meet user's query demand based on location-based service under big data.
The optional embodiment of example of the present invention, still, the embodiment of the present invention and unlimited are described in detail above in association with accompanying drawing
Detail in above-mentioned embodiment, can be to the embodiment of the present invention in the range of the technology design of the embodiment of the present invention
Technical scheme carry out a variety of simple variants, these simple variants belong to the protection domain of the embodiment of the present invention.
It is further to note that each particular technique feature described in above-mentioned embodiment, in not lance
In the case of shield, it can be combined by any suitable means.In order to avoid unnecessary repetition, the embodiment of the present invention pair
Various combinations of possible ways no longer separately illustrate.
It will be appreciated by those skilled in the art that realize that all or part of step in above-described embodiment method is to pass through
Program instructs the hardware of correlation to complete, and the program storage is in the storage medium, including some instructions are causing one
Individual (can be single-chip microcomputer, chip etc.) or processor (processor) perform the whole of each embodiment methods described of the application
Or part steps.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
In addition, it can also be combined between a variety of embodiments of the embodiment of the present invention, as long as it is not
The thought of the embodiment of the present invention is run counter to, it should equally be considered as disclosure of that of the embodiment of the present invention.
Claims (6)
1. a kind of mobile object inquiry unit, it is characterised in that the mobile object inquiry unit includes：
Pretreatment module, the mobile object for being detected in real time by buffer update the data the inquiry number with user's input
According to；And
Execution module, communicated with the pretreatment module, for obtaining the mobile object renewal number from the pretreatment module
According to the inquiry data, and by multi-core CPU the mobile object is updated the data and to rebuild rope with the inquiry data
Draw, then the index structure built is calculated by GPU, to obtain Query Result.
2. mobile object inquiry unit according to claim 1, it is characterised in that the pretreatment module is configured as having
Have multiple snapshot spaces, and in each snapshot space, the mobile object detected in real time by buffer update the data and
The inquiry data of user's input.
3. mobile object inquiry unit according to claim 1, it is characterised in that the execution module includes：
Receiving submodule, communicated with the pretreatment module, for obtaining the mobile object renewal from the pretreatment module
Data and the inquiry data；
First implementation sub-module, communicated with the receiving submodule, for being updated the data by multi-core CPU to the mobile object
Index is rebuild with the inquiry data；And
Second implementation sub-module, communicated with first implementation sub-module, for being carried out by GPU to the index structure built
Calculate, to obtain Query Result.
4. mobile object inquiry unit according to claim 1, it is characterised in that the execution module is configured as passing through
One multi-core CPU updates the data to the mobile object rebuilds index with the inquiry data, and passes through several GPU pairs
The index structure built is calculated.
5. mobile object inquiry unit as claimed in any of claims 1 to 4, it is characterised in that the movement pair
As inquiry unit also includes：
Scheduler module, communicated with the execution module, use is distributed to for obtaining the Query Result, and by the Query Result
Family.
6. mobile object inquiry unit according to claim 5, it is characterised in that the scheduler module includes：
Distribute submodule, communicated with the execution module, for obtaining the Query Result and being distributed to the Query Result
User；And
Submodule is deleted, is communicated with the execution module, for obtaining and deleting during the execution module calculated
Caused intermediate result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710446556.7A CN107341126A (en) | 2017-06-14 | 2017-06-14 | Mobile object inquiry unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710446556.7A CN107341126A (en) | 2017-06-14 | 2017-06-14 | Mobile object inquiry unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107341126A true CN107341126A (en) | 2017-11-10 |
Family
ID=60220597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710446556.7A Pending CN107341126A (en) | 2017-06-14 | 2017-06-14 | Mobile object inquiry unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107341126A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377782A (en) * | 2021-08-12 | 2021-09-10 | 深圳市数字城市工程研究中心 | City space moving object query method, device and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309958A (en) * | 2013-05-28 | 2013-09-18 | 中国人民大学 | OLAP star connection query optimizing method under CPU and GPU mixing framework |
-
2017
- 2017-06-14 CN CN201710446556.7A patent/CN107341126A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309958A (en) * | 2013-05-28 | 2013-09-18 | 中国人民大学 | OLAP star connection query optimizing method under CPU and GPU mixing framework |
Non-Patent Citations (2)
| Title |
|---|
| 薛忠斌，周烜，王珊: "双流模式下高吞吐量移动对象范围查询算法", 《软件学报》 * |
| 薛忠斌，白利光，何宁，周烜，周歆，王珊: "路网中高吞吐量移动对象实时查询算法", 《计算机科学》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377782A (en) * | 2021-08-12 | 2021-09-10 | 深圳市数字城市工程研究中心 | City space moving object query method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107515952A (en) | The method and its system of cloud data storage, parallel computation and real-time retrieval | |
| CN108475349A (en) | System and method for robust large-scale machine learning | |
| CN105468439A (en) | Adaptive parallel algorithm for traversing neighbors in fixed radius under CPU-GPU (Central Processing Unit-Graphic Processing Unit) heterogeneous framework | |
| CN103281376A (en) | Method for automatic caching construction of massive timing sequence remote-sensing images in cloud environment | |
| CN103595780A (en) | Cloud computing resource scheduling method based on repeat removing | |
| CN110059875A (en) | Public bicycles Demand Forecast method based on distributed whale optimization algorithm | |
| CN110287391A (en) | Multi-level trajectory data storage method, storage medium and terminal based on Hadoop | |
| CN100593925C (en) | Wireless sensor network local type node managing method | |
| CN103577602A (en) | Secondary clustering method and system | |
| CN107658010A (en) | Portable medical querying method and application based on the row's of falling Thiessen polygon index | |
| CN105897887A (en) | Clouding computing-based remote sensing satellite big data processing system and method | |
| CN115860441B (en) | Method and device for generating work order information and computer equipment | |
| EP3008597B1 (en) | Method for the continuous processing of two-level data on a system with a plurality of nodes | |
| CN105359142A (en) | Hash join method, device and database management system | |
| CN104424189A (en) | Positioning resolving method and positioning resolving system based on cloud platform | |
| CN103164440A (en) | Spatial data engine method for virtual reality | |
| CN104573082A (en) | Space small file data distribution storage method and system based on access log information | |
| CN107341126A (en) | Mobile object inquiry unit | |
| CN106155936B (en) | A kind of buffer replacing method and relevant apparatus | |
| CN102012908A (en) | Method for inquiring visible neighbours of moving objects in environment with barriers | |
| CN108614889B (en) | Moving object continuous k nearest neighbor query method and system based on Gaussian mixture model | |
| CN102523300A (en) | Data-intensive cloud storage model facing intelligent power grid | |
| CN109409604A (en) | It is a kind of based on genetic algorithm-support vector machines cooling load prediction method | |
| CN105573834B (en) | A kind of higher-dimension vocabulary tree constructing method based on heterogeneous platform | |
| CN107357820A (en) | mobile object range query method |
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: 20171110 |