CN111930871B - Extraction method and device based on high-precision map data recommendation sample - Google Patents
Extraction method and device based on high-precision map data recommendation sample Download PDFInfo
- Publication number
- CN111930871B CN111930871B CN202010827571.8A CN202010827571A CN111930871B CN 111930871 B CN111930871 B CN 111930871B CN 202010827571 A CN202010827571 A CN 202010827571A CN 111930871 B CN111930871 B CN 111930871B
- Authority
- CN
- China
- Prior art keywords
- recommended
- data
- precision map
- sample
- determining
- 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
- 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
- G06F16/29—Geographical information databases
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (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 relates to a method and a device for extracting recommended samples based on high-precision map data, wherein the method comprises the following steps: acquiring a data source of a high-precision map; determining the number of recommended samples, sample data records and the number of elements according to the inspection standard; acquiring a coherence factor according to the data source; determining a recommended sample meeting the condition according to the coherence factor and the element; and randomly extracting the recommended samples meeting the conditions. The method solves the problem of complexity in manually selecting the sampling data, saves the time for selecting the samples, enables the extraction process of the high-precision map data recommendation samples to be more scientific, and enables the sampling process to reflect the whole situation more accurately due to more sample coverage.
Description
Technical Field
The invention belongs to the field of high-precision electronic map manufacturing, and particularly relates to a method and a device for extracting recommended samples based on high-precision map data.
Background
The element types and attribute types of the high-precision map are richer than those of the traditional vehicle-mounted navigation electronic map, and the high-precision map is different in service objects and use scenes, so that a recommendation sample cannot be screened from the single information assistance perspective. The field of high-precision electronic map manufacturing urgently needs an extraction method which comprises more accurate elements, attributes and the like of a traditional sampling method of a vehicle-mounted navigation electronic map as related relationship factors to form a data recommendation sample.
Disclosure of Invention
The invention provides an extraction method of recommended samples based on high-precision map data, aiming at the technical problems of the existing high-precision map data sample extraction technology that the sampling data is selected manually, and the traditional vehicle-mounted navigation electronic map is single in information, not accurate enough and not wide in sample coverage in the process of screening the recommended samples.
The invention provides a method for extracting recommended samples based on high-precision map data, which comprises the following steps: acquiring a data source of a high-precision map; determining the number of recommended samples, sample data records and the number of elements according to the inspection standard; acquiring a coherence factor according to the data source; determining a recommended sample meeting the condition according to the coherence factor and the element; and randomly extracting the recommended samples meeting the conditions.
In some embodiments of the present invention, the data source of the high-precision map includes the product specification and the element information included in the high-precision map data according to the customer's needs and the national law.
In some embodiments of the present invention, said obtaining the coherence factor according to the data source comprises the steps of: and acquiring relevant relationship factors in the data source from the product specification data specification, the tool version, the data range and the task allocation.
In some embodiments of the invention, the coherence factors include road category, producer information, number of drawings, data update area.
Further, the condition that the recommended samples meet is determined according to the coherence factors and the factors, and the method comprises the following steps: obtaining the image-amplitude ratio of each road category in the total image-amplitude of the current batch; updating the quantity of each element to be extracted under different road types; obtaining the quantity of recommended and extracted image frames in the current batch according to the sampling standard; and determining constraint conditions according to the number of production headcount, the number of recommended and extracted figures and the number of each element in the current batch.
Further, the extracting data from the data source according to the recommended sample number comprises the following steps:
the constraint conditions determined according to the total number of production people, the number of recommended and extracted drawings and the number of each element in the current batch are as follows:
sa is more than or equal to m, and when Sa (k) is more than 0, Pb is more than or equal to n and more than or equal to m;
sa is more than or equal to m, and when Sa (k) is 0, m is more than or equal to n and Pb is more than or equal to n;
when Sa is less than m, m is more than or equal to n and Pb is more than or equal to n;
wherein Sa is the number of each element in the current batch, m is the total number of production people, k is the number of the map sheets, Sa (k) is the number of each element in the kth map, Pb is the number of the recommended map sheets, and n is the number of the recommended sample data.
Further, the determining the condition satisfied by the recommended sample according to the coherence factor and the factor further includes the following steps: if the data updating exists in the current batch, the recommended samples meeting the conditions are repeatedly sampled and selected according to a two-eight principle, so that the number of records extracted by each element of the data updating area accounts for 80%, and the number of records extracted by the non-updating area accounts for 20%.
The invention provides an extraction device based on high-precision map data recommendation samples, which comprises a first acquisition module, a first determination module, a second acquisition module, a second determination module and an extraction module, wherein the first acquisition module is used for acquiring a data source of a high-precision map; the first determining module is used for determining the number of recommended samples, sample data records and element numbers according to the inspection standard; the second acquisition module is used for acquiring the coherence factor according to the data source; the second determination module is used for determining a recommendation sample meeting the condition according to the coherence factor and the element; the extraction module is used for randomly extracting the recommended samples meeting the conditions.
A third aspect of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned extraction method based on high-precision map data recommendation samples when executing the computer program.
A fourth aspect of the present invention provides a non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processor, recommends the steps of the method for extracting samples based on high-precision map data described above.
The invention has the beneficial effects that: the problem of tedious manual selection of sampling data is solved, the time for selecting samples is saved, and the extraction process of high-precision map data recommendation samples is more scientific and more sample coverage is achieved.
Drawings
FIG. 1 is a basic flow diagram of a method for extracting recommended samples based on high-precision map data according to some embodiments of the invention;
FIG. 2 is a schematic diagram of a high-precision map data recommendation sample-based extraction device in some embodiments of the invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third aspect of the present invention.
Reference numerals
1. The extraction device for recommending samples based on high-precision map data comprises 11 a first acquisition module, 12 a first determination module, 13 a second acquisition module, 14 a second determination module, 15 an extraction module, 501 a processor, 502 a communication interface, 503 a memory and 504 a communication bus.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, a first aspect of the present invention provides a method for extracting recommended samples based on high-precision map data, including the following steps: s100, acquiring a data source of a high-precision map; s105, determining the number of recommended samples, sample data records and element numbers according to the inspection standard; s110, acquiring a coherence factor according to the data source; s115, determining a recommended sample meeting the condition according to the coherence factor and the element; s120, randomly extracting the recommended samples meeting the conditions.
In some embodiments of the invention, the recommended number of samples is used to determine the number of sample data records c (j) subsequently recommended, j being the number of elements, based on an Accepted Quality Limit (AQL) of 0.1, AQL0.1, using the general test level II, with reference to ANSI/ASQ Z1.4-2003.
In some embodiments of the present invention, the data source of the high-precision map includes the product specification and the element information included in the high-precision map data according to the customer's needs and the national law. Specifically, according to the product specification (i.e., the summary document of the production specification and the contents of the records of the high-precision map), the national law and the customer requirement, it is determined that the element information (coordinates, elevation information, etc.) included in the high-precision map data provided in the batch is not violated, and the element information is provided as a data source in the form of a database backup.
In some embodiments of the present invention, said obtaining the coherence factor according to the data source comprises the steps of: and acquiring relevant relationship factors in the data source from the product specification data specification, the tool version, the data range and the task allocation. Specifically, relevant system factors in the data source, namely, factors that are considered to affect data quality and human input, are obtained from documents such as product specifications, data specifications (that is, information including tool versions and data ranges of data submitted at this time), task allocation and the like attached to the data submission, such as: A. the road species: high speed, general road, etc.; B. information of a producer: personnel information for data production; C. number of figures: the number of the selected single operation areas; (breadth of the figure: extent of production individually per producer); D. a data update area.
Further, in step S115, under the determined coherence factor, the determining, according to the coherence factor and the factor, that the recommended sample satisfies the condition includes the following steps: obtaining the image-amplitude ratio of each road category in the total image-amplitude of the current batch; updating the quantity of each element to be extracted under different road types; obtaining the quantity of recommended and extracted image frames in the current batch according to the sampling standard; and determining constraint conditions according to the number of the production headcount, the number of the recommended drawings spoken by the sample data and the number of each element in the current batch.
Specifically, condition 1: road species
1.1 obtaining the map width ratio Pre of each road type in the total map width Pa of the current batch. i is the type of road category: pre (i) ═ Σ (type (i))/Pa;
1.2 Each element further has the quantity S that AQL needs to extract under different road categories. S (j) pre (i), Σ s (j) c (j); wherein, C (j) sample data records recommended subsequently, and j is the number of elements.
Condition 2: number of drawings
2.1 obtaining the recommended quantity Pb of the extracted pictures in the current batch according to the AQL0.1 sampling standard.
Condition 3: manufacturer
The number of production headcount m, the number of graph frames n where the recommended sample data is located, and the number Sa and K of each element in the current batch are graph frame serial numbers.
Further, in step S115, the determining, according to the coherence factor and the factor, that the recommended sample satisfies the condition includes the following steps:
and determining constraint conditions according to the number of production headcount, the number of recommended and extracted figures and the number of each element in the current batch. Comprises the following steps:
sa is more than or equal to m, and when Sa (k) is more than 0, Pb is more than or equal to n and more than or equal to m;
sa is more than or equal to m, and when Sa (k) is 0, m is more than or equal to n and Pb is more than or equal to n;
when Sa is less than m, m is more than or equal to n and Pb is more than or equal to n;
wherein Sa is the number of each element in the current batch, m is the total number of production people, k is the number of the map sheets, Sa (k) is the number of each element in the kth map, Pb is the number of the recommended map sheets, and n is the number of the recommended sample data.
Further, the determining the condition satisfied by the recommended sample according to the coherence factor and the factor further includes the following steps: if the data updating exists in the current batch, repeating the steps S100 to S115 according to a twenty-eight principle, and sampling and selecting recommended samples meeting the conditions, so that the number of records extracted by each element in the data updating area accounts for 80%, and the number of records extracted by each element in the non-updating area accounts for 20%.
Specifically, the update area: s (j) ═ c (j) × pre (i) × 0.8; no update region: s (j) ═ c (j) × pre (i) × 0.2. The definitions of the formulae S (j), C (j), pre (i) in the above formulae are the same as the above.
Referring to fig. 2, a second aspect of the present invention provides an extraction apparatus 1 for recommending samples based on high-precision map data, including a first obtaining module 11, a first determining module 12, a second obtaining module 13, a second determining module 14, and an extraction module 15, where the first obtaining module 11 is configured to obtain a data source of a high-precision map; the first determining module 12 is configured to determine the recommended sample number, the sample data record, and the element number according to the inspection standard; the second obtaining module 13 is configured to obtain a coherence factor according to the data source; the second determining module 14 is configured to determine a recommended sample meeting a condition according to the coherence factor and the element; the extraction module 15 is configured to randomly extract the recommended samples that satisfy the condition.
Referring to fig. 3, a third aspect of the present invention provides an electronic device, comprising: a processor (processor)501, a communication Interface (Communications Interface)502, a memory (memory)503, and a bus 504, wherein the processor 501, the communication Interface 502, and the memory 503 are configured to communicate with each other via the bus 504. The processor 501 may call logic instructions in the memory 503 to perform methods such as obtaining a data source for a high precision map; determining the number of recommended samples, sample data records and the number of elements according to the inspection standard; acquiring a coherence factor according to the data source; determining a recommended sample meeting the condition according to the coherence factor and the element; and randomly extracting the recommended samples meeting the conditions.
A fourth aspect of the present invention provides a non-transitory computer-readable storage medium having stored thereon a computer program that, when executed by a processor, recommends the steps of the method for extracting samples based on high-precision map data, such as acquiring a data source of a high-precision map; determining the number of recommended samples, sample data records and the number of elements according to the inspection standard; acquiring a coherence factor according to the data source; determining a recommended sample meeting the condition according to the coherence factor and the element; and randomly extracting the recommended samples meeting the conditions.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A method for extracting recommended samples based on high-precision map data is characterized by comprising the following steps:
acquiring a data source of a high-precision map;
determining the number of recommended samples, sample data records and the number of elements according to the inspection standard;
acquiring a coherence factor according to the data source;
determining a recommended sample meeting the conditions according to the coherence factors and the elements, namely obtaining the image-amplitude ratio of each road category in the total image-amplitude of the current batch; determining the quantity of each element to be extracted under different road types; obtaining the quantity of recommended and extracted image frames in the current batch according to the sampling standard; determining constraint conditions according to the number of production headcount, the number of recommended and extracted maps and the number of each element in the current batch, wherein the relevant factors comprise road types, producer information, the number of maps and data updating areas;
and randomly extracting the recommended samples meeting the conditions.
2. The extraction method based on the high-precision map data recommendation sample according to claim 1, wherein the data source of the high-precision map comprises product specifications and element information contained in the high-precision map data according to customer requirements and national legal regulations.
3. The extraction method based on the high-precision map data recommendation sample according to claim 2, wherein the step of obtaining the coherence factor according to the data source comprises the following steps:
and acquiring relevant relationship factors in the data source from the product specification data specification, the tool version, the data range and the task allocation.
4. The extraction method based on the high-precision map data recommendation sample according to claim 1, wherein the constraint conditions determined according to the number of production headcount, the number of recommended and extracted maps and the number of each element in the current batch are as follows:
sa is more than or equal to m, and when Sa (k) is more than 0, Pb is more than or equal to n and more than or equal to m;
sa is more than or equal to m, and when Sa (k) =0 exists, m is more than or equal to n and Pb is more than or equal to n;
when Sa is less than m, m is more than or equal to n and Pb is more than or equal to n;
wherein Sa is the number of each element in the current batch, m is the total number of production people, k is the number of the map sheets, Sa (k) is the number of each element in the kth map, Pb is the number of the recommended map sheets, and n is the number of the recommended sample data.
5. The extraction method based on the high-precision map data recommendation sample according to claim 1, wherein the step of determining the recommendation sample meeting the condition according to the coherence factor and the element further comprises the following steps:
If the data updating exists in the current batch, the recommended samples meeting the conditions are repeatedly sampled and selected according to a two-eight principle, so that the number of records extracted by each element of the data updating area accounts for 80%, and the number of records extracted by the non-updating area accounts for 20%.
6. An extraction device based on high-precision map data recommendation samples is characterized by comprising a first acquisition module, a first determination module, a second acquisition module, a second determination module and an extraction module,
the first acquisition module is used for acquiring a data source of a high-precision map;
the first determining module is used for determining the number of recommended samples, sample data records and element numbers according to the inspection standard;
the second acquisition module is used for acquiring the coherence factor according to the data source;
the second determining module is used for determining a recommended sample meeting the conditions according to the coherence factor and the elements, namely obtaining the map number ratio of each road type in the total map number of the current batch; determining the quantity of each element to be extracted under different road types; obtaining the quantity of recommended and extracted image frames in the current batch according to the sampling standard; determining constraint conditions according to the number of production headcount, the number of recommended and extracted maps and the number of each element in the current batch, wherein the relevant factors comprise road types, producer information, the number of maps and data updating areas;
The extraction module is used for randomly extracting the recommended samples meeting the conditions.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method for extracting a recommended sample based on high precision map data according to any one of claims 1 to 5.
8. A non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of the method for extracting a recommendation sample based on high accuracy map data as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010827571.8A CN111930871B (en) | 2020-08-17 | 2020-08-17 | Extraction method and device based on high-precision map data recommendation sample |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010827571.8A CN111930871B (en) | 2020-08-17 | 2020-08-17 | Extraction method and device based on high-precision map data recommendation sample |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111930871A CN111930871A (en) | 2020-11-13 |
| CN111930871B true CN111930871B (en) | 2022-05-31 |
Family
ID=73311915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010827571.8A Active CN111930871B (en) | 2020-08-17 | 2020-08-17 | Extraction method and device based on high-precision map data recommendation sample |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111930871B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710331A (en) * | 2008-10-23 | 2010-05-19 | 中国科学院地理科学与资源研究所 | System and method for layering population sample survey sample |
| WO2013049736A1 (en) * | 2011-09-30 | 2013-04-04 | Bhardwaj Anurag | Image feature data extraction and use |
| CN106997420A (en) * | 2016-01-22 | 2017-08-01 | 北京四维图新科技股份有限公司 | The method and device of intelligent sampling Detection map datum |
-
2020
- 2020-08-17 CN CN202010827571.8A patent/CN111930871B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101710331A (en) * | 2008-10-23 | 2010-05-19 | 中国科学院地理科学与资源研究所 | System and method for layering population sample survey sample |
| WO2013049736A1 (en) * | 2011-09-30 | 2013-04-04 | Bhardwaj Anurag | Image feature data extraction and use |
| CN106997420A (en) * | 2016-01-22 | 2017-08-01 | 北京四维图新科技股份有限公司 | The method and device of intelligent sampling Detection map datum |
Non-Patent Citations (1)
| Title |
|---|
| 顾依依等.基于凸边界的学习样本抽取方法.《计算机应用》.2019, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111930871A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428599B (en) | Bill identification method, device and equipment | |
| CN110995524B (en) | Flow data monitoring method and device, electronic equipment and computer readable medium | |
| CN110134689B (en) | Target group screening method and system based on main body object label change and computer equipment | |
| CN113434527B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN109800277A (en) | A kind of machine learning platform and the data model optimization method based on the platform | |
| CN111444188A (en) | Stock test data preparation method and device, storage medium and electronic equipment | |
| CN112308727A (en) | Insurance claim settlement service processing method and device | |
| CN111930871B (en) | Extraction method and device based on high-precision map data recommendation sample | |
| CN113449979A (en) | Rock mineral analysis, test and management system | |
| CN116823464B (en) | Data asset management platform, electronic device, and computer-readable storage medium | |
| CN112862593A (en) | Credit scoring card model training method, device, system and computer storage medium | |
| CN109600428B (en) | Method and device for automatically uploading attachment and matching association | |
| Williams et al. | Counting cells in sectioned material: a suite of techniques, tools, and tips | |
| CN115034742A (en) | Attendance checking method and system | |
| CN115617670A (en) | Software test management method, storage medium and system | |
| CN116150199A (en) | Data checking method and system based on RPA robot | |
| KR102159574B1 (en) | Method for estimating and managing the accuracy of work results of crowdsourcing based projects for artificial intelligence training data generation | |
| CN114356781A (en) | Software function testing method and device | |
| CN117217628B (en) | Carbon credit project rating method and device | |
| CN112862264A (en) | Enterprise operation condition analysis method, computer device and computer storage medium | |
| CN112036280A (en) | Waterfowl population dynamic monitoring method, device and equipment | |
| CN115858377B (en) | Data testing system and method based on guest group management | |
| CN112084765A (en) | Automatic classification method and device, electronic equipment and storage medium | |
| CN117369776A (en) | Architecture object management method, system and medium based on EA system | |
| CN114239499A (en) | Recruitment information management method, system 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 |