CN111400519A - Efficient customized massive similar house type searching method - Google Patents
Efficient customized massive similar house type searching method Download PDFInfo
- Publication number
- CN111400519A CN111400519A CN201911234105.2A CN201911234105A CN111400519A CN 111400519 A CN111400519 A CN 111400519A CN 201911234105 A CN201911234105 A CN 201911234105A CN 111400519 A CN111400519 A CN 111400519A
- Authority
- CN
- China
- Prior art keywords
- room
- similar
- codes
- coding
- size
- 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.)
- Granted
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
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- 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)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a high-efficiency customized searching method for similar house types in mass, which relates to the technical field of data warehouse and data mining, wherein each room entity is provided with dimension information of structural levels such as doors, windows, walls, indoor/outdoor, sizes and the like, firstly, the room is subjected to size coding and structural coding to generate multi-level fingerprints, then each room entity is provided with M level size codes and N level fingerprint codes, in addition, each room is also provided with a use attribute, the mass rooms are generated into an index library according to the use attribute, the multi-level size codes and the multi-level fingerprint codes, and when a given house type is input, the similar house types are quickly retrieved through a room use bucket, a multi-level size bucket and a multi-level fingerprint bucket. The invention can efficiently detect similar house types and has an auxiliary effect in the field of automatic layout of indoor scene furniture.
Description
Technical Field
The invention relates to the technical field of data warehouse and data mining, in particular to a searching method for massive similar house types.
Background
In the field of three-dimensional indoor design, a designer needs to arrange furniture to a reasonable position, different designers have different design requirements, in order to improve the design efficiency of the designer, an indoor scene furniture automatic arrangement algorithm is developed, and an efficient massive similar house type search method provides an auxiliary effect for the automatic arrangement algorithm and provides data support for the research and optimization of the automatic arrangement algorithm, however, a classical similar search method cannot meet the customized service of the designer and the automatic arrangement algorithm.
The invention provides an efficient customized massive similar house type searching method, which can provide customized data service for the field of automatic layout.
Disclosure of Invention
The invention aims to solve the technical problem that the conventional similar data detection cannot provide customized data, and aims to provide a more efficient customized massive similar house type searching method.
The invention adopts the following technical scheme for solving the technical problems:
an efficient customized massive similar house type searching method comprises the steps of constructing a customized index library and searching similar rooms, and specifically comprises the following steps:
and 5, searching a similar room list from the customized index library according to the encoding result.
As a further preferable scheme of the efficient customized massive similar house type searching method of the present invention, in step 2, the room usage attribute multilevel coding specifically comprises the following steps:
the room use can be configured according to the requirement level, the more fuzzy the configuration is, the coarser the room use type division is, and the fewer the coding number is; the finer the configuration is, the more detailed the room purpose type division is, and the more the number of codes is;
the room use attribute can be configured according to the requirement in a diversified way, and two attribute codes can be configured for the room.
As a further preferable scheme of the method for efficiently customizing the search of the massive similar house types, in step 2, the room size multilevel coding specifically comprises the following steps: the rooms in two critical sizes can be set with two size codes according to the division of preset size intervals, the larger the preset size interval is, the smaller the number of size buckets is, the less the searched similar house types are sensitive to the sizes, the larger the preset size interval is, the larger the number of size buckets is, and the closer the searched similar house types are to the given house types.
As a further preferable scheme of the efficient customized massive similar house type searching method of the present invention, in step 2, the room infrastructure structure multilevel fingerprint coding specifically comprises the following steps: 1-N level codes are constructed for a room, the fingerprint codes with higher levels describe the room structure more finely, the fingerprint codes with lower levels describe the room structure more coarsely, the fingerprints with lower levels are used for filtering the room in the index database, and the fingerprints with higher levels are used for calculating the similarity of the room.
As a further preferable scheme of the efficient customized massive similar house type search method of the present invention, in step 2, the room multilevel index library is constructed as follows: the method comprises the steps that the rooms are hung on nodes corresponding to an index library according to attribute codes, size codes and fingerprint codes of the rooms, one room can be hung under one node or a plurality of nodes according to configuration, and massive rooms are stored on the nodes of the index library to form the index library.
As a further preferable scheme of the efficient customized massive similar house type searching method of the invention, the step 3 is as follows: and (3) obtaining a candidate room list through screening of the index bucket, removing duplicate of the candidate room list if one room is possibly hung under a plurality of nodes according to configuration, calculating similarity according to high-level fingerprints, and searching topK similar rooms according to heap sequencing.
Has the advantages that:
compared with the prior art, the invention adopting the technical scheme has the following technical effects:
1. the invention relates to an efficient customized massive similar house type searching method, which can configure an individualized house type room coding scheme aiming at different research or index requirements, obtain differentiated search results and meet the individualized requirements of users.
2. The invention carries out verification on a room index library with the capacity of 448888, the purpose code is set as a living room, a bedroom, a dining room, a toilet, a kitchen, a balcony, a study room, a cloakroom, a storage room, a tea room, a multifunctional room and a gymnasium, the size code interval is set as 1 meter, the first-level fingerprint grid code is directly set as 20 x 20, the topK is set as 5, 1000 times of search is carried out randomly, the time consumption of each search of the living room, the living room and the coat room is respectively 2.9 milliseconds, 2.1 milliseconds and 3.2 milliseconds, other rooms are all within 3 milliseconds, the verification environment is configured as a 64-bit operating system of windows10, the memory is 16GB, the processor is Intel i5-8400 CPU @2.880GHz, and the search method can carry out efficient search on the premise of meeting the personalized requirements of users.
Drawings
FIG. 1 is a flow chart of a customized search for massive similar housing types according to an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a room multi-level fingerprint encoding of the present invention;
FIG. 3 is a diagram illustrating an exemplary structure of a customized index library according to the present invention;
FIG. 4 is a diagram illustrating an example of a structure of an inverted index library according to the present invention;
fig. 5 is a flow chart of a similar room searching method of the present invention.
Detailed Description
The present invention is further illustrated by the following examples, which are intended to be purely exemplary and are not intended to limit the scope of the invention, as various equivalent modifications of the invention will occur to those skilled in the art upon reading the present disclosure and fall within the scope of the appended claims.
As shown in fig. 1, an efficient customized massive similar house type search method includes the steps of constructing a customized index library and searching similar rooms, and specifically includes the following steps:
and 5, searching a similar room list from the customized index library according to the encoding result.
An example of the multi-level fingerprint coding of a room is shown in FIG. 2, the first-level fingerprint coding simply describes the number of doors and windows of the room and is used for rapidly screening similar rooms, for example, D1W1 represents 1 Door (Door) and 1 Window (Window), D2W1 represents 2 doors and 1 Window, the second-level fingerprint coding roughly describes the position information of the doors, windows and walls of the room, the second-level fingerprint coding establishes a polar coordinate system by taking the center of a rectangular outer-wrapping rectangle of the room as an origin, the polar coordinate system is rasterized according to configuration, the grid is 0-8 in the graph and 9 positions in total, the position expression is roughly carried out, D8W 5L 0 represents that the Door (Door) is at the position No. 8, the Window (Window) is at the position No. 5, the Wall (Wall) is at the position No. 0, and when the rough position of the Wall is calculated, the room is firstly subjected to convex outer-wrappingObtaining K edges, and calculating a unit normal vector of each edge pointing from the inside of the room to the outside of the roomvThe method comprises the steps of solving vectors and obtaining a final normal vector for K unit normal vectors, obtaining the position of a wall according to the direction of the normal vectors, wherein the wall position of a second room in the figure 2 is L2 after calculation and rasterization, the grid granularity of polar coordinates can be configured according to requirements, the smaller the grid granularity is, the more similar the rooms under a fingerprint bucket are, three-level rasterized fingerprint coding is a sequence with the length of N x N, the coding method is that a picture is cut into N x N grids, each grid takes a value of 0-F to respectively show whether four basic constructions (door, window, wall and indoor space) exist in the grid, whether each basic construction exists in binary coding, and 16 results in the four basic constructions are obtained, namely each grid takes 16 values.
FIG. 3 is a diagram illustrating an exemplary structure of a customized index library according to the present invention. The index library is layered according to codes and is divided into a purpose barrel, a size barrel and a multi-level fingerprint barrel, the number of fingerprint levels can be configured as required, and the example in the figure is a three-level fingerprint barrel, wherein the one-level fingerprint barrel is used for screening according to the number of doors and windows, the two-level fingerprint barrel is used for screening according to the coarse positions of the doors and windows, and the inverted index library is arranged below the three-level fingerprint barrel and is used for calculating the similarity and searching for similar rooms.
Where room usage property multi-level coding is key to customization, for example:
(1) primary use granularity division: bedrooms, kitchens, living rooms, dining rooms, balconies;
(2) and (3) secondary use granularity division: main bed, secondary bed, guest room, children room, old people room, kitchen, living room, dining room, living balcony, leisure balcony, bedroom balcony;
(3) three-level application granularity division: a main bed, a secondary bed, a guest room, a child room, an old person room, a nurse room, a study room, a tatami room, a multifunctional room, a kitchen, a meeting room, an entertainment hall, a dining room, a living balcony, a leisure balcony and a bedroom balcony;
when the room purpose is coded in multiple stages, the coding is carried out according to the design customization requirement. When a room can have multiple uses, its uses are encoded as a sequence, such as: a sub-bedroom | guest room | child room | old person room | nurse room | tatami room.
The room size multi-level coding first classifies the room sizes according to a preset size, for example, the preset size is k meters, and the room sizes can be divided into S buckets, wherein the size of the ith bucket is in the range of [ (i-1) × k, i × k ] (unit: meters). The larger the preset size k is, the larger the range covered by one barrel is, the larger the allowable size fluctuation range of the searched similar house type is, the smaller the preset size k is, the smaller the range covered by one barrel is, and the smaller the allowable size fluctuation range of the searched similar house type is. In addition, different size intervals can be set below the barrels for different purposes, and customization requirements are met.
The method comprises the steps that a multi-level fingerprint code of a capital construction structure of a room is a key of similar house type search, 1-N levels of fingerprint codes are constructed for the room, the higher the level of the fingerprint codes is, the more fine the description of the room structure is, the lower the level of the fingerprint codes is, the coarser the description of the room structure is, the lower level of fingerprints are used for filtering the room in an index database, and the higher level of fingerprints are used for calculating the similarity of the room. For example, a building structure fingerprint of a room is encoded as follows:
(1) 1 level fingerprint: number of doors | number of windows
(2) 2, level fingerprint: door position window position wall position
(3) 3, grade fingerprint: n x N trellis coded
After each attribute dimension of a room is coded, an index library needs to be constructed, each room application codes one sub-index library, and similar items of a given room are searched only in the sub-libraries matched with the room application. Similarly, in each room type usage sub-library, S buckets are formed according to size ranges, and placed into corresponding buckets according to the size of the room. For a room with the size close to the dividing point, the strategy is that the room is respectively placed into barrels on two sides of the dividing point, and the room can be searched from any one of the barrels on two sides of the dividing point during searching; and the second strategy is to put the obtained object into a barrel on one side according to the partition standard, and search in the barrels on two sides of the critical point respectively if the size of the given barrel is close to the critical point during searching. And a level 1 fingerprint bucket or a level 1-2 fingerprint bucket is set under the size bucket according to the configuration for screening and filtering.
When a candidate bucket is searched from the index database, the room lists under the bucket have similar purposes, sizes and infrastructure structures, then coarse screening is carried out in the inverted index database, the rooms with similar topK and Rc are screened out, then accurate rasterization coding comparison is carried out in the coarsely screened rooms, more accurate similarity is obtained, and the most similar room lists with topK are finally screened out.
The structure of the inverted index library in the present invention is shown in fig. 4. In the example of 2 × 2 grids, each grid takes on 16 buckets of 0 to F, a list of rooms hung under bucket j of grid i takes on j of grid position i of this part of rooms, as shown in the figure, position 1 of grid 1 hangs r3, position 7 of grid 1 shows 1 of grid code of r3, positions 7 of grid 1 hang r1 and r2, and position 1 of grid code of r1 and r2 shows 7.
The detailed flow of the similar room search of the present invention is shown in fig. 5. Firstly, a room needing to search similar house types is given (step 50), and the given room is subjected to purpose coding, size coding and multilevel fingerprint coding (step 51); then finding the corresponding inverted index library of the room according to the encoding result of the room (step 52); selecting R grid positions from the N × N rasterized codes of the room for calculation (step 53), wherein when the number N × N is large, selecting R important positions can reduce the calculation complexity; assuming that the value of the ith grid of the current room is v, traversing a room list under a node v in the ith grid bucket, and updating the similarity of the group of rooms, wherein the smaller the number of the rooms mounted under the node is, the higher the similarity is (step 54); after calculating the R grids, obtaining a rough candidate room list, and roughly obtaining topK × Rc rooms with higher similarity according to a small root heap method (step 55); finally, comparing the rasterized code of the current room with the rasterized codes of topK × Rc rooms one by one, calculating more accurate similarity, and finally searching a list of topK similar rooms.
The invention relates to an efficient customized massive similar house type searching method, which can configure an individualized house type room coding scheme aiming at different research or index requirements, obtain differentiated search results and meet the individualized requirements of users.
The invention carries out verification on a room index library with the capacity of 448888, the purpose code is set as a living room, a bedroom, a dining room, a toilet, a kitchen, a balcony, a study room, a cloakroom, a storage room, a tea room, a multifunctional room and a gymnasium, the size code interval is set as 1 meter, the first-level fingerprint grid code is directly set as 20 x 20, the topK is set as 5, 1000 searches are randomly carried out, the average time consumption of each search of the living room, the living room and the hats is respectively 2.9 milliseconds, 2.1 milliseconds and 3.2 milliseconds, other rooms are all within 3 milliseconds, the verification environment is configured as a 64-bit operating system of windows10, the memory is 16GB, and the processor is Intel i5-8400 CPU @2.880 GHz. The searching method can perform efficient searching on the premise of meeting the personalized requirements of the user.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention. While the embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (6)
1. An efficient customized massive similar house type searching method is characterized in that: the method comprises the steps of constructing a customized index library and searching similar rooms, and specifically comprises the following steps:
step 1, acquiring massive house type original data;
step 2, analyzing the acquired massive house type original data, performing room use attribute multilevel coding, room size multilevel coding and room infrastructure structure multilevel fingerprint coding, and further constructing a customized index library according to a coding result;
step 3, searching similar house types after the index database is built, and giving a room to be searched for similar items;
step 4, performing room usage attribute multilevel coding, room size multilevel coding and room infrastructure structure multilevel fingerprint coding on a given room;
and 5, searching a similar room list from the customized index library according to the encoding result.
2. The method for efficiently customizing the similar house types in the mass according to claim 1, wherein the method comprises the following steps: in one embodiment, in step 2, the room use attribute is encoded in multiple levels, specifically as follows:
the room use can be configured according to the requirement level, the more fuzzy the configuration is, the coarser the room use type division is, and the fewer the coding number is; the finer the configuration is, the more detailed the room purpose type division is, and the more the number of codes is;
the room use attribute can be configured according to the requirement in a diversified way, and two attribute codes can be configured for the room.
3. The method for efficiently customizing the similar house types in the mass according to claim 1, wherein the method comprises the following steps: in one embodiment, in step 2, the room size is encoded in multiple levels, specifically as follows: the rooms in two critical sizes can be set with two size codes according to the division of preset size intervals, the larger the preset size interval is, the smaller the number of size buckets is, the less the searched similar house types are sensitive to the sizes, the larger the preset size interval is, the larger the number of size buckets is, and the closer the searched similar house types are to the given house types.
4. The method for efficiently customizing the similar house types in the mass according to claim 1, wherein the method comprises the following steps: in one embodiment, in step 2, the room infrastructure multilevel fingerprint coding is as follows: 1-N level codes are constructed for a room, the fingerprint codes with higher levels describe the room structure more finely, the fingerprint codes with lower levels describe the room structure more coarsely, the fingerprints with lower levels are used for filtering the room in the index database, and the fingerprints with higher levels are used for calculating the similarity of the room.
5. The method for efficiently customizing the similar house types in the mass according to claim 1, wherein the method comprises the following steps: in one embodiment, in step 2, the room multilevel index library is constructed as follows: the method comprises the steps that the rooms are hung on nodes corresponding to an index library according to attribute codes, size codes and fingerprint codes of the rooms, one room can be hung under one node or a plurality of nodes according to configuration, and massive rooms are stored on the nodes of the index library to form the index library.
6. The method as claimed in claim 1, wherein the customized massive similar house types are searched efficiently
Characterized in that: in one embodiment, the step 3 is specifically as follows: and (3) obtaining a candidate room list through screening of the index bucket, removing duplicate of the candidate room list if one room is possibly hung under a plurality of nodes according to configuration, calculating similarity according to high-level fingerprints, and searching topK similar rooms according to heap sequencing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911234105.2A CN111400519B (en) | 2019-12-05 | 2019-12-05 | Efficient customized massive similar house type searching method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911234105.2A CN111400519B (en) | 2019-12-05 | 2019-12-05 | Efficient customized massive similar house type searching method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111400519A true CN111400519A (en) | 2020-07-10 |
| CN111400519B CN111400519B (en) | 2022-08-12 |
Family
ID=71428363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911234105.2A Active CN111400519B (en) | 2019-12-05 | 2019-12-05 | Efficient customized massive similar house type searching method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400519B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360981A (en) * | 2021-06-04 | 2021-09-07 | 深圳须弥云图空间科技有限公司 | Automatic furniture layout method and device, storage medium and electronic equipment |
| CN113920250A (en) * | 2021-10-21 | 2022-01-11 | 广东三维家信息科技有限公司 | Household code matching method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815440A (en) * | 2017-01-19 | 2017-06-09 | 深圳市彬讯科技有限公司 | The structural commodities intelligent distribution method and system of a kind of household Size Dwelling Design |
| CN106844614A (en) * | 2017-01-18 | 2017-06-13 | 天津中科智能识别产业技术研究院有限公司 | A kind of floor plan functional area system for rapidly identifying |
| CN107368911A (en) * | 2017-06-11 | 2017-11-21 | 杭州巨梦科技有限公司 | A kind of furniture layout method based on placement regulation |
| CN109992693A (en) * | 2019-04-17 | 2019-07-09 | 广东三维家信息科技有限公司 | House type matching process and device |
-
2019
- 2019-12-05 CN CN201911234105.2A patent/CN111400519B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844614A (en) * | 2017-01-18 | 2017-06-13 | 天津中科智能识别产业技术研究院有限公司 | A kind of floor plan functional area system for rapidly identifying |
| CN106815440A (en) * | 2017-01-19 | 2017-06-09 | 深圳市彬讯科技有限公司 | The structural commodities intelligent distribution method and system of a kind of household Size Dwelling Design |
| CN107368911A (en) * | 2017-06-11 | 2017-11-21 | 杭州巨梦科技有限公司 | A kind of furniture layout method based on placement regulation |
| CN109992693A (en) * | 2019-04-17 | 2019-07-09 | 广东三维家信息科技有限公司 | House type matching process and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113360981A (en) * | 2021-06-04 | 2021-09-07 | 深圳须弥云图空间科技有限公司 | Automatic furniture layout method and device, storage medium and electronic equipment |
| CN113360981B (en) * | 2021-06-04 | 2024-04-16 | 深圳须弥云图空间科技有限公司 | Furniture automatic layout method and device, storage medium and electronic equipment |
| CN113920250A (en) * | 2021-10-21 | 2022-01-11 | 广东三维家信息科技有限公司 | Household code matching method and device |
| WO2023065570A1 (en) * | 2021-10-21 | 2023-04-27 | 广东三维家信息科技有限公司 | House type coding and matching method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111400519B (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nasraoui et al. | Tecno-streams: Tracking evolving clusters in noisy data streams with a scalable immune system learning model | |
| CN111400519B (en) | Efficient customized massive similar house type searching method | |
| US7239989B2 (en) | Within-distance query pruning in an R-tree index | |
| US20040215641A1 (en) | Query prunning using exterior tiles in an R-tree index | |
| CN111091618B (en) | Combined indoor layout method and system based on house type data driving | |
| Botella‐Rocamora et al. | Spatial moving average risk smoothing | |
| CN111985039B (en) | House type reconstruction scheme determination method and device and computer readable storage medium | |
| Schimmerling et al. | Square in core models | |
| CN111709061A (en) | Automatic indoor article placement processing method, device and equipment and storage medium | |
| Garro et al. | Scale space graph representation and kernel matching for non rigid and textured 3D shape retrieval | |
| Deng et al. | Multi‐scale approach to mining significant spatial co‐location patterns | |
| Shao et al. | Efficiently processing spatial and keyword queries in indoor venues | |
| Tran et al. | Delaunay triangulation‐based spatial colocation pattern mining without distance thresholds | |
| CN110717086A (en) | Mass data clustering analysis method and device | |
| Tran et al. | Mining spatial co-location patterns based on overlap maximal clique partitioning | |
| CN114722442B (en) | Cabinet layout method and device, computer equipment and storage medium | |
| CN114491772B (en) | Household layout generation method and device | |
| Wessel et al. | Efficient retrieval of 3D building models using embeddings of attributed subgraphs | |
| Alamri et al. | Vertical indexing for moving objects in multifloor environments | |
| Sumathi et al. | Spatial data mining-techniques trends and its applications | |
| KR102680460B1 (en) | Method, device, and system for automatically generating architectural facility blueprints based on architectural blueprints | |
| Alharbi et al. | Frequent itemsets mining on weighted uncertain data | |
| Joseph_Ikughur et al. | Application of Agglomerative Hierarchical Clustering to Classification of Housing Units in Nigeria by Types of Construction Materials | |
| CN117807691B (en) | Information model data integration method and system based on building visualization | |
| Jiang | Smart Home Product Layout Design Method Based on Real‐Number Coding Genetic Algorithm |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 211100 floor 5, block a, China Merchants high speed rail Plaza project, No. 9, Jiangnan Road, Jiangning District, Nanjing, Jiangsu (South Station area) Applicant after: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. Address before: 211100 No. 18 Zhilan Road, Science Park, Jiangning District, Nanjing City, Jiangsu Province Applicant before: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |