CN114491779A - Method for generating sketch through intelligent planning and related equipment - Google Patents
Method for generating sketch through intelligent planning and related equipment Download PDFInfo
- Publication number
- CN114491779A CN114491779A CN202210361889.0A CN202210361889A CN114491779A CN 114491779 A CN114491779 A CN 114491779A CN 202210361889 A CN202210361889 A CN 202210361889A CN 114491779 A CN114491779 A CN 114491779A
- Authority
- CN
- China
- Prior art keywords
- record
- area
- building
- label
- library
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Architecture (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a method for generating a sketch through intelligent planning and related equipment, which comprises the steps of determining a first area occupied by a building sketch; generating a first record aiming at the building sketch based on the building materials distributed in the first area, wherein the building materials distributed in the first area come from a material library; storing the first record into a record library; providing the first record to user equipment, wherein the first record is used for displaying the floor sketch or used for updating the floor sketch by a user; generating a second record aiming at the building sketch according to the update of the building sketch corresponding to the first record, wherein the update of the building sketch corresponding to the first record comprises the update of the first area and/or the update of the building materials arranged in the first area; storing the second record in the record repository. By adopting the method and the device, the floor sketch of the planning area on the target drawing can be quickly generated, and the floor type planning efficiency is improved.
Description
Technical Field
The present application relates to the field of intelligent planning, and in particular, to a method and related apparatus for generating a sketch by intelligent planning.
Background
With the development of scientific technology, the requirements on the planning efficiency of buildings are higher and higher. In the process of building planning, the process of generating the draft is often very complicated, users are usually required to master drawing skills and data calculation skills, a lot of time is consumed for planning the building draft, and if the user is not skilled in drawing skills, the building draft is very disordered. In some cases, complicated steps such as rendering are required to be added to enable the sketch to be clearer, a mode for quickly generating the sketch is lacked for the selected planning area, and the sketch generation efficiency is reduced.
Disclosure of Invention
The embodiment of the application discloses a method and related equipment for generating a draft by intelligent planning, which can be used for quickly generating a floor draft of a target area on a target drawing and improving the efficiency of floor type planning.
In a first aspect, an embodiment of the present application provides a method for generating a sketch by intelligent planning, which is characterized by including:
determining a first area occupied by a building sketch, wherein the first area is used for arranging building materials;
generating a first record for the building sketch based on the building materials arranged in the first area, the building materials arranged in the first area being from a material library;
storing the first record into a record library, wherein the storing mode comprises integral storage and divided storage aiming at the first record;
providing the first record to a user device, wherein the first record is used for displaying the floor sketch or used for updating the floor sketch by a user;
generating a second record aiming at the building sketch according to the updating of the building sketch corresponding to the first record, wherein the updating of the building sketch corresponding to the first record comprises updating of the first area and/or updating of building materials arranged in the first area;
storing the second record in the record repository.
In the method, when the sketch is generated on the target drawing in an intelligent planning manner, the building materials are distributed on the first area (the selected target area) to generate the record corresponding to the sketch, and the sketch of the first area is generated by automatically distributing the materials or applying the record, but the materials are not randomly distributed through the pointing position of a user, so that the scheme for automatically distributing the materials and the formed application record are lacked.
In an optional aspect of the first aspect, the method further comprises:
obtaining a first building material according to building configuration parameters input by a user;
storing the first building material into the material library.
In the method, a plurality of materials can be generated correspondingly by selecting different configuration parameters related to the building materials, the generated materials are stored in a material library, so that when the sketch is planned in the first area, the materials with the configuration parameters set or the existing materials meeting the intention can be selected into the first area, and the sketch scheme related to the first area is generated based on the building materials arranged in the first area.
In yet another alternative of the first aspect, the first building material corresponds to a first material tag, the first material tag includes at least one tag in a first tag library, and the first tag library includes the following tags: the type, orientation, area, number of layers, layer height, elevator room ratio and shape of the building material;
the method further comprises the following steps:
inputting material tags corresponding to the first building material into a first tag prediction model, wherein the first tag prediction model comprises a plurality of tag sets, each tag set comprises at least two tags in a first tag library, and the tags in each tag set are different from each other;
if the similarity between a first material label and a first label set in a plurality of label sets is higher than a first preset threshold value, attributing the first material label to the first label set;
and storing the first building material into a first sub-library of a material library according to a first label set to which the first material label belongs, wherein the first sub-library is used for storing the material of which the label belongs to the first label set.
In the method, a user does not directly store the material into a material library, but first extracts a first material label of a certain material (such as a first building material), inputs the first material label into a first label prediction model, determines a first label set with similarity higher than a first preset threshold value with a first label set in a plurality of label sets, and then classifies and stores the material into the material library according to the set (classification) form.
It should be noted that, a large amount of historical data about each type of material and its configuration parameters are stored in the first label prediction model, where the historical data may include orientation, area, number of layers, layer height, elevator ratio, shape, etc. about the type of lake material, shape, floor area, type, orientation, etc. about the type of greening material, shape, floor area, type, etc. about the type of lake material; inputting a large amount of data about material types or configuration parameters and the like into a first label prediction model for training to obtain a more accurate first label prediction model; the first label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the first label library. It can be understood that, because the first label prediction model fully learns a large amount of material historical data input for people, it can summarize the basic rules of the classification set of the stored materials, and can more accurately predict the classification storage of a plurality of materials.
In yet another optional aspect of the first aspect, the storage manner is to store a first record as a whole, the first record corresponds to a first record tag, the first record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the method further comprises the following steps:
inputting the record label corresponding to the first record label into a second label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in a second label library, and the labels in each label set are different from each other;
if the similarity between a first record label and a second label set in a plurality of label sets is higher than a first preset threshold value, attributing the first record label to the second label set;
and storing the first record into a second sub-library of the record library according to a second label set to which the first record label belongs, wherein the second sub-library is used for storing records of which the labels belong to the second label set.
In the method, a user does not directly store the record into the record library, but extracts a first record label of a certain record (such as a first record), inputs the first record label into a second label prediction model, determines a second label set with similarity higher than a second preset threshold value with a second label set in a plurality of label sets, and then classifies and stores the record into the record library according to the set (classification) form.
It should be noted that, the second label prediction model stores a large amount of historical data about each type record, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and the large amount of data about the records is input into the second label prediction model for training to obtain a more accurate second label prediction model; the second material prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the second label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In yet another optional aspect of the first aspect, the method further comprises:
dividing the first area to obtain a plurality of divided areas;
generating a plurality of third records corresponding to the plurality of partitioned areas according to the building materials distributed in the partitioned areas, wherein one third record is used for representing the building materials distributed in one partitioned area;
and respectively storing the plurality of third records into the record library.
In the method, the first area in which the first record is generated based on the material arrangement is divided again, so that the first area corresponds to a plurality of divided areas, each of the plurality of divided areas corresponds to one third record, and the plurality of third records are stored in the record library.
In yet another optional aspect of the first aspect, the storage manner is a split storage for the first record, each of the third records corresponds to a third record tag, the third record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the method further comprises the following steps:
inputting the second record label corresponding to the third record into the third label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in a second label library, and the labels in each label set are different from each other;
if the similarity between a third record label corresponding to the third record and a third label set in the plurality of label sets is higher than a third preset threshold, attributing the third record label to the third label set;
and storing the third record into a third sub-library of a record library according to a third label set to which the third record label belongs, wherein the third sub-library is used for storing the record of which the label belongs to the third label set.
In the method, a user does not directly store the records in the record library or directly store the first records corresponding to the first area in the material library as a whole, but firstly divides the first area to obtain a plurality of third records corresponding to a plurality of divided areas, extracts a third record label of a certain third record, inputs the third record label into a second label prediction model, determines a third label set with the similarity higher than a third preset threshold value with the third label set in the plurality of label sets, and then classifies and stores the plurality of third records in the record library according to the form of set (classification).
It should be noted that, a large amount of historical data about each type record is stored in the third label prediction model, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and a large amount of data about records is input into the third label prediction model for training to obtain a more accurate third label prediction model; the third label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the third label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In yet another optional aspect of the first aspect, the segmenting the first region to obtain a plurality of sub-regions includes:
determining a plurality of color blocks included in the first area, wherein the area type corresponding to each color block comprises at least one of a building, an outer wall, a green area and a lake;
and inputting the color blocks into a segmentation prediction model to obtain a plurality of segmented areas after segmentation.
In the method, different sub-areas in the first area are colored, the type of the sub-area is determined according to the colors of color blocks corresponding to the different sub-areas, then a plurality of color blocks are input into a segmentation prediction model, and a plurality of segmented areas after segmentation are obtained according to the plurality of color blocks.
It should be noted that, a great deal of historical data about each preset region type, color block and segmentation scheme is stored in the segmentation prediction model; inputting a large amount of data about color blocks or types of preset areas and the like into a segmentation prediction model for training to obtain a more accurate segmentation prediction model; the segmentation prediction model stores a plurality of segmentation schemes for segmenting the region according to the color blocks, and each segmentation scheme is a scheme for segmenting and dividing the region according to the region type corresponding to the color block. It can be understood that, because the segmentation prediction model has fully learned the historical data of a large number of preset region types, color blocks and segmentation schemes which are input manually, the basic rule of the segmentation scheme can be summarized, and the segmentation of the first region can be predicted more accurately.
In yet another optional aspect of the first aspect, the determining a plurality of color blocks included in the first region includes:
comparing the first area with a preset area type, wherein the preset area type comprises a preset building type, a preset outer wall type, a preset greening type and a green lake type, the preset building type comprises any one of villas, multi-layer buildings, middle and high-rise buildings and super high-rise buildings, the preset outer wall type comprises any one of solid walls, partition walls and composite walls, the preset greening type comprises any one of gardens, parks and landscapes, and the preset lake type comprises any one of natural lakes and artificial lakes;
if the first subregion type of the first region does not belong to the preset region type, modifying the color of the color block corresponding to the first subregion type into a background color;
if the second subregion type of the first region belongs to the preset region type, modifying the color of a color block corresponding to the second subregion type into a key color, wherein if the second subregion type belongs to the preset building type, modifying the color of the color block of the preset building type into the first key color; if the second subregion type belongs to the preset outer wall type, modifying the color of the color block of the preset outer wall type into a second key color; if the second subregion type belongs to the preset greening type, modifying the color of the color block of the preset greening type into a third key color; if the second sub-area type belongs to the preset lake type, modifying the color of a color block of the preset lake type into a fourth key color;
and obtaining a plurality of color blocks in the first region according to the key colors and the background colors.
In the method, the color blocks of different sub-areas in the first area are also different in color, the color of the different color blocks represents the type of the area corresponding to the color blocks, and different buildings, such as buildings, houses, greenery, outer walls, landscapes and the like, in the first area are identified through the form of the color blocks.
In yet another optional aspect of the first aspect, the method further comprises:
receiving a search keyword input into a search prediction model, wherein the search keyword is a keyword included in the first tag library or the second tag library, and the search keyword includes at least one of the type, the orientation, the area, the number of floors, the floor height, the elevator ratio, the shape, the floor number, the building name and the location of a building material;
and determining a plurality of selectable materials in a plurality of materials corresponding to the search keyword according to the search prediction model, and determining a plurality of selectable materials in a plurality of records corresponding to the search keyword according to the search prediction model.
In the method, the user does not actively select the target record or the target material in the material library or the record library which is not subjected to classified storage, or actively select the target record or the target material in the material library or the record library which is subjected to classified storage (integral storage or divided storage), but inputs keywords related to the target material or the target record, and screens a plurality of optional materials and a plurality of optional records which meet the conditions from the material library or the record library through the search keywords, so that the efficiency of searching the target material or the target record by the user is greatly improved.
In yet another alternative of the first aspect, a plurality of selectable materials in a plurality of materials corresponding to the search keyword are determined according to the search prediction model, and a plurality of selectable materials in a plurality of records corresponding to the search keyword are determined according to the search prediction model, and a user selects a target selectable material or a target selectable record which meets the user's intention from the plurality of selectable records or the plurality of selectable materials, so that the efficiency of searching the materials or the records which meet the user's intention is improved for the user.
In yet another optional aspect of the first aspect, the generating a second record for the floor sketch based on the first record and the update of the floor sketch comprises:
determining a first modified region in the first region;
modifying configuration parameters of the first modification area;
generating a second record for the floor sketch based on the update of the configuration parameters for the first modified zone in the first record,
wherein the configuration parameters include one or more of: a right type of the first modified area, one or more tags in the first tag library, one or more tags included in the second tag library; the land type of the first modified area comprises a residential area, a greening area, a lake area, a fitness area or a road area.
In the method, the first record of the first area is updated by modifying the configuration parameters of the first area to obtain a new record, or the corresponding record of the first modified area is updated by modifying the configuration parameters of the first modified area to obtain a new record.
In yet another optional aspect of the first aspect, the generating a second record for the floor sketch according to the update of the floor sketch corresponding to the first record includes:
receiving an adjustment to a coverage of the first area;
generating a second record for the floor sketch.
In the method, the first record of the first area is updated by modifying the floor area range of the first area to obtain a new record, the method can modify the floor area range of the area according to the intention of a user on the basis of the original record to obtain the new record, and the efficiency of planning the sketch of the building area by the user is increased.
It should be noted that, if the first area is a polygon, the manner of changing the size of the first area may be changing the size of a node of the polygon, and if the first area is a circle, the manner of changing the size of the first area may be changing the size of a radius, and the shape of the first area is not limited in this embodiment of the present application.
In yet another alternative of the first aspect, an adjustment of a coverage of the first modified zone for the first zone is received; generating a second record for the floor sketch. In the method, the corresponding record of the first modification area is updated by modifying the floor area range of the first modification area to obtain a new record.
In yet another optional aspect of the first aspect, the determining the first area occupied by the roulette sketch comprises:
receiving selection indication information aiming at a fourth record in the record library, wherein the fourth record is used for representing the arrangement of the building materials in a second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area.
In the method, a user can select one record (namely, a fourth record) of the record library from an interface provided by the cloud, the fourth record is applied, a second area corresponding to the fourth record can be obtained, the size of the second area can reflect the size of the first area before the first area does not exist on the target drawing, the record of the record library can be directly applied to the method, the corresponding area can be generated, the time for selecting the area on the target drawing is saved, and the efficiency of planning the sketch of the building area by the user is increased.
In yet another optional aspect of the first aspect, the determining the first area occupied by the roulette sketch comprises:
the fourth record belongs to any record in the plurality of optional records, and selection indication information aiming at the fourth record in the record library is received, wherein the fourth record is used for representing the arrangement of the building materials in the second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area.
In the method, the user can select one record (namely, the fourth record) from a plurality of selectable records corresponding to the keyword search, and the fourth record is applied to obtain the second area corresponding to the fourth record.
In yet another optional aspect of the first aspect, receiving selection indication information for a fourth record in the record library, where the fourth record is used to characterize the arrangement of the building materials in the second area; determining a first division area occupied by the building sketch, wherein one division area of the first area is the same as the second area, and the arrangement of building materials of one sub-area of the first area is the same as the arrangement of the building materials in the second area.
In the method, a user can select one record (namely, a fourth record) of the record library from an interface provided by the cloud, and the fourth record is applied to obtain a second area corresponding to the fourth record, and when the first area exists on the target drawing, the size of the second area can reflect the size of the first segmentation area.
In yet another optional aspect of the first aspect, the determining the first area occupied by the roulette sketch comprises:
receiving a first circling area on a target drawing, wherein the first circling area comprises at least two of a constructable area, an un-constructable area, a public area and a constructed area;
inputting the first circumflex area into a land prediction model to obtain the first area in the target drawing, wherein the type of the first area is a constructable area.
In the method, the rough area on the target drawing, namely the first circled area, is selected, the first circled area is input into the plot prediction model, the non-architectural area, the public area and the built area in the first circled area can be screened, the architectable area (namely the first area) is reserved, the method does not need a user to click a node on an interface provided by a server through a mouse or draw a circle through a radius, the rough area is circled, the first area with accurate range is obtained, and the accuracy and the efficiency of building type planning are improved.
In yet another optional scenario of the first aspect, the material library includes M target materials, where any target material in the M materials corresponds to a projection range, and the projection range includes a sum of an occupied area of the target material and an influence range outside the occupied area, where the influence range is used to represent an ideal interval between the target material and a surrounding material;
the generating a first record for the building sketch based on the building material arranged in the first zone includes:
receiving selection operation aiming at M target materials;
obtaining N materials in a first area based on the M target materials, distributing the N materials in the first area to obtain a first record aiming at the building sketch, wherein the types corresponding to the M materials are the same as the types corresponding to the N materials, and M and N are integers,
the area of the overlapping range of the projection range of the first target material contained in the N materials is smaller than a first threshold value, the distance between the edges of the occupation range of the first target material contained in the N materials is larger than a second threshold value, the area of the overlapping range of the projection range of the second target material contained in the N materials is smaller than a third threshold value, the distance between the edges of the occupation range of the second target material contained in the N materials is larger than a fourth threshold value, and the target materials comprise building materials and landscape materials.
In the method, a user drags a plurality of materials in a material library to a first area on an interface provided by a cloud end, a first record is generated based on automatic arrangement of the plurality of materials, the area of an overlapping range of a projection range of a first target material is followed by an automatic arrangement mode of the plurality of materials is smaller than a first threshold, the distance between edges of an occupied area range of the first target material is larger than a second threshold, and the second target material is similar to the first target material.
In a second aspect, the present application provides a computing device, which includes a processing unit and a communication unit, and is configured to implement the method described in the first aspect or any possible implementation manner of the first aspect.
In a possible implementation manner of the second aspect, the processing unit may specifically include a first determining unit, a first generating unit, a first storing unit, an updating unit, and a second storing unit. Wherein:
the first determining unit is used for determining a first area occupied by the building sketch, and the first area is used for arranging building materials;
a first generating unit, configured to generate a first record for the building sketch based on the building materials arranged in the first area, where the building materials arranged in the first area are from a material library;
the first storage unit is used for storing the first record into a record library, wherein the storage mode comprises integral storage and divided storage aiming at the first record;
the communication unit is used for providing the first record for user equipment, and the first record is used for displaying the floor sketch or used for updating the floor sketch by a user;
the updating unit is used for generating a second record aiming at the building sketch according to the updating of the building sketch corresponding to the first record, wherein the updating of the building sketch corresponding to the first record comprises updating of the first area and/or updating of building materials arranged in the first area;
and the second storage unit is used for storing the second record into the record library.
It can be seen that when a sketch is generated on a target drawing in an intelligent planning manner, building materials are distributed on a first area (a selected target area), records corresponding to the sketch are generated, the materials are automatically distributed or the records are applied to generate the sketch of the first area, the materials are not randomly distributed at the pointed positions of users, and therefore a scheme for automatically distributing the materials and formed application records are lacked.
In a possible implementation manner of the second aspect, the apparatus further includes:
the second generation unit is used for obtaining a first building material according to the building configuration parameters input by the user;
and the third storage unit is used for storing the first building material into the material library.
It can be seen that by selecting different configuration parameters related to the building materials, a plurality of materials can be generated correspondingly, and the generated materials are stored in a material library, so that when a sketch is planned in a first area, the materials with the configuration parameters set or the existing materials meeting the intention can be selected into the first area, and a sketch scheme related to the first area is generated based on the building materials arranged in the first area.
In yet another possible implementation manner of the second aspect, the first building material corresponds to a first material tag, the first material tag includes at least one tag in a first tag library, and the first tag library includes the following tags: the type, orientation, area, layer number, layer height, elevator door ratio and shape of the building material;
the device further comprises:
a first input unit, configured to input material tags corresponding to the first building material into a first tag prediction model, where the first tag prediction model includes a plurality of tag sets, each tag set includes at least two tags in a first tag library, and tags included in each tag set are different from each other;
the first attribution unit is used for attributing a first material label to a first label set in a plurality of label sets if the similarity between the first material label and the first label set is higher than a first preset threshold value;
and the fourth storage unit is used for storing the first building material into a first sub-library of a material library according to the first label set to which the first material label belongs, wherein the first sub-library is used for storing the material of which the label belongs to the first label set.
It can be seen that a user does not directly store the material into the material library, but first extracts a first material label of a certain material (for example, a first building material), inputs the first material label into a first label prediction model, determines a first label set with similarity higher than a first preset threshold value with a first label set of a plurality of label sets, and then classifies and stores the material into the material library according to a set (classification) form.
It should be noted that, a large amount of historical data about each type of material and its configuration parameters are stored in the first label prediction model, where the historical data may include orientation, area, number of layers, layer height, elevator ratio, shape, etc. about the type of lake material, shape, floor area, type, orientation, etc. about the type of greening material, shape, floor area, type, etc. about the type of lake material; inputting a large amount of data about material types or configuration parameters and the like into the first label prediction model for training to obtain a more accurate first label prediction model; the first label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the first label library. It can be understood that, because the first label prediction model fully learns the historical data of a large number of artificially input materials, it can summarize the basic rules of the classification sets of the stored materials, and can more accurately predict the classification storage of a plurality of materials.
In yet another possible implementation manner of the second aspect, the storage manner is that a first record is stored as a whole, the first record corresponds to a first record tag, the first record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the device further comprises:
a second input unit, configured to input record labels corresponding to the first record labels into a second label prediction model, where the second label prediction model includes a plurality of label sets, each label set includes at least two labels in a second label library, and the labels included in each label set are different from each other;
the second attribution unit is used for attributing the first record label to a second label set in the plurality of label sets if the similarity between the first record label and the second label set is higher than a first preset threshold value;
a fifth storage unit, configured to store the first record into a second sub-library of the record library according to a second tag set to which the first record tag belongs, where the second sub-library is used to store records whose tags belong to the second tag set.
It can be seen that the user does not directly store the record into the record library, but first extracts a first record label of a certain record (for example, a first record), inputs the first record label into a second label prediction model, determines a second label set with similarity higher than a second preset threshold with a second label set of a plurality of label sets, and then classifies and stores the record into the record library according to the set (classification) form.
It should be noted that, the second label prediction model stores a large amount of historical data about each type record, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and the large amount of data about the records is input into the second label prediction model for training to obtain a more accurate second label prediction model; the second material prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the second label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In yet another optional manner of the second aspect, the apparatus further includes:
a dividing unit configured to divide the first region to obtain a plurality of divided regions;
a third generating unit, configured to generate a plurality of third records corresponding to the plurality of partitioned areas according to the building materials arranged in the plurality of partitioned areas, where one third record is used to represent the building material arranged in one partitioned area;
a sixth storage unit, configured to store the plurality of third records in the record library, respectively.
It can be seen that the first area in which the first record has been generated based on the material arrangement is divided again, so that the first area corresponds to a plurality of divided areas, each of the plurality of divided areas corresponds to one third record, and the plurality of third records are stored in the record library.
In yet another optional manner of the second aspect, the storage manner is a split storage manner for the first record, each of the third records in the plurality of third records corresponds to a third record tag, the third record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the device further comprises:
a third input unit, configured to input a label of the third record corresponding to the third record into the second label prediction model, where the second label prediction model includes a plurality of label sets, each label set includes at least two labels in a second label library, and the labels included in each label set are different from each other;
a third attribution unit, configured to attribute a third record label corresponding to the third record to a third label set in the plurality of label sets if a similarity between the third record label and the third label set is higher than a third preset threshold;
a seventh storage unit, configured to store the third record into a third sub-library of the record library according to a third tag set to which the third record tag belongs, where the third sub-library is used to store records to which tags belong to the third tag set.
It can be seen that, a user does not directly store records in the record library or directly store the first record corresponding to the first region in the material library as a whole, but first segments the first region to obtain a plurality of third records corresponding to a plurality of segmented regions, extracts a third record label of a certain third record, inputs the third record label into the second label prediction model, determines a third label set with similarity higher than a third preset threshold with a third label set in the plurality of label sets, and then classifies and stores the plurality of third records in the record library according to a set (classification) form.
It should be noted that, a large amount of historical data about each type record is stored in the third label prediction model, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and a large amount of data about records is input into the third label prediction model for training to obtain a more accurate third label prediction model; the third label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the third label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In another optional manner of the second aspect, the segmentation unit is specifically configured to:
determining a plurality of color blocks included in the first area, wherein the area type corresponding to each color block comprises at least one of a building, an outer wall, a green area and a lake;
and inputting the color blocks into a segmentation prediction model to obtain a plurality of segmented areas after segmentation.
It can be seen that different sub-regions in the first region are colored, the type of the sub-region is determined by the colors of the color blocks corresponding to the different sub-regions, then a plurality of color blocks are input into the segmentation prediction model, and a plurality of segmented regions after segmentation are obtained according to the plurality of color blocks.
It should be noted that, a great deal of historical data about each preset region type, color block and segmentation scheme is stored in the segmentation prediction model; inputting a large amount of data about color blocks or types of preset areas and the like into a segmentation prediction model for training to obtain a more accurate segmentation prediction model; the segmentation prediction model stores a plurality of segmentation schemes for segmenting the region according to the color blocks, and each segmentation scheme is a scheme for segmenting and dividing the region according to the region type corresponding to the color block. It can be understood that, because the segmentation prediction model has fully learned the historical data of a large number of preset region types, color blocks and segmentation schemes which are input manually, the basic rule of the segmentation scheme can be summarized, and the segmentation of the first region can be predicted more accurately.
In yet another optional manner of the second aspect, in the aspect of determining the plurality of color blocks included in the first region, the dividing unit is specifically configured to:
comparing the first area with a preset area type, wherein the preset area type comprises a preset building type, a preset outer wall type, a preset greening type and a green lake type, the preset building type comprises any one of villas, multi-layer buildings, middle and high-rise buildings and super high-rise buildings, the preset outer wall type comprises any one of solid walls, partition walls and composite walls, the preset greening type comprises any one of gardens, parks and landscapes, and the preset lake type comprises any one of natural lakes and artificial lakes;
if the first subregion type of the first region does not belong to the preset region type, modifying the color of the color block corresponding to the first subregion type into a background color;
if the second subregion type of the first region belongs to the preset region type, modifying the color of a color block corresponding to the second subregion type into a key color, wherein if the second subregion type belongs to the preset building type, modifying the color of the color block of the preset building type into the first key color; if the second subregion type belongs to the preset outer wall type, modifying the color of the color block of the preset outer wall type into a second key color; if the second subregion type belongs to the preset greening type, modifying the color of the color block of the preset greening type into a third key color; if the second sub-area type belongs to the preset lake type, modifying the color of a color block of the preset lake type into a fourth key color;
and obtaining a plurality of color blocks in the first region according to the key colors and the background colors.
It can be seen that the color blocks of different sub-areas in the first area are also different colors, the colors of the different color blocks represent the types of the areas corresponding to the color blocks, different buildings, such as buildings, houses, greenery, exterior walls, landscapes and the like, in the first area are identified through the forms of the color blocks, and the method can clearly distinguish the building materials in the first area so as to conveniently divide the first area.
In yet another optional manner of the second aspect, the apparatus further includes:
a receiving unit, configured to receive a search keyword input to a search prediction model, where the search keyword is a keyword included in the first tag library or the second tag library, and the search keyword includes at least one of a type, an orientation, an area, a floor number, a floor height, a stairway ratio, a shape, a building number, a building name, and a location of a building material;
and the second determining unit is used for determining a plurality of selectable materials in a plurality of materials corresponding to the search keyword according to the search prediction model and determining a plurality of selectable materials in a plurality of records corresponding to the search keyword according to the search prediction model.
It can be seen that, the user does not actively select the target record or the target material in the material library or the record library which is not classified for storage, or actively selects the target record or the target material in the material library or the record library which is classified for storage (integrally stored or stored in a divided manner), but inputs the keyword related to the target material or the target record, and selects a plurality of optional materials and a plurality of optional records which meet the conditions from the material library or the record library by searching the keyword, thereby greatly improving the efficiency of searching the target material or the target record by the user.
In another optional manner of the second aspect, the updating unit is specifically configured to:
determining a first modified region in the first region;
modifying configuration parameters of the first modification area;
generating a second record for the floor sketch based on the update of the configuration parameters for the first modified zone in the first record,
wherein the configuration parameters include one or more of: a right type of the first modified area, one or more tags in the first tag library, one or more tags included in the second tag library; the land type of the first modified area comprises a residential area, a greening area, a lake area, a fitness area or a road area.
The method can modify the configuration parameters according to the intention of the user on the basis of the original record to obtain a new record, and increases the efficiency of planning the sketch of the building area by the user.
In yet another optional manner of the second aspect, in the aspect that the second record for the floor sketch is generated according to the update of the floor sketch corresponding to the first record, the updating unit is specifically configured to:
receiving an adjustment to a coverage of the first area;
generating a second record for the floor sketch.
It can be seen that the first record of the first area is updated by modifying the floor space range of the first area to obtain a new record, and the method can modify the floor space range of the area according to the intention of a user on the basis of the original record to obtain the new record, thereby increasing the efficiency of planning the sketch of the building area by the user.
It should be noted that, if the first region is a polygon, the size of the first region may be changed by changing the size of a node of the polygon, and if the first region is a circle, the size of the first region may be changed by changing the size of a radius.
In another optional manner of the second aspect, the first determining unit specifically includes:
receiving selection indication information aiming at a fourth record in the record library, wherein the fourth record is used for representing the arrangement of the building materials in a second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area.
It can be seen that a user can select a certain record (i.e., a fourth record) of the record library from an interface provided by the cloud, and apply the fourth record to obtain a second area corresponding to the fourth record, and before the first area does not exist on the target drawing, the size of the second area can reflect the size of the first area.
In another optional manner of the second aspect, the first determining unit specifically includes:
receiving a first circling area on a target drawing, wherein the first circling area comprises at least two of a constructable area, an un-constructable area, a public area and a constructed area;
inputting the first circumflex area into a land prediction model to obtain the first area in the target drawing, wherein the type of the first area is a constructable area.
It can be seen that by selecting an approximate area on a target drawing, namely the first circled area, inputting the first circled area into the block prediction model, the non-architectural area, the public area and the built area in the first circled area can be screened out, the architectable area (namely the first area) is reserved, and the method does not need a user to click a node on an interface provided by a server through a mouse or draw a circle through a radius to obtain the first area, but the approximate area is circled, so that the first area with an accurate range is obtained, and the accuracy and the efficiency of building type planning are improved.
In yet another optional manner of the second aspect, the material library includes M target materials, any target material in the M materials corresponds to a projection range, the projection range includes a sum of an occupied area of the target material and an influence range outside the occupied area, and the influence range is used to represent an ideal interval between the target material and a surrounding material;
the first generating unit specifically includes:
receiving selection operation aiming at M target materials;
obtaining N materials in a first area based on the M target materials, distributing the N materials in the first area to obtain a first record aiming at the building sketch, wherein the types corresponding to the M materials are the same as the types corresponding to the N materials, and M and N are integers,
the area of the overlapping range of the projection range of the first target material contained in the N materials is smaller than a first threshold value, the distance between the edges of the occupation range of the first target material contained in the N materials is larger than a second threshold value, the area of the overlapping range of the projection range of the second target material contained in the N materials is smaller than a third threshold value, the distance between the edges of the occupation range of the second target material contained in the N materials is larger than a fourth threshold value, and the target materials comprise building materials and landscape materials.
It can be seen that a user drags a plurality of materials in a material library to a first area on an interface provided by a server, a first record is generated based on automatic arrangement of the plurality of materials, the area of an overlapping range of a projection range of a first target material is followed by an automatic arrangement mode of the plurality of materials is smaller than a first threshold, the distance between edges of an occupied range of the first target material is larger than a second threshold, and the second target material is similar.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a transceiver, a processor, and a memory, where the memory is used to store a computer program, and the processor invokes the computer program to execute any one of the methods for intelligently planning and generating a sketch in the first aspect and the first aspect of the embodiments of the present application. In a fourth aspect, an embodiment of the present application provides a computer storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for generating a sketch by intelligent planning in any one of the first aspect and the second aspect of the embodiments of the present application is implemented. In a fifth aspect, the present application provides a computer program product, which when run on an electronic device, causes the electronic device to execute the method for generating a sketch through intelligent planning according to the first aspect of the present application and any one of the first aspects. In a sixth aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a device that performs the method or the apparatus described in any embodiment of the present application. The electronic device is, for example, a chip. It should be appreciated that the description of technical features, solutions, benefits, or similar language in this application does not imply that all of the features and advantages may be realized in any single embodiment. Rather, it is to be understood that the description of a feature or advantage is intended to include the specific features, aspects or advantages in at least one embodiment. Therefore, the descriptions of technical features, technical solutions or advantages in the present specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and advantages described in the present embodiments may also be combined in any suitable manner. One skilled in the relevant art will recognize that an embodiment may be practiced without one or more of the specific features, aspects, or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments.
Drawings
The drawings used in the embodiments of the present application are described below.
Fig. 1 is a schematic diagram of an architecture of a sketch generation system 10 according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for generating a sketch by intelligent planning according to an embodiment of the present application;
fig. 3 is a schematic view of a scenario for determining a first area according to an embodiment of the present disclosure;
fig. 4A is a schematic view of a scene where a first area is generated according to a fourth record according to an embodiment of the present application;
fig. 4B is a schematic view of a scene of generating a first area according to a fourth record according to an embodiment of the present application;
fig. 5 is a schematic view of a scene in which a first building material is generated according to configuration parameters according to an embodiment of the present application;
fig. 6 is a schematic view of a scenario in which a first building material is stored in a first sub-library of the material library 500 according to an embodiment of the present application;
fig. 7 is a schematic view of a scene in which 4 target materials are dragged to a first area according to an embodiment of the present application;
fig. 8 is a scene schematic diagram of a first record of a building sketch for arranging N materials in a first area to generate the first area according to an embodiment of the present application;
fig. 9 is a scene schematic diagram of a projection range of a target material according to an embodiment of the present application;
fig. 10 is a schematic view of a scenario in which a first record is stored in a second sub-library of the record library 400 according to an embodiment of the present application;
fig. 11 is a schematic view of a scene for determining multiple color blocks of a first region according to an embodiment of the present application;
fig. 12 is a schematic view of a scene in which a first region is partitioned according to a plurality of color blocks according to an embodiment of the present application;
fig. 13 is a schematic view of a scenario that updates a record by modifying a configuration parameter according to an embodiment of the present application;
fig. 14 is a schematic view of a scene for modifying the size of the first area range according to an embodiment of the present application;
fig. 15A is a schematic view of a scene for filtering records according to keywords according to an embodiment of the present application;
fig. 15B is a schematic view of another scenario for screening records according to keywords according to an embodiment of the present application;
fig. 16 is a schematic view of another scenario for screening records according to keywords according to an embodiment of the present application;
fig. 17 is a schematic structural diagram of a computing device 170 according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be described in detail and clearly with reference to the accompanying drawings. The terminology used in the description of the embodiments herein is for the purpose of describing particular embodiments herein only and is not intended to be limiting of the application.
The embodiment of the application provides a method and related equipment for generating a sketch through intelligent planning, which can enable a user to rapidly plan a building area when generating a planning scheme of the building area, so as to obtain a floor sketch related to the building area.
The following description of the architecture designed by the embodiments of the present application is provided, and it should be understood that the following description of the architecture is only one possible scenario, and the present application is applicable to similar architectures as the technology evolves and new scenarios emerge.
Referring to fig. 1, fig. 1 is a schematic diagram of a sketch generation system 10 according to an embodiment of the present disclosure, which includes a cloud 101 and a user device 102.
The cloud 101 has computing power and storage space. The cloud can quickly generate the sketch of the building, and stores the materials related to the sketch and the record of the sketch. The storage space has stored therein a computer program or data which may include material or sketch records relating to the planning of the building area. Optionally, the specific form of the cloud 101 may be an entity device such as a server or a host, or may be a virtual device such as a virtual machine or a container.
The user device 102 is an electronic device having data processing and data transceiving capabilities, and may present an operation interface to a user, and the user may design, select, arrange, and the like materials in the operation interface. The user equipment receives data input by a user or indication information of operation, and provides the data or the indication information of operation to the cloud, so that the cloud provides service for the user. Alternatively, the user device 102 may comprise a stand-alone device such as a handheld terminal, a wearable device, a vehicle, a robot, etc., or may be a component (e.g., a chip or an integrated circuit) included in a stand-alone device. For example, when the terminal device is a handheld terminal, it may be a mobile phone (mobile phone), a tablet computer (pad), a computer (e.g., a laptop, a palmtop, etc.), and the like. Optionally, the number of the user equipment may be one or more, and the number of the user equipment is not limited in the present application.
In one possible implementation, the operation of the intelligent planning sketch described above may form an intelligent sketch generation cloud service. For example, after a user requests the intelligent sketch generation cloud service, the cloud end responds to a request triggered by the user and provides various materials and records for the user to select. Correspondingly, the user equipment used by the user can present an editing interface, and the user equipment can rapidly plan a sketch for the user after selecting materials or records.
The method of the embodiments of the present application is described in detail below.
Referring to fig. 2, fig. 2 is a schematic flowchart of a method for generating a sketch by intelligent planning according to an embodiment of the present application. Optionally, the method may be implemented based on the system 10 shown in fig. 1, for example, implemented by the cloud 101 in the system 10. The method includes, but is not limited to, the steps of:
s201: the computing device determines a first area occupied by the floor plan.
The computing device may be the cloud 101 shown in fig. 1, or may be other devices with computing capabilities.
The first area is used for arranging building materials. That is, the first area is an area for planning a floor plan. This range may be a specific location selected on the drawing, and may be a graphical region identified in the canvas.
In the embodiment of the present application, the first area occupied by the building sketch may be determined in various ways. For ease of understanding, two possible approaches are listed below:
in the method 1, the calculation device receives a region (hereinafter referred to as a first circling region for convenience of distinction) circled on the target drawing, and obtains the first region based on the first circling region. As shown in fig. 3, fig. 3 is a schematic view of a scenario for determining a first area according to an embodiment of the present application. The user defines a rough area on the target drawing, which represents the user's intent to perform floor planning in the rough area, as shown by the first defined area 301.
In one possible case, the first circumferential region can be directly the first region.
In yet another possible scenario, the first circumflex area may contain multiple types of areas, and some areas may not be able to be planned for a building. As a possible solution, the computing device may take a region that can be built in the first circumflex as the first region. For example, the first circumflex area may comprise at least two types of areas of a buildable area, a non-buildable area, a public area, a built area; and the computing device obtains a first area in the target drawing according to the first circling area, wherein the type of the first area is a constructable area. As shown in fig. 3, the first circling zone 301 includes a built zone 302, a public zone 303, an unestablished zone 304, and an unestablished buildable zone (first zone 305). In the embodiment of the present application, the computing device may remove the built area 302, the public area 303, and the non-built area 304 from the first circled area 301, leave the non-built and built area (i.e., the first area 305), and refine the first circled area 301 roughly circled by the user to obtain the first area 305 in the target drawing as shown in fig. 3.
As a possible solution, the first region may be quickly determined based on the first circumflex region by a block prediction model. The computing equipment inputs the first circled area into the plot prediction model, and the plot prediction module determines the area of the building sketch planning in the first circled area and outputs the first area.
The parcel prediction module may be trained based on historical data of parcel information. The historical data may include, among other things, information regarding the types and shapes of plots for blank areas, architectable areas, public areas, architected areas, non-architectable areas, and the like. And inputting a large amount of data about the land types, the shapes and the like of the areas into a land prediction model for training to obtain a more accurate land prediction model. It can be understood that, because the plot prediction model fully learns a large amount of manually input plot historical data, the plot planning model can summarize the basic rules for dividing the plot, so that the prediction of the first region can be accurately performed.
In particular, the computing device may receive selection indication information for a fourth record in the record repository, wherein the fourth record is used to characterize the arrangement of the building material in the second area. And determining a first area occupied by the building sketch according to a second area corresponding to the fourth record, wherein the first area is the same as the second area. Further optionally, the arrangement of the building materials in the first area may also be the same as the arrangement of the building materials in the second area, so that the user may adjust the building materials arranged in the fourth record to generate a new building sketch.
Alternatively, the fourth record may be an optional one of a plurality of records stored in the record library by the user according to his or her intention. The user clicks and applies the record, a second area corresponding to the selected record (fourth record) can be generated, and it can be understood that at this time, the user does not need to define a rough area on the target drawing and use the land parcel prediction model to obtain the first area, but applies the record selected by the user in the record library, and the second area corresponding to the fourth record can be automatically generated, the second area corresponding to the application record is equivalent to the first area generated according to the record, and the arrangement of the building materials in the first area is the same as that in the second area.
As shown in fig. 4A, fig. 4A is a scene schematic diagram of generating a first area according to a fourth record according to an embodiment of the present application, and as shown in fig. 4A, a user clicks the fourth record (record 4) in a record library, a building material arrangement has been generated in a second area 401 corresponding to the fourth record, and the user clicks the fourth record and applies the fourth record. As shown in fig. 4B, fig. 4B is a schematic view of a scene where a first area is generated according to a fourth record provided in this embodiment of the present application, where the fourth record (record 4) is a corresponding second area 401 on the target drawing, and the second area 401 is a first area occupied by a floor plan. It can be seen that the user does not need to define a rough region on the target drawing and obtain the region by using the land parcel prediction model, but directly applies the record to obtain the region.
S202: the computing device generates a first record for a building sketch based on the building materials arranged in the first zone.
Specifically, the building materials arranged in the first area come from a material library, a plurality of types of materials are stored in the material library, one material of each type corresponds to one parameter setting, a plurality of types of materials can be generated by setting different configuration parameters, or the generated materials can be modified by modifying corresponding configuration parameters based on the generated materials.
In the embodiment of the application, the types of the materials can be building materials, greening materials, lake materials and the like, and specifically, the building materials can be modified by adjusting configuration parameters such as orientation, area, layer number, layer height, elevator ratio, single-layer height and the like corresponding to the building materials so as to generate new building materials; the lake materials can be modified by adjusting configuration parameters such as the shape, the floor area, the depth and the orientation corresponding to the lake materials so as to generate new lake materials; the greening material can be modified by adjusting configuration parameters such as the shape, the floor area, the type and the orientation corresponding to the greening material so as to generate a new greening material.
Alternatively, the materials in the library may be preconfigured, predefined, or provided by default by the system. Alternatively, the material in the material library may be input by the user. In some embodiments, the computing device obtains the first building material based on the building configuration parameters entered by the user.
When developing the material, the user may generate the material by setting different configuration parameters, or the user may modify corresponding configuration parameters based on the generated material to obtain a new material. For ease of understanding, two possible designs of development material are exemplified below:
in design 1, a computing device obtains a first building material according to building configuration parameters input by a user. As shown in fig. 5, fig. 5 is a schematic view of a scene for generating a first building material according to configuration parameters according to an embodiment of the present application. When the material is a building material, the configuration parameters such as orientation, area, number of floors, floor height, elevator hall ratio and the like included in the configuration parameters 501 are modified, specific values of the configuration parameters are set, for example, the standard floor height is set to be 8 floors, the height of each floor is 3m, the elevator hall ratio is 1 elevator 2 hall, the total floor height is 11 floors, and the orientation is specified to be a fixed north-south 0 degree, and a first building material 502 is obtained according to the set configuration parameters.
The storage of the materials of the material library can be in various storage modes. As a possible scheme, in order to facilitate searching for the material and provide the material of a scene needed by the user, a tag may be attached to the material, and the material may be stored through the tag. The following takes the example of storing a first building material, and an exemplary description is given of an embodiment of storing material based on tags:
in the embodiment of the application, the building material corresponds to a material label, and the material label is used for describing the attribute or the characteristic of the building material. In the embodiment of the present application, the material tags may specifically include a plurality of tags, and the tags belong to a tag library. Illustratively, for example, a certain tag library (hereinafter referred to as a first tag library for convenience of description), one or more tags may be included, such as the type, orientation, area, number of layers, height of layers, elevator ratio, shape, etc. of the building material. It can be seen that each tag in the first tag library corresponds to a feature, e.g., one feature oriented, one feature area, etc.
The first building material corresponds to a first material label. The tags contained in the first material tags belong to a first tag library. Optionally, the number of the tags included in the first material tag may be one or more.
The computing device inputs a first material tag of the first building material into the first tag prediction model. The first label prediction model comprises a plurality of label sets, each label set comprises at least two labels in the first label library, and the labels in each label set are different from each other. If the similarity between the first material label and a first label set in the plurality of label sets is higher than a first preset threshold value, attributing the first material label to the first label set; and storing the first building material into a first sub-library of the material library according to a first label set to which the first material label belongs, wherein the first sub-library is used for storing the material of which the label belongs to the first label set. It should be understood that in the embodiments of the present application, "higher" may or may not include the case of equal, and the specific implementation case controls.
Taking the material library 500 shown in fig. 5 as an example, if a plurality of materials in the material library 500 are not stored according to a material set, when a user selects a target material among the plurality of materials, the user needs to search for a needed material among a large number of materials, which results in a decrease in efficiency of selecting the material by the user.
By the method, the materials can be classified and stored, and the efficiency of selecting the materials by a user is improved. As shown in fig. 5, a first material tag corresponding to the first building material 502 is extracted, the first material tag including: the standard floor is 8 floors high, the height of each floor is 3m, the elevator hall is 1 elevator hall and 2 elevators hall, the total floor is 11 floors high, and the orientation is designated as fixed north and south 0 degrees. The first material label is input into a first label prediction model, wherein labels included in a first label set in the first label prediction model are 10 layers to 16 layers of total layer height, 2.8m to 3.2m of each layer height and 0 degree to 30 degrees towards north and south, and labels included in one label set in the rest label sets may be 3 layers to 10 layers of labels, 3.2m to 4.3m of each layer height and 45 degrees to 50 degrees towards north and south. The first material tags are input into the first tag prediction model, and the similarity between the first material tags and the first tag set obtained by comparison is higher than a first preset threshold, which may be understood that a minimum threshold of the similarity (proximity) between the first material tags and the first tag set is regarded as a first preset threshold (for example, the similarity is 80%), in this embodiment, the similarity between the first material tags and the first tag set reaches 100%, that is, the tag content of the first material tags is a tag subset of the first tag set and is higher than the first threshold (80%), so that the first material tags may be assigned to the first tag set, as shown in fig. 6, fig. 6 is a scene diagram provided in this embodiment and used for storing the first building material in the first sub-library of the material library 500. The first building material 502 is stored in a first sub-library 601 of the material library 500 according to a first tag set to which the first material tag belongs, the first sub-library 601 being used to store the material to which the tag belongs.
In the above embodiment, the first label prediction module used may be generated by training through historical data about the material. The historical data may include, among other things, orientation, area, number of floors, floor height, gradient, shape, etc. for types of lake material, shape, footprint, type, orientation, etc. for types of greening material, shape, footprint, type, etc. for types of lake material. The model training equipment can input a large amount of data about material types or configuration parameters and the like into the first label prediction model for training to obtain a more accurate first label prediction model; the first label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the first material library. It can be understood that, because the first label prediction model fully learns a large amount of material historical data input for people, it can summarize the basic rules of the classification set of the stored materials, and can more accurately predict the classification storage of a plurality of materials.
It should be noted that, if the similarity between the first material tag and the first tag set in the plurality of tag sets is higher than a first preset threshold, the first material tag is attributed to the first tag set, which can be understood as attributing the type of the first building material to the first tag set according to the first tag prediction model, and then storing the first building tag into the first sub-library of the material library according to the first tag set corresponding to the first building tag.
In some embodiments, a first record for a building sketch is generated based on the building material arranged in the first zone. The specific process can be understood as follows: the plurality of materials in the material library include a plurality of (M) target materials, the target materials are materials selected by the user according to the intention of the user, and it should be noted that the target materials selected by the user may be materials selected from materials which are not classified by sub-libraries in the material library 500 shown in fig. 5, or materials selected from materials which are stored in the material library 500 shown in fig. 6 and classified by sub-libraries, which is not limited in the embodiment of the present application. Each target material corresponds to a projection range, the projection range comprises the sum of the occupied area range of a certain target material and an influence range outside the occupied area range, the influence range is used for representing the ideal interval between the target material and the surrounding materials, and the occupied area range is used for representing the actual occupied area range of the target material; the method comprises the following steps that a user drags a plurality of (M) selected target materials to a first area, N materials in the first area are obtained based on the M target materials, the N materials are arranged in the first area, and a first record aiming at the building sketch is obtained, wherein the type corresponding to the M materials is the same as the type corresponding to the N materials, M and N are integers, the N materials are arranged in the first area, and the first record aiming at the building sketch is obtained, wherein the target materials comprise the following types of materials: the building material comprises villas, multi-storey buildings, middle and high-rise buildings and super high-rise buildings, and the landscape material comprises gardens, parks, landscapes, natural lakes and artificial lakes. The area of the overlapping range of the projection range of the first target material contained in the N materials is smaller than a first threshold value, the distance between the edges of the occupation range of the first target material contained in the N materials is larger than a second threshold value, the area of the overlapping range of the projection range of the second target material contained in the N materials is smaller than a third threshold value, the distance between the edges of the occupation range of the second target material contained in the N materials is larger than a fourth threshold value, and the target materials comprise building materials and landscape materials.
Specifically, as shown in fig. 7, fig. 7 is a scene schematic diagram for dragging 4 target materials to a first area according to an embodiment of the present disclosure, a user selects 4 target materials (i.e., M = 4) in a material library 500, for example, the 4 target materials may be a high-rise building, a multi-story building, a lake, and a landscape, and drags the 4 target materials to a first area 305, as shown in fig. 8, fig. 8 is a scene schematic diagram for arranging N materials in the first area to generate a first record of a roulette sketch of the first area according to an embodiment of the present disclosure. As shown in fig. 7, after 4 target materials (M = 4) are dragged into the first area 305, as shown in fig. 8, 12 (N = 12) materials are generated based on the 4 target materials (M = 4), the category corresponding to the 4 (M = 4) target materials is the same as the category corresponding to the 12 (N = 12) materials, it can be understood that M represents the number of categories of target materials selected by the user from the material library, N represents that the user automatically plans after dragging the M target materials to the first area, the number of M target materials is increased, and 12 (N = 12) materials are arranged in the first area to obtain a first record for the roulette chart, it should be noted that the first record is a roulette chart for the first area, and the specific steps of obtaining the first record are as follows:
specifically, the projection range of the target material includes a footprint range and an influence range, the influence range is used for representing an ideal interval between the target material and surrounding materials, and the footprint range is used for representing an actual footprint range of the target material. As shown in fig. 9, fig. 9 is a schematic view of a scene of a projection range of a target material provided in an embodiment of the present application, where the projection range of a building 801 (high level) includes a floor area 901 and an influence area 902, the projection range of a building 802 (multiple levels) includes a floor area 903 and an influence area 904, the projection range of a green plant 803 includes a floor area 905 and an influence area 906, and the projection range of a lake 804 includes a floor area 907 and an influence area 908, where an area of an overlapping range 909 of the projection ranges of a first target material (building 801) contained in 12 (N = 12) materials is smaller than a first threshold, and an edge distance 910 between the floor areas of the first target material contained in 12 (N = 12) materials is greater than a second threshold; the area of the overlapping range 911 of the projection range of the second target material (building 802) included in the 12 (N = 12) materials is smaller than the third threshold value, and the edge distance 912 between the floor ranges of the second target materials included in the N materials is larger than the fourth threshold value.
It should be noted that the first threshold may be understood as a maximum overlapping area of the projection range of the first target material and the projection ranges of the remaining regions; the second threshold may be understood as the minimum distance between the edge of the footprint of the first target material and the edge of the footprint of the remaining area; the third threshold value may be understood as a maximum overlapping area of the projection range of the second target material and the projection ranges of the remaining areas; the fourth threshold may be understood as the minimum distance between the edge of the footprint of the second target material and the edge of the footprint of the remaining area.
It should be noted that, in the embodiment shown in fig. 9, the first target material is a building 801, the second target material is a building 802, the first target material may also be a green 803 and a lake 804, or may be any one of 12 (N = 12) materials; the second target material may be greening 803 or lake 804, or may be any one of 12 (N = 12) materials.
And arranging the N materials according to the rule to obtain a first record.
The storage process of the first record is explained in detail below:
s203: the computing device stores the first record in a record repository.
The storage mode of the first record may be to generate a new record, and store the new record directly into the record library, which may cause a situation that when there are too many records in the record library, the storage of the record is complicated, and it is difficult for a user to select a record related to a user's intention from a plurality of records in the record library, and therefore, it is necessary to store the first record in a classified manner, where the classified storage mode includes an overall storage and a divided storage for the first record, and the following two storage modes are described:
in some embodiments, the first record is stored in a repository. The specific stored procedure can be understood as: the storage mode is that the first record is stored as a whole, the first record corresponds to a first record label, the first record label comprises at least one label in a second label library, and the second label library comprises the following labels: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material; inputting the record labels corresponding to the first record labels into a second label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in a second label library, and the labels contained in each label set are different from each other; if the similarity between the first record label and a second label set in the plurality of label sets is higher than a first preset threshold value, attributing the first record label to the second label set; and storing the first record into a second sub-library of the record library according to a second label set to which the first record label belongs, wherein the second sub-library is used for storing the record of which the label belongs to the second label set.
It should be noted that the second label library includes a plurality of labels, each label corresponds to a feature, for example, the orientation is one label, the area is one label, the number of layers is one feature, and the like; the first record label corresponding to the first record can be at least two items in the second label library; a large amount of historical data about each type record is stored in the second label prediction model, wherein the historical data can comprise the type, the orientation, the area, the number of layers, the height of each layer, the elevator ratio, the shape, the number of each layer, the name of each layer, the location and the like of each layer about a sketch of each layer, and the large amount of data about the records are input into the second label prediction model for training to obtain a more accurate second label prediction model; the second material prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second material library. It can be understood that, since the second label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
It should be noted that, if the similarity between the first record label and the second label set in the plurality of label sets is higher than the second preset threshold, the first record label is attributed to the second label set, which may be understood as attributing the type of the first record to the second label set according to the second label prediction model, and then storing the first record in the second sub-repository of the record repository according to the second label set corresponding to the first record.
As shown in fig. 4A, in the record library 400 of fig. 4A, a plurality of records are not stored according to a record set, and when a user selects a target record in the plurality of records, the user needs to search for a needed record in a large number of records, which causes a decrease in efficiency of selecting a record by the user, and therefore the records need to be sorted and stored, which specifically includes the following steps:
as shown in fig. 4A, the first record (record 4) is extracted to correspond to a record label 402, the record label 402 including: the south Beijing is a place, the terrace is a Wanke gold region bay, the ladder house is two terraces and four terraces, the total floor is 34 layers high, the area is 338.76 square meters, the fifth terraces, the east is a place, the total floor is 6 layers high, the ladder house is two terraces, the total area is 174.88 square meters, and the total area is 19 terraces. Inputting the first record label into a second label prediction model, wherein labels included in a second label set in the second label prediction model are Nanjing in a place, a building is a Wanke gold region bay, a ladder house is higher than two ladders and four households, the total layer is 28-34 layers, the area is 200-400 square meters, the fifth building, the east China in the place, the total layer is 3-6 layers, the ladder house is higher than one ladder and two households, the total area is 100-180 square meters, and the number of the buildings is 15-20; in addition, the labels included in one of the rest label sets may be a place Nanjing, a building plate is a Wanke Jinyun Bay, a ladder house is 10-15 layers higher than a ladder, the area is 70-90 square meters, the fifth floor of the building, and the place Huadong, the total layer is 10-16 layers higher than the ladder house is two ladders, the total area is 100-150 square meters, and the number of the floors is 5-6. The first record label is input into the second label prediction model, and the similarity between the first record label and the second label set is obtained by comparing the first record label and the second label set and is higher than a second preset threshold (for example, the similarity is 70%), it is understood that the minimum threshold of the similarity (proximity) between the first record label and the first label set is regarded as the second preset threshold, and this embodiment summarizes that the similarity between the first record label and the first label set reaches 100%, that is, the label content of the first record label is a label subset of the second label set and is higher than the second threshold (70%), so that the first record label may be assigned to the second label set, as shown in fig. 10, fig. 10 is a scene diagram provided by this embodiment and storing the first record in the second sub-library of the record library 400. The first record 800 is stored in a second sub-repository 1001 of the record repository 400 according to a second set of tags to which the first record tag belongs, the second sub-repository 1001 being configured to store records to which tags belong to the second set of tags.
The above describes a detailed description of the whole storing process of the first record of the first area into the record library, and the following describes a detailed description of the storing process of the first area division into the record library:
in some embodiments, a plurality of color blocks included in the first area are determined, wherein the area type corresponding to each color block comprises at least one of a building, an outer wall, a green building and a lake; the specific steps of determining a plurality of color blocks included in the first region are as follows: comparing the first area with a preset area type, wherein the preset area type comprises a preset building type, a preset outer wall type, a preset greening type and a green lake type, the preset building type comprises any one of villas, multi-layer buildings, medium-high-rise buildings and super high-rise buildings, the preset outer wall type comprises any one of solid walls, partition walls and composite walls, the preset greening type comprises any one of gardens, parks and landscapes, and the preset lake type comprises any one of natural lakes and artificial lakes; if the first subregion type of the first region does not belong to the preset region type, modifying the color of the color block corresponding to the first subregion type into a background color; if the second subregion type of the first region belongs to the preset region type, modifying the color of a color block corresponding to the second subregion type into a key color, wherein if the second subregion type belongs to the preset building type, modifying the color of the color block of the preset building type into the first key color; if the second area type belongs to the preset outer wall type, modifying the color of the color block of the preset outer wall type into a second key color; if the second area type belongs to the preset greening type, modifying the color of the color block of the preset greening type into a third key color; and if the second area type belongs to the preset lake type, modifying the color of the color block of the preset lake type into a fourth key color. And obtaining a plurality of color blocks in the first region according to the key colors and the background colors.
Specifically, as shown in fig. 8, the types and the number of materials included in the first area 305 are: the 4 buildings 801 correspond to serial numbers 1, 2, 3 and 4, the 6 buildings 802 correspond to serial numbers 5, 6, 7, 8, 9 and 10, the lake 804 corresponds to serial number 11, and the landscape 803 (greening) corresponds to serial number 12. Comparing the first area with a preset area type, wherein 4 buildings 801 (corresponding to serial numbers 1, 2, 3 and 4) belong to a high floor in the preset building type, and the color of a color block of each building is set as a first key color (for example, dark brown); 6 buildings 802 (corresponding to serial numbers 5, 6, 7, 8, 9 and 10) belong to villas in a preset building type, and the color of a color block of the buildings is set as a first key color (for example, light brown); the landscape 803 (green) belongs to a preset green type, the color of which is set to a third key color (e.g., green); the lake 804 belongs to a preset lake type, the color of the lake is set as a fourth key color (for example, orange), and the region of the first region, which does not belong to the preset region type, is set as a background color (for example, white), as shown in fig. 11, where fig. 11 is a scene schematic diagram for determining multiple color blocks of the first region according to the embodiment of the present application. And obtaining a plurality of color blocks in the first region according to the key color and the background color, wherein the color of 1-4 color blocks is dark brown, the color of 5-10 color blocks is light brown, the color of 11 color blocks is orange, and the color of 12 color blocks is green.
In some embodiments, according to the determined plurality of color blocks in the first region, the plurality of color blocks of the first region are input into the segmentation prediction model, so as to obtain a plurality of segmented regions after segmentation. It should be noted that, a great deal of historical data about each preset region type, color block and segmentation scheme is stored in the segmentation prediction model; inputting a large amount of data about color blocks or types of preset areas and the like into a segmentation prediction model for training to obtain a more accurate segmentation prediction model; the segmentation prediction model stores a plurality of segmentation schemes for segmenting the region according to the color blocks, and each segmentation scheme is a scheme for segmenting and dividing the region according to the region type corresponding to the color block. It can be understood that, because the segmentation prediction model has fully learned the historical data of a large number of preset region types, color blocks and segmentation schemes which are input manually, the basic rule of the segmentation scheme can be summarized, and the segmentation of the first region can be predicted more accurately. Inputting a plurality of color blocks of a first region into a segmentation prediction model, as shown in fig. 12, fig. 12 is a schematic view of a scene in which the first region is segmented according to the plurality of color blocks, which is provided in this embodiment of the present application, and the obtained segmented regions are a first segmented region 1201 and a second segmented region 1202, where the first segmented region 1201 includes color block numbers of 1 to 4; the number of color blocks included in the second divided area 1202 is 5 to 12.
In some embodiments, for the second area corresponding to the fourth record, the second area may also be the same as a certain sub-area (i.e., the first divided area) in the first area in size, which may be understood as the building material arrangement of one sub-area of the first area, which is the same as the building material arrangement in the second area, so that a new area and a record of the building sketch corresponding to the new area may be quickly generated in the first area, and the efficiency of generating the sketch is improved, and the specific process is the same as that in S201 and is not described again.
The specific procedure of storing the plurality of third records will be described in detail below.
In some embodiments, the plurality of third records are stored in the record library respectively in a manner of partitioned storage for the first record, each of the plurality of third records corresponds to a third record tag, the third record tag includes at least one tag in the second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material; inputting second record labels corresponding to the third record into the third label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in the second label library, and the labels contained in each label set are different from each other; if the similarity between a third record label corresponding to the third record and a third label set in the plurality of label sets is higher than a third preset threshold, attributing the third record label to the third label set; and storing the third record into a third sub-library of the record library according to a third label set to which the third record label belongs, wherein the third sub-library is used for storing the record of which the label belongs to the third label set.
As shown in fig. 12, a third record corresponding to the first split area 1201 and a third record corresponding to the second split area 1202 are respectively stored in a record library, wherein a record label corresponding to the third record corresponding to the first split area 1201 is input into a third label prediction model, and a record label corresponding to the third record corresponding to the second split area 1202 is input into the third label prediction model, if the similarity between the third record label corresponding to the first split area 1201 and a third label set in the plurality of label sets is higher than a third preset threshold, the third record label is assigned to the third label set, and then the third record is stored in a third sub-library of the record library according to the third label set to which the third record label belongs, and the third sub-library is used for storing the record of which the label belongs to the third label set. If the similarity between the third record label corresponding to the second partition area 1202 and the third label set in the plurality of label sets is higher than a third preset threshold, attributing the third record label to the third label set, and storing the third record into a third sub-library of the record library according to the third label set to which the third record label belongs, where the third sub-library is used for storing the record to which the label belongs to the third label set, and the specific process is consistent with the overall storage of the first record, and is not described again.
The following describes in detail a specific process of obtaining the second record based on the first record update:
s204: the computing device provides a first record to the user device, the first record being used to present a floor plan or for the user to update the floor plan.
It should be noted that, on a server provided by the cloud 101, the cloud provides an interface, where the interface includes a material library, a record library, a target drawing, and the like, as shown in fig. 4A, a first record is provided to the user equipment, for example, the first record is record 4, the record is used for displaying a building sketch or is used for a user to update the building sketch, as shown in fig. 4B, displaying the building sketch may be understood as that record 4 corresponds to the second area 401, and a planning and parameter label of a record model is displayed; the records may also be used by the user to update a floor plan (described in detail below).
S205: the computing device generates a second record aiming at the building sketch according to the updating of the building sketch corresponding to the first record;
the updating of the first record corresponding to the building sketch comprises updating the first area and/or updating the building materials arranged in the first area, wherein the updating of the first area can be understood as changing the size of the first area or changing the size of a partial area (a first modification area) in the first area so as to achieve the purpose of generating a second record based on the updating of the first record; the updating of the building material arranged in the first area may be understood as changing the configuration parameters of the first area, or changing the configuration parameters of a partial area (first modification area) of the first area, so as to achieve the purpose of generating the second record based on the first record update, which is described in the following two ways:
in some embodiments, a first modified region in the first region is determined; modifying the configuration parameters of the first modification area; generating a second record for the floor sketch based on the updating of the configuration parameters for the first modified zone in the first record, wherein the configuration parameters include one or more of: the land use type of the first modified area, one or more tags in the first tag library, one or more tags included in the second tag library; the land type of the first modified area includes a residential area, a green area, a lake area, a fitness area, or a road area.
Specifically, as shown in fig. 13, fig. 13 is a schematic view of a scenario that updates a record by modifying a configuration parameter according to an embodiment of the present application. The user clicks the first area 305, the configuration parameters corresponding to the first area are displayed in the server interface, and the attributes of the configuration parameters are changed to achieve the purpose of generating new records, for example, the generation preference is changed from volume rate priority to lighting priority, a second record is correspondingly generated, and the second record is stored in the record library, where the specific storage mode may be an overall storage mode or a classified storage mode in S203, and the steps are consistent and are not repeated.
It should be noted that, if the size of the first modification area is equal to the size of the first area, the first modification area is equivalent to the first area at this time, that is, the configuration parameters of the first modification area are modified, and the configuration parameters of the first area are also modified, and the detailed process is not repeated.
It should be noted that, if only the configuration parameters of a partial area (the first modification area 1301) in the first area need to be modified to generate a new record corresponding to the first modification area 1301, the user clicks the first modification area 1301, the configuration parameters corresponding to the first modification area 1301 are displayed in the service-side interface, and attributes of the configuration parameters are changed to achieve the purpose of generating the new record, for example, the orientation angle is changed from a custom-specified 25 ° to a north-south orientation 0 °, a second record is correspondingly generated, and the second record is stored in the record library, where the specific storage manner may be an overall storage manner or a classified storage manner in S203, and the steps are consistent and are not described again.
In some embodiments, an adjustment is received for a coverage of a first area; a second record for the floor plan is generated.
It should be noted that, if the first region is a polygon, the size of the first region may be changed by changing the size of a node of the polygon, and if the first region is a circle, the size of the first region may be changed by changing the size of a radius.
Specifically, as shown in fig. 14, fig. 14 is a schematic view of a scene provided by the embodiment of the present application for modifying the size of the first area range. When the first region 305 is a polygon region, the nodes of the polygon region are changed to change the size of the first region 305, the changed region is the region 1401, a new second record is generated based on the changed first region, and the second record is stored in the record library, where the specific storage manner may be the overall storage manner or the classified storage manner in S203, and the steps are identical and are not repeated.
It should be noted that, the size of the first area is changed, or the size of a partial area (first modified area) in the first area is changed, so as to achieve the purpose of generating the second record based on the first record update, and a specific process of changing the size of the first modified area is consistent with a process of changing the size of the first area, and is not described again.
S206: the computing device stores the second record in a record repository.
The second record is updated based on the first record, and the storage process of the second record is consistent with the first record, and may be stored for the second record as a whole, or stored for the second record in a divided manner, and the specific process is consistent with the first record, and please refer to S203 for the specific step, which is not described again.
If the user needs to actively search the keywords to achieve the purpose of selecting the target selectable materials or the target selectable records in the material library or the record library, the specific steps are as follows:
in the process that a user selects target selectable materials or target selectable records in a material library or a record library, if a plurality of materials or a plurality of records in the material library or the record library are stored in a storage mode which is not stored according to classification (namely, stored randomly), the keyword search of the user is the search of the material library or the record library which is not stored according to classification; if the storage mode is the storage according to the whole classified storage or the divided classification of the first record in step S203, the keyword of the user is a search for the material library or the record library that has been stored in the whole classified storage or the divided classification, and the following description is given in terms of a search for the material library or the record library that has not been stored in the divided classification:
in some embodiments, a search keyword input into the search prediction model is received, wherein the search keyword is a keyword included in the first tag library or the second tag library, and the search keyword includes at least one of a type, an orientation, an area, a floor number, a floor height, a stairway ratio, a shape, a floor number, a building name, and a place of the building material; and determining a plurality of selectable materials in a plurality of materials corresponding to the search keyword according to the search prediction model, and determining a plurality of selectable materials in a plurality of records corresponding to the search keyword according to the search prediction model, wherein the user can select a target selectable material in the plurality of selectable materials and a target selectable record in the plurality of selectable records, and the target selectable material or the target selectable record is applied according to the intention of the user.
The following description will be made by taking the example of filtering a plurality of selectable records according to keywords:
specifically, for a record library stored unclassified, as shown in fig. 15A, fig. 15A is a schematic view of a scene for filtering records according to keywords according to an embodiment of the present application. As shown in fig. 15A, the record library includes 8 records corresponding to records 1 to 8, and there are many records in the record library, and if a user selects a record on an interface provided by the server, the user may be required to point a mouse to the record to display the parameter information corresponding to the record, which results in very complicated steps, so that the user may input a search keyword, for example, the input keyword is: towards north and south 20 °, eight households of six ladders filter records according to the input search keyword, as shown in fig. 15B, fig. 15B is a scene schematic diagram of filtering records according to the keyword provided by the embodiment of the present application, two records, namely record 7 and record 8, corresponding to the keyword are obtained, and the user selects the two records, so that time is saved.
Specifically, for a record library which has been integrally classified or separately classified and stored, as shown in fig. 10, a first record 800 is stored in a second sub-library 1001, the second sub-library 1001 further includes other records such as a second record, and the other records include other sub-libraries besides the second sub-library, and there are more records in the record library 400, if a user selects a record on an interface provided by a server, the user may be required to point a mouse to a certain record in a certain sub-library to display parameter information corresponding to the record, which may cause very complicated steps, so that the user may input a search keyword, for example, the input keyword is: 18, two ladders and four users filter records according to the input search keywords, as shown in fig. 16, fig. 16 is another scene schematic diagram provided by the embodiment of the present application and filtering records according to keywords, to obtain a first record 800 corresponding to the keyword, and the user selects the first record conforming to the keyword, which saves time.
It should be noted that the specific process of keyword search for multiple selectable materials is consistent with the keyword search for multiple selectable records, and is not repeated.
It should be noted that, after the user inputs the search keyword, if there is no material or record required by the user in the displayed multiple selectable materials or multiple records, the keyword may be re-input for searching, or an or is added as a relationship connector in the keyword, or the other ways are also possible, which is not limited in this embodiment of the present application.
It should be noted that, for a material library or a record library which is not stored in a classified manner, keywords of the material library or the record library search for a plurality of corresponding selectable materials or a plurality of selectable records, and for a material library or a record library which is stored in an overall classified manner or stored in a divided classified manner, keywords of the material library or the record library search for a plurality of corresponding selectable materials or a plurality of selectable records, the two presentation manners may be the same or different, and embodiments of the present application are not limited. Specifically, if the two presentation modes are the same, the multiple selectable materials or the multiple selectable records may be understood as being displayed in a new area in an interface provided by the server, and the new area is not affected by the storage modes of the material library or the record library, that is, the presentation modes of keyword searches corresponding to the two storage modes may be the same.
If the two presentation manners are different, it can be understood that a plurality of selectable materials or a plurality of selectable records are directly displayed in the material library or the record library (materials or records not related to keywords are not displayed), and the presentation manners at this time are different, for example, the presentation manners of keyword search for the unclassified and stored record library shown in fig. 15B are different from the presentation manners of keyword search for the whole or divided and stored record library shown in fig. 16. The method includes that a material library or a record library which is stored in an overall classified or divided classified manner is classified and screened according to sub libraries, final display may also be classified and displayed according to the sub libraries, a material library or a record library which is not stored in a classified manner is screened in all materials, and finally is not classified and displayed according to the sub libraries.
In some embodiments, the fourth record may also be any one of a plurality of selectable records, and the fourth record is used for representing the arrangement of the building materials in the second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area. The fourth record is a record which is selected by the user according to the user intention from a plurality of optional records obtained by searching according to the keyword, each optional record corresponds to a floor sketch of an area, the user clicks and applies the optional record to generate a second area corresponding to the selected optional record (fourth record), understandably, compared with the case that the fourth record is a record which is selected by the user according to the user intention from a plurality of records stored in the record library, the fourth record is a certain optional record in the plurality of optional records, and the second area corresponding to the fourth record can be automatically generated by applying the optional record, the generation type of the second area can be selected on the basis of the generation of the second area, the second area related to the search keyword is generated, and the efficiency and the use experience of the user are improved.
The method for generating a lightning sketch in relation to an intelligent planning is described above, and the apparatus of the method is described below.
As shown in fig. 17, fig. 17 is a schematic structural diagram of a computing device 170 according to an embodiment of the present disclosure. Alternatively, the computing device 170 may be a stand-alone device, or may be a device included in a stand-alone device, such as a chip, a software module, or an integrated circuit. The computing device is used for implementing the method for generating the sketch by the intelligent planning, such as the method described in the embodiment shown in fig. 2.
Computing device 170 may include a processing unit 1701 and a communication unit 1702. Optionally, the processing unit 1701 is configured to implement operations related to determining, calculating, processing, generating, updating, or storing, and the communication unit 1702 is configured to implement operations related to receiving, sending, or providing data. It should be understood that the division of the units in the embodiments of the present application is illustrative, and is only one logical function division, and there may be other division manners in actual implementation. In the specific implementation process, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one functional unit. The integrated functional unit can be realized in a form of hardware or a form of software functional unit.
In one possible implementation, the processing unit 1701 may include: a first determining unit 1703, a first generating unit 1704, a first storage unit 1705, an updating unit 1706, and a second storage unit 1707, where the apparatus 170 may be the device or a device or module in the device. It should be understood that the above units (or modules) are function modules divided according to functions, in a specific implementation, some function modules may be subdivided into more tiny function modules, and some function modules may also be combined into one function module, but whether the function modules are subdivided or combined, the general flow executed in the process of quickly generating the building sketch of the planned area on the target drawing is the same. Typically, each functional module corresponds to a respective program code (i.e. a computer program stored in a memory of the device), and when the respective program code of these functional modules runs on a processor, the functional modules execute corresponding procedures to implement corresponding functions. The individual units of the computing device 170 are described as follows:
a first determining unit 1703, configured to determine a first area occupied by the building sketch, where the first area is used for arranging building materials;
a first generation unit 1704 for generating a first record for the building sketch based on the building materials arranged in the first area from a material library;
a first storage unit 1705, configured to store the first record into a record library, where the storage manner includes integral storage and split storage of the first record;
a communication unit 1702, configured to provide the first record to a user device, where the first record is used to display the floor sketch or used for a user to update the floor sketch;
an updating unit 1706, configured to generate a second record for the floor sketch according to updating of the floor sketch corresponding to the first record, where the updating of the floor sketch corresponding to the first record includes updating of the first area and/or updating of building materials arranged in the first area;
a second storage unit 1707, configured to store the second record in the record library.
When a draft is generated through intelligent planning on a target drawing, building materials are distributed on a first area (a selected target area), records corresponding to the draft are generated, the draft of the first area is generated through automatic distribution of the application materials or through the records, the materials are not randomly distributed through the pointed position of a user, and therefore the automatic distribution scheme of the materials and the formed application records are lacked.
In one possible implementation manner, the apparatus 170 further includes:
the second generation unit is used for obtaining a first building material according to the building configuration parameters input by the user;
and the third storage unit is used for storing the first building material into the material library.
It can be seen that by selecting different configuration parameters related to the building materials, a plurality of materials can be generated correspondingly, and the generated materials are stored in a material library, so that when a sketch is planned in a first area, the materials with the configuration parameters set or the existing materials meeting the intention can be selected into the first area, and a sketch scheme related to the first area is generated based on the building materials arranged in the first area.
In one possible implementation, the first building material corresponds to a first material tag, the first material tag includes at least one tag in a first tag library, and the first tag library includes the following tags: the type, orientation, area, layer number, layer height, elevator door ratio and shape of the building material;
the apparatus 170 further comprises:
a first input unit, configured to input material tags corresponding to the first building material into a first tag prediction model, where the first tag prediction model includes a plurality of tag sets, each tag set includes at least two tags in a first tag library, and tags included in each tag set are different from each other;
the first attribution unit is used for attributing a first material label to a first label set in a plurality of label sets if the similarity between the first material label and the first label set is higher than a first preset threshold value;
and the fourth storage unit is used for storing the first building material into a first sub-library of a material library according to the first label set to which the first material label belongs, wherein the first sub-library is used for storing the material of which the label belongs to the first label set.
It can be seen that a user does not directly store the material into the material library, but first extracts a first material label of a certain material (for example, a first building material), inputs the first material label into a first label prediction model, determines a first label set with similarity higher than a first preset threshold value with a first label set of a plurality of label sets, and then classifies and stores the material into the material library according to a set (classification) form.
It should be noted that, a large amount of historical data about each type of material and its configuration parameters are stored in the first label prediction model, where the historical data may include orientation, area, number of layers, layer height, elevator ratio, shape, etc. about the type of lake material, shape, floor area, type, orientation, etc. about the type of greening material, shape, floor area, type, etc. about the type of lake material; inputting a large amount of data about material types or configuration parameters and the like into a first label prediction model for training to obtain a more accurate first label prediction model; the first label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the first label library. It can be understood that, because the first label prediction model fully learns a large amount of material historical data input for people, it can summarize the basic rules of the classification set of the stored materials, and can more accurately predict the classification storage of a plurality of materials.
In a possible implementation manner, the storage manner is to store a first record as a whole, the first record corresponds to a first record tag, the first record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the apparatus 170 further comprises:
a second input unit, configured to input a record label corresponding to the first record label into a second label prediction model, where the second label prediction model includes a plurality of label sets, each label set includes at least two labels in a second label library, and the labels included in each label set are different from each other;
the second attribution unit is used for attributing the first record label to a second label set in the plurality of label sets if the similarity between the first record label and the second label set is higher than a first preset threshold value;
and a fifth storage unit, configured to store the first record into a second sub-library of the record library according to a second tag set to which the first record tag belongs, where the second sub-library is used to store records to which tags belong to the second tag set.
The method includes the steps that a user does not directly store records into a record library, first record labels of a certain record (such as a first record) are extracted, the first record labels are input into a second label prediction model, a second label set with the similarity higher than a second preset threshold value with a second label set in a plurality of label sets is determined, and then the records are stored into the record library in a classified mode according to the set (classification) mode.
It should be noted that, the second label prediction model stores a large amount of historical data about each type record, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and the large amount of data about the records is input into the second label prediction model for training to obtain a more accurate second label prediction model; the second material prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the second label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In an optional manner, the apparatus 170 further comprises:
a dividing unit configured to divide the first region to obtain a plurality of divided regions;
a third generating unit, configured to generate a plurality of third records corresponding to the plurality of partitioned areas according to the building materials arranged in the plurality of partitioned areas, where one third record is used to represent the building material arranged in one partitioned area;
a sixth storage unit, configured to store the plurality of third records in the record library, respectively.
It can be seen that the first area in which the first record has been generated based on the material arrangement is divided again, so that the first area corresponds to a plurality of divided areas, each of the plurality of divided areas corresponds to one third record, and the plurality of third records are stored in the record library.
In an optional manner, the storage manner is a split storage for the first record, each of the third records in the plurality of third records corresponds to a third record tag, the third record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the apparatus 170 further comprises:
a third input unit, configured to input a label of the third record corresponding to the third record into the second label prediction model, where the second label prediction model includes a plurality of label sets, each label set includes at least two labels in a second label library, and the labels included in each label set are different from each other;
a third attribution unit, configured to attribute a third record label corresponding to the third record to a third label set in the plurality of label sets if a similarity between the third record label and the third label set is higher than a third preset threshold;
a seventh storage unit, configured to store the third record into a third sub-library of the record library according to a third tag set to which the third record tag belongs, where the third sub-library is used to store records to which tags belong to the third tag set.
It can be seen that, a user does not directly store records in the record library or directly store the first record corresponding to the first region in the material library as a whole, but first segments the first region to obtain a plurality of third records corresponding to a plurality of segmented regions, extracts a third record label of a certain third record, inputs the third record label into the second label prediction model, determines a third label set with similarity higher than a third preset threshold with a third label set in the plurality of label sets, and then classifies and stores the plurality of third records in the record library according to a set (classification) form.
It should be noted that, a large amount of historical data about each type record is stored in the third label prediction model, where the historical data may include a building type, an orientation, an area, a floor number, a floor height, a stairwell ratio, a shape, a building number, a building name, a location, and the like about a building sketch, and a large amount of data about records is input into the third label prediction model for training to obtain a more accurate third label prediction model; the third label prediction model stores a plurality of label sets, and each label set at least comprises at least two items in the second label library. It can be understood that, since the third label prediction model fully learns a large amount of record historical data input by people, it can summarize the basic rules of the classification set of the stored records, and can more accurately predict the classification storage of a plurality of records.
In an optional manner, the segmentation unit is specifically configured to:
determining a plurality of color blocks included in the first area, wherein the area type corresponding to each color block comprises at least one of a building, an outer wall, a green area and a lake;
and inputting the color blocks into a segmentation prediction model to obtain a plurality of segmented areas after segmentation.
It can be seen that different sub-regions in the first region are colored, the type of the sub-region is determined by the colors of the color blocks corresponding to the different sub-regions, then a plurality of color blocks are input into the segmentation prediction model, and a plurality of segmented regions after segmentation are obtained according to the plurality of color blocks.
It should be noted that, a great deal of historical data about each preset region type, color block and segmentation scheme is stored in the segmentation prediction model; inputting a large amount of data about color blocks or types of preset areas and the like into a segmentation prediction model for training to obtain a more accurate segmentation prediction model; the segmentation prediction model stores a plurality of segmentation schemes for segmenting the region according to the color blocks, and each segmentation scheme is a scheme for segmenting and dividing the region according to the region type corresponding to the color block. It can be understood that, because the segmentation prediction model has fully learned the historical data of a large number of preset region types, color blocks and segmentation schemes which are input manually, the basic rule of the segmentation scheme can be summarized, and the segmentation of the first region can be predicted more accurately.
In an optional manner, in the aspect of determining the plurality of color blocks included in the first region, the dividing unit is specifically configured to:
comparing the first area with a preset area type, wherein the preset area type comprises a preset building type, a preset outer wall type, a preset greening type and a green lake type, the preset building type comprises any one of villas, multi-layer buildings, middle and high-rise buildings and super high-rise buildings, the preset outer wall type comprises any one of solid walls, partition walls and composite walls, the preset greening type comprises any one of gardens, parks and landscapes, and the preset lake type comprises any one of natural lakes and artificial lakes;
if the first subregion type of the first region does not belong to the preset region type, modifying the color of the color block corresponding to the first subregion type into a background color;
if the second subregion type of the first region belongs to the preset region type, modifying the color of a color block corresponding to the second subregion type into a key color, wherein if the second subregion type belongs to the preset building type, modifying the color of the color block of the preset building type into the first key color; if the second subregion type belongs to the preset outer wall type, modifying the color of the color block of the preset outer wall type into a second key color; if the second subregion type belongs to the preset greening type, modifying the color of the color block of the preset greening type into a third key color; if the second sub-area type belongs to the preset lake type, modifying the color of a color block of the preset lake type into a fourth key color;
and obtaining a plurality of color blocks in the first region according to the key colors and the background colors.
It can be seen that the color blocks of different sub-areas in the first area are also different colors, the colors of the different color blocks represent the types of the areas corresponding to the color blocks, different buildings, such as buildings, households, greenery, outer walls, landscapes and the like, in the first area are identified through the forms of the color blocks, and the method can clearly distinguish the building materials in the first area so as to divide the first area.
In an optional manner, the apparatus 170 further comprises:
a receiving unit, configured to receive a search keyword input to a search prediction model, where the search keyword is a keyword included in the first tag library or the second tag library, and the search keyword includes at least one of a type, an orientation, an area, a floor number, a floor height, a stairway ratio, a shape, a building number, a building name, and a location of a building material;
and the second determining unit is used for determining a plurality of selectable materials in a plurality of materials corresponding to the search keyword according to the search prediction model and determining a plurality of selectable materials in a plurality of records corresponding to the search keyword according to the search prediction model.
It can be seen that, the user does not actively select the target record or the target material in the material library or the record library which is not classified for storage, or actively selects the target record or the target material in the material library or the record library which is classified for storage (integrally stored or stored in a divided manner), but inputs the keyword related to the target material or the target record, and selects a plurality of optional materials and a plurality of optional records which meet the conditions from the material library or the record library by searching the keyword, thereby greatly improving the efficiency of searching the target material or the target record by the user.
In an optional manner, the updating unit 1706 is specifically configured to:
determining a first modified region in the first region;
modifying configuration parameters of the first modification area;
generating a second record for the floor sketch based on an update to the configuration parameters for the first modified zone in the first record,
wherein the configuration parameters include one or more of: a right type of the first modified area, one or more tags in the first tag library, one or more tags included in the second tag library; the land type of the first modified area comprises a residential area, a greening area, a lake area, a fitness area or a road area.
The method can modify the configuration parameters according to the intention of the user on the basis of the original record to obtain a new record, and increases the efficiency of planning the sketch of the building area by the user.
In an optional manner, in the aspect of generating the second record for the floor sketch according to the update of the floor sketch corresponding to the first record, the updating unit 1706 is specifically configured to:
receiving an adjustment to a coverage of the first area;
generating a second record for the floor sketch.
Therefore, the method can modify the floor area of the area according to the intention of the user on the basis of the original record to obtain the new record, and the efficiency of planning the sketch of the building area by the user is increased.
It should be noted that, if the first region is a polygon, the size of the first region may be changed by changing the size of a node of the polygon, and if the first region is a circle, the size of the first region may be changed by changing the size of a radius.
In an optional manner, the first determining unit 1703 specifically includes:
receiving selection indication information aiming at a fourth record in the record library, wherein the fourth record is used for representing the arrangement of the building materials in a second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area.
It can be seen that a user can select a certain record (i.e., a fourth record) of the record library from an interface provided by the cloud, and apply the fourth record to obtain a second area corresponding to the fourth record, and before the first area does not exist on the target drawing, the size of the second area can reflect the size of the first area.
In an optional manner, the first determining unit 1703 specifically includes:
receiving a first circling area on a target drawing, wherein the first circling area comprises at least two of a constructable area, an un-constructable area, a public area and a constructed area;
inputting the first circumflex area into a land prediction model to obtain the first area in the target drawing, wherein the type of the first area is a constructable area.
It can be seen that by selecting an approximate area on a target drawing, namely the first circled area, inputting the first circled area into the block prediction model, the non-architectural area, the public area and the built area in the first circled area can be screened out, the architectable area (namely the first area) is reserved, and the method does not need a user to click a node on an interface provided by a server through a mouse or draw a circle through a radius to obtain the first area, but the approximate area is circled, so that the first area with an accurate range is obtained, and the accuracy and the efficiency of building type planning are improved.
In an optional mode, the material library includes M target materials, any target material in the M materials corresponds to a projection range, the projection range includes a sum of an occupied area range of the target material and an influence range outside the occupied area range, and the influence range is used for representing an ideal interval between the target material and surrounding materials;
the first generation unit 1704 specifically includes:
receiving selection operation aiming at M target materials;
obtaining N materials in a first area based on the M target materials, distributing the N materials in the first area to obtain a first record aiming at the building sketch, wherein the types corresponding to the M materials are the same as the types corresponding to the N materials, and M and N are integers,
the area of the overlapping range of the projection range of the first target material contained in the N materials is smaller than a first threshold value, the distance between the edges of the occupation range of the first target material contained in the N materials is larger than a second threshold value, the area of the overlapping range of the projection range of the second target material contained in the N materials is smaller than a third threshold value, the distance between the edges of the occupation range of the second target material contained in the N materials is larger than a fourth threshold value, and the target materials comprise building materials and landscape materials.
It can be seen that a user drags a plurality of materials in a material library to a first area on an interface provided by a server, a first record is generated based on automatic arrangement of the plurality of materials, the area of an overlapping range of a projection range of a first target material is followed by an automatic arrangement mode of the plurality of materials is smaller than a first threshold, the distance between edges of an occupied range of the first target material is larger than a second threshold, and the second target material is similar.
An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed on a processor, the computer program implements the method flow shown in fig. 2.
An embodiment of the present invention further provides a computer program product, which when running on a processor, implements the method flow shown in fig. 2.
In summary, by implementing the embodiment of the present application, a plurality of materials can be generated accordingly by selecting different configuration parameters related to the building materials, and the generated plurality of materials are stored in the material library, so that when a sketch is planned in the first area, a material with the configuration parameters set or an existing material meeting an intention can be selected into the first area, and a sketch scheme related to the first area is generated based on the building materials arranged in the first area.
One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments can be implemented by hardware associated with a computer program that can be stored in a computer-readable storage medium, and when executed, can include the processes of the above method embodiments. And the aforementioned storage medium includes: various media that can store computer program codes, such as a read-only memory ROM or a random access memory RAM, a magnetic disk, or an optical disk.
Claims (17)
1. A method for generating a sketch by intelligent planning is characterized by comprising the following steps:
determining a first area occupied by a building sketch, wherein the first area is used for arranging building materials;
generating a first record for the building sketch based on the building materials arranged in the first area, the building materials arranged in the first area being from a material library;
storing the first record into a record library, wherein the storage mode comprises integral storage and divided storage aiming at the first record;
providing the first record to a user device, wherein the first record is used for displaying the floor sketch or used for updating the floor sketch by a user;
generating a second record aiming at the building sketch according to the updating of the building sketch corresponding to the first record, wherein the updating of the building sketch corresponding to the first record comprises the updating of the first area and/or the updating of the building materials arranged in the first area;
storing the second record in the record repository.
2. The method of claim 1, further comprising:
obtaining a first building material according to building configuration parameters input by a user;
storing the first building material into the material library.
3. The method of claim 2, wherein the first building material corresponds to a first material tag, the first material tag comprising at least one tag from a first tag library, the first tag library comprising the following tags: the type, orientation, area, number of layers, layer height, elevator room ratio and shape of the building material;
the method further comprises the following steps:
inputting material tags corresponding to the first building material into a first tag prediction model, wherein the first tag prediction model comprises a plurality of tag sets, each tag set comprises at least two tags in the first tag library, and the tags in each tag set are different from each other;
if the similarity between the first material label and a first label set in a plurality of label sets is higher than a first preset threshold value, attributing the first material label to the first label set;
and storing the first building material into a first sub-library of a material library according to a first label set to which the first material label belongs, wherein the first sub-library is used for storing the material of which the label belongs to the first label set.
4. The method according to claim 1, wherein the storage manner is an overall storage for a first record, the first record corresponds to a first record tag, the first record tag comprises at least one tag in a second tag library, and the second tag library comprises the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the method further comprises the following steps:
inputting record labels corresponding to the first records into a second label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in the second label library, and the labels in each label set are different from each other;
if the similarity between the first record label and a second label set in a plurality of label sets is higher than a first preset threshold value, attributing the first record label to the second label set;
and storing the first record into a second sub-library of the record library according to a second label set to which the first record label belongs, wherein the second sub-library is used for storing records of which the labels belong to the second label set.
5. The method of claim 1, further comprising:
dividing the first area to obtain a plurality of divided areas;
generating a plurality of third records corresponding to the plurality of partitioned areas according to the building materials distributed in the partitioned areas, wherein one third record is used for representing the building materials distributed in one partitioned area;
and respectively storing the plurality of third records into the record library.
6. The method according to claim 5, wherein the storage manner is a split storage for the first record, each of the plurality of third records corresponds to a third record tag, the third record tag includes at least one tag in a second tag library, and the second tag library includes the following tags: the type, orientation, area, number of floors, floor height, elevator hall ratio, shape, building number, building name and place of the building material;
the method further comprises the following steps:
inputting the second record label corresponding to the third record into a third label prediction model, wherein the second label prediction model comprises a plurality of label sets, each label set comprises at least two labels in a second label library, and the labels in each label set are different from each other;
if the similarity between a third record label corresponding to the third record and a third label set in the plurality of label sets is higher than a third preset threshold, attributing the third record label to the third label set;
and storing the third record into a third sub-library of a record library according to a third label set to which the third record label belongs, wherein the third sub-library is used for storing the record of which the label belongs to the third label set.
7. The method of claim 5, wherein the segmenting the first region into a plurality of sub-regions comprises:
determining a plurality of color blocks included in the first area, wherein the area type corresponding to each color block comprises at least one of a building, an outer wall, a greening layer and a lake;
and inputting the color blocks into a segmentation prediction model to obtain a plurality of segmented areas after segmentation.
8. The method of claim 7, wherein the determining the plurality of color blocks included in the first region comprises:
comparing the first area with a preset area type, wherein the preset area type comprises a preset building type, a preset outer wall type, a preset greening type and a preset lake type, the preset building type comprises any one of villas, multi-layer buildings, medium-high-rise buildings and super high-rise buildings, the preset outer wall type comprises any one of solid walls, partition walls and composite walls, the preset greening type comprises any one of gardens, parks and landscapes, and the preset lake type comprises any one of natural lakes and artificial lakes;
if the first subregion type of the first region does not belong to the preset region type, modifying the color of the color block corresponding to the first subregion type into a background color;
if the second subregion type of the first region belongs to the preset region type, modifying the color of a color block corresponding to the second subregion type into a key color, wherein if the second subregion type belongs to the preset building type, modifying the color of the color block of the preset building type into the first key color; if the second subregion type belongs to the preset outer wall type, modifying the color of the color block of the preset outer wall type into a second key color; if the second subregion type belongs to the preset greening type, modifying the color of the color block of the preset greening type into a third key color; if the second sub-area type belongs to the preset lake type, modifying the color of a color block of the preset lake type into a fourth key color;
and obtaining a plurality of color blocks in the first region according to the key colors and the background colors.
9. The method of claim 1, further comprising:
receiving a search keyword input into a search prediction model, wherein the search keyword comprises at least one of the type, the orientation, the area, the number of floors, the floor height, the elevator hall ratio, the shape, the building number, the building name and the place of a building material;
and determining a plurality of selectable materials in a plurality of materials corresponding to the search keyword according to the search prediction model, and determining a plurality of selectable materials in a plurality of records corresponding to the search keyword according to the search prediction model.
10. The method of claim 1, wherein generating a second record for the floor sketch based on the first record and the update of the floor sketch comprises:
determining a first modified region in the first region;
modifying configuration parameters of the first modification area;
generating a second record for the floor sketch based on the update of the configuration parameters for the first modified zone in the first record;
wherein the configuration parameters include one or more of: the land use type of the first modification area, one or more tags in a first tag library, one or more tags included in a second tag library; the land type of the first modification area comprises a residential area, a greening area, a lake area, a fitness area or a road area;
wherein the first tag library comprises the following tags: the type, orientation, area, number of layers, layer height, elevator room ratio and shape of the building material; the second library of tags comprises the following tags: type, orientation, area, number of floors, floor height, stairwell ratio, shape, building number, building name, location of the building material.
11. The method of claim 10, wherein generating a second record for the floor plan according to the update to the floor plan corresponding to the first record comprises:
receiving an adjustment to a coverage of the first area;
generating a second record for the floor sketch.
12. The method of claim 1, wherein determining the first area occupied by the building sketch comprises:
receiving selection indication information aiming at a fourth record in the record library, wherein the fourth record is used for representing the arrangement of the building materials in a second area; and determining a first area occupied by the building sketch, wherein the first area is the same as the second area, and the arrangement of the building materials in the first area is the same as that of the building materials in the second area.
13. The method of any one of claims 1-12, wherein said determining a first area occupied by a floor plan comprises:
receiving a first circling area on a target drawing, wherein the first circling area comprises at least two of a constructable area, an un-constructable area, a public area and a constructed area;
inputting the first circumflex area into a land prediction model to obtain the first area in the target drawing, wherein the type of the first area is a constructable area.
14. The method according to any one of claims 1-12, wherein the material library comprises M target materials, any target material in the M target materials corresponds to a projection range, the projection range comprises a sum of a floor area of the target material and an influence range outside the floor area, and the influence range is used for representing an ideal interval between the target material and surrounding materials;
the generating a first record for the floor sketch based on the building materials arranged in the first zone includes:
receiving selection operation aiming at M target materials;
obtaining N materials in a first area based on the M target materials, and distributing the N materials in the first area to obtain a first record aiming at the building sketch, wherein the types corresponding to the M materials are the same as the types corresponding to the N materials, and M and N are integers;
the area of the overlapping range of the projection range of the first target material contained in the N materials is smaller than a first threshold value, the distance between the edges of the occupation range of the first target material contained in the N materials is larger than a second threshold value, the area of the overlapping range of the projection range of the second target material contained in the N materials is smaller than a third threshold value, the distance between the edges of the occupation range of the second target material contained in the N materials is larger than a fourth threshold value, and the target materials comprise building materials and landscape materials.
15. A computing device comprising a processing unit and a communication unit, the computing device being configured to implement the method of any of claims 1-14.
16. An electronic device comprising a transceiver, a processor and a memory, the memory for storing a computer program, the processor invoking the computer program for performing the method of any one of claims 1-14.
17. A computer storage medium, in which a computer program is stored which, when executed by a processor, performs the method of any one of claims 1 to 14.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210361889.0A CN114491779B (en) | 2022-04-07 | 2022-04-07 | Method for generating sketch through intelligent planning and related equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210361889.0A CN114491779B (en) | 2022-04-07 | 2022-04-07 | Method for generating sketch through intelligent planning and related equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114491779A true CN114491779A (en) | 2022-05-13 |
CN114491779B CN114491779B (en) | 2022-08-12 |
Family
ID=81488435
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210361889.0A Active CN114491779B (en) | 2022-04-07 | 2022-04-07 | Method for generating sketch through intelligent planning and related equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114491779B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117113514A (en) * | 2023-10-17 | 2023-11-24 | 中天昊建设管理集团股份有限公司 | Building design layout optimizing system based on BIM technology |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007089105A1 (en) * | 2006-02-01 | 2007-08-09 | Nhn Corporation | Method and system for providing estate plane figure service |
CN107480828A (en) * | 2017-08-24 | 2017-12-15 | 湖南图龙信息技术有限公司 | The method and system of flow guiding are carried out based on architectural drawing optimization database |
US20200151923A1 (en) * | 2018-11-09 | 2020-05-14 | Autodesk, Inc. | Automated parametrization of floor-plan sketches for multi-objective building optimization tasks |
CN111177840A (en) * | 2019-12-31 | 2020-05-19 | 广东博智林机器人有限公司 | Updating method and device for building information model, storage medium and processor |
CN112163252A (en) * | 2020-08-31 | 2021-01-01 | 重庆宝图科技发展有限公司 | Method and system for landing real estate sketch |
CN112800516A (en) * | 2021-01-21 | 2021-05-14 | 深圳市优博建筑设计咨询有限公司 | Building design system with real-scene three-dimensional space model |
CN113158312A (en) * | 2021-04-26 | 2021-07-23 | 深圳小库科技有限公司 | Construction plan generation method and device for construction land, storage medium and processor |
CN113327324A (en) * | 2021-06-25 | 2021-08-31 | 广东博智林机器人有限公司 | Method and device for constructing three-dimensional building model, computer equipment and storage medium |
CN114021222A (en) * | 2021-09-30 | 2022-02-08 | 深圳先进技术研究院 | Building modeling method, electronic device, and computer storage medium |
-
2022
- 2022-04-07 CN CN202210361889.0A patent/CN114491779B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007089105A1 (en) * | 2006-02-01 | 2007-08-09 | Nhn Corporation | Method and system for providing estate plane figure service |
CN107480828A (en) * | 2017-08-24 | 2017-12-15 | 湖南图龙信息技术有限公司 | The method and system of flow guiding are carried out based on architectural drawing optimization database |
US20200151923A1 (en) * | 2018-11-09 | 2020-05-14 | Autodesk, Inc. | Automated parametrization of floor-plan sketches for multi-objective building optimization tasks |
CN111177840A (en) * | 2019-12-31 | 2020-05-19 | 广东博智林机器人有限公司 | Updating method and device for building information model, storage medium and processor |
CN112163252A (en) * | 2020-08-31 | 2021-01-01 | 重庆宝图科技发展有限公司 | Method and system for landing real estate sketch |
CN112800516A (en) * | 2021-01-21 | 2021-05-14 | 深圳市优博建筑设计咨询有限公司 | Building design system with real-scene three-dimensional space model |
CN113158312A (en) * | 2021-04-26 | 2021-07-23 | 深圳小库科技有限公司 | Construction plan generation method and device for construction land, storage medium and processor |
CN113327324A (en) * | 2021-06-25 | 2021-08-31 | 广东博智林机器人有限公司 | Method and device for constructing three-dimensional building model, computer equipment and storage medium |
CN114021222A (en) * | 2021-09-30 | 2022-02-08 | 深圳先进技术研究院 | Building modeling method, electronic device, and computer storage medium |
Non-Patent Citations (6)
Title |
---|
刘兼唐等: "基于CATIA三维技术的数字模型设计――以校园规划单体建筑的设计为例", 《电子测试》 * |
吕帅等: "基于快速反馈的建筑方案数字设计方法研究", 《建筑学报》 * |
李海海: "浅析Sketchup草图大师在建筑设计课程中的辅助作用", 《大众文艺》 * |
梁亮 李静: "SketchUp软件在景观...念性设计表现中的优势及应用", 《现代农业科技》 * |
王宇翔: "草图大师SketchUp在建筑设计中的应用探讨", 《福建建筑》 * |
马亮: "Google SketchUp与Google Earth在城市设计中的应用研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117113514A (en) * | 2023-10-17 | 2023-11-24 | 中天昊建设管理集团股份有限公司 | Building design layout optimizing system based on BIM technology |
CN117113514B (en) * | 2023-10-17 | 2024-01-09 | 中天昊建设管理集团股份有限公司 | Building design layout optimizing system based on BIM technology |
Also Published As
Publication number | Publication date |
---|---|
CN114491779B (en) | 2022-08-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108499103B (en) | Scene element display method and device | |
McGarigal | FRAGSTATS help | |
US20180225539A1 (en) | Systems and methods for extracting information about objects from scene information | |
CN111737800B (en) | Primitive selection method and device and electronic equipment | |
US5727138A (en) | Method of and apparatus for generating three-dimensional model | |
CN1755617B (en) | Entity domains | |
CN109614238A (en) | A kind of recongnition of objects method, apparatus, system and readable storage medium storing program for executing | |
CN112784002A (en) | Virtual scene generation method, device, equipment and storage medium | |
WO2022159710A1 (en) | Systems and methods for facilitating parcel combination | |
CN114491779B (en) | Method for generating sketch through intelligent planning and related equipment | |
CN106709503A (en) | Large spatial data clustering algorithm K-DBSCAN based on density | |
CN111744199A (en) | Image processing method and device, computer readable storage medium and electronic device | |
CN114943456A (en) | Resource scheduling method and device, electronic equipment and storage medium | |
US20160085831A1 (en) | Method and apparatus for map classification and restructuring | |
CN109544423A (en) | Assets management method, device and computer readable storage medium | |
US20130231897A1 (en) | Systems and methods for efficient analysis of topographical models | |
WO1995004962A1 (en) | Object-oriented graphic picking system | |
CN113096251A (en) | Model processing method, device and equipment based on CIM and storage medium | |
Taghavi et al. | Visualization of multi-objective design space exploration for embedded systems | |
CN113297652A (en) | Construction drawing generation method, device and equipment | |
CN114491778B (en) | Parking space arrangement generation method, device, equipment and medium based on human-computer interaction | |
US20210150087A1 (en) | Methods, systems, and media for data visualization and navigation of multiple simulation results in urban design | |
CN114943407A (en) | Area planning method, device, equipment, readable storage medium and program product | |
KR102236240B1 (en) | Device for converting terrain shape files | |
Oscar et al. | Generative design in civil construction: a case study in Brazil |
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 |