Disclosure of Invention
The present disclosure has been made in order to solve the above technical problems. The embodiment of the disclosure provides an automatic indoor article placement processing method and device, electronic equipment and storage medium.
According to an aspect of the embodiments of the present disclosure, there is provided an automatic indoor article placement processing method, including: acquiring house type structure data corresponding to a target room, first article attribute information of articles placed in the target room and second article attribute information of articles to be placed; acquiring at least one candidate placement information corresponding to the object to be placed by using a preset object position screening rule according to the house type structure data, the first object attribute information and the second object attribute information; acquiring the placement probability corresponding to the candidate placement information by using a neural network model, and acquiring at least one piece of recommended placement information corresponding to the object to be placed based on the placement probability; and generating an article placement scheme corresponding to the target room based on the recommended placement information and the house type structural data.
Optionally, the number of the articles to be placed is a plurality, and the method further comprises: setting the target room as an empty room state, sequentially determining a plurality of candidate placement information corresponding to each article to be placed, and sequentially acquiring the recommended placement information corresponding to each article to be placed; and setting the articles to be placed, for which the candidate placement information is determined, as the articles placed in the target room.
Optionally, the acquiring the recommended placement information corresponding to the to-be-placed object includes: respectively acquiring a plurality of placement probabilities corresponding to the plurality of candidate placement information by using the neural network model; and sequencing the plurality of placement probabilities from large to small, acquiring one or more placement probabilities positioned at the sequencing head, and taking one or more candidate placement information corresponding to the one or more placement probabilities as the recommended placement information.
Optionally, the generating the item placement scheme corresponding to the target room based on the recommended placement information and the house type structural data includes: acquiring all recommended placement information corresponding to all articles to be placed, and generating a plurality of article placement schemes according to all recommended placement information, the association relation among all recommended placement information and the house type structural data.
Optionally, the first item attribute information and the second item attribute information include: one or more of article category, article style, article size, article placement attribute; the already placed articles and the articles to be placed comprise: one or more of furniture, electrical appliances, and decorations; the house type structure data comprises: one or more of wall surface distribution data, door and window distribution data, area data and layer height data.
Optionally, after the article placement scheme is generated, optimizing the placement position and the placement azimuth of the articles to be placed in the article placement scheme based on a preset article placement strategy and according to the house type structure data; wherein, the article placement strategy comprises: one or more of a wall-sticking strategy, a floor-sticking strategy, a void-retaining strategy.
Optionally, based on a preset scheme screening rule, screening the optimized item placement scheme.
Optionally, the obtaining, according to the house type structural data, the first article attribute information and the second article attribute information, at least one candidate placement information corresponding to the article to be placed using a preset article position screening rule includes: calculating a mask map corresponding to the target room according to the house type structure data, the first article attribute information and the second article attribute information; determining the plurality of candidate placement information in the mask map by using the article position screening rule according to the first article attribute information and the second article attribute information; wherein, the article position screening rule includes: one or more of placing overlap prohibition, wall penetration prohibition, and road blocking prohibition rules.
Optionally, the neural network model includes: pre-trained graph neural network GNN model; the candidate placement information includes: a first placement position and orientation; the recommended placement information includes: a second placement position and orientation.
According to another aspect of the embodiments of the present disclosure, there is provided an automatic indoor article placement processing device, including: the information acquisition module is used for acquiring house type structure data corresponding to a target room, first article attribute information of articles placed in the target room and second article attribute information of articles to be placed; the candidate placement acquisition module is used for acquiring at least one candidate placement information corresponding to the to-be-placed object by using a preset object position screening rule according to the house type structural data, the first object attribute information and the second object attribute information; the recommendation placing and acquiring module is used for acquiring placing probability corresponding to the candidate placing information by utilizing a neural network model and acquiring at least one recommendation placing information corresponding to the article to be placed based on the placing probability; and the placement scheme generating module is used for generating an article placement scheme corresponding to the target room based on the recommended placement information and the house type structure data.
Optionally, the number of the articles to be placed is multiple, wherein the candidate placement acquisition module is used for setting the target room to be in a null room state, and sequentially determining multiple candidate placement information corresponding to each article to be placed; the recommending and placing acquisition module is used for sequentially acquiring the recommending and placing information corresponding to each article to be placed; the candidate placement acquisition module sets the articles to be placed, for which the candidate placement information is determined, as the articles placed in the target room.
Optionally, the recommendation placement acquisition module is specifically configured to acquire a plurality of placement probabilities corresponding to the plurality of candidate placement information by using the neural network model; and sequencing the plurality of placement probabilities from large to small, acquiring one or more placement probabilities positioned at the sequencing head, and taking one or more candidate placement information corresponding to the one or more placement probabilities as the recommended placement information.
Optionally, the placement scheme generating module is configured to obtain all recommended placement information corresponding to all articles to be placed, and generate a plurality of article placement schemes according to the all recommended placement information, the association relationship among the all recommended placement information, and the household structural data.
Optionally, the first item attribute information and the second item attribute information include: one or more of article category, article style, article size, article placement attribute; the already placed articles and the articles to be placed comprise: one or more of furniture, electrical appliances, and decorations; the house type structure data comprises: one or more of wall surface distribution data, door and window distribution data, area data and layer height data.
Optionally, the placement scheme optimizing module is configured to optimize, after the article placement scheme is generated, a placement position and a placement azimuth of the article to be placed in the article placement scheme based on a preset article placement strategy and according to the house type structural data; wherein, the article placement strategy comprises: one or more of a wall-sticking strategy, a floor-sticking strategy, a void-retaining strategy.
Optionally, the placement scheme screening module is configured to perform screening processing on the optimized article placement scheme based on a preset scheme screening rule.
Optionally, the candidate placement acquisition module is specifically configured to calculate a mask map corresponding to the target room according to the house type structure data, the first article attribute information and the second article attribute information; determining the plurality of candidate placement information in the mask map by using the article position screening rule according to the first article attribute information and the second article attribute information; wherein, the article position screening rule includes: one or more of placing overlap prohibition, wall penetration prohibition, and road blocking prohibition rules.
Optionally, the neural network model includes: pre-trained graph neural network GNN model; the candidate placement information includes: a first placement position and orientation; the recommended placement information includes: a second placement position and orientation.
According to yet another aspect of the disclosed embodiments, there is provided a computer-readable storage medium storing a computer program for executing the above-described method.
According to still another aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; the processor is used for executing the method.
Based on the method and the device for automatically placing and processing the indoor articles, the electronic equipment and the storage medium provided by the embodiment of the disclosure, the article placing scheme corresponding to the target room can be intelligently generated by considering the position constraint relation among the placed articles, the rules of forbidden placement of the articles and the like, and the rationality of the article placing scheme can be ensured; the method saves designer resources and design flow time, provides reasonable reference suggestions for article placement, can simplify the decoration design link flow and can provide convenience for user decoration decision.
The technical scheme of the present disclosure is described in further detail below through the accompanying drawings and examples.
Detailed Description
Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present disclosure and not all of the embodiments of the present disclosure, and that the present disclosure is not limited by the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.
It will be appreciated by those of skill in the art that the terms "first," "second," etc. in embodiments of the present disclosure are used merely to distinguish between different steps, devices or modules, etc., and do not represent any particular technical meaning nor necessarily logical order between them.
It should also be understood that in embodiments of the present disclosure, "plurality" may refer to two or more, and "at least one" may refer to one, two or more.
It should also be appreciated that any component, data, or structure referred to in the presently disclosed embodiments may be generally understood as one or more without explicit limitation or the contrary in the context.
In addition, the term "and/or" in this disclosure is merely an association relationship describing an association object, and indicates that three relationships may exist, such as a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the front and rear association objects are an or relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and that the same or similar features may be referred to each other, and for brevity, will not be described in detail.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Embodiments of the present disclosure are applicable to electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with the terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above systems, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computing system storage media including memory storage devices.
Summary of the application
In the process of implementing the disclosure, the inventor finds that, although the existing method for generating the object placement scheme can utilize the neural network model to predict the placement position and orientation of objects in a room, the positional constraint relationship between the placed objects, the rule of prohibiting the placement of the objects (for example, the dressing table is not generally placed in the direction of the bed tail, the sink is closest to the toilet door, etc.), and the like are not considered, which easily causes abnormal situations such as overlapping of the objects in the generated placement scheme.
According to the indoor article automatic placement processing method, candidate placement information corresponding to articles to be placed is obtained by using preset article position screening rules according to household structure data, first article attribute information of the articles already placed in a target room and second article attribute information of the articles to be placed; the neural network model is utilized to acquire the placement probability corresponding to the candidate placement information, the recommended placement information of the articles to be placed is acquired based on the placement probability, the article placement scheme is generated based on the recommended placement information and the household structure data, the position constraint relation among the placed articles and rules such as the forbidden placement of the articles can be considered, and the article placement scheme corresponding to the target household can be intelligently generated.
Exemplary method
Fig. 1 is a flowchart of an embodiment of a method for automatically placing and processing indoor articles according to the present disclosure, where the method shown in fig. 1 includes the steps of: S101-S104. The steps are described separately below.
S101, acquiring house type structure data corresponding to a target room, first article attribute information of articles placed in the target room and second article attribute information of articles to be placed.
The target room can be a bedroom, a living room, a bathroom and the like; the house type graph can be generated by CAD modeling tools and the like, and can be a vector graph and the like; the house type map has a plurality of house type elements, the house type structure data corresponding to the house type map is obtained, and the house type structure data comprises: wall distribution data, bearing wall distribution data, door and window distribution data, area data, floor height data, position coordinate data and the like of a house.
The already placed articles and the articles to be placed include: furniture, electrical appliances, decorations, and the like; the first article attribute information and the second article attribute information include: item category, item style, item size, item placement properties, etc., the item placement properties include: the placement location, orientation, whether the article must be against a wall, whether the article has a front door area, whether the article can enter a front door area of other articles, etc.
S102, acquiring at least one candidate placement information corresponding to the object to be placed by using a preset object position screening rule according to the house type structure data, the first object attribute information and the second object attribute information. The item location screening rules may include a variety of rules, such as, for example, inhibit placement overlap, inhibit wall penetration, inhibit road blocking rules, and the like.
S103, acquiring the placement probability corresponding to the candidate placement information by using the neural network model, and acquiring at least one piece of recommended placement information corresponding to the object to be placed based on the placement probability.
A training sample set can be generated in advance according to house type structure data, first article attribute information, second article attribute information, placement positions and the like, and training of the neural network is carried out according to the training sample, so that a trained neural network model is obtained; and acquiring the placement probability corresponding to the candidate placement information of the articles to be placed by using the trained neural network model.
S104, generating an article placement scheme corresponding to the target room based on the recommended placement information and the house type structural data.
The number of item placement schemes may be one or more; the object placement scheme comprises a placement chart and the like for showing the placement positions, orientations and the like of objects such as tables, beds and electric appliances in a target room.
In one embodiment, the number of articles to be placed is multiple, a target room is set to be in an empty room state, multiple candidate placement information corresponding to each article to be placed is sequentially determined, and recommended placement information corresponding to each article to be placed is sequentially obtained; when the candidate placement information is determined, the articles to be placed, for which the candidate placement information is determined, are set as articles which are placed in a target room. The candidate placement information comprises a first placement position, an orientation and the like of the article; the recommended placement information includes a second placement location and orientation of the item, and so on.
FIG. 2 is a flowchart of generating candidate placement information in an embodiment of an automatic indoor item placement processing method of the present disclosure, where the method shown in FIG. 2 includes the steps of: S201-S202. The steps are described separately below.
S201, calculating a mask diagram corresponding to the target room according to the house type structure data, the first article attribute information and the second article attribute information.
The mask map and the house type map of the target room have the same pixels and the same size, the house type map has articles to be placed and articles to be placed which need to calculate candidate placement information at the time, the value of each pixel point in the mask map is 0 or 255, and if the value of a certain pixel point is 0, the position where the articles to be placed can be placed is indicated.
S202, determining a plurality of candidate placement information in the mask map by using the item position screening rule according to the first item attribute information and the second item attribute information.
Calculating a plurality of discrete candidate placement information according to the mask map, the first article attribute information and the second article attribute information, wherein each candidate placement information comprises a first placement position and an orientation, and the orientation can be up, down, left and right; candidate placement information is used as a potential option of the placement position of the object to be placed; the article location screening rules include: the object position screening rule can be used for checking candidate placement information, and if the candidate placement information can cause abnormal results such as wall crossing, object overlapping and road blocking, the candidate placement information is deleted.
Fig. 3 is a flowchart of acquiring recommended placement information in an embodiment of the indoor article automatic placement processing method of the present disclosure, where the method shown in fig. 3 includes the steps of: S301-S302. The steps are described separately below.
S301, respectively acquiring a plurality of placement probabilities corresponding to a plurality of candidate placement information by using a neural network model.
The neural network model can be various, such as a graph neural network GNN (Graphical Neural Network) model and the like; the GNN network is based on the existing fixed point Query algorithm (Position Query), and the GNN model is trained in advance to obtain a trained GNN model. The GNN model outputs the placement probability corresponding to the candidate placement information of the articles to be placed for a given house type diagram and the articles already placed, wherein the placement probability is the probability that the articles corresponding to the candidate placement information are the articles to be placed.
S302, sorting the plurality of placement probabilities from large to small, obtaining one or more placement probabilities positioned at the sorting head, and taking one or more candidate placement information corresponding to the one or more placement probabilities as recommended placement information.
K values can be set, K is 1,2,3 and the like, and K candidate placement information corresponding to the K maximum placement probabilities is selected as K recommended placement information.
FIG. 4 is a flowchart of generating an item placement plan in one embodiment of the method for automatically placing and processing indoor items of the present disclosure, the method shown in FIG. 4 including the steps of: S401-S403. The steps are described separately below.
S401, acquiring all recommended placement information corresponding to all articles to be placed, and generating a plurality of article placement schemes according to all recommended placement information, the association relation among all recommended placement information and house type structure data.
When a plurality of candidate placement information corresponding to each article to be placed is determined, the article to be placed with the candidate placement information determined is set as an article placed in a target room, the article to be placed can have a plurality of recommended placement information, a plurality of recommended placement information of the next article to be placed can be obtained based on each recommended placement information, the recommended placement information and the plurality of recommended placement information of the next article to be placed have an association relationship, and similarly, the association relationship between all the recommended placement information can be determined.
S402, after the article placement scheme is generated, the placement positions and placement orientations of the articles to be placed in the article placement scheme are optimized based on a preset article placement strategy and according to house type structural data.
The article placement strategy comprises the following steps: wall-sticking strategies, ground-sticking strategies, void-retaining strategies, etc. The wall-attaching strategy can be a wall-attaching algorithm and the like, and the ground-attaching strategy can be a ground-attaching algorithm and the like; the void retention policy may be a retention policy for voids between articles, and the retention policy may be varied, for example, if two articles are adjacent but leave an insufficient gap therebetween to allow the articles to be brought into close proximity.
S403, screening the optimized object placement scheme based on a preset scheme screening rule.
The scheme screening rules can be preset forced rules, and if the object placement scheme accords with the scheme screening rules, the scheme is deleted; all the object placement schemes can be evaluated manually or automatically, and the object placement schemes with high evaluation scores are recommended preferentially.
In one embodiment, the house type structural data corresponding to the target room includes structural data of a door, a window, a wall, and the like, and the list list_furniture= [ "bed", "wardrobe", "dressing table", "table" ] is generated based on the items to be put. As shown in fig. 5A to 5E, the target room is set to be in a null room state, a plurality of candidate placement information corresponding to each article to be placed is determined in sequence, recommended placement information corresponding to each article to be placed is acquired in sequence, and an article placement scheme is generated.
And taking one article to be placed out of list_funnitures, and calculating a mask diagram corresponding to the target room according to the house type structural data, the first article attribute information and the second article attribute information, wherein the size of the mask diagram is consistent with the house type size of the target room, and the value of each point in the mask is 0 or 255. According to the first article attribute information and the second article attribute information, a plurality of candidate placement information is determined in the mask diagram by using an article position screening rule, and the candidate placement information which can cause abnormal results such as crossing a wall, overlapping the placed article, blocking a road and the like is deleted.
Respectively acquiring a plurality of placement probabilities corresponding to a plurality of candidate placement information by utilizing a pre-trained graph neural network GNN model; and ordering the plurality of placement probabilities from large to small, acquiring two placement probabilities positioned at the ordering head, taking two candidate placement information corresponding to the two placement probabilities as recommended placement information, and generating a list selected_Proposals.
And sequentially and circularly executing the method, acquiring all the recommended placement information corresponding to all the articles to be placed in the llist_furnitures, and generating a plurality of article placement schemes according to all the recommended placement information, the association relation among all the recommended placement information and the house type structure data. Optimizing the placement position and placement direction of the articles to be placed in each article placement scheme, and carrying out screening treatment.
Exemplary apparatus
In one embodiment, as shown in fig. 6A, the present disclosure provides an automatic indoor article placement processing device, including: an information acquisition module 601, a candidate placement acquisition module 602, a recommended placement acquisition module 603, and a placement scheme generation module 604.
The information acquisition module 601 acquires house type structure data corresponding to a target room, first article attribute information of articles already placed in the target room, and second article attribute information of articles to be placed. The candidate placement acquisition module 602 acquires at least one candidate placement information corresponding to an object to be placed using a preset object position screening rule according to the house type structure data, the first object attribute information and the second object attribute information.
The recommended placement acquisition module 603 acquires placement probabilities corresponding to candidate placement information using a neural network model, and acquires at least one recommended placement information corresponding to an item to be placed based on the placement probabilities. The placement scheme generation module 604 generates an item placement scheme corresponding to the target room based on the recommended placement information and the house type structure data. The neural network model includes: pre-trained graph neural network GNN model; the candidate placement information includes: a first placement position and orientation; the recommended placement information includes: a second placement position and orientation.
In one embodiment, the first item attribute information and the second item attribute information include: article category, article style, article size, article placement attribute; the already placed articles and the articles to be placed include: one or more of furniture, electrical appliances, and decorations; the house type structure data includes: one or more of wall surface distribution data, door and window distribution data, area data and layer height data.
The candidate placement acquisition module 602 calculates a mask map corresponding to the target room according to the house type structure data, the first item attribute information, and the second item attribute information. The candidate placement acquisition module 602 determines a plurality of candidate placement information in the mask map using the item location screening rule according to the first item attribute information and the second item attribute information; wherein, article position screening rules include: one or more of placing overlap prohibition, wall penetration prohibition, and road blocking prohibition rules.
The number of the articles to be placed is multiple, the candidate placement acquisition module 602 sets the target room to be in a null room state, and sequentially determines multiple candidate placement information corresponding to each article to be placed. The recommendation placing and acquiring module 603 acquires recommendation placing information corresponding to each article to be placed in sequence; wherein, the candidate placement acquisition module 602 sets the to-be-placed items for which the candidate placement information has been determined as the items that have been placed in the target room.
The recommended placement acquisition module 603 acquires a plurality of placement probabilities corresponding to the plurality of candidate placement information respectively by using a neural network model; the recommended placement acquisition module 603 sorts the placement probabilities from large to small, acquires one or more placement probabilities located in the sorting header, and uses one or more candidate placement information corresponding to the one or more placement probabilities as recommended placement information.
The placement scheme generation module 604 obtains all recommended placement information corresponding to all articles to be placed, and generates a plurality of article placement schemes according to all recommended placement information, association relations among all recommended placement information, and house type structure data.
In one embodiment, as in fig. 6B, the indoor article automatic placement processing device includes: a placement scheme optimization module 605 and a placement scheme screening module 606. After generating the article placement scheme, the placement scheme optimizing module 605 optimizes the placement position and placement orientation of the articles to be placed in the article placement scheme based on a preset article placement strategy and according to the house type structure data; wherein, article placement strategy includes: one or more of a wall-sticking strategy, a floor-sticking strategy, a void-retaining strategy. The placement plan screening module 606 performs a screening process on the optimized item placement plan based on preset plan screening rules.
Fig. 7 is a block diagram of one embodiment of an electronic device of the present disclosure, as shown in fig. 7, the electronic device 71 including one or more processors 711 and memory 712.
The processor 711 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 71 to perform desired functions.
Memory 712 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or nonvolatile memory. Volatile memory, for example, may include: random Access Memory (RAM) and/or cache, etc. Non-volatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on a computer readable storage medium and the processor 711 may execute the program instructions to implement the indoor article automatic placement handling method and/or other desired functions of the various embodiments of the present disclosure above. Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device 71 may further include: input devices 713, output devices 714, and the like, interconnected by a bus system and/or other forms of connection mechanisms (not shown). In addition, the input device 713 may also include, for example, a keyboard, mouse, and the like. The output device 714 can output various information to the outside. The output device 714 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 71 relevant to the present disclosure are shown in fig. 7 for simplicity, components such as buses, input/output interfaces, and the like being omitted. In addition, the electronic device 71 may include any other suitable components depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in an indoor item automatic placement processing method according to various embodiments of the present disclosure described in the "exemplary methods" section of the present description.
The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform the steps in the indoor article automatic placement processing method according to various embodiments of the present disclosure described in the above "exemplary method" section of the present disclosure.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.
According to the indoor article automatic placement processing method, the device, the electronic equipment and the storage medium, candidate placement information corresponding to the articles to be placed is obtained by using a preset article position screening rule according to the house type structure data, the first article attribute information of the articles already placed in the target room and the second article attribute information of the articles to be placed; acquiring a placement probability corresponding to the candidate placement information by utilizing a neural network model, acquiring recommended placement information of the articles to be placed based on the placement probability, and generating an article placement scheme based on the recommended placement information and the house type structure data; the method has the advantages that the object placement scheme corresponding to the target room can be intelligently generated by considering the position constraint relation among the objects placed, the rules of forbidden placement of the objects and the like, and the rationality of the object placement scheme can be ensured; the method has the advantages of saving designer resources and design flow time, providing reasonable reference suggestions for article placement, helping users to make decoration decisions, saving designer resources and design flow time, simplifying decoration design link flow, providing convenience for user decoration decisions and reducing decoration cost.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, so that the same or similar parts between the embodiments are mutually referred to. For system embodiments, the description is relatively simple as it essentially corresponds to method embodiments, and reference should be made to the description of method embodiments for relevant points.
The block diagrams of the devices, apparatuses, devices, systems referred to in this disclosure are merely illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatus, devices, and systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the apparatus, devices and methods of the present disclosure, components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered equivalent to the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects, and the like, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.