CN115115846A

CN115115846A - Automatic generation method and device of house type layout, computer equipment and storage medium

Info

Publication number: CN115115846A
Application number: CN202210897679.3A
Authority: CN
Inventors: 胡元超
Original assignee: Hangzhou Qunhe Information Technology Co Ltd
Current assignee: Hangzhou Qunhe Information Technology Co Ltd
Priority date: 2022-07-28
Filing date: 2022-07-28
Publication date: 2022-09-27

Abstract

The application discloses a method, a device, computer equipment and a storage medium for automatically generating a house type layout, which relate to the technical field of computer application, wherein the method comprises the steps of obtaining image characteristics of a house type, carrying out autoregressive processing on the image characteristics to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise structural layout relations representing the house type, and screening out target layout results from the plurality of layout results, on one hand, because the autoregressive processing can generate a plurality of different prediction results for a fixed input, the technical scheme adopts the characteristics and combines a way of combining house design and deep learning to ensure that the generated layout results are more diversified and strong in robustness, more house type layout references are provided for a user, on the other hand, the output layout results are further screened, so that the final output target layout results are closer to the demand tendency of the user on the house type layout, the success rate and the efficiency of the use of the target layout result are improved.

Description

Automatic generation method and device of house type layout, computer equipment and storage medium

Technical Field

The present application relates to the field of computer application technologies, and in particular, to an automatic generation method and apparatus for a house layout, a computer device, and a storage medium.

Background

In recent years, with the continuous integration of home design and computer technology, the intelligent design of indoor home has received wide attention from people. The furniture design layout is generally based on a fixed design template, so that the furniture layout result provided for a user is very limited and is single.

Disclosure of Invention

The embodiment of the application aims to provide an automatic generation method of a house type layout so as to solve the problem of single furniture layout result.

In order to solve the foregoing technical problem, an embodiment of the present application provides an automatic generation method for a house type layout, including the following steps:

acquiring the image characteristics of the house type;

performing autoregressive processing on the image characteristics to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise a structural layout relation representing the house type;

and screening out a target layout result from the plurality of layout results.

In some embodiments, the image features are subjected to an autoregressive process to obtain a plurality of layout results corresponding to the house type, including:

acquiring a plurality of preset initial furniture sequences, wherein the number of the initial furniture sequences is the same as that of the layout results;

inputting the image characteristics and each initial furniture sequence into a preset autoregressive model for prediction so as to output each predicted target furniture sequence, wherein each value in the target furniture sequence represents furniture attribute information;

and outputting a layout result corresponding to each house type according to each target furniture sequence and the image characteristics.

In some embodiments, obtaining image features of the house type includes:

acquiring a house type image;

and extracting the image characteristics of the house type image through a preset residual error network.

In some embodiments, after outputting each predicted target furniture sequence, the method further comprises:

and obtaining the self-defined furniture attribute information, and updating the self-defined furniture attribute information into a target sequence.

In some embodiments, the target layout result is screened from a plurality of layout results, including:

obtaining the scoring value of each layout result;

filtering the scoring values according to a preset scoring threshold value;

and taking the layout result corresponding to the grade value obtained by filtering as a target layout result.

In some embodiments, obtaining a score value for each layout result comprises:

obtaining a plurality of initial scoring values of each layout result;

and summing the plurality of initial scoring values of each layout result to obtain the scoring value of each layout result.

In order to solve the above technical problem, an embodiment of the present application further provides an apparatus for automatically generating a house layout, including:

the acquisition module is used for acquiring the image characteristics of the house type;

the autoregressive processing module is used for carrying out autoregressive processing on the image characteristics to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise a structural layout relation representing the house type;

and the screening module is used for screening the target layout result from the multiple layout results.

In some embodiments, the autoregressive processing module comprises:

the system comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring a plurality of preset initial furniture sequences, and the number of the initial furniture sequences is the same as that of the layout results;

the regression unit is used for inputting the image characteristics and each initial furniture sequence into a preset autoregressive model for prediction so as to output each predicted target furniture sequence, wherein each value in the target furniture sequence represents furniture attribute information;

and the layout unit is used for outputting a layout result corresponding to each house type according to each target furniture sequence and the image characteristics.

In some embodiments, the obtaining module comprises:

an image acquisition unit for acquiring a house type image;

and the extraction unit is used for extracting the image characteristics of the house type image from a preset residual error network.

In some embodiments, the apparatus for automatically generating a house layout further comprises:

and the custom module is used for acquiring custom furniture attribute information and updating the custom furniture attribute information into the target sequence.

In some embodiments, the screening module comprises:

a score value obtaining unit for obtaining a score value of each layout result;

the filtering unit is used for filtering the scoring value according to a preset scoring threshold value;

and the target layout unit is used for taking the layout result corresponding to the grade value obtained by filtering as the target layout result.

In some embodiments, the score value obtaining unit includes:

the obtaining subunit is used for obtaining a plurality of initial scoring values of each layout result;

and the calculating subunit is used for summing the plurality of initial scoring values of each layout result to obtain the scoring value of each layout result.

In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the automatic generation method for a layout of a user when executing the computer program.

In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the steps of the automatic generation method for a floor plan described above.

Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:

by obtaining the image characteristics of the house type and carrying out autoregressive processing on the image characteristics to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise a structural layout relation representing the house type, and target layout results are screened from the plurality of layout results, on one hand, the autoregressive processing is a mathematical model based on a probability prediction time sequence, and has the characteristic of outputting a plurality of prediction sequences in the prediction process, namely the characteristic can generate a plurality of different prediction results for a fixed input, so the technical scheme adopts the characteristic, combines a way of combining house design and deep learning, ensures that the generated layout results are more diversified and have strong robustness, provides more house type layout references for users, and on the other hand, further screens the output layout results, and ensures that the final output target layout results are closer to the requirement trend of the users on the house type layout, the success rate and the efficiency of the use of the target layout result are improved.

Drawings

In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.

FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;

FIG. 2 is a flow diagram of one embodiment of a method for automatic generation of a layout of a dwelling provided herein;

fig. 3 is a schematic structural diagram of a depth residual error network provided in the present application;

fig. 4 is a schematic flow chart of the house type image after autoregressive processing according to the embodiment of the present application. (ii) a

FIG. 5 is a schematic diagram of yet another embodiment of a method for automatic generation of a floor plan as provided herein;

FIG. 6 is a schematic view of an automatically generated layout of a house layout provided by the present application;

FIG. 7 is a schematic structural diagram of an embodiment of an apparatus for automatically generating a layout of a house;

FIG. 8 is a schematic block diagram illustrating one embodiment of a computer device provided herein.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof in the description and claims of this application and the description of the figures above, are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between

terminal devices

101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, motion Picture Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion Picture Experts compression standard Audio Layer 4), a laptop portable computer, a desktop computer, and the like.

The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the

terminal devices

101, 102, 103.

It should be noted that, the automatic generation method of the house layout provided by the embodiment of the present application generally consists of the server/terminalTerminal equipmentThe execution, and accordingly, the automatic generation means of the layout of the house type are generally provided in the server/terminal device.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to FIG. 2, a flow diagram of one embodiment of a method for automatic generation of a layout of a dwelling of the present application is shown. The automatic generation method of the house type layout comprises the following steps:

s201: and acquiring the image characteristics of the house type.

The house type is a house type scheme in the embodiment of the application, the house type scheme includes space data of the house type, for example, the space size of the house type, the space layout of the house type, and the like, and the house type scheme may further include a house type space decoration style.

In some embodiments, obtaining image features of the house type includes:

acquiring a house type image;

Specifically, it may be that the user inputs a user-type image in the terminal device; the house type image can be obtained by inquiring from a data database in which the house type image is stored in advance according to the user information; the user may acquire the house type image uploaded by the user through a wireless network/bluetooth/4G/5G, and the acquisition mode is not limited in this application. The house type image may be a two-dimensional image or a three-dimensional image, may be an RGB image, and may also be a grayscale image, and the image type of the house type image is not limited herein.

The image feature extraction for the house type image may use Histogram of Oriented Gradient (HOG), Local Binary Pattern (LBP), or deep learning neural network algorithm, which is not limited herein.

Further, the image features are extracted by adopting a deep learning neural network algorithm, for example, the features of the house type image are extracted by adopting a deep residual error network in the embodiment of the application, the deep residual error network can extract deeper semantic information by adding a corresponding deep neural network, the accuracy of the feature extraction is improved, and the gradient disappearance problem caused by adding depth in the deep neural network is relieved because the deep residual error network uses jump connection.

Referring to fig. 3, fig. 3 is a schematic structural diagram of a deep residual error network provided in the present application. As shown in fig. 3, the depth residual network includes 5 residual blocks, each consisting of two convolutions of 3 × 3. Specifically, a 7 × 96 user type image is input into a depth residual error network, after convolution with 3 × 3 × 64, the size of a feature map obtained by convolution is reduced by half to obtain a 4 × 48 × 64 feature map, after maximum pooling of the 4 × 48 × 64 feature map is performed with 3 × 3 × 64, the size of a feature map obtained by pooling is reduced by half to obtain a 2 × 24 × 64 feature map, the 2 × 24 × 64 feature map is processed by five residual error modules to obtain a 2 × 24 × 64 feature map, and then global average pooling is performed to finally obtain the user type image feature, where the convolution depth in the embodiment of the present application is 64, and the size of the feature map is kept unchanged during residual error processing.

It should be noted that the specific dimension of the input image and the number of residual modules are hyper-parameters, and are adjusted accordingly according to actual situations.

In the embodiment of the application, the image features are feature vectors of house type, and the feature vectors x obtained by processing the house type image x through the depth residual error network can be used _vec Is represented as x _vec Resnet (x). The feature vector may include a house type, an orientation size of the house type, and furniture attribute information such as a furniture type, a number of furniture types, a size of the furniture type, a furniture placing position and orientation, for example, the house type may be a living room, a kitchen, a bathroom, etc., the furniture type may be a television cabinet, a sofa, a toilet, a bed, a hand washing table, etc., and is not limited herein.

S202: and performing autoregressive processing on the image characteristics to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise a structural layout relation representing the house type.

Wherein the autoregressive process is realized by an autoregressive model. Among them, the autoregressive model is a transform (transformation model), which is a model that uses the attention mechanism to increase the training speed of the model. The Transformer architecture has two input sequences, namely an encoder (encoder) input sequence and a decoder (decoder) input sequence, the structure of each encoder is the same but the encoders do not share the weight of the encoders, and each encoder comprises a self-attention layer (self-attention) and a fully-connected feedforward network layer (feed-forward). Each decoder also includes a self-attention layer (self-attention) and a fully-connected feed-forward network layer (feed-forward), with an attention layer between the two layers.

In the embodiment of the application, the image features are used as an input sequence of an encoder, the initial furniture sequence is used as an input sequence of a decoder, and the initial furniture sequence is obtained by cyclic prediction of an autoregressive model in advance, so that each initial furniture sequence can output a target furniture sequence through the processing of the autoregressive model, and the number of the set initial furniture sequences is equal to that of the target furniture sequences. Each value in the target furniture sequence represents a value for predicting each furniture, for example, each value can be used for representing each furniture category, furniture size and the like, namely, the output target furniture sequence determines the structural layout relationship of the house type. The structural layout relationship of the house type reflects the size of each furniture category and the position relationship in the house type. And generating a layout result of the house type according to the predicted target furniture sequence and the image characteristics, wherein the layout result comprises images of the layout of each furniture category in the house type, and an effect graph is shown in fig. 6.

Specifically, image feature x _vec And an initial furniture sequence v ^seq Inputting the data into an autoregressive model (Transformer), and obtaining a probability distribution matrix of the next value in the initial furniture sequence, wherein the probability distribution matrix is expressed as Transformer (x) _vec ，v ^seq ) Sampling (sample) the probability distribution matrix of the next value, and expressing the sampled value as v _n Obtaining v _n May be denoted as v _n ＝sample(Transformer(x _vec ，v ^seq )). The Sampling operation may be to take the value with the highest probability in the probability distribution matrix, or to obtain the optimal value through kernel Sampling (nuclear Sampling). Further, v is _n Is added toAt the end of the initial furniture sequence, to update the initial furniture sequence and continue the updated initial furniture sequence according to v _n ＝sample(Transformer(x _vec ，v ^seq ) Get the next v _n And (4) stopping prediction until traversing and predicting each value of the whole initial furniture sequence, and outputting the target furniture sequence. The preset value of each initial furniture sequence when the autoregressive model is input may be all 0, 1, …, n-1, n, n being a positive integer, for example, the first initial furniture sequence ═ 0, 0, 0]The second initial furniture sequence ═ 1, 1, 1]…, nth initial furniture sequence ═ n, n, n]。

For example, when the auto-regression model needs to predict a first value of a first initial furniture sequence, a probability distribution of the value is obtained through auto-regression processing, a preset sampling operation is adopted, for example, a value with the highest probability in the probability distribution is taken as the value, the first value is assumed to be 1 and is added to the end of the initial furniture sequence, at this time, the updated initial furniture sequence is [1 ], ] and the updated initial furniture sequence is [1 ], ] is continuously input into the auto-regression model, then, the sampling operation is performed to obtain a second value of the initial furniture sequence, at this time, the initial furniture sequence is updated to [1 ], ] is obtained, at this time, the updated values in the entire initial furniture sequence, that is, the target furniture sequence is obtained, at this time, for example, the target furniture sequence is [1,3 ], 3, 2, 4, 5, 1, 4, 5, 7, 8], the initial sequence of furniture representing a chair of size [3, 2] in position [4, 5] and a table of size [4, 5] in position [7, 8], i.e. the first 5 values represent attribute information for a chair and the last 5 values represent attribute information for a table.

In the embodiment of the present application, each target furniture sequence may represent a layout result, that is, a layout scheme of a house type, and the probability of the target furniture sequence may be calculated as a probability of a layout in the house type. The finally output target furniture can determine the reliability of the layout result of the target furniture sequence through probability calculation, and a calculation formulaIs composed of

Wherein p is the probability of the entire target furniture sequence; a theta autoregressive model parameter; v ^seq The target furniture sequence is represented here; v. of _n Representing the nth value in the target furniture sequence. According to the formula, the probability of each value in the target sequence is multiplied to finally obtain the probability of the target furniture sequence, and the larger the probability of the target furniture sequence is, the more the output layout result conforms to the structural layout relationship of the current house type.

and acquiring the self-defined furniture attribute information, and taking the self-defined furniture attribute information as new furniture attribute information.

The furniture attribute information comprises furniture types, furniture sizes and furniture placing positions in the house type. For example, in a bathroom setting the furniture categories may include a wash station, a bathtub, a toilet, etc., may be the size of the wash station and the location of the wash station in the dwelling, etc. The user can control the furniture attribute information of the prediction sequence in the house type layout design process, so that the obtained house type layout result is closer to the requirement of the user, and the interactivity of the house type layout design is improved. For example, in the furniture layout process of the bedroom, the user can arbitrarily select the size and the orientation of the bed as new furniture attribute information, and output the position of the bed in the current house type after the bed is predicted by autoregressive.

With continuing reference to fig. 4, fig. 4 is a schematic flow chart of the house type image after the autoregressive process according to the embodiment of the present application. As shown in fig. 4, a house type image input by a user is obtained, feature extraction is performed on the house type image through a feature extraction network to obtain image features, and a prediction sequence including feature vectors is generated from the image features through an autoregressive model, so that the furniture attribute information in the feature vectors of the prediction sequence represents the layout result of each furniture type of the house type. For example, the furniture attribute information included in the prediction sequence is a two-dimensional vector in an actual scene, and the prediction sequence is a one-dimensional vector in the embodiment of the present application, so that the two-dimensional vector needs to be split, for example, the length and the width of the furniture are split into a length and a width, and the one-dimensional vector may represent the category of the furniture, the size of the furniture, the orientation of the furniture, and the like. Meanwhile, the user can adjust the prediction sequence by self-defining furniture attribute information of the feature vectors in the control prediction sequence in the terminal equipment, and a new layout result is generated.

Furthermore, behavior information of the user on the selection and adjustment of the furniture attribute information is recorded, the behavior information is further converted into a series of house type design schemes for the learning of the autoregressive model, and finally the iterative optimization of the autoregressive model is achieved.

S203: and screening out a target layout result from the plurality of layout results.

Since the number of layout results obtained by autoregressive prediction is large, not every layout result is reasonable and effective in layout relative to the structural relationship of the house type. Therefore, each layout result needs to be screened, so that the layout result with the higher rank is output as the target layout result, and the effectiveness of the layout scheme of the house type is improved.

It should be noted that, in the embodiment of the present application, the filtering may be performed according to the probability of the target furniture sequence, for example, the target furniture sequence greater than a preset probability threshold is used as the layout result, and then the target layout result is obtained through the following filtering manner.

obtaining the scoring value of each layout result;

filtering the scoring values according to a preset scoring threshold value;

In the embodiment of the present application, obtaining the score value of each layout result includes:

obtaining a plurality of initial scoring values of each layout result;

Specifically, each rule may be a function, and a corresponding score is input, and the score value output in each rule for each layout result is an initial score value. Assume that a certain layout result is layout _i At a certain rule _j Lower is scored as score _i，j ＝rule _j (layout _i ) Layout of layout _i The total of (A) is: score _i ＝∑ _j rule _j (layout _i ) That is, a plurality of initial score values are summed, and the sum is used as a score value.

Further, each layout result can be evaluated by a pre-scoring system to obtain a scoring value of each layout result. The scoring system is composed of a series of scoring rules, and each rule is preset with a corresponding score, so that whether each layout result meets each scoring rule in the scoring system or not is inquired, and the final score of each layout result is obtained by counting the scores corresponding to whether the rules are met or not.

It should be noted that, the user may adjust the scoring rule in the scoring system, for example, a certain rule is unreasonable, and may select to delete the rule.

Further, a preset scoring threshold may be set according to an actual scene, the scoring value of each layout result is compared with the scoring threshold, and the layout results smaller than the scoring threshold are filtered to obtain the layout results larger than the scoring threshold. For example, the score threshold is 90, and a layout result having a score value greater than or equal to 90 is taken as the target result.

With continued reference to fig. 5, fig. 5 is a schematic diagram of yet another embodiment of a method for automatic generation of a house layout as provided herein. The layout results of the furniture are input into a grading system in parallel, the layout scheme in the furniture layout results is graded through a plurality of different grading rules, namely corresponding scores are obtained according to whether the grading rules are met or not, the total score of each furniture layout result in all the grading rules is counted, the layout results with too low scores are filtered according to the total score of each layout result, for example, the total score is sorted according to the score, and the final furniture layout result is output.

And the layout results are screened through the scoring values, so that the output target layout results are more efficient, and the structural layout relation of the house type is more reasonable.

Further, as shown in fig. 6, fig. 6 is a scene diagram of automatic generation of the layout of the house type provided by the present application. The first diagram, as shown in fig. 6, is an input structure diagram of a house type, such as a structure diagram of a toilet, gray represents a wall, white represents a room door, and black represents a floor. The user defines the relevant parameters of the house type structure diagram, for example, the parameter definition includes newly added furniture types, furniture attribute information, and the like, or adjusts the relevant parameters, for example, the house type structure diagram positioned below the first diagram in fig. 6 has newly added boxes with different colors compared with the first diagram, for example, a bathroom is taken as a scene, the user can newly add a washbasin, a closestool, a shower room, and the like in the house type structure diagram, and simultaneously, the user can also adjust the values of the width and the depth of the shower room, and further screens the layout results obtained by the autoregressive processing to obtain the final layout results, for example, the right two house type structure diagrams in fig. 6 not only include the furniture types input by the user, but also show the placing position relationship of each furniture type in the current house type.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

With further reference to fig. 7, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an apparatus for automatically generating a layout of a house, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 7, fig. 7 is a schematic structural diagram of an embodiment of an automatic generation apparatus for a house layout provided in the present application, wherein the automatic generation apparatus for a house layout further includes: an obtaining module 701, an autoregressive processing module 702 and a screening module 703. Wherein:

an obtaining module 701, configured to obtain an image feature of a house type;

an auto-regression processing module 702, configured to perform auto-regression processing on the image features to obtain multiple layout results corresponding to the house type, where the layout results include a structural layout relationship representing the house type;

the screening module 703 is configured to screen out a target layout result from the multiple layout results.

In some embodiments, the autoregressive processing module 702 includes:

In some embodiments, the obtaining module 701 includes:

an image acquisition unit for acquiring a house type image;

In some embodiments, the screening module 703 comprises:

a score value obtaining unit for obtaining a score value of each layout result;

In some embodiments, the score value obtaining unit includes:

With regard to the automatic generation apparatus of the layout of the house type in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

In order to solve the technical problem, the embodiment of the application further provides computer equipment. Referring to fig. 8, fig. 8 is a block diagram of a basic structure of a computer device according to the present embodiment.

The computer device 8 comprises a memory 81, a processor 82, a network interface 83 communicatively connected to each other via a system bus. It is noted that only computer device 8 having components 81-83 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.

The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.

The memory 81 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., an SD or D layout auto generation memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 81 may be an internal storage unit of the computer device 8, such as a hard disk or a memory of the computer device 8. In other embodiments, the memory 81 may also be an external storage device of the computer device 8, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 8. Of course, the memory 81 may also comprise both an internal storage unit of the computer device 8 and an external storage device thereof. In this embodiment, the memory 81 is generally used for storing an operating system installed in the computer device 8 and various types of application software, such as program codes of an automatic generation method of a layout. Further, the memory 81 may also be used to temporarily store various types of data that have been output or are to be output.

The processor 82 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 82 is typically used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is configured to execute the program code stored in the memory 81 or process data, for example, execute the program code of the automatic generation method of the layout.

The network interface 83 may comprise a wireless network interface or a wired network interface, and the network interface 83 is generally used for establishing communication connections between the computer device 8 and other electronic devices.

The present application further provides another embodiment, which is to provide a computer-readable storage medium storing an automatic generation program of a floor plan, which can be executed by at least one processor to cause the at least one processor to execute the steps of the automatic generation method of a floor plan as described above.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.

It should be understood that the above-described embodiments are merely exemplary of some, and not all, embodiments of the present application, and that the drawings illustrate preferred embodiments of the present application without limiting the scope of the claims appended hereto. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.

Claims

1. A method for automatic generation of a house layout, the method comprising:

acquiring the image characteristics of the house type;

performing autoregressive processing on the image features to obtain a plurality of layout results corresponding to the house type, wherein the layout results comprise a structural layout relationship representing the house type;

and screening out a target layout result from the plurality of layout results.

2. The method of claim 1, wherein the performing autoregressive processing on the image features to obtain multiple layout results corresponding to the house type comprises:

inputting the image features and each initial furniture sequence into a preset autoregressive model for prediction so as to output each predicted target furniture sequence, wherein each value in the target furniture sequence represents furniture attribute information;

3. The method of claim 1, wherein the obtaining image features of the house type comprises:

acquiring a house type image;

4. The method of automatic generation of a house layout according to claim 2, characterized in that after said outputting each predicted sequence of target furniture, the method further comprises:

and obtaining the self-defined furniture attribute information, and updating the self-defined furniture attribute information into the target sequence.

5. The method of claim 1, wherein the step of selecting a target layout result from the plurality of layout results comprises:

obtaining the scoring value of each layout result;

filtering the scoring value according to a preset scoring threshold value;

6. The method for automatically generating a house layout according to claim 1, wherein said obtaining a score value of each layout result comprises:

obtaining a plurality of initial scoring values of each layout result;

7. An apparatus for automatically generating a house layout, comprising:

and the screening module is used for screening the target layout result from the plurality of layout results.

8. The method of claim 7, wherein the autoregressive processing module comprises:

the system comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring a plurality of preset initial furniture sequences, and the number of the initial furniture sequences is the same as that of layout results;

9. A computer device comprising a memory in which a computer program is stored and a processor which, when executing said computer program, carries out the steps of a method for automatic generation of a floor plan as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the method for automatic generation of a house layout according to any of the claims 1 to 6.