Furniture drawing auxiliary system, method and device and storage medium

Abstract

The embodiment of the invention provides a furniture drawing auxiliary system, method and device and a storage medium, and relates to the field of furniture drawing, the system comprises a voice input module, a touch screen recognition module, a set picture generation module and a processor; the processor is configured to obtain at least one furniture drawing instruction of a user from the voice input module and / or the touch screen recognition module, and for each furniture drawing instruction, a plurality of candidate furniture component drawing blocks are called from a furniture database based on the furniture drawing instruction; determining a plurality of target furniture component blocks corresponding to the furniture drawing instruction from the plurality of candidate furniture component blocks; and generating a target furniture model based on a plurality of target furniture component blocks corresponding to the at least one furniture drawing instruction. According to the embodiment of the invention, the target furniture component module is determined through the furniture drawing instruction input by the user, and then the target furniture model is generated, so that the furniture model can be called and generated in a drawing mode, and the furniture drawing efficiency is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of furniture drawing, and in particular to a furniture drawing auxiliary system, method, device and storage medium. Background Art

[0002] The current method is that the designer first draws the furniture model through drawing software, and then produces and assembles the furniture according to the furniture model. However, the direct drawing method is often time-consuming and labor-intensive, and there are many repetitive and inefficient operations. CN107636593B provides a device, method and user interface for a ruler on a drawing screen, which provides many functions that help users to perform freehand sketching, including line drawing, masking and filling functions. However, this does not substantially solve the problem of repetitive and inefficient operations.

[0003] Therefore, it is necessary to provide a furniture drawing auxiliary system and method to improve drawing efficiency. Summary of the invention

[0004] The technical problem to be solved by the embodiments of the present invention is how to reduce repetitive and inefficient operations and improve the efficiency of furniture drawing.

[0005] One or more embodiments of the present invention provide a furniture drawing assistance system, the system comprising: a voice input module 140, a touch screen recognition module 130, a set drawing generation module 110 and a processor 120; the set drawing generation module 110 comprises a furniture database; the processor 120 is communicatively connected with the touch screen recognition module 130 and drawing software; the processor 120 is configured to: obtain at least one furniture set drawing instruction of the user from at least one of the voice input module 140 and the touch screen recognition module 130, and for each furniture set drawing instruction: based on the furniture set drawing instruction, retrieve multiple candidate furniture component blocks from the furniture database; determine multiple target furniture component blocks corresponding to the furniture set drawing instruction from the multiple candidate furniture component blocks; and generate a target furniture model based on the multiple target furniture component blocks corresponding to the at least one furniture set drawing instruction.

[0006] One of the embodiments of the present invention provides a furniture drawing assistance method, the method comprising: obtaining at least one furniture set drawing instruction of a user, and for each furniture set drawing instruction: based on the furniture set drawing instruction, retrieving multiple candidate furniture component blocks from a furniture database; determining multiple target furniture component blocks corresponding to the furniture set drawing instruction from the multiple candidate furniture component blocks; and generating a target furniture model based on the multiple target furniture component blocks corresponding to the at least one furniture set drawing instruction.

[0007] One or more embodiments of the present invention provide a furniture drawing assistance device, including a processor, wherein the processor is used to execute the furniture drawing assistance method described in any embodiment of this specification.

[0008] One or more embodiments of the present invention provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the furniture drawing auxiliary method described in any embodiment of this specification.

[0009] The beneficial effects of the present invention include but are not limited to: determining the target furniture component module through the furniture set drawing instruction input by the user, and then generating the target furniture model, which can realize the retrieval and generation of the furniture model in the form of a set drawing, thereby greatly improving the efficiency of furniture drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0011] Figure 1 is an exemplary module diagram of a furniture drawing assistance system according to some embodiments of this specification;

[0012] Figure 2 is an exemplary flow chart of a furniture drawing assistance method according to some embodiments of this specification;

[0013] Figure 3 It is an exemplary schematic diagram of a matching degree prediction model shown in some embodiments of this specification.

[0014] Description of reference numerals:

[0015] 100. Furniture drawing auxiliary system; 110. Picture set generation module; 120. Processor; 130. Touch screen recognition module; 140. Voice input module. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0020] In some embodiments, Figure 1 As shown, the furniture drawing assistance system 100 includes a set of drawings generating module 110 , a processor 120 , a touch screen recognition module 130 and a voice input module 140 .

[0021] In some embodiments, the set of pictures generating module 110 includes a furniture database. The furniture database refers to a database storing a plurality of furniture component tiles. In some embodiments, the set of pictures generating module 110 may generate a plurality of furniture component tiles in advance and store the generated furniture component tiles in the furniture database.

[0022] The processor 120 may process data and / or information obtained from other devices or system components. The processor 120 may execute program instructions based on the data, information and / or processing results to perform one or more functions described in this specification. As an example only, the processor 120 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), etc., or any combination thereof.

[0023] In some embodiments, the processor 120 is in communication with the touch screen recognition module 130, the voice input module 140, the set drawing generation module 110, and the drawing software. The drawing software refers to the software used to draw furniture components, that is, the software used by the user to draw the furniture model. The drawing software is an external software that is in communication with the furniture drawing auxiliary system 100. In some embodiments, when the furniture drawing auxiliary system 100 generates the target furniture model, the processor 120 sends the generated target furniture model to the drawing software.

[0024] In some embodiments, the processor 120 is configured to obtain at least one furniture set drawing instruction of the user from at least one of the voice input module 140 and the touch screen recognition module 130, and for each furniture set drawing instruction: based on the furniture set drawing instruction, retrieve multiple candidate furniture component tiles from the furniture database; determine multiple target furniture component tiles corresponding to the furniture set drawing instruction from the multiple candidate furniture component tiles; and generate a target furniture model based on the multiple target furniture component tiles corresponding to the at least one furniture set drawing instruction.

[0025] In some embodiments, in response to the matching degree between the candidate furniture component tile and the user requirement parameter being greater than a first preset threshold, the processor 120 is further configured to determine the candidate furniture component tile as the target furniture component tile.

[0026] In some embodiments, the processor 120 is further configured to determine the degree of matching between the user demand parameters and the candidate furniture component tiles through a matching degree prediction model based on the user demand parameters, furniture set instructions, the candidate furniture component tiles and the shape features of the candidate furniture component tiles, and the matching degree prediction model is a machine learning model.

[0027] In some embodiments, the processor 120 is further configured to, for each furniture set drawing instruction, wherein the furniture set drawing instruction includes multiple furniture set drawing sub-instructions, obtain the instruction levels of the multiple furniture set drawing sub-instructions included in the furniture set drawing instruction; and determine the number of candidate furniture component blocks to be called based on the furniture set drawing instruction based on the instruction levels of the multiple furniture set drawing sub-instructions.

[0028] In some embodiments, the touch screen recognition module 130 is configured to receive a user's gesture and transmit the gesture to the processor 120. In some embodiments, the touch screen recognition module 130 may include a touch screen.

[0029] In some embodiments, the voice input module 140 is configured to receive the user's voice and transmit it to the processor 120. In some embodiments, the voice input module 140 may include a voice recognition device.

[0030] For more information about each module, please refer to the relevant description below.

[0031] It should be understood that Figure 1 The illustrated system and its modules may be implemented in various ways.

[0032] It should be noted that the above description of the furniture drawing auxiliary system 100 and its modules is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 1 The image set generation module 110, processor 120, touch screen recognition module 130 and voice input module 140 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the scope of protection of this specification.

[0033] In some embodiments, the process of the furniture drawing assistance method can be executed by a processor.

[0034] In some embodiments, the processor can obtain at least one furniture set drawing instruction from the user, and for each furniture set drawing instruction, retrieve multiple candidate furniture component tiles from a furniture database based on the furniture set drawing instruction; determine multiple target furniture component tiles corresponding to the furniture set drawing instruction from the multiple candidate furniture component tiles; and generate a target furniture model based on the multiple target furniture component tiles corresponding to the at least one furniture set drawing instruction.

[0035] like Figure 2 As shown, the process of the furniture drawing auxiliary method includes the following steps:

[0036] Step 210, obtaining at least one furniture set drawing instruction from the user.

[0037] The furniture set drawing instruction refers to an instruction issued by a user for obtaining furniture component blocks. The user refers to a person involved in furniture drawing, such as a designer. When a user needs to draw a furniture model, the user can directly obtain the required target furniture model by issuing a furniture set drawing instruction. In some embodiments, the furniture set drawing instruction may include a description of the required furniture component blocks (e.g., size information, scene information, and shape information of the furniture component blocks, etc.) and a corresponding combination method.

[0038] In some embodiments, the furniture set map instruction may include a gesture set map instruction and / or a voice set map instruction. A gesture set map instruction refers to an instruction generated according to a user's gesture. A voice set map instruction refers to an instruction generated according to a user's voice.

[0039] The furniture component tiles refer to standardized graphical representations used to describe furniture components. The combination mode corresponding to the furniture component tiles refers to the connection relationship corresponding to each furniture component tile. The connection relationship may include connected furniture component tiles and edges for connection.

[0040] As an example only, assume that the furniture component tiles required in the furniture set drawing instruction are A, B, and C, where furniture component tile A includes three edges a1, a2, and a3, furniture component tile B includes four edges b1, b2, b3, and b4, and furniture component tile C includes three edges c1, c2, and c3, where furniture component tile A is connected to furniture component tile B through a1 and to furniture component tile C through a3, then the connection relationship of furniture component tile A can be expressed as ((AB, a1), (AC, a3)).

[0041] In some embodiments, the processor may obtain at least one furniture set diagram instruction of the user from the voice input module and / or the touch screen recognition module. The processor may receive the user's gesture through the touch screen recognition module and / or receive the user's voice through the voice input module, and convert the received gesture and / or language into an instruction code as the furniture set diagram instruction.

[0042] Step 220: for each furniture set drawing instruction, based on the furniture set drawing instruction, retrieve multiple candidate furniture component blocks from the furniture database.

[0043] The candidate furniture component tile refers to a furniture component tile that can be used as an alternative.

[0044] The furniture component tiles in the furniture database can be divided into multiple categories, for example, they can be divided into board categories, cabinet categories, sofa categories, etc. according to the furniture category.

[0045] In some embodiments, the description of the required furniture component tiles in the furniture set instruction may also include the category of the required furniture component tiles. In some embodiments, for each furniture set instruction, the processor may identify the furniture set instruction and select all furniture component tiles in the category in the furniture database according to the category corresponding to the furniture set instruction as candidate furniture component tiles.

[0046] In some embodiments, a furniture slip instruction includes a plurality of furniture slip sub-instructions.

[0047] The furniture set sub-instruction refers to a sub-instruction corresponding to each furniture component block in the furniture set instruction. In some embodiments, each furniture set instruction includes a plurality of furniture set sub-instructions.

[0048] For each furniture set drawing instruction, the processor may obtain instruction levels of multiple furniture set drawing sub-instructions included in the furniture set drawing instruction; and determine the number of candidate furniture component tiles to be retrieved based on the furniture set drawing instruction based on the instruction levels of the multiple furniture set drawing sub-instructions.

[0049] The instruction level refers to the level corresponding to the furniture set sub-instructions after hierarchical division. The instruction level of the furniture set sub-instructions can indicate the difficulty of matching the furniture set sub-instructions with the corresponding candidate furniture component tiles.

[0050] In some embodiments, the processor may set the instruction level of the furniture set sub-instruction according to the experience of relevant personnel (eg, designers).

[0051] In some embodiments, the processor may determine the instruction levels of the plurality of furniture set diagram sub-instructions based on the usage frequencies of the plurality of furniture set diagram sub-instructions and the matching degree distribution data.

[0052] The usage frequency of the furniture set sub-command refers to the average number of times the furniture set sub-command is used in multiple preset historical periods. The preset historical period refers to a certain period in history.

[0053] The matching degree distribution data refers to the multiple matching degrees and corresponding matching times of the candidate furniture component tiles corresponding to the furniture set diagram sub-instruction in the historical data. For the matching degrees of the candidate furniture component tiles, please refer to step 230 and its related description.

[0054] In some embodiments, the processor may determine the instruction level of the furniture set picture sub-instruction through a first preset table based on the usage frequency and matching degree distribution data of the furniture set picture sub-instruction.

[0055] The first preset table may include the corresponding relationship between the usage frequency of the furniture set sub-command, the matching degree mean of the furniture set sub-command, different combinations of the matching degree standard deviation of the furniture set sub-command and the command level of the furniture set sub-command. The first preset table may be pre-constructed based on historical data.

[0056] The matching degree mean value and matching degree standard deviation of the furniture set sub-instruction can be calculated based on the matching degree distribution data. The matching degree mean value of the furniture set sub-instruction is the mean value of all matching degrees of the candidate furniture component tiles corresponding to the furniture set sub-instruction. The matching degree standard deviation of the furniture set sub-instruction is the standard deviation of all matching degrees of the candidate furniture component tiles corresponding to the furniture set sub-instruction.

[0057] In the embodiment of the present specification, a relatively accurate instruction level of the furniture set sub-instruction can be obtained through the usage frequency and matching degree distribution data of the furniture set sub-instruction, thereby determining the number of suitable candidate furniture component tiles.

[0058] The number of candidate furniture component tiles refers to the number of furniture component tiles that the processor needs to call as candidates for the furniture set drawing instruction.

[0059] In some embodiments, the processor may determine the instruction level of the furniture set drawing instruction based on the weighted sum of the instruction levels of multiple furniture set drawing sub-instructions; and based on the instruction level of the furniture set drawing instruction, determine the number of candidate furniture component blocks that need to be called through a second preset table.

[0060] In some embodiments, the weight coefficients of the multiple furniture set sub-commands can be set according to the experience of relevant personnel (eg, designers).

[0061] In some embodiments, the weight coefficients of the instruction levels of the plurality of furniture set sub-instructions are related to the shape complexity of the candidate furniture component tiles corresponding to the furniture set sub-instructions.

[0062] Shape complexity refers to a numerical value describing the complexity of the geometric structure of a furniture component tile. In some embodiments, shape complexity can be determined based on the proportion of irregular edges of the candidate furniture component tile. The proportion of irregular edges refers to the ratio of the number of curved edges, broken line edges, etc. to the number of all edges. For each furniture set sub-instruction, the higher the shape complexity of the corresponding candidate furniture component tile, the higher the weight coefficient corresponding to the furniture set sub-instruction. The processor can pre-set the corresponding relationship between shape complexity and weight coefficient based on historical data.

[0063] In the embodiments of the present specification, the higher the shape complexity of the candidate furniture component tiles, the more difficult it is to calculate their matching degree. In this case, it is necessary to increase the weight coefficient of the furniture set sub-instruction corresponding to the candidate furniture component tiles to obtain more candidate furniture component tiles, so as to ensure that even if errors occur in the matching degree calculation, a sufficient number of candidate furniture component tiles with a high matching degree can be obtained.

[0064] The second preset table may include a correspondence between the instruction level of the furniture set instruction and the number of candidate furniture component blocks to be retrieved. The second preset table may be pre-constructed based on historical data.

[0065] In some embodiments, the processor may select the number of candidate furniture component blocks that need to be retrieved corresponding to the instruction level of the furniture set instruction from the second preset table.

[0066] In the embodiment of the present specification, a more accurate number of candidate furniture component tiles that need to be retrieved can be determined through the instruction levels of multiple furniture set sub-instructions to ensure that a sufficient number of candidate furniture component tiles with a high degree of matching are obtained.

[0067] In some embodiments, for a furniture set picture sub-instruction whose instruction level exceeds a level threshold, the processor may determine an ambiguity risk value of the furniture set picture sub-instruction based on matching degree distribution data of the furniture set picture sub-instruction; based on the ambiguity risk value, generate a supplementary input instruction to obtain a supplementary instruction from the user; and based on the supplementary instruction, optimize the furniture set picture sub-instruction.

[0068] The third-level furniture set sub-command is a furniture set sub-command of the third level, that is, the command with the highest matching difficulty.

[0069] The ambiguity risk value refers to the risk level of ambiguity in the furniture set sub-instructions.

[0070] In some embodiments, the processor may use the ratio of the number of matches with a matching degree lower than a second preset threshold to the total number of matches in the matching degree distribution data as the ambiguity risk value of the furniture set sub-instruction. A low matching degree indicates that there may be an error in the recognition of the furniture set sub-instruction, and the furniture set sub-instruction is considered to be ambiguous. The second preset threshold can be set based on experience.

[0071] The supplementary input instruction refers to an instruction prompting the user to supplement the input of the corresponding furniture set sub-instruction. For example, the supplementary input instruction may be an instruction prompting the user to supplement the furniture shape, furniture size, etc.

[0072] The supplementary instruction refers to an instruction obtained by the user's supplementary input.

[0073] In some embodiments, the processor may combine the supplemental instruction with the third-level furniture set diagram sub-instruction to obtain an optimized third-level furniture set diagram sub-instruction.

[0074] In the embodiment of the present specification, for the third-level furniture set picture sub-instruction, the user's supplementary instructions are obtained according to the ambiguity risk value to optimize the third-level furniture set picture sub-instruction, which can avoid ambiguity in the furniture set picture sub-instruction as much as possible and make the matching of the furniture set picture sub-instruction more accurate.

[0075] Step 230 , determining a plurality of target furniture component tiles corresponding to the furniture set drawing instruction from a plurality of candidate furniture component tiles.

[0076] The target furniture component tile refers to the furniture component tile that is finally determined.

[0077] In some embodiments, the processor may determine the target furniture component tile by manually (eg, a designer) selecting a plurality of candidate furniture component tiles.

[0078] In some embodiments, in response to a matching degree between a candidate furniture component tile and a user requirement parameter being greater than a first preset threshold, the processor may determine the candidate furniture component tile as a target furniture component tile.

[0079] User demand parameters refer to parameters that describe and quantify the characteristics, functions or standards of the furniture component tiles desired by the user. In some embodiments, the user demand parameters may include the user's scene requirements, as well as the furniture components required by the user and the corresponding size information, shape information, etc.

[0080] In some embodiments, the processor may determine the user requirement parameters according to the furniture set drawing instruction. For example, the processor may use the size information, scene information, and shape information contained in the furniture set drawing instruction issued by the user as the user requirement parameters.

[0081] In some embodiments, the processor may determine user demand parameters of a user (hereinafter referred to as a current user) based on at least one furniture set map instruction and a historical usage data distribution.

[0082] In some embodiments, the processor may count the user demand parameters of the reference users corresponding to the furniture component blocks required by at least one furniture set instruction of the current user in the historical usage data distribution of multiple reference users. The processor may determine the average of the user demand parameters of the multiple reference users as the user demand parameter of the current user.

[0083] The historical usage data distribution refers to the scene information set by the user (for example, including the reference user or the current user) during the historical usage process, the setting frequency corresponding to the scene information, and the size information and shape information and usage frequency of each furniture component actually used.

[0084] In some embodiments, the processor may determine the reference user through cluster analysis. The processor may cluster multiple cluster vectors to obtain multiple cluster clusters, determine the cluster cluster containing the target vector as the target cluster cluster; and use the users corresponding to all cluster vectors in the target cluster cluster as reference users. A cluster vector refers to a vector constructed based on the distribution of historical usage data. Each cluster vector includes the distribution of historical usage data of multiple different users. The target vector is a vector constructed based on the historical usage data of the current user.

[0085] In the embodiments of the present specification, through the furniture set map instructions and the historical usage data distribution, combined with the historical situation, more accurate user demand parameters can be determined, so that the determined target furniture component blocks are more accurate.

[0086] The matching degree refers to the matching degree between the candidate furniture component tiles and the user's required parameters.

[0087] In some embodiments, the processor may determine the degree of match in a variety of ways. For example, the processor may match the size information and shape information of the candidate furniture component tile with the size information and shape information in the user requirement parameters to determine the degree of match.

[0088] In some embodiments, the processor may determine the degree of matching between the user demand parameters and the candidate furniture component tiles through a matching degree prediction model based on the user demand parameters, the furniture set drawing instructions, the candidate furniture component tiles and the shape features of the candidate furniture component tiles.

[0089] The matching prediction model refers to a model used to determine the matching degree between the user demand parameters and the candidate furniture component tiles. In some embodiments, the matching prediction model may be a machine learning model. For example, the matching prediction model may be one or any combination of a neural network model (NN), a deep neural network model (DNN), etc.

[0090] In some embodiments, Figure 3 As shown, the input of the matching prediction model 320 may include user requirement parameters 311, furniture set instructions 312, candidate furniture component tiles 313, and shape features of the candidate furniture component tiles 314. The output of the matching prediction model 320 may include the matching degree 330 between the user requirement parameters and the candidate furniture component tiles.

[0091] Among them, the processor can input a single candidate furniture component tile into the matching prediction model, and output the matching degree between the candidate furniture component tile and the user demand parameters, or can simultaneously input multiple candidate furniture component tiles into the matching prediction model, and output the matching degrees between multiple candidate furniture component tiles and the user demand parameters respectively.

[0092] The shape feature of the candidate furniture component tile refers to the shape of the candidate furniture component tile and the size of each side.

[0093] It should be noted that the furniture set instructions in the matching prediction model input include the combination of the required furniture component tiles. Therefore, the matching degree between the output user demand parameters and the candidate furniture component tiles also includes the adaptability of the candidate furniture component tiles when combined.

[0094] In some embodiments, the processor may train a matching prediction model based on multiple sets of labeled training samples. In some embodiments, the training samples may include sample user demand parameters, sample furniture set instructions, sample candidate furniture component tiles, and shape features of sample candidate furniture component tiles, and the labels corresponding to the training samples may be the matching degree between the sample user demand parameters corresponding to the training samples and the sample candidate furniture component tiles. In some embodiments, the training samples may be user demand parameters, furniture set instructions, and multiple candidate furniture component tiles and shape features of candidate furniture component tiles used when generating a target furniture model for different users in historical data. In some embodiments, the processor may use the ratio of the original size of the candidate furniture component tiles to the size difference after the target furniture model in the training samples is generated in the historical data as a label. The size difference is the difference between the actual size and the original size.

[0095] In some embodiments, the processor can input a large number of training samples into the initial matching prediction model, construct a loss function based on the output of the initial matching prediction model and the labels of the corresponding training samples, and iteratively update the initial matching prediction model based on the loss function; when the value of the loss function meets the iteration completion condition, the training is completed and a trained matching prediction model is obtained. The iteration completion condition may include the convergence of the loss function, the number of iterations reaching a threshold, etc. The trained matching prediction model can be stored in a storage module or a processor, and the processor can call the matching prediction model to determine the matching degree between the user's demand parameters and the candidate furniture component tiles.

[0096] In some embodiments of the present specification, the matching degree between the user demand parameters and the candidate furniture component tiles is determined by a matching degree prediction model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of historical data, effectively reduce errors, and improve the efficiency and accuracy of matching degree determination.

[0097] The first preset threshold is a preset threshold for selecting a target furniture component tile. In some embodiments, the first preset threshold can be set based on experience.

[0098] In some embodiments, the first preset threshold value may be related to the combination complexity of the target furniture component tile. The combination complexity of the target furniture component tile may be represented by the number of irregular edges (e.g., curved edges and broken line edges) of the target furniture component tile. The higher the combination complexity of the target furniture component tile, the higher the first preset threshold value.

[0099] The more irregular edges of the target furniture component tiles, the higher the difficulty of assembling the target furniture component tiles. In this case, candidate furniture component tiles with higher matching degrees are needed to ensure that the furniture component tiles can be successfully assembled.

[0100] In the embodiment of the present specification, the target furniture component tile is determined by the matching degree between the candidate furniture component tile and the user requirement parameter, so that the furniture component tile that better meets the user requirement can be determined.

[0101] Step 240: Generate a target furniture model based on a plurality of target furniture component blocks corresponding to at least one furniture set drawing instruction.

[0102] The target furniture model refers to the furniture model required by the user. The target furniture model can be directly used by the user for subsequent applications, such as home design.

[0103] In some embodiments, the processor may combine multiple target furniture component tiles according to corresponding combination methods to generate a target furniture model. The combination methods corresponding to the furniture component tiles may be obtained from the furniture set drawing instruction.

[0104] In some embodiments, the processor may obtain at least one set of picture modification instructions from the user from the voice input module and / or the touch screen recognition module; and modify multiple target furniture component blocks based on the at least one set of picture modification instructions.

[0105] A set of picture modification instructions refers to an instruction issued by a user to modify a target furniture component. In some embodiments, the set of picture modification instructions may include gesture modification instructions and / or voice modification instructions. A gesture modification instruction refers to an instruction issued by a user to modify a furniture component using gestures. For example, sliding to modify the size of a furniture component. A voice modification instruction refers to an instruction issued by a user to modify a furniture component using voice. For example, the user's voice may be "adjust the length" and the corresponding parameters.

[0106] In some embodiments, the processor can modify the corresponding target furniture component block according to the set image modification instruction. For example, if the voice modification instruction is to adjust the length of the sofa, the processor can adjust the length of the corresponding sofa in the target furniture component block.

[0107] In the embodiments of the present specification, the target furniture component blocks are modified through the set of image modification instructions. Before generating the target furniture model, the target furniture model can be modified according to the user's instructions to obtain a target furniture model that better meets the user's needs, thereby improving the user's experience.

[0108] In some embodiments, the processor may modify the plurality of target furniture component tiles based on at least one set of image modification instructions and the matching degree between the plurality of target furniture component tiles and the user requirement parameters.

[0109] In some embodiments, the processor may determine an adjustment ratio through a third preset table based on the degree of matching; and modify multiple target furniture component tiles based on the adjustment ratio.

[0110] The adjustment ratio refers to the ratio of the user gesture modification amplitude to the actual adjustment parameter of the target furniture component tile. The user gesture modification amplitude refers to the amplitude of the furniture component modification input by the user through the gesture. The user gesture modification amplitude can be determined by the gesture modification instruction.

[0111] In some embodiments, the first preset table may include a matching degree and a corresponding adjustment ratio. The first preset table may be set based on experience. The lower the matching degree, the higher the adjustment ratio.

[0112] In the embodiments of the present specification, the target furniture component blocks are modified through the set image modification instructions and the matching degree, so as to further improve the accuracy of the target furniture model.

[0113] In the embodiments of the present specification, the target furniture component module is determined by the furniture set drawing instruction input by the user, and then the target furniture model is generated. It is possible to retrieve and generate the furniture model in a set drawing manner, thereby greatly improving the efficiency of furniture drawing.

[0114] It should be noted that the above description of steps 210 to 240 is only for illustration and description, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to steps 210 to 240 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0115] Some embodiments of the present specification also provide a furniture drawing assistance device, including a processor, the processor is used to execute at least part of the computer instructions to implement the furniture drawing assistance method described in any embodiment of the present specification.

[0116] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the furniture drawing auxiliary device method described in any embodiment of the present specification.

[0117] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0118] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0119] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0120] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0121] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0122] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0123] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A furniture drawing auxiliary system, characterized in that: include: A voice input module (140), a touch screen recognition module (130), a set of pictures generating module (110) and a processor (120); The set of pictures generating module (110) includes a furniture database; The processor (120) is communicatively connected with the voice input module (140), the touch screen recognition module (130), the set of pictures generating module (110) and the drawing software; The processor (120) is used for: Acquire at least one furniture set diagram instruction of the user from at least one of the voice input module (140) and the touch screen recognition module (130), and for each furniture set diagram instruction: Based on the furniture set drawing instruction, a plurality of candidate furniture component blocks are retrieved from the furniture database; Determine a plurality of target furniture component tiles corresponding to the furniture set drawing instruction from the plurality of candidate furniture component tiles; A target furniture model is generated based on the multiple target furniture component blocks corresponding to the at least one furniture set drawing instruction.

2. The furniture drawing auxiliary system according to claim 1, characterized in that: The processor (120) is further configured to: In response to a matching degree between the candidate furniture component tile and the user requirement parameter being greater than a first preset threshold, the candidate furniture component tile is determined as the target furniture component tile.

3. The furniture drawing assistance system according to claim 2, characterized in that: The processor (120) is further configured to: Based on the user demand parameters, the furniture set drawing instructions, the candidate furniture component tiles and the shape features of the multiple candidate furniture component tiles, the matching degree between the user demand parameters and the candidate furniture component tiles is determined by a matching degree prediction model, and the matching degree prediction model is a machine learning model.

4. The furniture drawing assistance system according to claim 1, characterized in that: The processor (120) is further configured to: For each furniture set instruction, the furniture set instruction includes a plurality of furniture set sub-instructions, Acquire the instruction levels of the plurality of furniture set diagram sub-instructions included in the furniture set diagram instruction; Based on the instruction levels of the plurality of furniture set drawing sub-instructions, the number of the candidate furniture component tiles called based on the furniture set drawing instruction is determined.

5. A furniture drawing auxiliary method, characterized in that: include: Acquire at least one furniture set diagram instruction of the user from at least one of the voice input module (140) and the touch screen recognition module (130), and for each furniture set diagram instruction: Based on the furniture set drawing instruction, a plurality of candidate furniture component blocks are retrieved from a furniture database; Determine from the plurality of candidate furniture component tiles a plurality of target items corresponding to the furniture set diagram instruction Label furniture component tiles; A target furniture model is generated based on the multiple target furniture component blocks corresponding to the at least one furniture set drawing instruction.

6. The furniture drawing auxiliary method according to claim 5, characterized in that: The step of determining a plurality of target furniture component tiles corresponding to the furniture set drawing instruction from the plurality of candidate furniture component tiles comprises: In response to a matching degree between the candidate furniture component tile and the user requirement parameter being greater than a first preset threshold, the candidate furniture component tile is determined as the target furniture component tile.

7. The furniture drawing auxiliary method according to claim 6, characterized in that: The method further comprises: Based on the user demand parameters, the furniture set drawing instructions, the candidate furniture component tiles and the shape features of the multiple candidate furniture component tiles, the matching degree between the user demand parameters and the candidate furniture component tiles is determined by a matching degree prediction model, and the matching degree prediction model is a machine learning model.

8. The furniture drawing auxiliary method according to claim 5, characterized in that The instruction for obtaining multiple furniture set pictures of the user includes: For each furniture set instruction, the furniture set instruction includes a plurality of furniture set sub-instructions, Acquire the instruction levels of the plurality of furniture set diagram sub-instructions included in the furniture set diagram instruction; Based on the instruction levels of the plurality of furniture set drawing sub-instructions, the number of the candidate furniture component tiles called based on the furniture set drawing instruction is determined.

9. A furniture drawing assistance device, comprising a processor (120), wherein the processor is used to execute the furniture drawing assistance method according to any one of claims 5 to 8.

10. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the furniture drawing auxiliary method according to any one of claims 5 to 8.

Images