Model assembling method and device, electronic equipment and storage medium

Abstract

The invention provides a model assembling method and device, electronic equipment and a storage medium. The method comprises the following steps: in response to a model assembly instruction, obtaining first feature data of a to-be-assembled model through the model assembly instruction; wherein the first feature data is used for indicating overall features and / or component features of a to-be-assembled model, and the to-be-assembled model is composed of models of at least two components; obtaining target component information matched with the first feature data from a preset feature database; wherein the target component information comprises index information, corresponding to at least one sample type component model, of each component; based on the target component information, obtaining at least one target component model corresponding to each component; and according to the at least two components forming the to-be-assembled model, assembling the target component model to obtain at least one target assembly model. According to the invention, the controllability of model assembly can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of model generation, and in particular to a model assembly method, device, electronic device and storage medium. Background Art

[0002] Some models can be split into multiple components. Component models of different styles can be assembled together to obtain overall models of different styles. For example, the clothing of a character model can be assembled from component models of types such as tops, skirts, and ribbons. Component models of different styles can be assembled into different styles of clothing combinations, making the character model more diverse.

[0003] Existing model assembly technologies are usually random assembly, which makes it difficult to obtain an assembly model with a specific style or that meets specific requirements, and there is a technical problem of poor controllability. Summary of the invention

[0004] In view of this, an object of the present disclosure is to provide a model assembly method, device, electronic device and storage medium to improve the controllability of model assembly.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for assembling a model, the method comprising: in response to a model assembly instruction, obtaining first feature data of a model to be assembled through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; obtaining target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of at least one style of component model corresponding to each component; based on the target component information, obtaining at least one target component model corresponding to each component; and assembling the target component model according to the at least two components constituting the model to be assembled to obtain at least one target assembly model.

[0006] In a second aspect, an embodiment of the present disclosure provides an assembly device for a model, the device comprising: a response module, used to respond to a model assembly instruction, and obtain first feature data of a model to be assembled through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; a matching module, used to obtain target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of a component model of at least one style corresponding to each component; an acquisition module, used to obtain at least one target component model corresponding to each component based on the target component information; and an assembling module, used to assemble the target component models according to the at least two components constituting the model to be assembled, to obtain at least one target assembly model.

[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device, including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned model assembly method.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned model assembly method.

[0009] The embodiments of the present disclosure bring the following beneficial effects:

[0010] The above-mentioned model assembly method, device, electronic device and storage medium can indicate the overall characteristics or component characteristics of the model to be assembled through the model assembly instructions. Through these characteristics, component models of different styles can be matched to assemble assembly models of different styles, so that the style or specific requirements of the assembly model can be expressed through the instruction indication characteristics, reducing the randomness of the model assembly and improving the controllability of the model assembly.

[0011] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or understood by practicing the present disclosure. The purpose and other advantages of the present disclosure are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0012] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 is a flow chart of an embodiment of a method for assembling a model in an embodiment of the present disclosure;

[0015] Figure 2 A schematic diagram of an assembly device of a model provided by an embodiment of the present disclosure;

[0016] Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0018] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiment of the present disclosure is described below. Figure 1 , an embodiment of the assembly method of the model in the embodiment of the present disclosure includes:

[0020] Step S10, in response to the model assembly instruction, obtaining first characteristic data of the model to be assembled through the model assembly instruction; wherein the first characteristic data is used to indicate the overall characteristics and / or component characteristics of the model to be assembled, and the model to be assembled is composed of models of at least two components;

[0021] It should be noted that many models can be composed of models of at least two components. In other words, many models can be split into models of at least two components. For example, a suit clothing model can be composed of two component models of a top and a bottom, a human body model can be composed of four component models of hair, head, upper torso and lower torso, and a car model can be composed of three component models of a shell, wheels and a frame. The embodiments of the present disclosure can obtain assembled models of different styles by assembling components of different styles to meet the diverse needs of the models.

[0022] In this embodiment, the assembly parameters of the model to be assembled can be specified through the model assembly instruction. The assembly parameters are used to indicate the assembly method of the model to be assembled. For example, the assembly parameters may include: the number, category, component type, matching degree, feature bearing object, type of feature bearing object, whether random assembly is performed, whether the component model can be reused, export file format, etc. of the target assembly model. No specific limitations are made here.

[0023] As an example but not limitation, the client can specify the above-mentioned assembly parameters and submit them to the server through a model assembly instruction. The server can generate at least one target assembly model according to the above-mentioned assembly parameters and send it to the client, or the server can obtain at least one target component model corresponding to each component and send it to the client, and the client will assemble the target component models. The specific details are not limited here.

[0024] Among them, the feature-bearing object carries the features of the model to be assembled and can be used to obtain the first feature data of the model to be assembled. Different types of feature-bearing objects have different corresponding methods for obtaining the first feature data. For example, the type of the feature-bearing object can be text, image, voice, etc. The type of the feature-bearing object indicated by the model assembly instruction can include one or more, which is not specifically limited here.

[0025] For example, assuming that an image-type feature-bearing object provides an image of a clothing suit, the image of the clothing suit can also be supplemented by a text-type feature-bearing object. The features of the model to be assembled can be extracted from both the image and the text to obtain the first feature data. The specific details are not limited here.

[0026] In this embodiment, the first feature data may include the overall feature and / or component feature of the model to be assembled, the overall feature refers to the feature of the overall structure of the model to be assembled, and the component feature refers to the feature of at least two components in the model to be assembled, the overall feature can be used to match the overall model, and the component feature can be used to match the component model, which is not specifically limited here. The above feature data can be a vector, which is not specifically limited here.

[0027] In one embodiment, when obtaining the first feature data of the model to be assembled through the model assembly instruction, the features of the model to be assembled can be identified from the feature bearing objects indicated by the model assembly instruction through a pre-trained artificial intelligence model, thereby obtaining the first feature data. Different artificial intelligence models can be used according to different types of feature bearing objects, which are not specifically limited here.

[0028] It should be noted that the component type of the model to be assembled can be identified from the feature bearing object indicated by the model assembly instruction, or can be directly specified by the model assembly instruction. The component type of the model to be assembled can also be determined based on the identified component type and / or the specified component type.

[0029] For example, assuming that component type 1 and component type 2 are identified from the feature-bearing object, and the model assembly instruction specifies component type 2 and component type 3, then the component types of the model to be assembled include component type 1 and component type 2, and may also include component type 2 and component type 3, or may be determined based on component type 1, component type 2, and component type 3, which is not specifically limited here.

[0030] Step S20, obtaining target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of a component model of at least one style corresponding to each component;

[0031] It can be understood that the feature database includes feature data of overall models and / or component models of multiple styles. According to the first feature data, at least one style of target overall model and / or target component model corresponding to each component can be matched in the preset feature database, and then according to the target overall model and / or target component model, the index information of at least one style of component model corresponding to each component can be obtained to obtain the target component information.

[0032] Among them, in the preset feature database, each overall model can correspond to at least two component models, and the overall model at least includes the model of the most basic component of the model. For example, for the overall model of a suit of clothing, the most basic components are the top and bottom, while hats, shawls, capes, gloves, etc. are not the most basic components, and the specific details are not limited here.

[0033] In one embodiment, a model database may be used to pre-store a variety of styles of overall models and component models, wherein the component model may be obtained by splitting the overall model, and each overall model may be split according to at least one component classification method, that is, each overall model may be split at least once according to different splitting methods, thereby obtaining a richer component model.

[0034] For example, assuming that the overall model is a suit clothing model, which includes the structure of a dress and stockings, then the suit clothing model can be split into two component models of a dress and stockings, or it can be split into three component models of a top, a skirt and stockings, and the specifics are not limited here.

[0035] In one embodiment, the component model can also be obtained by other means. For example, the component model can be independently produced, can be transformed from a component model of a basic style, or can be split from an overall model of other types that are not models to be assembled. For example, the component model of a skirt can be obtained from a basic style skirt model by changing the color, length, pattern and other styles, or it can be split from a character model. The specifics are not limited here.

[0036] It can be understood that the models in the model database can all be pre-identified to obtain target feature data, stored in the feature database, and by establishing an association relationship between the index information of the model in the model database and the feature data in the feature database, after matching the target feature data that matches the first feature data from the feature database, the index information corresponding to the target feature data can be obtained based on the association relationship, which is the above-mentioned method of obtaining the target component information, and both the retrieval efficiency and the matching accuracy are improved.

[0037] Step S30: based on the target component information, obtaining at least one target component model corresponding to each component;

[0038] In this implementation, after obtaining the index information of the component model of at least one style corresponding to each component, at least one target component model corresponding to each component can be searched and obtained in the model database according to the index information, wherein each style corresponds to a target component model, and the number of styles corresponding to each component can be the same or different, which is not limited here.

[0039] For example, assuming that the target component information includes index information of component models of five styles corresponding to two types of components, namely, upper and lower components, respectively, then the number of target component models obtained is 10, including component models of five styles of upper components and component models of five styles of lower components, which are not specifically limited here.

[0040] Step S40: assemble the target component model according to at least two components constituting the model to be assembled to obtain at least one target assembly model.

[0041] In this embodiment, after obtaining at least one target component model corresponding to each component, target component models of different styles can be assembled to obtain target assembly models with rich styles, wherein the target component models are assembled according to the component types of the models to be assembled. For example, if the component types of the models to be assembled include tops and skirts, then the target assembly models include top component models and skirt component models. The component models of different target assembly models are at least partially different, which is not specifically limited here.

[0042] The model assembly method provided in the above-mentioned embodiment can indicate the overall characteristics or component characteristics of the model to be assembled through the model assembly instructions. Through these characteristics, component models of different styles can be matched to assemble assembly models of different styles, so that the style or specific requirements of the assembly model can be expressed through the instruction indication features, reducing the randomness of the model assembly and improving the controllability of the model assembly.

[0043] Next, the method of matching the first feature data with the component information is specifically described. The first feature data can be used to indicate the overall features and / or component features of the model to be assembled. The data indicating the overall features are called the overall feature data in the first feature data, and the data indicating the component features are called the component feature data in the first feature data. According to the overall features or component features, different methods can be used to obtain the target component information matching the first feature data from the preset feature database.

[0044] It should be noted that the target component information includes component information that matches the overall feature data and / or component feature data. The target feature data that matches the first feature data can be obtained from a preset feature database, and then the target component information corresponding to the target feature data can be obtained, making the model matching more flexible.

[0045] In one embodiment, when obtaining target component information matching the first feature data from a preset feature database, the matching overall model information is obtained from the preset feature database based on the overall features of the model to be assembled indicated by the first feature data; wherein the overall model information is used to indicate a target overall model of at least one style; based on the overall model information, the index information of the component models constituting the target overall model is obtained to obtain the target component information.

[0046] It can be understood that the model database can store overall models of various styles, and the feature data of the overall models can be pre-stored in the feature database. In this embodiment, each overall model also corresponds to at least two components. Therefore, after matching at least one style of the target overall model from the preset feature database through the overall features of the model to be assembled, the index information of the component model corresponding to the target overall model can be obtained, thereby obtaining the target component information.

[0047] In one embodiment, the overall model and component model in the model database can be bound / mapped with the feature data of the model in the feature database through index information. For example, each model in the model database can correspond to a model identifier, and the feature data of each model in the feature database can correspond to a feature identifier. For the same model, the model identifier and the feature identifier are associated and stored to establish a binding / mapping relationship between the two for easy query.

[0048] Similarly, the binding / mapping relationship between the overall model and the component models obtained by splitting it can also be set in the above manner. Specifically, the model identifier corresponding to each overall model can be stored in association with the model identifier of its component model. For example, the overall model A corresponds to the component models a1 and a2. This is not limited here today.

[0049] As an example but not limitation, assuming that feature data A and feature data B are matched from the feature database based on the overall features of the model to be assembled, then the corresponding model identifiers can be queried based on the feature identifiers A and B, assuming that they correspond to the target overall model A1 and the target overall model B1 respectively. Then, the model identifiers of the corresponding component models can be queried based on the model identifiers A1 and B1. assuming that the model identifiers of the component model corresponding to A1 include: a1 and a2, and the model identifiers of the component model corresponding to B1 include: b1, b2 and b3, then a1, a2, b1, b2 and b3 are the index information of the component models constituting the target overall model, that is, the component information that matches the overall feature data in the first feature data, that is, part or all of the target component information, which is not limited here.

[0050] In one embodiment, the target component information may also include component information matching the component feature data in the first feature data. When the target component information matching the first feature data is obtained from a preset feature database, the component features of the model to be assembled are indicated by the first feature data, and the matching component model information is obtained from the preset feature database; wherein the component model information is used to indicate that each component corresponds to at least one style of target component model; according to the component model information, the index information of each target component model is obtained to obtain the target component information.

[0051] It is understandable that component models of various styles may be stored in the model database, and the feature data of the component models may be pre-stored in the feature database. The models in the model database and the feature data in the feature database may be bound / mapped by association through index information. For example, each model in the model database may correspond to a model identifier, and the feature data of each model in the feature database may correspond to a feature identifier. For the same model, the model identifier and the feature identifier may be associated and stored to establish a binding / mapping relationship between the two for easy query.

[0052] In this embodiment, for the component feature data in the first feature data, feature data of at least one style of the target component model can be directly matched from a preset feature database, and then based on the association between the feature data and the model data, the index information of the target component model can be obtained, thereby obtaining component information that matches the component feature data in the first feature data, that is, part or all of the target component information, which is not limited here.

[0053] For example, assuming that according to the component features of the model to be assembled, feature data M, feature data N, feature data O and feature data P are matched from a preset feature database, then the corresponding model identifiers can be queried according to the feature identifiers M, N, O, P. Assuming that they correspond to target component model M1, target component model N1, target component model O1 and target component model P1 respectively, then M1, N1, O1 and P1 are the index information of the target component model, that is, part or all of the target component information, which is not limited here.

[0054] In this example, assuming that the model to be assembled is a suit clothing model, the queried target component model M1 may be a target component model of one style corresponding to the upper garment, and the queried target component model N1, target component model O1, and target component model P1 may be target component models of three styles corresponding to the lower garment. The number of styles corresponding to each component may be the same or different, which is not specifically limited here.

[0055] In one embodiment, in the target component information, the number of styles corresponding to each component can also be indicated by a model assembly instruction. For example, the terminal can specify that the number of styles of the upper component is 1 and the number of styles of the lower component is 3 when triggering the model assembly instruction. Then, when the component types of the model to be assembled are only upper components and lower components, in all the generated target assembly models, the styles of the upper components are the same, and the styles of the lower components are different, thereby achieving the purpose of more flexible control of model combination.

[0056] In one embodiment, in order to make the assembled model more consistent with the expected matching degree, the target matching degree of the model to be assembled can also be specified through the model assembly instruction, so that when the target component information matching the first feature data is obtained from the preset feature database, the target feature data whose matching degree with the first feature data meets the target matching degree can be obtained first, and then the corresponding target component information can be obtained according to the target feature data.

[0057] Specifically, in one embodiment, the model assembly instruction is also used to indicate the target matching degree of the model to be assembled; the matching degree of the target feature data and the first feature data meets the target matching degree; wherein the target feature data is used to indicate the feature data of the component model indicated by the target component information.

[0058] In this embodiment, the target feature data is feature data in the feature database whose matching degree with the first feature data meets the target matching degree. For example, assuming the target matching degree is 90%, meeting the target matching degree means greater than or equal to 90%. Then, the feature data of the matched target component model has a matching degree greater than or equal to 90% with the corresponding component features, so that the matching degree between the assembled model and the expected one is more controllable.

[0059] Furthermore, when obtaining the matching overall model information from the preset feature database, the matching degree between the feature data of the matched target overall model and the first feature data also meets the target matching degree. Similarly, when obtaining the matching component model information from the preset feature database, the matching degree between the feature data of the matched target component model and the first feature data also meets the target matching degree. The details will not be repeated here.

[0060] In one embodiment, the model assembly instruction can also be used to indicate a feature bearing object, and the feature bearing object can be any data format that can bear features, such as text, image, voice, etc., which is not limited here. When the first feature data of the model to be assembled is obtained through the model assembly instruction in response to the model assembly instruction, the feature bearing object indicated by the model assembly instruction is obtained in response to the model assembly instruction; wherein the feature bearing object is a prompt word, and the type of the prompt word is a text type or an image type; the first feature data of the model to be assembled is extracted from the prompt word of the text type or the image type.

[0061] It should be noted that a prompt is an input instruction used to guide the artificial intelligence model to generate output of a specific type, theme or format. The types of prompts may include text type, image type, audio type, file type, instruction type, operation type, etc. In this embodiment, the feature-bearing object is a prompt of text type or image type, which carries the features of the model to be assembled. Based on the prompt, the feature data of the model to be assembled can be extracted by the artificial intelligence model, thereby obtaining the first feature data.

[0062] For example, the client can specify an image as a feature-bearing object through a model assembly instruction. Assuming that the image contains a person wearing a suit of clothing, then the image is input into the artificial intelligence model as a prompt word to obtain the first feature data of the suit of clothing of the person in the image, which can be used for matching the component model.

[0063] It is understandable that the component type of the model to be assembled can be specified by the model assembly instruction, can be identified from the feature bearing object, or can be determined by combining the specified and identified. The following is a specific description of the component type determination method of the model to be assembled.

[0064] In one embodiment, the model assembly instruction is also used to indicate at least two first component types of the model to be assembled, and the model to be assembled can be composed of component models of at least two first component types. For example, the client can check the component types of a suit, such as tops, pants, skirts, capes, gloves, shawls, shoes, hair accessories, etc. The checked component types are sent to the server through the model assembly instruction and can be used as the target component types of the model to be assembled, so that the target component models matched subsequently also belong to the range of the target component types.

[0065] In one embodiment, at least two second component types can also be identified from the feature bearing objects indicated by the model assembly instruction, and as part of the first feature data, the model to be assembled can be composed of component models of at least two second component types. For example, if the artificial intelligence model identifies that the image submitted by the client as a feature bearing object contains tops, pants, and shoes, then these three categories can be used as target component types of the model to be assembled, so that the target component models matched subsequently also fall within the scope of the target component type.

[0066] In one embodiment, the target component type of the model to be assembled can also be determined in combination with the first component type specified by the model assembly instruction and the identified second component type. Specifically, the model assembly instruction is also used to indicate at least one first component type of the model to be assembled, and the first characteristic data also includes at least one second component type identified from the characteristic bearing object indicated by the model assembly instruction; before the step of obtaining target component information matching the first characteristic data from a preset characteristic database, at least two components constituting the model to be assembled are determined based on the first component type and the second component type.

[0067] In this embodiment, at least two components of the model to be assembled can be determined from the first component type and the second component type according to actual needs, that is, the target component type of the model to be assembled. For example, if the second component type identified by artificial intelligence has a higher confidence level, then when determining the at least two components constituting the model to be assembled, the second component type can be preferred, that is, more of the second component type is retained; otherwise, the first component type can be preferred, that is, more of the first component type is retained.

[0068] In one embodiment, in order to make the component type of the model to be assembled more accurate, the same component type in the first component type and the second component type can also be determined as the target component type of the model to be assembled. For example, assuming that the first component type includes tops, bottoms, and hats, and the second component type includes tops, bottoms, and hair accessories, then the target component type of the model to be assembled can only include tops and bottoms, which is not limited here.

[0069] In one embodiment, in order to make the component type of the model to be assembled more controllable, when determining the target component type of the model to be assembled, it is more inclined to the first component type specified by the model assembly instruction, that is, when determining at least two components constituting the model to be assembled based on the first component type and the second component type, the same component type in the first component type and the second component type, as well as the first component type, are determined as the at least two components constituting the model to be assembled.

[0070] The following is a detailed description of how to assemble the model.

[0071] In one embodiment, according to at least two components constituting the model to be assembled, target component models are assembled to obtain at least one target assembly model, and a target number of models to be assembled is obtained through a model assembly instruction; at least one target component model corresponding to each component is combined in a specified manner to obtain a component model list of the target number; the component model list includes first component models corresponding to at least two components respectively; and the first component models in each component model list are spliced ​​to obtain the target number of target assembly models.

[0072] In this embodiment, the target number of generated target assembly models can also be indicated through the model assembly instruction, so that the assembly of the model is more flexible. After obtaining the target number, one is obtained from at least one target component model corresponding to each component according to the component type, and is put into the component model list, so that each component model list contains the first component models corresponding to at least two components.

[0073] For example, assuming that the model to be assembled consists of two components, an upper body and a lower body, and the target number of models to be assembled is 5, the target component models corresponding to the upper body include upper body 1, upper body 2, upper body 3 and upper body 4, and the target component models corresponding to the lower body include lower body 1 and lower body 2. Then, when generating component model list 1, select one from upper body 1, upper body 2, upper body 3 and upper body 4 and put it into component model list 1, and select one from lower body 1 and lower body 2 and put it into component model list 1, so that component model list 1 contains component models of the two components of upper body and lower body, thereby assembling to obtain target assembly model 1. The assembly method of the remaining 4 target assembly models is the same, and the details will not be repeated here.

[0074] In one embodiment, the combination of the specified methods may be a random combination, a non-repeating arrangement and combination, or a repeatable arrangement and combination, etc., wherein the specified method may also be indicated by a model assembly instruction, so that the assembly of the model is more controllable.

[0075] In one embodiment, when the target component models corresponding to each component are less than the target number, the target component models of the corresponding component type can be supplemented from the model database so that the number of target component models corresponding to each component is greater than or equal to the target number to meet the model quantity requirement.

[0076] Furthermore, when supplementing the target component model of the corresponding component type from the model database, the target component model with a higher matching degree of feature data may be supplemented first, so that the supplemented target component model better meets the specified style requirements.

[0077] In this embodiment, after obtaining the target number of component model lists, the first component models in the component model list can be assembled / joined together to obtain the target number of target assembly models. In one embodiment, the component models in the model database are all pre-adjusted with respect to the preset reference coordinate position, such as coordinates, rotation, and scaling, according to the splicing requirements. When splicing, the same coordinates of the component models can be directly merged to obtain the target assembly model.

[0078] In one embodiment, when the first component model in each component model list is spliced ​​to obtain a target number of target assembly models, the target loading position of the target component model in each component model list is calculated according to the coordinate information, rotation information and scaling information of the target component model; the target loading positions of the target component models in each component model list are merged to obtain the target number of target assembly models.

[0079] In this embodiment, the position state information such as coordinate information, rotation information and scaling information of the target component model is first obtained, wherein these position state information can be based on a preset reference coordinate position. When calculating the target loading position, the target component models in the same component model list can all be referenced to the same preset reference coordinate position to obtain a target loading position that can be spliced, and then the coordinates of the target loading positions are merged to obtain the target assembly model.

[0080] Corresponding to the above method embodiment, see Figure 2A schematic diagram of a model assembly device is shown, the device comprising: a response module 20, for responding to a model assembly instruction, and obtaining first feature data of the model to be assembled through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; a matching module 22, for obtaining target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of at least one style of component model corresponding to each component; an acquisition module 24, for obtaining at least one target component model corresponding to each component based on the target component information; and an assembling module 26, for assembling the target component model according to the at least two components constituting the model to be assembled to obtain at least one target assembly model.

[0081] The assembly device of the above-mentioned model can indicate the overall characteristics or component characteristics of the model to be assembled through the model assembly instructions. Through these characteristics, component models of different styles can be matched to assemble assembly models of different styles, so that the style or specific requirements of the assembly model can be expressed through the instruction indication characteristics, reducing the randomness of the model assembly and improving the controllability of the model assembly.

[0082] Optionally, the matching module 22 is further used to: obtain matching overall model information from a preset feature database according to the overall features of the model to be assembled indicated by the first feature data; wherein the overall model information is used to indicate a target overall model of at least one style; and obtain index information of component models constituting the target overall model according to the overall model information to obtain target component information.

[0083] Optionally, the matching module 22 is further used to: obtain matching component model information from a preset feature database according to the component features of the model to be assembled indicated by the first feature data; wherein the component model information is used to indicate that each component corresponds to at least one style of target component model; and obtain index information of each target component model according to the component model information to obtain target component information.

[0084] Optionally, the above-mentioned response module 20 is specifically used to: respond to a model assembly instruction, obtain a feature-bearing object indicated by the model assembly instruction; wherein the feature-bearing object is a prompt word, and the type of the prompt word is a text type or an image type; extract the first feature data of the model to be assembled from the prompt word of the text type or the image type.

[0085] Optionally, the model assembly instruction is also used to indicate a target matching degree of the model to be assembled; the matching degree between the target feature data and the first feature data conforms to the target matching degree; wherein the target feature data is used to indicate feature data of the component model indicated by the target component information.

[0086] Optionally, the model assembly instruction is also used to indicate at least one first component type of the model to be assembled, and the first characteristic data also includes at least one second component type identified from the characteristic bearing object indicated by the model assembly instruction; the above-mentioned device also includes: a determination module, used to determine at least two components constituting the model to be assembled based on the first component type and the second component type.

[0087] Optionally, the above-mentioned assembly module 26 includes: an acquisition unit, used to obtain a target number of models to be assembled through the model assembly instruction; a combination unit, used to combine at least one target component model corresponding to each component in a specified manner to obtain a component model list of the target number; the component model list includes first component models corresponding to at least two components respectively; and a splicing unit, used to splice the first component models in each component model list to obtain the target assembly model of the target number.

[0088] Optionally, the above-mentioned splicing unit is specifically used to: calculate the target loading position of the target component model in each component model list according to the coordinate information, rotation information and scaling information of the target component model; merge the target loading positions of the target component model in each component model list to obtain the target number of target assembly models.

[0089] This embodiment also provides an electronic device, including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned model assembly method. The electronic device can be a server or a terminal device.

[0090] See also Figure 3 As shown, the electronic device includes a processor 100 and a memory 101. The memory 101 stores machine executable instructions that can be executed by the processor 100. The processor 100 executes the machine executable instructions to implement the above-mentioned model assembly method.

[0091] Further, Figure 3 The electronic device shown further includes a bus 102 and a communication interface 103 , and the processor 100 , the communication interface 103 and the memory 101 are connected via the bus 102 .

[0092] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0093] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 100. The above processor 100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the method of the above embodiment in combination with its hardware, for example:

[0094] In response to a model assembly instruction, first feature data of the model to be assembled is obtained through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; target component information matching the first feature data is obtained from a preset feature database; wherein the target component information includes index information of at least one style of component model corresponding to each component; based on the target component information, at least one target component model corresponding to each component is obtained; according to the at least two components constituting the model to be assembled, the target component model is assembled to obtain at least one target assembly model.

[0095] In this method, the overall characteristics or component characteristics of the model to be assembled can be indicated through the model assembly instructions. Through these characteristics, component models of different styles can be matched to assemble assembly models of different styles, so that the style or specific requirements of the assembly model can be expressed through the instruction indication features, reducing the randomness of model assembly and improving the controllability of model assembly.

[0096] Optionally, the step of obtaining target component information matching the first feature data from a preset feature database includes: obtaining matching overall model information from a preset feature database based on the overall features of the model to be assembled indicated by the first feature data; wherein the overall model information is used to indicate a target overall model of at least one style; and obtaining index information of component models constituting the target overall model based on the overall model information to obtain the target component information.

[0097] Optionally, the step of obtaining target component information matching the first feature data from a preset feature database includes: obtaining matching component model information from a preset feature database according to the component features of the model to be assembled indicated by the first feature data; wherein the component model information is used to indicate that each component corresponds to at least one style of target component model; and obtaining index information of each target component model according to the component model information to obtain the target component information.

[0098] Optionally, in response to a model assembly instruction, the step of obtaining first feature data of the model to be assembled through the model assembly instruction includes: in response to the model assembly instruction, obtaining a feature bearing object indicated by the model assembly instruction; wherein the feature bearing object is a prompt word, and the type of the prompt word is a text type or an image type; and extracting the first feature data of the model to be assembled from the prompt word of the text type or the image type.

[0099] Optionally, the model assembly instruction is also used to indicate a target matching degree of the model to be assembled; the matching degree of the target feature data and the first feature data meets the target matching degree; wherein the target feature data is used to indicate feature data of the component model indicated by the target component information.

[0100] Optionally, the model assembly instruction is also used to indicate at least one first component type of the model to be assembled, and the first characteristic data also includes at least one second component type identified from the characteristic bearing object indicated by the model assembly instruction; before the step of obtaining target component information matching the first characteristic data from a preset characteristic database, it also includes: determining at least two components constituting the model to be assembled based on the first component type and the second component type.

[0101] Optionally, the step of assembling target component models according to at least two components constituting the model to be assembled to obtain at least one target assembly model includes: obtaining a target number of models to be assembled through a model assembly instruction; combining at least one target component model corresponding to each component in a specified manner to obtain a target number of component model lists; the component model list includes first component models corresponding to at least two components respectively; and splicing the first component models in each component model list to obtain the target number of target assembly models.

[0102] Optionally, the step of splicing the first component model in each component model list to obtain a target number of target assembly models includes: calculating the target loading position of the target component model in each component model list according to the coordinate information, rotation information and scaling information of the target component model; and merging the target loading positions of the target component models in each component model list to obtain the target number of target assembly models.

[0103] This embodiment further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned model assembly method, for example:

[0104] In response to a model assembly instruction, first feature data of the model to be assembled is obtained through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; target component information matching the first feature data is obtained from a preset feature database; wherein the target component information includes index information of at least one style of component model corresponding to each component; based on the target component information, at least one target component model corresponding to each component is obtained; according to the at least two components constituting the model to be assembled, the target component model is assembled to obtain at least one target assembly model.

[0105] In this method, the overall characteristics or component characteristics of the model to be assembled can be indicated through the model assembly instructions. Through these characteristics, component models of different styles can be matched to assemble assembly models of different styles, so that the style or specific requirements of the assembly model can be expressed through the instruction indication features, reducing the randomness of model assembly and improving the controllability of model assembly.

[0106] Optionally, the step of obtaining target component information matching the first feature data from a preset feature database includes: obtaining matching overall model information from a preset feature database based on the overall features of the model to be assembled indicated by the first feature data; wherein the overall model information is used to indicate a target overall model of at least one style; and obtaining index information of component models constituting the target overall model based on the overall model information to obtain the target component information.

[0107] Optionally, the step of obtaining target component information matching the first feature data from a preset feature database includes: obtaining matching component model information from a preset feature database according to the component features of the model to be assembled indicated by the first feature data; wherein the component model information is used to indicate that each component corresponds to at least one style of target component model; and obtaining index information of each target component model according to the component model information to obtain the target component information.

[0108] Optionally, in response to a model assembly instruction, the step of obtaining first feature data of the model to be assembled through the model assembly instruction includes: in response to the model assembly instruction, obtaining a feature bearing object indicated by the model assembly instruction; wherein the feature bearing object is a prompt word, and the type of the prompt word is a text type or an image type; and extracting the first feature data of the model to be assembled from the prompt word of the text type or the image type.

[0109] Optionally, the model assembly instruction is also used to indicate a target matching degree of the model to be assembled; the matching degree of the target feature data and the first feature data meets the target matching degree; wherein the target feature data is used to indicate feature data of the component model indicated by the target component information.

[0110] Optionally, the model assembly instruction is also used to indicate at least one first component type of the model to be assembled, and the first characteristic data also includes at least one second component type identified from the characteristic bearing object indicated by the model assembly instruction; before the step of obtaining target component information matching the first characteristic data from a preset characteristic database, it also includes: determining at least two components constituting the model to be assembled based on the first component type and the second component type.

[0111] Optionally, the step of assembling target component models according to at least two components constituting the model to be assembled to obtain at least one target assembly model includes: obtaining a target number of models to be assembled through a model assembly instruction; combining at least one target component model corresponding to each component in a specified manner to obtain a target number of component model lists; the component model list includes first component models corresponding to at least two components respectively; and splicing the first component models in each component model list to obtain the target number of target assembly models.

[0112] Optionally, the step of splicing the first component model in each component model list to obtain a target number of target assembly models includes: calculating the target loading position of the target component model in each component model list according to the coordinate information, rotation information and scaling information of the target component model; and merging the target loading positions of the target component models in each component model list to obtain the target number of target assembly models.

[0113] The computer program product of the model assembly method, device, electronic device and storage medium provided in the embodiments of the present disclosure includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0115] In addition, in the description of the embodiments of the present disclosure, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present disclosure can be understood according to specific circumstances.

[0116] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0117] In the description of the present disclosure, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present disclosure and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present disclosure. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0118] Finally, it should be noted that the above embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above embodiments, those skilled in the art should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for assembling a model, characterized in that: The method comprises: In response to a model assembly instruction, first feature data of the model to be assembled is acquired through the model assembly instruction; wherein the first feature data is used to indicate the overall feature and / or component feature of the model to be assembled, and the model to be assembled is composed of models of at least two components; Obtaining target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of a component model of at least one style corresponding to each component; Based on the target component information, obtaining at least one target component model corresponding to each component; According to at least two components constituting the model to be assembled, the target component model is assembled to obtain at least one target assembly model.

2. The method according to claim 1, characterized in that The step of obtaining target component information matching the first feature data from a preset feature database comprises: According to the first feature data indicating the overall features of the model to be assembled, the matching overall model information is obtained from a preset feature database; wherein the overall model information is used to indicate a target overall model of at least one style; According to the overall model information, the index information of the component models constituting the target overall model is acquired to obtain the target component information.

3. The method according to claim 1, characterized in that The step of obtaining target component information matching the first feature data from a preset feature database comprises: According to the first feature data indicating the component features of the model to be assembled, matching component model information is acquired from a preset feature database; wherein the component model information is used to indicate that each component corresponds to at least one style of target component model; According to the component model information, the index information of each target component model is obtained to obtain the target component information.

4. The method according to claim 1, characterized in that: The step of obtaining first characteristic data of the model to be assembled through the model assembly instruction in response to the model assembly instruction includes: In response to the model assembly instruction, obtaining a feature bearing object indicated by the model assembly instruction; wherein the feature bearing object is a prompt word, and the type of the prompt word is a text type or an image type; The first feature data of the model to be assembled is extracted from the prompt words of the text type or the image type.

5. The method according to claim 1, characterized in that The model assembly instruction is also used to indicate the target matching degree of the model to be assembled; The matching degree between the target feature data and the first feature data meets the target matching degree; wherein the target feature data is used to indicate feature data of a component model indicated by the target component information.

6. The method according to claim 1, characterized in that The model assembly instruction is also used to indicate at least one first component type of the model to be assembled, and the first characteristic data also includes at least one second component type identified from the characteristic bearing object indicated by the model assembly instruction; Before the step of obtaining target component information matching the first feature data from a preset feature database, the method further includes: At least two components constituting the to-be-assembled model are determined according to the first component type and the second component type.

7. The method according to claim 1, characterized in that The step of assembling the target component model according to at least two components constituting the model to be assembled to obtain at least one target assembly model comprises: Obtaining a target number of models to be assembled through the model assembly instruction; Combining at least one target component model corresponding to each component in a specified manner to obtain a component model list of the target number; the component model list includes first component models corresponding to at least two components respectively; The first component model in each component model list is spliced ​​to obtain the target number of target assembly models.

8. The method according to claim 7, characterized in that The step of splicing the first component model in each component model list to obtain the target number of target assembly models comprises: Calculating a target loading position of a target component model in each component model list according to coordinate information, rotation information and scaling information of the target component model; The target loading positions of the target component models in each component model list are merged to obtain the target number of target assembly models.

9. A model assembly device, characterized in that: The device comprises: A response module, used to respond to a model assembly instruction and obtain first characteristic data of a model to be assembled through the model assembly instruction; wherein the first characteristic data is used to indicate an overall characteristic and / or a component characteristic of the model to be assembled, and the model to be assembled is composed of models of at least two components; A matching module, used to obtain target component information matching the first feature data from a preset feature database; wherein the target component information includes index information of a component model corresponding to at least one style for each component; An acquisition module, used for acquiring at least one target component model corresponding to each component based on the target component information; The assembly module is used to assemble the target component model according to at least two components constituting the model to be assembled, so as to obtain at least one target assembly model.

10. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the model assembling method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the model assembly method described in any one of claims 1-8.

Images