A method and system for generating splicable models based on artificial intelligence technology

Abstract

The present invention belongs to the technical field of computer-aided design. A method and system for generating a splicable model based on artificial intelligence technology is provided. The method comprises: shooting first image data of a target object from multiple angles, extracting second image data associated with the target object from each first image data; extracting three-dimensional structure data of the target object based on each second image data, stereoscopically splicing each three-dimensional structure data to obtain a three-dimensional model of the target object; inputting the three-dimensional model into a decomposition model based on artificial intelligence to obtain a number of three-dimensional sub-models. The present invention realizes the rapid generation of a three-dimensional splicable model through image recognition and artificial intelligence technology, without the need to manually measure the size data of the target object in the real world, and greatly improves the generation efficiency of the three-dimensional splicable model.

Description

Technical Field

[0001] The present invention relates to the technical field of computer-aided design, and in particular to a method and system for generating a splicable model based on artificial intelligence technology. Background Art

[0002] 3D splicing building blocks are becoming more and more popular among customers, and people of all ages can get a good experience from using 3D splicing building blocks. In order to further improve the realism of 3D splicing building blocks, it is generally necessary to produce them in proportion to real objects. A well-known building is reduced in proportion to 1:128, and then the building is cut into corresponding blocks to construct 3D splicing building blocks. However, the size data of the real object still needs to be obtained manually, and the artificial data of many real objects is difficult to obtain, which is not conducive to the rapid production of 3D splicing building blocks. The present invention aims to solve this technical problem. Summary of the invention

[0003] In this regard, the present invention provides a method, system, electronic device, computer storage medium and computer program product for generating a splicable model based on artificial intelligence technology to solve the above-mentioned technical problems.

[0004] The present invention discloses a method for generating a splicable model based on artificial intelligence technology, the method comprising the following steps:

[0005] Taking first image data of a target object from multiple angles, and extracting second image data associated with the target object from each of the first image data;

[0006] Extracting three-dimensional structure data of the target object based on each of the second image data, and stereoscopically stitching each of the three-dimensional structure data to obtain a three-dimensional model of the target object;

[0007] The three-dimensional model is input into a decomposition model based on artificial intelligence to obtain a plurality of three-dimensional sub-models.

[0008] In some embodiments, the multi-angle first image data of the target object includes:

[0009] Shooting first image data of the target object from a front angle, and extracting first three-dimensional structure data based on the first image data;

[0010] Analyzing the structural complexity of the target object according to the first three-dimensional structure data, and determining a number of angles according to the structural complexity when the structural complexity is higher than a complexity threshold;

[0011] The first image data of multiple angles of the target object is captured according to each of the angles.

[0012] In some embodiments, analyzing the structural complexity of the target object according to the first three-dimensional structure data includes: ; In the formula, Represents the structural complexity of the frontal angle of the target object, A normalized representation value representing the relevant parameters of the protruding structure extracted from the first image data at the front angle of the target object, a normalized representation value representing a parameter related to a shadow feature extracted from the first image data at a front angle of the target object, For The associated adjustment value.

[0013] In some embodiments, extracting the three-dimensional structure data of the target object based on each of the second image data includes:

[0014] Preprocessing the second image data to identify non-target objects therein;

[0015] The three-dimensional structure data of each target object is obtained by performing structure extension processing on the second three-dimensional structure data of the surroundings of each non-target object.

[0016] In some embodiments, the three-dimensional structure data are stereoscopically stitched together to obtain the three-dimensional model of the target object, including:

[0017] Stereoscopically stitching the three-dimensional structure data to obtain a first three-dimensional model of the target object, and performing a closure analysis on the first three-dimensional model to obtain a closure representation value;

[0018] When the closure representation value is higher than a closure threshold, using the first three-dimensional model as the three-dimensional model of the target object;

[0019] When the closedness representation value is lower than the closedness threshold, the accessibility of the network resources of the target object is evaluated according to the attributes of the target object;

[0020] If the availability is high, obtaining third image data of the target object through network resources, and fusing the three-dimensional structure data extracted from the third image data with the first three-dimensional model to obtain a second three-dimensional model;

[0021] If the availability is low, outputting the first three-dimensional model to prompt the user to take a plurality of fourth image data of the target object at a second angle, and fusing the three-dimensional structure data extracted from the fourth image data with the first three-dimensional model to obtain a second three-dimensional model;

[0022] The second three-dimensional model is used as the three-dimensional model of the target object.

[0023] In some embodiments, the inputting the three-dimensional model into the decomposition model based on artificial intelligence to obtain a plurality of three-dimensional sub-models includes:

[0024] Pre-segmenting the three-dimensional model based on the decomposition model of artificial intelligence to obtain a plurality of first three-dimensional sub-models and the three-dimensional model with segmentation dashed lines;

[0025] Receiving a user's instruction to adjust the split dotted line, the decomposition model re-segments the three-dimensional model to obtain a plurality of second three-dimensional sub-models and the three-dimensional model with the split dotted line;

[0026] After receiving the user's confirmation signal, each of the second three-dimensional sub-models is numbered, and the inner connection components of adjacent second three-dimensional sub-models are determined according to the component connection rule library, and each of the inner connection components is synthesized into the corresponding second three-dimensional sub-model.

[0027] The present invention also discloses a splicable model generation system based on artificial intelligence technology, the system comprises a shooting module, a processing module, and a storage module, the processing module is electrically connected to the storage module and the shooting module respectively;

[0028] The shooting module is used to shoot multi-angle image data of the target object and transmit the image data to the processing module;

[0029] The storage module is used to store computer programs;

[0030] The processing module is used to call and execute the computer program in the storage module to perform any of the above methods to achieve the generation of a splicable model.

[0031] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0032] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0033] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0034] The beneficial effects of the present invention are:

[0035] The present invention realizes the rapid generation of three-dimensional spliceable models through image recognition and artificial intelligence technology, without the need to manually measure the size data of target objects in the real world, thereby greatly improving the generation efficiency of three-dimensional spliceable models. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flowchart of a method for generating a splicable model based on artificial intelligence technology disclosed in an embodiment of the present invention;

[0038] Figure 2 It is a schematic diagram of an example of a three-dimensional splicable model of a target object implemented according to the solution of the present invention;

[0039] Figure 3 It is a structural schematic diagram of a splicable model generation system based on artificial intelligence technology disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0041] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0042] like Figure 1-Figure 2 As shown, the embodiment of the present invention discloses a method for generating a splicable model based on artificial intelligence technology, and the method comprises the following steps:

[0043] Shooting first image data of a target object from multiple angles, and extracting second image data associated with the target object from each of the first image data;

[0044] Extracting three-dimensional structure data of the target object based on each of the second image data, and stereoscopically stitching each of the three-dimensional structure data to obtain a three-dimensional model of the target object;

[0045] The three-dimensional model is input into a decomposition model based on artificial intelligence to obtain a plurality of three-dimensional sub-models.

[0046] In view of the technical problems mentioned in the background technology, the present invention first uses a camera device to capture the first image data of the target object in the real world from multiple angles (such as the front, side, back, etc.), identifies the pixel area of ​​the target object, and then extracts the three-dimensional structure data of the target object at the corresponding angle. The three-dimensional structure data are stereoscopically spliced ​​to obtain a three-dimensional model of the target object. Finally, the three-dimensional model of the target object is decomposed according to certain rules using a decomposition model based on artificial intelligence, that is, a plurality of splicing blocks are obtained. In this way, the rapid generation of a three-dimensional splicable model is achieved, without the need to manually measure the size data of the target object in the real world, which greatly improves the generation efficiency of the three-dimensional splicable model.

[0047] The three-dimensional structure data extracted above includes structural features and corresponding size features, both of which can be extracted through image recognition technology. Since it belongs to relatively mature existing technologies, the present invention will not go into details.

[0048] In some embodiments, the multi-angle first image data of the target object includes:

[0049] Shooting first image data of the target object from a front angle, and extracting first three-dimensional structure data based on the first image data;

[0050] Analyzing the structural complexity of the target object according to the first three-dimensional structure data, and determining a number of angles according to the structural complexity when the structural complexity is higher than a complexity threshold;

[0051] The first image data of multiple angles of the target object is captured according to each of the angles.

[0052] In order to extract the three-dimensional structural features of the target object more comprehensively and accurately, it is necessary to shoot the image of the target object from as many angles as possible, but shooting at too many angles will increase the manual load, and shooting at certain angles may be limited by the geographical environment and cannot be achieved. In this regard, the present invention first shoots the first image data of the front angle of the target object. The front angle can represent the significant structural features of the target object and the most complex structural features are generally located at the front angle. The number of shooting angles required is determined based on the relationship between the structural complexity extracted from the front angle and the complexity threshold.

[0053] An example is as follows: if the first three-dimensional structural data of the target object indicates that it has fewer protruding structures and lower protruding heights, then its structural complexity is determined to be low, otherwise, its structural complexity is determined to be high. When the structural complexity of the target object is high, image data from more angles is required to analyze its three-dimensional structural features. Among them, the structural complexity can also take into account the shadow features in the first image data at the first angle. Some protruding structures cannot be directly extracted, and in this case, the shadow features can be used for analysis.

[0054] The shooting angles may be spaced at fixed angles (eg, 60°), or the size of the fixed angles may be determined according to the complexity of the structure. Generally, the higher the complexity of the structure, the smaller the fixed angles.

[0055] In some embodiments, analyzing the structural complexity of the target object according to the first three-dimensional structure data includes: ; In the formula, Represents the structural complexity of the frontal angle of the target object, A normalized representation value representing the relevant parameters of the protruding structure extracted from the first image data at the front angle of the target object, a normalized representation value representing a parameter related to a shadow feature extracted from the first image data at a front angle of the target object, For The associated adjustment value.

[0056] The structural complexity of the target object is directly related to the relevant parameters of the protrusion structure (mainly the number of protrusions and the height of the protrusions). The corresponding characterization value can be calculated based on these relevant parameters, but the characterization value needs to be normalized first. At the same time, some protrusion structures cannot be extracted through image recognition, such as a small protrusion that is completely opposite to the camera lens. In this case, the relevant parameters of the protrusion can be inferred from the shadow, but the shadow feature includes both the protrusions that have not been recognized by the image and the protrusions that have been recognized by the image, so the normalized characterization value of the relevant parameters of the shadow feature (mainly the area and maximum length of the shadow) needs to be appropriately lowered. Specifically, the parameter " " to achieve it.

[0057] In some embodiments, extracting the three-dimensional structure data of the target object based on each of the second image data includes:

[0058] Preprocessing the second image data to identify non-target objects therein;

[0059] The three-dimensional structure data of each target object is obtained by performing structure extension processing on the second three-dimensional structure data of the surroundings of each non-target object.

[0060] The outer contour of the target object can be extracted from the first image data, so that the pixels located in the outer contour are classified as the target object. However, since the first image data taken is an image of the target object in the real world, the second image data will contain non-target objects such as road signs, pedestrians, and banners. In order to ensure that the extracted three-dimensional structural data is true, it is necessary to pre-process the second image data, identify the non-target objects therein, and remove them. At the same time, if the non-target objects are directly removed, more holes will appear in the second image data, and the obtained three-dimensional structural data will be incomplete. In this regard, the present invention is based on the structural extension processing of the second three-dimensional structural data of the surroundings of each non-target object, that is, according to the second three-dimensional structural data belonging to the target object of the surroundings of the non-target object in the second image data, the structural trend, color characteristics, etc. of the target object in the area are determined, and the extension calculation is performed to the area where the non-target object is located according to these characteristics, thereby avoiding the appearance of the above-mentioned holes, and the authenticity of the three-dimensional structural data of the target object can be maintained as much as possible.

[0061] The recognition of non-target objects can be achieved through a pre-trained recognition model, and there is no specific limitation.

[0062] In some embodiments, the three-dimensional structure data are stereoscopically stitched together to obtain the three-dimensional model of the target object, including:

[0063] Stereoscopically stitching the three-dimensional structure data to obtain a first three-dimensional model of the target object, and performing a closure analysis on the first three-dimensional model to obtain a closure representation value;

[0064] When the closure representation value is higher than a closure threshold, using the first three-dimensional model as the three-dimensional model of the target object;

[0065] When the closedness representation value is lower than the closedness threshold, the accessibility of the network resources of the target object is evaluated according to the attributes of the target object;

[0066] If the availability is high, obtaining third image data of the target object through network resources, and fusing the three-dimensional structure data extracted from the third image data with the first three-dimensional model to obtain a second three-dimensional model;

[0067] If the availability is low, outputting the first three-dimensional model to prompt the user to take a plurality of fourth image data of the target object at a second angle, and fusing the three-dimensional structure data extracted from the fourth image data with the first three-dimensional model to obtain a second three-dimensional model;

[0068] The second three-dimensional model is used as the three-dimensional model of the target object.

[0069] The above-mentioned method discloses determining the first image data of multiple angles that need to be shot by the structural complexity represented by the first image data of the front angle, but the angles involved may not be able to achieve complete coverage of the target object, for example, the image data of the back and top surfaces are missing, which will cause the three-dimensional model obtained by subsequent splicing to be non-closed or incomplete, which is not conducive to the decomposition model to decompose the usable three-dimensional sub-models therefrom. In this regard, the present invention first performs stereo splicing according to the extracted three-dimensional structural data to preliminarily obtain the first three-dimensional model of the target object, and then analyzes its closure. If the closure is high enough, it means that the first image data shot by the user has covered the full-view structure of the target object, and the first three-dimensional model is used as the final three-dimensional model. If the closure is not enough, it means that the first image data shot by the user has not yet covered the full-view structure of the target object, and it is necessary to further use network resources or prompt the user to take further photos to fill in the gaps in the three-dimensional model.

[0070] Specifically, the attributes of the target object are first evaluated to evaluate the accessibility of its network resources, and the attributes mainly involve the identity attributes represented by the first image data of the target object. Figure 2 In the "Tsinghua Garden" and "School Gate", we can analyze that Figure 2 If the network resource availability of the target object is high, the third image data related to the missing part can be directly searched through the network resources, and the corresponding three-dimensional structure data can be determined based on the color, line size and trend of the missing part represented in the third image data, and then supplemented to the first three-dimensional model obtained above. If the identity attribute of the target object is not represented in the first image data, the first three-dimensional model is further output to the user, and a prompt for supplementary shooting is given, so that the user can know which part is missing from the first three-dimensional model, and then change the shooting point to shoot, so as to supplement the first three-dimensional model.

[0071] The closedness threshold can be determined according to the type attribute of the target object itself. For example, when the type attribute of the target object itself is a building, due to the existence of windows, etc., its own closedness will be low, and the corresponding closedness threshold is set to be low; while for target objects such as sculptures, their own closedness is generally high, so the corresponding closedness threshold is set to be high. Specifically, a comparison table of various target object types and corresponding closedness thresholds can be established, which will not be described in detail.

[0072] In some embodiments, the inputting the three-dimensional model into the decomposition model based on artificial intelligence to obtain a plurality of three-dimensional sub-models includes:

[0073] Pre-segmenting the three-dimensional model based on the decomposition model of artificial intelligence to obtain a plurality of first three-dimensional sub-models and the three-dimensional model with segmentation dashed lines;

[0074] Receiving a user's instruction to adjust the split dotted line, the decomposition model re-segments the three-dimensional model to obtain a plurality of second three-dimensional sub-models and the three-dimensional model with the split dotted line;

[0075] After receiving the user's confirmation signal, each of the second three-dimensional sub-models is numbered, and the inner connection components of adjacent second three-dimensional sub-models are determined according to the component connection rule library, and each of the inner connection components is synthesized into the corresponding second three-dimensional sub-model.

[0076] The decomposition model based on artificial intelligence in the present invention first pre-segments the three-dimensional model obtained above, and after the pre-segmentation, a plurality of first three-dimensional sub-models displayed separately and the corresponding segmentation dotted lines drawn in the original three-dimensional model are obtained. The user can adjust and confirm the segmentation dotted lines in the three-dimensional model according to his own design requirements. The decomposition model is segmented twice to obtain the final second three-dimensional sub-model. In addition, the three-dimensional sub-model obtained by decomposition also includes numbers and internal connection components, wherein the numbers are mainly used to assist customers in improving the splicing rate, and the internal connection components are used to connect the splicing blocks to each other, and are generally arranged inside rather than directly exposed. For the internal connection components, the internal connection components that should be used by adjacent second three-dimensional sub-models can be determined based on the pre-designed component connection rule library, and the internal connection components are used to connect the second three-dimensional sub-models.

[0077] like Figure 3 As shown, the embodiment of the present invention also discloses a splicable model generation system based on artificial intelligence technology, the system includes a shooting module, a processing module, and a storage module, the processing module is electrically connected to the storage module and the shooting module respectively;

[0078] The shooting module is used to shoot multi-angle image data of the target object and transmit the image data to the processing module;

[0079] The storage module is used to store computer programs;

[0080] The processing module is used to call and execute the computer program in the storage module to perform the method described in the above embodiment to achieve the generation of the splicable model.

[0081] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.

[0082] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is characterized in that: the computer program is executed by a processor to implement the method described in the above embodiment.

[0083] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0084] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including 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 methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0090] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for generating a splicable model based on artificial intelligence technology, characterized in that: The method comprises the following steps: Taking first image data of a target object from multiple angles, and extracting second image data associated with the target object from each of the first image data; Extracting three-dimensional structure data of the target object based on each of the second image data, and stereoscopically stitching each of the three-dimensional structure data to obtain a three-dimensional model of the target object; Inputting the three-dimensional model into a decomposition model based on artificial intelligence to obtain a plurality of three-dimensional sub-models; The first image data of the target object captured from multiple angles includes: Shooting first image data of the target object from a front angle, and extracting first three-dimensional structure data based on the first image data; Analyzing the structural complexity of the target object according to the first three-dimensional structure data, and determining a number of angles according to the structural complexity when the structural complexity is higher than a complexity threshold; The first image data of multiple angles of the target object is captured according to each of the angles; The analyzing the structural complexity of the target object according to the first three-dimensional structure data includes: ; In the formula, Represents the structural complexity of the frontal angle of the target object, A normalized representation value representing the relevant parameters of the protruding structure extracted from the first image data at the front angle of the target object, a normalized representation value representing a parameter related to a shadow feature extracted from the first image data at a front angle of the target object, For The associated adjustment value.

2. The method for generating a splicable model based on artificial intelligence technology according to claim 1, characterized in that: Extracting and obtaining the three-dimensional structure data of the target object based on each of the second image data includes: Preprocessing the second image data to identify non-target objects therein; The three-dimensional structure data of each target object is obtained by performing structure extension processing on the second three-dimensional structure data of the surroundings of each non-target object.

3. The method for generating a splicable model based on artificial intelligence technology according to claim 2, characterized in that: The three-dimensional structure data are stereoscopically spliced ​​to obtain a three-dimensional model of the target object, including: Stereoscopically stitching the three-dimensional structure data to obtain a first three-dimensional model of the target object, and performing a closure analysis on the first three-dimensional model to obtain a closure representation value; When the closure representation value is higher than a closure threshold, using the first three-dimensional model as the three-dimensional model of the target object; When the closedness representation value is lower than the closedness threshold, the accessibility of the network resources of the target object is evaluated according to the attributes of the target object; If the availability is high, obtaining third image data of the target object through network resources, and fusing the three-dimensional structure data extracted from the third image data with the first three-dimensional model to obtain a second three-dimensional model; If the availability is low, outputting the first three-dimensional model to prompt the user to take a plurality of fourth image data of the target object at a second angle, and fusing the three-dimensional structure data extracted from the fourth image data with the first three-dimensional model to obtain a second three-dimensional model; The second three-dimensional model is used as the three-dimensional model of the target object.

4. The method for generating a splicable model based on artificial intelligence technology according to claim 1, characterized in that: The three-dimensional model is input into a decomposition model based on artificial intelligence to obtain a number of three-dimensional sub-models, including: Pre-segmenting the three-dimensional model based on the decomposition model of artificial intelligence to obtain a plurality of first three-dimensional sub-models and the three-dimensional model with segmentation dashed lines; Receiving a user's instruction to adjust the split dotted line, the decomposition model re-segments the three-dimensional model to obtain a plurality of second three-dimensional sub-models and the three-dimensional model with the split dotted line; After receiving the user's confirmation signal, each of the second three-dimensional sub-models is numbered, and the inner connection components of adjacent second three-dimensional sub-models are determined according to the component connection rule library, and each of the inner connection components is synthesized into the corresponding second three-dimensional sub-model.

5. A splicable model generation system based on artificial intelligence technology, the system comprising a shooting module, a processing module, and a storage module, wherein the processing module is electrically connected to the storage module and the shooting module respectively; The shooting module is used to shoot multi-angle image data of the target object and transmit the image data to the processing module; The storage module is used to store computer programs; Features: The processing module is used to call and execute the computer program in the storage module to perform the method according to any one of claims 1 to 4 to achieve the generation of a splicable model.

6. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 4.

7. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that: When the computer program product runs on a terminal, the terminal implements the method according to any one of claims 1 to 4.

Images