A Search Method and System for a Part

Abstract

The present invention provides a method and a system for searching parts, relating to the technical field of computer technology. The method uses an algorithm model to convert part feature information (including geometric structure, material properties, machining process information, etc.) into feature vectors, and the steps are as follows: Step 1, training the algorithm model for converting historical part feature information; Step 2, saving the trained model and historical part feature vectors, and constructing a historical feature vector library; Step 3, inputting the feature information of the part to be searched into the trained model to obtain a feature vector; Step 4, calculating the similarity between the feature vector of the part to be searched and all parts in the historical part feature vector library; Step 5, judging and outputting the search result. The present invention solves the technical problem of low retrieval accuracy in part retrieval in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of computer technology, and in particular, to a method and system for searching parts. Background Art

[0002] In the product development process of the mechanical design industry, there is a large amount of repetitive design (i.e., reusing past component designs), while new designs only account for a small part. Therefore, it is one of the keys to improving design efficiency and shortening the development cycle to simply, quickly, and accurately search for similar part models from the database and modify them.

[0003] The traditional method for searching parts is that designers pre-label each part, add some index information, classify them into different categories, and then search through keywords to achieve part indexing.

[0004] Due to the traditional method: designers need to label all parts, and new parts designed subsequently also need to be operated in this way, which is a long-term time-consuming and laborious task; the part labeling rules are usually relatively simple, and the retrieval results are not accurate enough; the retrieved results are often multiple, and designers still need to perform final screening, resulting in low retrieval accuracy and low retrieval efficiency for part retrieval.

[0005] In view of the above problems, no effective solution has been proposed yet. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to provide a method and system for searching parts to alleviate the technical problem of low retrieval accuracy in part retrieval in the prior art.

[0007] In the first aspect, an embodiment of the present invention provides a method for searching parts, including the following steps: Step 1, training an algorithm model for converting historical part feature information into feature vectors; Step 2, obtaining historical part feature vectors by using the trained model and constructing a historical part feature vector library; Step 3, inputting the feature information of the part to be searched into the trained model to obtain a feature vector; Step 4, calculating the similarity, that is, the vector distance, between the feature vector of the part to be searched and all historical part feature vectors in the historical part feature vector library; Step 5, determining a target feature vector based on the vector distance, and determining the historical part corresponding to the target feature vector as the search result.

[0008] Further, the part feature information includes geometric structure, material properties, and processing technology information.

[0009] Further, in Step 1, the historical part feature vectors are converted from part feature information by the algorithm model.

[0010] Further, the part feature information includes the geometric structure feature information of the part converted into an N*3 array representation, the material property feature information converted into a one-hot encoding representation of N*M1, and the processing technology feature information converted into a one-hot encoding representation of N*M2.

[0011] Further, training the part feature information conversion algorithm model includes the following steps: establishing a feature information library of historical parts, constructing a network model with an encoding-decoding structure, where the output of the encoding layer is the feature vector of the part; training the information conversion model to learn the mapping relationship between the historical part feature information and the feature vector; evaluating, optimizing, and outputting the trained information conversion model.

[0012] Further, the similarity between the feature vector of the part to be searched in step three and the historical part feature vectors includes the similarities in three aspects: geometric structure, material properties, and processing technology.

[0013] Further, during the training process of the network model with an encoding-decoding structure, the loss function Loss includes three dimensions. Among them, the loss function for geometric structure reconstruction is the chamfer distance (Loss1), the loss function for material properties is the Euclidean distance (Loss2), and the loss function for processing technology is the Euclidean distance (Loss3).

[0014] In the second aspect, an embodiment of the present invention further provides a part search system, including: a training unit, a construction unit, an acquisition unit, a calculation unit, and an output unit. Among them, the training unit is used to train the algorithm model for converting historical part feature information into feature vectors; the construction unit uses the trained model to obtain historical part feature vectors and constructs a historical part feature vector library; the acquisition unit is used to input the feature information of the part to be searched into the trained algorithm model to obtain the feature vector of the part to be searched; the calculation unit is used to calculate the distance between the feature vector of the part to be searched and the part feature vectors in the historical part feature vector library; the output unit determines the target feature vector according to the distance between the feature vectors and outputs the historical part corresponding to the target feature vector as the search result.

[0015] In the third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor. The memory is used to store a program that supports the processor to execute the method described in the first aspect above, and the processor is configured to execute the program stored in the memory.

[0016] In the fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, it executes the steps of the method described in the first aspect.

[0017] In an embodiment of the present invention, by obtaining the feature information of the part to be searched; inputting the feature information of the part to be searched into the part feature information conversion algorithm model to obtain the feature vector of the part to be searched; calculating the vector distance between the feature vector of the part to be searched and all historical part feature vectors in the historical part feature vector library; based on the vector distance, determining the target feature vector, and determining the part corresponding to the target feature vector as the search result, where the target feature vector is the historical part feature vector corresponding to the minimum vector distance, the purpose of using the learning model for part search is achieved, thereby solving the technical problem of low retrieval accuracy in part retrieval in the prior art, and thus realizing the technical effect of improving the retrieval accuracy of part retrieval.

[0018] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by practicing the present invention. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the specification, the claims, and the drawings.

[0019] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. Brief Description of the Drawings

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a flowchart of a method for searching parts provided by an embodiment of the present invention;

[0022] Figure 2 It is a schematic diagram of a part matching process provided by an embodiment of the present invention;

[0023] Figure 3 It is a schematic diagram of a system for searching parts provided by an embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0025] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0026] Embodiment 1:

[0027] According to an embodiment of the present invention, an embodiment of a method for searching for parts is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0028] Figure 1 is a flowchart of a method for searching for parts according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0029] Step S102, Step 1: Training an algorithm model for converting historical part feature information into feature vectors;

[0030] Step S104, Step 2: Obtaining historical part feature vectors by using the trained model and constructing a historical part feature vector library;

[0031] Step S106, Step 3: Inputting the feature information of the part to be searched into the trained model to obtain a feature vector;

[0032] Step S108, Step 4: Calculating the similarity, i.e., the vector distance, between the feature vector of the part to be searched and all the historical part feature vectors in the historical part feature vector library;

[0033] Step S110, Step 5: Determining a target feature vector based on the vector distance and determining the historical part corresponding to the target feature vector as the search result.

[0034] In an embodiment of the present invention, by obtaining the feature information of the part to be searched; inputting the feature information of the part to be searched into the part feature information conversion algorithm model to obtain the feature vector of the part to be searched; calculating the vector distance between the feature vector of the part to be searched and the historical part feature vectors; based on the vector distance, determining the target feature vector, and determining the part corresponding to the target feature vector as the search result, where the target feature vector is the historical part feature vector corresponding to the minimum vector distance, the purpose of using the learning model for part search is achieved, and further, the technical problem of low retrieval accuracy in part retrieval in the prior art is solved, thereby realizing the technical effect of improving the retrieval accuracy of part retrieval.

[0035] The following will be combined with Figure 2 to illustrate the above steps.

[0036] Algorithm model training for converting historical part feature information into feature vectors;

[0037] Using the trained model to obtain historical part feature vectors and constructing a historical part feature vector library;

[0038] Inputting the feature information of the part to be searched into the part feature information conversion algorithm model to obtain the feature vector of the part to be searched;

[0039] Calculating the vector distance between the feature vector of the part to be searched and all historical part feature vectors in the historical part feature vector library;

[0040] It should be noted that the vector distance between the feature vector of the part to be searched and the historical part feature vector can be calculated using the Euclidean distance formula. Specifically, the vector distance , where is the th element in the feature vector of the part to be searched, is the th element in any historical part feature vector.

[0041] Based on the vector distance, determining the target feature vector, and determining the part corresponding to the target feature vector as the search result, where the target feature vector is the historical part feature vector corresponding to the minimum vector distance.

[0042] In an embodiment of the present invention, the part feature information conversion algorithm model includes an encoding unit and a decoding unit, and the method further includes the following steps:

[0043] Step S201, inputting the feature information of the historical part into the encoding unit of the initial learning model to determine the feature vector of the historical part;

[0044] Step S202: Use the decoding unit of the initial learning model to reconstruct the feature vector of the historical part to obtain the reconstructed historical part feature information.

[0045] Step S203: Use the feature information difference between the historical part and the reconstructed historical part to optimize the initial learning model to obtain the part feature information conversion algorithm model.

[0046] In an embodiment of the present invention, first, input the historical part feature information into the encoding unit of the initial learning model to extract the feature vector of the historical part.

[0047] Then, use the decoding unit of the initial learning model to reconstruct the feature vector of the historical part to obtain the reconstructed historical part feature information.

[0048] Finally, use the feature information difference between the historical part and the reconstructed historical part to optimize the initial learning model to obtain the part feature information conversion algorithm model.

[0049] It should be noted that the above historical parts and their corresponding feature encodings can be added to the database to obtain a part feature vector library, and the part feature information conversion algorithm model uses an unsupervised deep learning algorithm.

[0050] In an embodiment of the present invention, step S203 includes the following steps:

[0051] Step S11: Calculate the geometric structure information loss between the geometric structure feature information of the historical part and the geometric structure feature information of the reconstructed historical part.

[0052] Step S12: Calculate the attribute information loss between the material attribute feature information of the historical part and the material attribute feature information of the reconstructed historical part.

[0053] Step S13: Calculate the process information loss between the processing technology feature information of the historical part and the processing technology feature information of the reconstructed historical part.

[0054] Step S14: Based on the geometric structure information loss, the material attribute information loss, and the processing technology information loss, calculate the final loss between the historical part and the reconstructed historical part.

[0055] Step S15: Use the final loss to optimize the initial learning model to obtain the part feature information conversion algorithm model.

[0056] It should be noted that the loss function for the loss of geometric structure information is the chamfer distance loss function; the loss functions for the loss of material property information and processing technology information are the Euclidean distance loss functions.

[0057] In the embodiment of the present invention, as Figure 3 shown, the loss of geometric structure information can be represented by the chamfer distance, and the chamfer distance loss function is , where is the point cloud set of the historical part, is the point cloud set of the reconstructed historical part, is any point in the point cloud set of the historical part, is any point in the point cloud set of the reconstructed historical part.

[0058] The loss of material property information and processing technology information can be represented by the Euclidean distance, and the Euclidean distance loss function is , where is the th element of the material property (processing technology) information of the historical part, is the th element of the material property (processing technology) information of the reconstructed historical part.

[0059] According to the loss of geometric structure information, material property information, and processing technology information, the final loss between the feature vector of the historical part and the feature vector of the reconstructed historical part can be obtained. The loss function of the final loss is Loss = a * Loss1 + b * Loss2 + c * Loss3 (where a, b, and c are the coefficients of the three loss functions respectively).

[0060] Finally, using the final loss, the initial learning model is optimized to obtain the part feature information conversion algorithm model.

[0061] In the embodiment of the present invention, step S108 includes the following steps:

[0062] Step S21, determining the index of the target feature vector in the part feature vector library;

[0063] Step S22, based on the index, obtaining the part corresponding to the target feature vector, and determining the historical part corresponding to the target feature vector as the search result.

[0064] In the embodiments of the present invention, the above-mentioned historical connection feature vectors are all stored in the part feature vector library, and each historical part feature vector and the part model corresponding to each historical part feature vector are configured with corresponding indexes in the part feature vector library. Therefore, after determining the target feature vector, the part corresponding to the target feature vector can be determined according to the index corresponding to the target feature vector, and the historical part corresponding to the target feature vector is determined as the search result.

[0065] Using the part search method provided by the embodiments of the present invention, designers do not need to spend a lot of time on data annotation, nor do they need to sort out the design logic of parts. They only need to have the original 3D parts and the corresponding material properties and processing technology information.

[0066] The part search method provided by the embodiments of the present invention automatically extracts the features of 3D parts and constructs a part vector library by inputting sample 3D part models and their corresponding material properties and processing technology information through AI learning. When a new 3D part is input, the most similar part in the part library is judged by comparing the part geometry, material properties and processing technology features, which can effectively improve the accuracy of part search and at the same time improve the search efficiency of part search.

[0067] Embodiment Two:

[0068] The embodiments of the present invention also provide a part search system, which is used to execute the part search method provided in the above content of the embodiments of the present invention. The following is a specific introduction to the part search system provided by the embodiments of the present invention.

[0069] As Figure 2 shown, Figure 2 is a schematic diagram of the above-mentioned part search system. The part search system includes: a training unit 10, a construction unit 20, an acquisition unit 30, a calculation unit 40 and an output unit 50.

[0070] The training unit 10 is used for training the algorithm model that converts historical part feature information into feature vectors;

[0071] The construction unit 20 uses the trained model to obtain historical part feature vectors and constructs a historical part feature vector library;

[0072] The acquisition unit 30 is used to input the feature information of the part to be searched into the trained algorithm model to obtain the feature vector of the part to be searched;

[0073] The calculation unit 40 is used to calculate the distance between the feature vector of the part to be searched and the part feature vectors in the historical part feature vector library;

[0074] The output unit 50 determines a target feature vector according to the distance between the feature vectors, and determines the historical part corresponding to the target feature vector as the search result for output.

[0075] In an embodiment of the present invention, by obtaining the feature information of the part to be searched; inputting the feature information of the part to be searched into the part feature information conversion algorithm model to obtain the feature vector of the part to be searched; calculating the vector distance between the feature vector of the part to be searched and the feature vectors of all historical parts; based on the vector distance, determining a target feature vector, and determining the part corresponding to the target feature vector as the search result, where the target feature vector is the historical part feature vector corresponding to the minimum value of the vector distance, the purpose of using the learning model for part search is achieved, and further the technical problem of low retrieval accuracy of part retrieval in the prior art is solved, thereby realizing the technical effect of improving the retrieval accuracy of part retrieval.

[0076] Further, the part feature information includes geometric structure, material properties, and processing technology information.

[0077] Further, in step one, the historical part feature vector is converted from the part feature information by the algorithm model.

[0078] Further, the part feature information includes that the geometric structure feature information of the part is converted into an array representation of N*3, the material property feature information is converted into a one-hot encoding representation of N*M1, and the processing technology feature information is converted into a one-hot encoding representation of N*M2.

[0079] Further, training the part feature information conversion algorithm model includes the following steps: Step (1), establishing a feature information library of historical parts, constructing a network model with an encoding-decoding structure, where the output of the encoding layer is the feature vector of the part; Step (2), training the information conversion model to learn the mapping relationship between the historical part feature information and the feature vector; Step (3), evaluating, optimizing, and outputting the trained information conversion model.

[0080] Further, the similarity between the feature vector of the part to be searched and the historical part feature vector in step three includes the similarities in three aspects: geometric structure, material properties, and processing technology.

[0081] Further, during the training process of the network model with an encoding-decoding structure, the loss function Loss includes three dimensions, where the loss function for geometric structure reconstruction is the chamfer distance (Loss1), the loss function for material properties is the Euclidean distance (Loss2), and the loss function for processing technology is the Euclidean distance (Loss3).

[0082] Embodiment Three:

[0083] An embodiment of the present invention further provides an electronic device, including a memory and a processor. The memory is used to store a program that supports the processor to execute the method described in the first embodiment above, and the processor is configured to execute the program stored in the memory.

[0084] Refer to Figure 4 , an embodiment of the present invention further provides an electronic device 100, including: a processor 60, a memory 61, a bus 62, and a communication interface 63. The processor 60, the communication interface 63, and the memory 61 are connected through the bus 62; the processor 60 is used to execute an executable module stored in the memory 61, such as a computer program.

[0085] Among them, the memory 61 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 63 (which can be wired or wireless), a communication connection is realized between this system network element and at least one other network element, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0086] The bus 62 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 4 only a bidirectional arrow is used in

[0087] to represent, but it does not mean that there is only one bus or one type of bus.

[0088] The processor 60 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 60 or the instructions in the form of software. The above-mentioned processor 60 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium 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. This storage medium is located in the memory 61, and the processor 60 reads the information in the memory 61 and combines its hardware to complete the steps of the above method.

[0089] Embodiment 4:

[0090] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the method described in Embodiment 1 above.

[0091] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0092] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention 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 should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0093] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0094] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0096] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments or can easily think of changes, or perform equivalent replacements on some of the technical features; 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 invention and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A search method for a part, characterized in that, It includes the following steps: Step 1: Training the algorithm model for converting historical part feature information into feature vectors; Step 2: Using the trained model to obtain historical part feature vectors and constructing a historical part feature vector library; Step 3: Inputting the feature information of the part to be searched into the trained model to obtain a feature vector; Step 4: Calculating the similarity, i.e., the vector distance, between the feature vector of the part to be searched and all the historical part feature vectors aggregated in the historical part feature vector library; Step 5: Based on the vector distance, determining the target feature vector and identifying the historical part corresponding to the target feature vector as the search result; Training the part feature information conversion algorithm model includes the following steps: Establishing a feature information library of historical parts and constructing a network model with an encoder-decoder structure, where the output of the encoder layer is the feature vector of the part; Training the information conversion model to learn the mapping relationship between historical part feature information and feature vectors; Evaluating, optimizing, and outputting the trained information conversion model; During the training process of the network model with an encoder-decoder structure, the loss function includes three dimensions. The loss function for geometric structure reconstruction is the chamfer distance, the loss function for material properties is the Euclidean distance, and the loss function for processing technology is the Euclidean distance.

2. The search method for a part according to claim 1, characterized in that, Part feature information includes geometric structure, material properties, and processing technology information.

3. The search method for a part according to claim 1, characterized in that, In Step 1, the historical part feature vector is converted from part feature information by the algorithm model.

4. The search method for a part according to claim 1, characterized in that, Part feature information includes converting the geometric structure feature information of the part into an N*3 array representation, converting the material property feature information into a one-hot encoding representation of N*M1, and converting the processing technology feature information into a one-hot encoding representation of N*M2.

5. The search method for a part according to claim 1, characterized in that, The similarity between the feature vector of the part to be searched in Step 3 and the historical part feature vector includes the similarities in three aspects: geometric structure, material properties, and processing technology.

6. A search system for parts, characterized in that, It includes: A training unit, a construction unit, an acquisition unit, a calculation unit, and an output unit, where The training unit is used for training the algorithm model for converting historical part feature information into feature vectors; The construction unit uses the trained model to obtain historical part feature vectors and constructs a historical part feature vector library; The acquisition unit is used for inputting the feature information of the part to be searched into the trained algorithm model to obtain the feature vector of the part to be searched; The calculation unit is used for calculating the distance between the feature vector of the part to be searched and the part feature vectors in the historical part feature vector library; The output unit determines the target feature vector according to the distance between the feature vectors and identifies the historical part corresponding to the target feature vector as the search result for output; During the process of training the part feature information conversion algorithm model, the training unit is also used for: establishing a feature information library of historical parts, constructing a network model with an encoder-decoder structure, where the output of the encoder layer is the feature vector of the part; training the information conversion model to learn the mapping relationship between historical part feature information and feature vectors; evaluating, optimizing, and outputting the trained information conversion model; During the training process of the network model with an encoding-decoding structure, the loss function includes three dimensions. Among them, the loss function for geometric structure reconstruction is the chamfer distance, the loss function for material properties is the Euclidean distance, and the loss function for processing technology is the Euclidean distance.

7. An electronic device, characterized in that, It includes a memory and a processor. The memory is used to store a program that supports the processor to execute the method according to any one of claims 1 to 5, and the processor is configured to execute the program stored in the memory.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, it executes the steps of the method according to any one of claims 1 to 5 above.

Images