Part cost data determination method, apparatus, computer-readable storage medium, and computer program product

Abstract

This application relates to a method, apparatus, computer-readable storage medium, and computer program product for determining part cost data. The method includes: extracting feature data across multiple dimensions from drawing data of a target part; generating a similarity score for each dimension by comparing the feature data of the target part in each dimension with pre-stored feature data of historical parts in the same dimension; obtaining a target similarity score between the target part and historical parts based on the similarity score for each dimension; and, if the target similarity score is greater than a similarity threshold, acquiring historical cost data of the historical parts and using the historical cost data to determine the target cost data of the target part. This method can quickly and accurately find historical parts similar to the target part using multi-dimensional features, thereby improving the efficiency of cost calculation for the target part based on prior knowledge of the cost calculation of historical parts.

Description

Technical Field

[0001] This application relates to the field of computer data processing technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining part cost data. Background Technology

[0002] In the machining industry, mold parts and complex machined parts have varying requirements for each drawing and involve complex manufacturing processes, making them non-standard, custom-made parts. Current technology requires experienced personnel to manually review the part drawings, identify the technical requirements for part processing, estimate the material costs and labor hours needed to produce the part, and finally summarize the material costs and labor hours to obtain the total cost data. However, this manual cost estimation method typically takes several hours or even days, resulting in low cost calculation efficiency. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining part cost data that can improve computational efficiency in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a method for determining part cost data, including:

[0005] Obtain the drawing data of the target part, and extract feature data in multiple dimensions from the drawing data;

[0006] By using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension, a similarity score is generated for each dimension.

[0007] Based on the similarity score corresponding to each dimension, the target similarity between the target part and the historical part is obtained;

[0008] If the target similarity is greater than the similarity threshold, the historical cost data of the historical parts is obtained, and the target cost data of the target parts is determined using the historical cost data.

[0009] In one embodiment, obtaining the target similarity between the target part and the historical part based on the similarity score corresponding to each dimension includes:

[0010] Obtain the initial weight parameter corresponding to each dimension, and adjust the initial weight parameter based on the target part type to which the target part belongs, to obtain the target weight parameter corresponding to each dimension;

[0011] Based on the comparison between the similarity score and the enhancement threshold, a similarity enhancement coefficient corresponding to the similarity score is determined. The enhancement threshold is used to define the numerical range in which the similarity score is located, and different numerical ranges correspond to different similarity enhancement coefficients.

[0012] The target similarity between the target part and the historical part is obtained by weighting the similarity score corresponding to each dimension, the target weight parameter, and the similarity enhancement coefficient.

[0013] In one embodiment, obtaining the initial weight parameter corresponding to each dimension, and adjusting the initial weight parameter based on the target part type to which the target part belongs, to obtain the target weight parameter corresponding to each dimension includes:

[0014] Based on the preset mapping relationship between part types and dimensions to be adjusted, a target adjustment dimension corresponding to the target part type and an adjustment range value corresponding to the target adjustment dimension are determined from multiple dimensions.

[0015] The adjustment magnitude value corresponding to the target adjustment dimension and the initial weight parameter under the target adjustment dimension are used for calculation to obtain the adjustment weight parameter of the target adjustment dimension;

[0016] The adjustment weight parameters of the target adjustment dimension and the initial weight parameters of the unadjusted dimensions among the multiple dimensions are normalized to obtain the target weight parameters for each dimension.

[0017] In one embodiment, the feature data under the multiple dimensions includes feature data under at least two of the following dimensions: basic geometric feature dimension, size feature dimension, topological feature dimension, shape descriptor dimension, moment of inertia feature dimension, convex hull feature dimension, symmetry feature dimension, and curvature feature dimension.

[0018] The extraction of feature data from the drawing data across multiple dimensions includes at least two of the following:

[0019] The volume, surface area, and compactness of the target part are extracted from the drawing data as feature data under the basic geometric feature dimension;

[0020] Extract the length, width, and height of the target part from the drawing data as feature data under the dimension of size feature;

[0021] The number of faces, edges, and vertices of the target part are extracted from the drawing data as feature data under the topological feature dimension;

[0022] The sphericity, rectangularity, elongation, and flatness of the target part are extracted from the drawing data as feature data under the shape descriptor dimension;

[0023] The moment of inertia of the target part on the three principal axes is extracted from the drawing data and used as feature data under the moment of inertia feature dimension;

[0024] The convexity and solidity of the target part are extracted from the drawing data as feature data under the convex hull feature dimension;

[0025] The mirror symmetry of the target part in the three principal axis directions is extracted from the drawing data as feature data under the symmetry feature dimension;

[0026] The mean and standard deviation of the curvature of the target part are extracted from the drawing data as feature data under the curvature feature dimension.

[0027] In one embodiment, before generating a similarity score for each dimension by using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension, the method further includes:

[0028] Determine the volume difference parameters, size ratio difference parameters, and topological structure difference parameters between the target part and the pre-stored historical parts;

[0029] If a historical part meets at least one of the following conditions: the volume difference parameter is greater than the volume difference threshold, the size ratio difference parameter is greater than the size difference threshold, or the topology difference parameter is greater than the topology difference threshold, the historical part is deleted.

[0030] In one embodiment, generating a similarity score for each dimension by using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension includes:

[0031] Based on the feature data of multiple historical parts in each dimension, the multiple historical parts are clustered to obtain multiple historical part clusters;

[0032] Determine the target part cluster corresponding to the target part from the plurality of historical part clusters;

[0033] The feature data of the target part in each dimension and the feature data of each historical part in the target part cluster in the same dimension are calculated respectively to obtain the similarity score between the target part and each historical part in the target part cluster in each dimension.

[0034] In one embodiment, the historical cost data includes historical production quantities and historical production man-hours;

[0035] The step of determining the target cost data of the target part using the historical cost data includes:

[0036] The target production hours for the target part are determined using the historical production hours, the historical production quantity, and the target production quantity of the target part.

[0037] Using the target production time and preset cost parameters, the processing cost data of the target part is determined;

[0038] The target cost data is calculated using the material cost data and the processing cost data of the target part.

[0039] Secondly, this application also provides a parts cost data determination device, comprising:

[0040] The feature extraction module is used to acquire the drawing data of the target part and extract feature data in multiple dimensions from the drawing data.

[0041] The dimension calculation module is used to calculate the similarity between the feature data of the target part in each dimension and the feature data of the pre-stored historical parts in the same dimension, so as to obtain the similarity score corresponding to each dimension.

[0042] A multi-dimensional fusion module is used to obtain the target similarity between the target part and the historical part based on the similarity score corresponding to each dimension.

[0043] The cost calculation module is used to obtain historical cost data of the historical parts when the target similarity is greater than a similarity threshold, and to determine the target cost data of the target parts using the historical cost data.

[0044] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the part cost data determination method described in any of the embodiments of the first aspect.

[0045] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the part cost data determination method described in any of the embodiments of the first aspect.

[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the part cost data determination method described in any of the embodiments of the first aspect.

[0047] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining part cost data acquires the drawing data of the target part and extracts feature data in multiple dimensions from the drawing data; uses the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension to generate a similarity score for each dimension; based on the similarity score for each dimension, the target similarity between the target part and historical parts is obtained; when the target similarity is greater than a similarity threshold, historical cost data of historical parts is acquired, and the target cost data of the target part is determined using the historical cost data. This allows for the rapid and accurate identification of historical parts similar to the target part using multi-dimensional features, thereby improving the cost calculation efficiency of the target part based on prior knowledge of the cost calculation of historical parts. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for determining part cost data in one embodiment;

[0050] Figure 2 This is a flowchart illustrating the target similarity determination steps in one embodiment;

[0051] Figure 3 This is a flowchart illustrating the steps for determining the target weight parameters in one embodiment;

[0052] Figure 4 This is a flowchart illustrating the steps for determining similarity scores in one embodiment;

[0053] Figure 5 A structural block diagram of a parts cost data determination device 500 in one embodiment;

[0054] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the terms "first," "second," etc., used in this application may be used to describe various elements, but these elements / data are not limited by these terms. These terms are only used to distinguish the first element / data from the second element / data. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the solutions, or any combination of multiple solutions. The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with relevant regulations.

[0057] In one embodiment, such as Figure 1 As shown, a method for determining part cost data is provided. This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps S102 to S108, wherein:

[0058] Step S102: Obtain the drawing data of the target part and extract feature data from multiple dimensions from the drawing data.

[0059] In this embodiment of the application, the target part is a non-standard customized part with unknown cost data.

[0060] For example, the server can receive the drawing data of the target part uploaded by the user through a client interface. Alternatively, it can read the drawing data of the target part from a data communication network through an application programming interface. The model structure of the target part in the drawing data is then parsed. Feature data of the model structure is extracted from dimensions such as geometry, dimensions, topology, and shape to obtain the feature data of the target part in multiple dimensions.

[0061] Step S104: Using the feature data of the target part in each dimension and the feature data of the historical parts in the same dimension that are stored in advance, generate a similarity score for each dimension.

[0062] Historical parts can be used to characterize parts whose cost data is known that have already been produced or processed.

[0063] For example, the server can pre-store historical drawing data of multiple historical parts, feature data of each historical part extracted from the historical drawing data across multiple dimensions, and historical cost data. Similarity matching between the target part and each historical part is performed as follows: the feature data of the target part and the feature data of the historical parts are vectorized for each dimension to determine the vector distance between the feature data of the target part and the feature data of the historical parts in each same dimension. Based on any mapping relationship between vector distance and similarity, such as the inverse relationship, inverse proportional transformation relationship, or complementary relationship after linear normalization, the vector distance in each same dimension is converted into a similarity score corresponding to each dimension.

[0064] Step S106: Based on the similarity score corresponding to each dimension, obtain the target similarity between the target part and the historical parts.

[0065] For example, the server can sum the similarity scores corresponding to each dimension to obtain the target similarity between the target part and the historical parts. Alternatively, the maximum or minimum similarity score among multiple dimensions can be used as the target similarity between the target part and the historical parts. Alternatively, a weighted calculation can be performed using the weight parameter corresponding to each dimension and the similarity score under the corresponding dimension to obtain the target similarity between the target part and the historical parts.

[0066] Step S108: If the target similarity is greater than the similarity threshold, obtain the historical cost data of the historical parts, and use the historical cost data to determine the target cost data of the target parts.

[0067] For example, the server can compare the target similarity between the target part and historical parts with a similarity threshold (such as 80%). If the target similarity is greater than the similarity threshold, the server can obtain the historical cost data of the historical parts corresponding to the target similarity and use the historical cost data as the target cost data of the target part; or, the server can dynamically adjust the historical cost data based on differences in production quantity and precision requirements between the target part and historical parts, and use the adjusted historical cost data as the target cost data of the target part.

[0068] In the above-mentioned method for determining part cost data, the drawing data of the target part is obtained, and feature data in multiple dimensions is extracted from the drawing data. The feature data of the target part in each dimension is compared with the feature data of historical parts in the same dimension that are stored in advance to generate a similarity score for each dimension. Based on the similarity score for each dimension, the target similarity between the target part and the historical parts is obtained. If the target similarity is greater than the similarity threshold, the historical cost data of the historical parts is obtained, and the target cost data of the target part is determined using the historical cost data. This method can quickly and accurately find historical parts similar to the target part by using multi-dimensional features, and thus improve the cost calculation efficiency of the target part based on the prior knowledge of the cost calculation of historical parts.

[0069] In one exemplary embodiment, such as Figure 2 As shown, step S106 may further include steps S202 to S206. Wherein:

[0070] Step S202: Obtain the initial weight parameters corresponding to each dimension, and adjust the initial weight parameters based on the target part type to which the target part belongs, to obtain the target weight parameters corresponding to each dimension.

[0071] The part types can include, but are not limited to, small and simple part types, complex part types, large part types, and flat part types.

[0072] For example, the server can store adjustment range values ​​corresponding to each part type. The adjustment range value corresponding to the target part is determined based on the target part type to which the current target part belongs. Optionally, in some embodiments, the adjustment range value can be used to adjust the initial weight parameters for each dimension. Alternatively, in other embodiments, the adjustment range value can be used to adjust the initial weight parameters for a specific dimension. For the adjusted dimension, the initial weight parameters adjusted by the adjustment range value are used as the target weight parameters for that dimension. For the unadjusted dimension, the initial weight parameters are used as its target weight parameters.

[0073] Step S204: Based on the comparison between the similarity score and the enhancement threshold, determine the similarity enhancement coefficient corresponding to the similarity score.

[0074] Among them, the enhancement threshold is used to define the numerical range of the similarity score, and different numerical ranges correspond to different similarity enhancement coefficients.

[0075] For example, the server can compare the similarity score for each dimension with an enhancement threshold. If the similarity score is greater than the enhancement threshold, the coefficient corresponding to the score greater than the enhancement threshold is used as the similarity enhancement coefficient for the current dimension. If the similarity score is less than the enhancement threshold, the coefficient corresponding to the score less than the enhancement threshold is used as the similarity enhancement coefficient for the current dimension.

[0076] Optionally, in some implementations, the enhancement threshold may further include a larger first enhancement threshold (e.g., 0.95) and a smaller second enhancement threshold (e.g., 0.3). When the similarity score is greater than the first enhancement threshold, a coefficient for increasing the similarity (e.g., 1.1) can be selected as the similarity enhancement coefficient corresponding to the current dimension's similarity score. When the similarity score is less than the second enhancement threshold, a coefficient for decreasing the similarity (e.g., 0.8) can be selected as the similarity enhancement coefficient corresponding to the current dimension's similarity score.

[0077] Step S206: Use the similarity score, target weight parameter and similarity enhancement coefficient corresponding to each dimension to perform weighted calculation to obtain the target similarity between the target part and the historical part.

[0078] For example, the server can use the target weight parameter and the similarity enhancement coefficient to perform weighted calculations on the similarity scores under the corresponding dimensions to obtain the weighted similarity score under each dimension. The weighted similarity scores under each dimension are summed to obtain the target similarity between the target part and the historical parts.

[0079] Optionally, in some implementations, the server may also store feature reliability parameters corresponding to each dimension. The reliability parameters may be determined based on statistical errors of historical data, the inherent accuracy of sensors or measurement methods, or the confidence level of the data source. Furthermore, the similarity scores for each dimension may be weighted using target weight parameters, similarity enhancement coefficients, and feature reliability parameters to obtain a weighted similarity score for each dimension.

[0080] In this embodiment, the initial weight parameters are adjusted based on the target part type to obtain the target weight parameters for each dimension. The corresponding similarity enhancement coefficient is determined based on the comparison between the similarity score and the enhancement threshold. The target display degree is obtained by weighting the target weight parameters, the similarity enhancement coefficient, and the similarity score. This allows for dynamic adjustment of the decision weight of the similarity score in each dimension on the target similarity between the target part and historical parts based on the target part type and the magnitude of the similarity score, thereby improving the accuracy of target similarity calculation.

[0081] In an exemplary embodiment, the feature data used to calculate the similarity score across multiple dimensions may include, but is not limited to, feature data across at least two of the following dimensions: basic geometric feature dimension, size feature dimension, topological feature dimension, shape descriptor dimension, moment of inertia feature dimension, convex hull feature dimension, symmetry feature dimension, and curvature feature dimension.

[0082] Step S102 may also include at least two of the following operating methods:

[0083] a. Extract the volume, surface area, and compactness of the target part from the drawing data as feature data under the basic geometric feature dimension.

[0084] Compactness can be used to characterize the degree of compactness of the geometry of a target part. Optionally, in some embodiments, compactness can be obtained by calculating the ratio of the surface area of ​​a sphere of the same volume to that of the target part.

[0085] For example, the server can process the drawing data of the target part by calling the shape parameterization model (shape), obtaining the volume of the target part from the volume attribute of the shape parameterization model, and obtaining the surface area of ​​the target part from the surface area attribute of the shape parameterization model. Based on the preset data relationship between volume, surface area, and compactness, the volume and surface area of ​​the target part are calculated to obtain the compactness of the target part. In this embodiment, by using the above method to treat the volume, surface area, and compactness of the target part as feature data under the basic geometric feature dimension, it is convenient to subsequently use the volume, which directly determines the material cost, the surface area, which affects the time and material consumption of surface treatment, and the compactness, which reflects the degree of hollowing or filling, to determine the similarity between the target part and historical parts in terms of basic cost composition.

[0086] b. Extract the length, width, and height of the target part from the drawing data as feature data under the dimensional feature dimension.

[0087] For example, the server can process the drawing data of the target part by calling the shape parametric model, and obtain the length, width, and height of the target part from the bounding box attribute of the shape parametric model. In this embodiment, by using the length, width, and height of the target part as feature data under the dimension of size features, it is convenient to use the length, width, and height to evaluate the similarity between the target part and historical parts in terms of the required processing equipment and clamping method.

[0088] c. Extract the number of faces, edges, and vertices of the target part from the drawing data as feature data under the topological feature dimension.

[0089] For example, the server can process the drawing data of the target part by calling the shape parameterization model, obtaining the number of faces of the target part from the face count attribute, the number of edges of the target part from the edge count attribute, and the number of vertices of the target part from the vertex count attribute. In this embodiment, by using the number of faces, edges, and vertices of the target part as feature data under the topological feature dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of processing complexity and programming processing cost based on the number of faces, edges, and vertices.

[0090] d. Extract the sphericity, rectangularity, elongation, and flatness of the target part from the drawing data as feature data under the shape descriptor dimension.

[0091] Sphericity is an index used to characterize the similarity between the shape of a part and an ideal sphere. Its value is between [0,1], and the closer the value is to 1, the closer the shape is to a sphere.

[0092] Rectangularity can be used to characterize how close a part's actual shape is to its smallest bounding box.

[0093] Elongation is an indicator used to characterize the ratio of a part's length to its width and height, representing the part's slenderness.

[0094] Flatness can be used to characterize the degree of flatness and extension of a part in space.

[0095] For example, the server can use the volume of the target part to determine an ideal sphere with the same volume as the target part, and calculate the ratio between the surface area of ​​the ideal sphere and the surface area of ​​the target part as sphericity. The server can also calculate the ratio between the bounding box volume of the target part and the volume of the target part as rectangularity. Furthermore, the server can calculate the ratio between the maximum and minimum dimensions of the target part as elongation. Finally, the server can calculate the product of the maximum and intermediate dimensions of the target part and the square of the minimum dimension, and divide the product by the square to obtain the flatness. In this embodiment, by using the sphericity, rectangularity, elongation, and flatness of the target part as feature data under the shape descriptor dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of processing technology type from aspects such as sphericity, rectangularity, elongation, and flatness.

[0096] e. Extract the moment of inertia of the target part along the three principal axes from the drawing data as feature data under the moment of inertia feature dimension.

[0097] For example, the server can process the drawing data of the target part by calling the shape parameterization model, and obtain the moment of inertia of the target part on the three principal axes (x-axis, y-axis, and z-axis) from the inertia matrix attribute of the shape parameterization model. In this embodiment, by using the moment of inertia of the target part on the three principal axes as feature data under the moment of inertia feature dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of mass distribution and cutting stability in mechanical characteristics.

[0098] f. Extract the convexity and solidity of the target part from the drawing data as feature data under the convex hull feature dimension.

[0099] Convexity can be used to evaluate the degree of protrusion and depression of a part. It is the ratio of the part volume to the part bulge volume, and its value ranges from [0,1].

[0100] Solidity can be used to assess the internal density of a part. Solidity is inversely proportional to convexity.

[0101] For example, the server can calculate the push-out and solidity using the actual volume of the target part and the volume of the convex hull portion of the target part, respectively. In this embodiment, by using the convexity and solidity of the target part as feature data under the convex hull feature dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of processing difficulty and process requirements.

[0102] g. Extract the mirror symmetry of the target part in the three principal axis directions from the drawing data as feature data under the symmetry feature dimension.

[0103] For example, the server can extract the geometric overlap or distance deviation between the model data of the target part in the positive and negative directions of each principal axis to obtain the mirror symmetry of the target part on each principal axis. In this embodiment, by using the mirror symmetry of the target part in the three principal axis directions as feature data under the symmetry feature dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of clamping strategy.

[0104] h. Extract the mean and standard deviation of the curvature of the target part from the drawing data as feature data under the curvature feature dimension.

[0105] For example, the server can calculate the mean curvature and standard deviation of the curvature of the target part using the local curvature of each point in the drawing data. In this embodiment, by using the mean curvature and standard deviation of the target part as feature data under the curvature feature dimension, it is convenient to subsequently evaluate the similarity between the target part and historical parts in terms of surface machining difficulty and post-processing requirements.

[0106] In this embodiment, feature data from at least two of the following dimensions—basic geometric feature dimension, size feature dimension, topological feature dimension, shape descriptor dimension, moment of inertia feature dimension, convex hull feature dimension, symmetry feature dimension, and curvature feature dimension—is used as feature data for calculating similarity scores across multiple dimensions. This allows for the characterization of the production and processing cost structure of a part from different dimensions, such as material cost, equipment requirements, process type, processing difficulty, stability, clamping strategy, and surface complexity. This helps to subsequently use the feature data to perform similarity calculations and obtain historical parts with similar production and processing cost structures to the target part, thereby improving the reliability and accuracy of the target cost data determined using the historical cost data of historical parts.

[0107] In one exemplary embodiment, such as Figure 3 As shown, step S202 can be derived from steps S302 to S306. Wherein:

[0108] Step S302: Based on the preset mapping relationship between part types and dimensions to be adjusted, determine the target adjustment dimension corresponding to the target part type and the adjustment range value corresponding to the target adjustment dimension from multiple dimensions.

[0109] The part types can include, but are not limited to, small simple part types, complex part types, large part types, and flat part types. Small simple part types can be used to characterize parts with a volume less than 1,000,000 cubic millimeters and fewer than 100 faces. Complex part types can be used to characterize parts with more than 500 faces. Large part types can be used to characterize parts with a volume greater than 1,000,000 cubic millimeters. Flat part types can be used to characterize parts with a flatness greater than 5.0.

[0110] For example, for small, simple part types, the dimensions to be adjusted that have a mapping relationship with them can include basic geometric feature dimensions, dimensional feature dimensions, topological feature dimensions, and shape descriptor dimensions. Furthermore, for small, simple part types, the adjustment range value corresponding to the basic geometric feature dimension can be 1.1, the adjustment range value corresponding to the dimensional feature dimension can be 1.2, the adjustment range value corresponding to the topological feature dimension can be 0.8, and the adjustment range value corresponding to the shape descriptor dimension can be 0.7. Therefore, when the target part type is a small, simple part type, the basic geometric feature dimension, dimensional feature dimension, topological feature dimension, and shape descriptor dimension can be determined from multiple dimensions as the target adjustment dimensions corresponding to the target part type, and the adjustment range value corresponding to each target adjustment dimension can be read.

[0111] For complex part types, the dimensions to be adjusted that have a mapping relationship with them can include topological feature dimensions, shape descriptor dimensions, convex hull feature dimensions, and dimensional feature dimensions. Furthermore, for complex part types, the adjustment range value corresponding to the topological feature dimension can be 1.3, the adjustment range value corresponding to the shape descriptor dimension can be 1.2, the adjustment range value corresponding to the convex hull feature dimension can be 1.1, and the adjustment range value corresponding to the dimensional feature dimension can be 0.8. Therefore, when the target part type is a complex part type, the topological feature dimension, shape descriptor dimension, convex hull feature dimension, and dimensional feature dimension can be determined from multiple dimensions as the target adjustment dimensions corresponding to the target part type, and the adjustment range value corresponding to each target adjustment dimension can be read.

[0112] For large parts, the dimensions to be adjusted that have a mapping relationship with them can include basic geometric feature dimensions, moment of inertia feature dimensions, symmetry feature dimensions, and curvature feature dimensions. Furthermore, for complex parts, the adjustment range for the basic geometric feature dimension can be 1.2, the adjustment range for the moment of inertia feature dimension can be 1.1, the adjustment range for the symmetry feature dimension can be 0.8, and the adjustment range for the curvature feature dimension can be 0.7. Therefore, when the target part type is complex, the basic geometric feature dimension, moment of inertia feature dimension, symmetry feature dimension, and curvature feature dimension can be determined from multiple dimensions as the target adjustment dimensions corresponding to the target part type, and the adjustment range values ​​corresponding to each target adjustment dimension can be read.

[0113] For flat part types, the dimensions to be adjusted that have a mapping relationship with them can include the symmetry feature dimension and the shape descriptor dimension. Furthermore, for flat part types, the adjustment range value corresponding to the symmetry feature dimension can be 1.2, and the adjustment range value corresponding to the shape descriptor dimension can be 1.1. Therefore, when the target part type is a flat part type, the symmetry feature dimension and the shape descriptor dimension can be determined from multiple dimensions as the target adjustment dimensions corresponding to the target part type, and the adjustment range value corresponding to each target adjustment dimension can be read.

[0114] Step S304: The adjustment magnitude value corresponding to the target adjustment dimension and the initial weight parameters under the target adjustment dimension are used for calculation to obtain the adjustment weight parameters of the target adjustment dimension.

[0115] Step S306: Normalize the adjustment weight parameters of the target adjustment dimension and the initial weight parameters of the unadjusted dimensions among multiple dimensions to obtain the target weight parameters for each dimension.

[0116] For example, the server can multiply the adjustment magnitude value corresponding to the target adjustment dimension with the initial weight parameter under the target adjustment dimension to obtain the initial weight parameter under the target adjustment dimension. The adjustment weight parameter of the target adjustment dimension and the initial weight parameters of the unadjusted dimensions are then normalized so that the sum of the weight parameters of each dimension after normalization is one. This normalized weight parameter is then used as the target weight parameter for each dimension.

[0117] In this embodiment, the target adjustment dimension and the corresponding adjustment range value are determined according to the target part type. The initial weight parameters of the target adjustment dimension are dynamically adjusted using the corresponding adjustment range value, and finally normalized to obtain the target weight parameters of each dimension. This makes the weights of each dimension more consistent with the actual production and processing cost structure of different part types, which helps to improve the accuracy and practicality of subsequent calculation of target cost data based on historical cost data.

[0118] In an exemplary embodiment, prior to performing step S104, the following may also be included:

[0119] Determine the volume difference parameters, size ratio difference parameters, and topology difference parameters between the target part and pre-stored historical parts. Delete the historical part if it meets at least one of the following conditions: volume difference parameter is greater than a volume difference threshold, size ratio difference parameter is greater than a size difference threshold, or topology difference parameter is greater than a topology difference threshold.

[0120] For example, the server can first extract the volume, size ratio, and topology parameters of the target part and historical parts. It then determines the volume difference parameters, size ratio difference parameters, and topology difference parameters between the target part and pre-stored historical parts. The volume difference parameters are compared with a volume difference threshold, the size ratio difference parameters are compared with a size difference threshold, and the topology difference parameters are compared with a topology difference threshold, respectively. If a historical part meets at least one of the following conditions: its volume difference parameter is greater than the volume difference threshold, its size ratio difference parameter is greater than the size difference threshold, or its topology difference parameter is greater than the topology difference threshold, the historical part is deleted. Subsequently, step S104 can be performed to calculate the similarity score between the remaining historical parts and the target part in each dimension.

[0121] In this embodiment, by pre-screening historical parts using volume, size ratio, and topology, and deleting historical parts that are too different from the target part, the amount of calculation for subsequent similarity scores can be effectively reduced, thereby improving the overall data processing efficiency.

[0122] In one exemplary embodiment, such as Figure 4As shown, step S104 includes steps S402 to S406. Wherein:

[0123] Step S402: Based on the feature data of multiple historical parts in each dimension, cluster the multiple historical parts to obtain multiple historical part clusters.

[0124] For example, the server can use K-means iterative clustering algorithm, density clustering algorithm or probabilistic clustering algorithm to construct initial clusters, use the feature data of historical parts in each dimension to calculate the distance between them and the initial clusters, thereby dividing the historical parts into the corresponding clusters and obtaining multiple historical part clusters.

[0125] Step S404: Determine the target part cluster corresponding to the target part from multiple historical part clusters.

[0126] For example, the server can use the feature data of the target part in each dimension to calculate the distance between the target part and the cluster center of each historical part cluster. The historical part cluster with the smallest distance is then selected as the target part cluster corresponding to the target part.

[0127] Step S406: Calculate the feature data of the target part in each dimension and the feature data of each historical part in the target part cluster in the same dimension, and obtain the similarity score of the target part and each historical part in the target part cluster in each dimension.

[0128] For example, the server can obtain the feature data of each historical part in the target part cluster under each dimension. Then, for each historical part in the target part cluster, the following operations are performed: using the feature data and the corresponding feature data under each same dimension, a similarity score is calculated for each dimension.

[0129] In this embodiment, by first performing clustering processing on historical parts to determine the target cluster most similar to the target part, and then calculating the similarity between the target part and the historical parts within the target cluster, the number of similarity calculations for the target part can be reduced, thereby improving the efficiency of determining the target cost data.

[0130] In an exemplary embodiment, historical cost data may include historical production data and historical production man-hours. Step S108 may include: determining the target production man-hours for the target part using historical production man-hours, historical production quantities, and the target production quantity of the target part; determining the processing cost data for the target part using the target production man-hours and preset configured cost parameters; and calculating the target cost data using the material cost data and processing cost data of the target part.

[0131] For example, the server can divide the historical production time by the historical production quantity to obtain the unit production time required to produce each historical part. Multiplying the unit production time by the target production quantity of the current target part yields the target production time for the target part.

[0132] Among them, the cost parameter can be used to characterize the process cost rate required for production per hour.

[0133] For example, the server can multiply the target production time by a preset cost parameter to obtain the processing cost data of the target part. Optionally, in some embodiments, when the target part requires multiple processes, the cost parameter corresponding to each process can be multiplied by the time required to use that process and then summed to obtain the total processing cost data of the target part.

[0134] For example, the server can calculate the material cost data of the target part using its volume, density, target production quantity, and the unit price of the materials used in the target part. The material cost data is then added to the processing cost data to obtain the target cost data.

[0135] In this embodiment, the target production time of the target part is determined by utilizing historical production hours, historical production quantities, and the target production quantity of the target part. The processing cost data of the target part is determined by using the target production time and the preset cost parameters. The target cost data is calculated by using the material cost data and processing cost data of the target part, which can improve the data reliability of the target cost data.

[0136] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0137] Based on the same inventive concept, this application also provides a part cost data determination apparatus for implementing the part cost data determination method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the part cost data determination apparatus provided below can be found in the limitations of the part cost data determination method described above, and will not be repeated here.

[0138] In one exemplary embodiment, such as Figure 5 As shown, a part cost data determination device 500 is provided, including: a feature extraction module 502, a dimension calculation module 504, a multi-dimensional fusion module 506, and a cost calculation module 508, wherein:

[0139] The feature extraction module 502 is used to acquire the drawing data of the target part and extract feature data in multiple dimensions from the drawing data.

[0140] The dimension calculation module 504 is used to calculate the similarity between the feature data of the target part in each dimension and the feature data of the pre-stored historical parts in the same dimension, and obtain the similarity score corresponding to each dimension.

[0141] The multidimensional fusion module 506 is used to obtain the target similarity between the target part and the historical parts based on the similarity score corresponding to each dimension.

[0142] The cost calculation module 508 is used to obtain historical cost data of historical parts when the similarity to the target is greater than the similarity threshold, and to determine the target cost data of the target part using the historical cost data.

[0143] In an exemplary embodiment, the multi-dimensional fusion module 506 includes: a weight adjustment unit, configured to obtain initial weight parameters corresponding to each dimension, and adjust the initial weight parameters based on the target part type to which the target part belongs, to obtain target weight parameters corresponding to each dimension; a similarity enhancement unit, configured to determine a similarity enhancement coefficient corresponding to the similarity score based on the comparison result between the similarity score and the enhancement threshold, wherein the enhancement threshold is used to define the numerical range in which the similarity score falls, and different numerical ranges correspond to different similarity enhancement coefficients; and a weighted calculation unit, configured to perform a weighted calculation using the similarity score corresponding to each dimension, the target weight parameters, and the similarity enhancement coefficients to obtain the target similarity between the target part and historical parts.

[0144] In an exemplary embodiment, the weight adjustment unit is further configured to determine, based on a preset mapping relationship between part types and dimensions to be adjusted, a target adjustment dimension corresponding to the target part type and an adjustment magnitude value corresponding to the target adjustment dimension from multiple dimensions; perform calculations using the adjustment magnitude value corresponding to the target adjustment dimension and the initial weight parameters under the target adjustment dimension to obtain the adjustment weight parameters of the target adjustment dimension; and normalize the adjustment weight parameters of the target adjustment dimension and the initial weight parameters of the unadjusted dimensions among multiple dimensions to obtain the target weight parameters of each dimension.

[0145] In an exemplary embodiment, the feature data under multiple dimensions includes feature data under at least two of the following dimensions: basic geometric feature dimension, size feature dimension, topological feature dimension, shape descriptor dimension, moment of inertia feature dimension, convex hull feature dimension, symmetry feature dimension, and curvature feature dimension. The feature extraction module 502 is also used to extract the volume, surface area, and compactness of the target part from the drawing data as feature data under the basic geometric feature dimension; extract the length, width, and height of the target part from the drawing data as feature data under the dimensional feature dimension; extract the number of faces, edges, and vertices of the target part from the drawing data as feature data under the topological feature dimension; extract the sphericity, rectangularity, elongation, and flatness of the target part from the drawing data as feature data under the shape descriptor dimension; extract the moment of inertia of the target part on the three principal axes from the drawing data as feature data under the moment of inertia feature dimension; extract the convexity and solidity of the target part from the drawing data as feature data under the convex hull feature dimension; extract the mirror symmetry of the target part in the three principal axis directions from the drawing data as feature data under the symmetry feature dimension; and extract the mean and standard deviation of the curvature of the target part from the drawing data as feature data under the curvature feature dimension.

[0146] In an exemplary embodiment, the part cost data determination device 500 further includes a pre-screening module for determining the volume difference parameters, size ratio difference parameters, and topology difference parameters between the target part and pre-stored historical parts; and deleting the historical part if the historical part meets at least one of the following conditions: the volume difference parameter is greater than the volume difference threshold, the size ratio difference parameter is greater than the size difference threshold, or the topology difference parameter is greater than the topology difference threshold.

[0147] In an exemplary embodiment, the dimension calculation module 504 is further configured to perform clustering processing on multiple historical parts based on the feature data of multiple historical parts in each dimension to obtain multiple historical part clusters; determine the target part cluster corresponding to the target part from the multiple historical part clusters; and calculate the feature data of the target part in each dimension and the feature data of each historical part in the target part cluster in the same dimension to obtain the similarity score between the target part and each historical part in the target part cluster in each dimension.

[0148] In an exemplary embodiment, historical cost data includes historical production quantity and historical production man-hours. The cost calculation module 508 is further configured to determine the target production man-hours for the target part using historical production man-hours, historical production quantity, and the target production quantity of the target part; determine the processing cost data for the target part using the target production man-hours and preset cost parameters; and calculate the target cost data using the material cost data and processing cost data of the target part.

[0149] Each module in the aforementioned parts cost data determination device 500 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0150] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores drawing data, feature data, similarity scores, adjustment values, initial weight parameters, target weight parameters, similarity enhancement coefficients, target similarity, historical cost data, target cost data, and other data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for determining part cost data.

[0151] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0152] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0153] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0154] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0155] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0156] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0157] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining part cost data, characterized in that, The method includes: Obtain the drawing data of the target part, and extract feature data in multiple dimensions from the drawing data; By using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension, a similarity score is generated for each dimension. Based on the similarity score corresponding to each dimension, the target similarity between the target part and the historical part is obtained; If the target similarity is greater than the similarity threshold, the historical cost data of the historical parts is obtained, and the target cost data of the target parts is determined using the historical cost data.

2. The method according to claim 1, characterized in that, The process of obtaining the target similarity between the target part and the historical parts based on the similarity score corresponding to each dimension includes: Obtain the initial weight parameter corresponding to each dimension, and adjust the initial weight parameter based on the target part type to which the target part belongs, to obtain the target weight parameter corresponding to each dimension; Based on the comparison between the similarity score and the enhancement threshold, a similarity enhancement coefficient corresponding to the similarity score is determined. The enhancement threshold is used to define the numerical range in which the similarity score is located, and different numerical ranges correspond to different similarity enhancement coefficients. The target similarity between the target part and the historical part is obtained by weighting the similarity score corresponding to each dimension, the target weight parameter, and the similarity enhancement coefficient.

3. The method according to claim 2, characterized in that, The step of obtaining the initial weight parameters corresponding to each dimension, and adjusting the initial weight parameters based on the target part type to which the target part belongs, to obtain the target weight parameters corresponding to each dimension, includes: Based on the preset mapping relationship between part types and dimensions to be adjusted, a target adjustment dimension corresponding to the target part type and an adjustment range value corresponding to the target adjustment dimension are determined from multiple dimensions. The adjustment magnitude value corresponding to the target adjustment dimension and the initial weight parameter under the target adjustment dimension are used for calculation to obtain the adjustment weight parameter of the target adjustment dimension; The adjustment weight parameters of the target adjustment dimension and the initial weight parameters of the unadjusted dimensions among the multiple dimensions are normalized to obtain the target weight parameters for each dimension.

4. The method according to claim 1, characterized in that, The feature data under the multiple dimensions includes feature data under at least two of the following dimensions: basic geometric feature dimension, size feature dimension, topological feature dimension, shape descriptor dimension, moment of inertia feature dimension, convex hull feature dimension, symmetry feature dimension, and curvature feature dimension. The extraction of feature data from the drawing data across multiple dimensions includes at least two of the following: The volume, surface area, and compactness of the target part are extracted from the drawing data as feature data under the basic geometric feature dimension; Extract the length, width, and height of the target part from the drawing data as feature data under the dimension of size feature; The number of faces, edges, and vertices of the target part are extracted from the drawing data as feature data under the topological feature dimension; The sphericity, rectangularity, elongation, and flatness of the target part are extracted from the drawing data as feature data under the shape descriptor dimension; The moment of inertia of the target part on the three principal axes is extracted from the drawing data and used as feature data under the moment of inertia feature dimension; The convexity and solidity of the target part are extracted from the drawing data as feature data under the convex hull feature dimension; The mirror symmetry of the target part in the three principal axis directions is extracted from the drawing data as feature data under the symmetry feature dimension; The mean and standard deviation of the curvature of the target part are extracted from the drawing data as feature data under the curvature feature dimension.

5. The method according to claim 1, characterized in that, Before generating a similarity score for each dimension by using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension, the method further includes: Determine the volume difference parameters, size ratio difference parameters, and topological structure difference parameters between the target part and the pre-stored historical parts; If a historical part meets at least one of the following conditions: the volume difference parameter is greater than the volume difference threshold, the size ratio difference parameter is greater than the size difference threshold, or the topology difference parameter is greater than the topology difference threshold, the historical part is deleted.

6. The method according to claim 1, characterized in that, The step of generating a similarity score for each dimension by using the feature data of the target part in each dimension and the feature data of pre-stored historical parts in the same dimension includes: Based on the feature data of multiple historical parts in each dimension, the multiple historical parts are clustered to obtain multiple historical part clusters; Determine the target part cluster corresponding to the target part from the plurality of historical part clusters; The feature data of the target part in each dimension and the feature data of each historical part in the target part cluster in the same dimension are calculated respectively to obtain the similarity score between the target part and each historical part in the target part cluster in each dimension.

7. The method according to claim 1, characterized in that, The historical cost data includes historical production quantities and historical production man-hours; The step of determining the target cost data of the target part using the historical cost data includes: The target production hours for the target part are determined using the historical production hours, the historical production quantity, and the target production quantity of the target part. Using the target production time and preset cost parameters, the processing cost data of the target part is determined; The target cost data is calculated using the material cost data and the processing cost data of the target part.

8. A device for determining part cost data, characterized in that, The device includes: The feature extraction module is used to acquire the drawing data of the target part and extract feature data in multiple dimensions from the drawing data. The dimension calculation module is used to calculate the similarity between the feature data of the target part in each dimension and the feature data of the pre-stored historical parts in the same dimension, so as to obtain the similarity score corresponding to each dimension. A multi-dimensional fusion module is used to obtain the target similarity between the target part and the historical part based on the similarity score corresponding to each dimension. The cost calculation module is used to obtain historical cost data of the historical parts when the target similarity is greater than a similarity threshold, and to determine the target cost data of the target parts using the historical cost data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images