Similar product recommendation method and device based on part library, terminal and medium

Abstract

The invention provides a similar product recommendation method and device based on a part library, a terminal and a medium, and the method comprises the steps: obtaining a similarity dimension factor of a current product, carrying out the conversion of a first similarity dimension factor quantity of the similarity dimension factor, and obtaining the multi-dimensional label reference quantity of the current product; the first similarity dimension factor quantity at least comprises a classification category factor quantity and a material dimension factor quantity; screening a target similar product set from the part library according to a preset screening rule, and carrying out second similarity dimension factor quantity conversion on similarity dimension factors of the target similar product set one by one to obtain multi-dimensional label dimension quantities of target similar products; the second similarity dimension factor quantity at least comprises a model total area factor quantity, a model total volume factor quantity and a model bounding box factor quantity; calculating mutual similarity according to the label reference quantity, the label dimension and a similarity calculation formula; and according to the similarity result, determining a similar product recommendation result of the current product. The method is higher in recommendation accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of product design and manufacturing, and in particular to a method, device, terminal and medium for recommending similar products based on a parts library. Background Art

[0002] In the field of industrial product manufacturing, the current method for recommending parts similarity generally involves searching and comparing text keywords and geometric similarity to find products that match keywords and have high geometric shape similarity as recommended products. However, this recommendation method does not take material and functionality into consideration, resulting in that even some products with high similarity may not necessarily be close to the replaced products in terms of material and functionality, which means that the accuracy of the recommendation is still insufficient. Summary of the invention

[0003] The main purpose of the present invention is to provide a similar product recommendation method, device, terminal and medium based on a parts library, aiming to solve the technical problem that the recommendation accuracy of the current parts similarity recommendation method is still insufficient.

[0004] In a first aspect, the present invention provides a similar product recommendation method based on a parts library, comprising:

[0005] Get the similarity dimension factor of the current product;

[0006] The similarity dimension factor of the current product is converted into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity;

[0007] Filter the target similar product set from the parts library according to the preset filtering rules;

[0008] Convert the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity, and a model bounding box factor quantity;

[0009] Calculate the similarity between each of the target similar products and the current product according to the multi-dimensional label benchmark quantity of the current product, the multi-dimensional label dimension quantity of the target similar product, and a preset similarity calculation formula;

[0010] According to the calculated similarity result, a similar product recommendation result of the current product is determined.

[0011] In a specific embodiment, converting the similarity dimension factor of the current product into a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product includes:

[0012] The similarity dimension factor of the current product is labeled and quantified with a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product.

[0013] In a specific embodiment, the screening rule includes screening products in the same catalog and category as the current product and whose keyword matching degree is greater than a preset value, and screening a target similar product set from the parts library according to the preset screening rule includes:

[0014] Products in the same catalog and category as the current product and with a keyword matching degree greater than a preset value are screened out from the parts library and determined as target similar products, and are classified into a target similar product set.

[0015] In a specific embodiment, converting the second similarity dimension factor quantity of the target similar products in the target similar product set one by one to obtain the label dimension quantity of the target similar products includes:

[0016] The similarity dimension factors of the target similar products in the target similar product set are labeled and quantified with a second similarity dimension factor quantity one by one to obtain multi-dimensional label dimension quantities of the target similar products.

[0017] In a specific embodiment, the similarity calculation formula is:

[0018]

[0019] Among them, K a K is the similarity value between the a-th target similar product and the current product; 1j , K 2j , ..., K nj are the label reference quantities of the n dimensions of the current product; K 1a , K 2a , ..., K na are the label dimensions of the n dimensions of the a-th target similar product; η 1 , η 2 , ..., η n They are respectively the similarity coefficients of the n-dimensional factors of the a-th target similar product.

[0020] In a second aspect, the present invention provides a similar product recommendation device based on a parts library, comprising:

[0021] A similarity dimension factor acquisition module is used to obtain the similarity dimension factor of the current product;

[0022] A label reference quantity conversion module is used to convert the similarity dimension factor of the current product into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity;

[0023] A target similar product set screening module is used to screen the target similar product set from the parts library according to preset screening rules;

[0024] A label dimension quantity conversion module is used to convert the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity and a model bounding box factor quantity;

[0025] A similarity calculation module, used to calculate the similarity between each target similar product and the current product according to the multi-dimensional label reference quantity of the current product, the multi-dimensional label dimension quantity of the target similar product and a preset similarity calculation formula;

[0026] The target similar product recommendation module is used to determine the similar product recommendation result of the current product according to the calculated similarity result.

[0027] In a specific embodiment, the label reference quantity conversion module is specifically used to:

[0028] Labeling and quantifying the similarity dimension factor of the current product by a first similarity dimension factor amount to obtain a multi-dimensional label benchmark amount of the current product;

[0029] The label dimension conversion module is specifically used for:

[0030] The similarity dimension factors of the target similar products in the target similar product set are labeled and quantified with a second similarity dimension factor quantity one by one to obtain multi-dimensional label dimension quantities of the target similar products.

[0031] In a third aspect, the present invention provides a terminal comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for recommending similar products based on a parts library as described in the first aspect is implemented.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a similar product recommendation method based on a parts library as described in the first aspect.

[0033] Compared with the prior art, the beneficial effect of the present invention is that: by converting the similarity dimension factor of the current product into the first similarity dimension factor quantity, the multi-dimensional label benchmark quantity of the current product is obtained, and the similarity dimension factor of the target similar product in the target similar product set is converted into the second similarity dimension factor quantity one by one, and the multi-dimensional label dimension quantity of the target similar product is obtained, wherein the first similarity dimension factor quantity at least includes the classification category factor quantity and the material dimension factor quantity, and the second similarity dimension factor quantity at least includes the model total area factor quantity, the model total volume factor quantity and the model bounding box factor quantity; then, according to the multi-dimensional label benchmark quantity of the current product, the multi-dimensional label dimension quantity of the target similar product and the preset similarity calculation formula, the similarity between the current product and each target similar product is calculated; finally, according to the calculated similarity result, the similar product recommendation result of the current product is determined. In this way, the present invention is not limited to text keywords and geometric similarity comparison, but also performs multi-dimensional calculation comparison in terms of product classification category, material and usage functionality, searches out target similar products with high similarity and closer to interchangeable use, and the recommendation accuracy is higher. In addition, in the field of industrial product equipment development, the rapid selection of historical models or mature parts of other brands based on the parts library can not only shorten the selection cycle and control costs, but also improve product reliability and versatility, and promote product standardization and modularization. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of a method for recommending similar products based on a parts library provided by one embodiment of the present invention;

[0035] Figure 2 It is a structural schematic diagram of a similar product recommendation device based on a parts library provided by an embodiment of the present invention;

[0036] Figure 3 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention.

[0037] in:

[0038] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0039] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0040] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are 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 cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0043] See also Figure 1 , Figure 1 The present invention is a flowchart of a method for recommending similar products based on a parts library according to an embodiment of the present invention.

[0044] A similar product recommendation method based on a parts library according to an embodiment of the present invention comprises the following steps:

[0045] S100, obtaining the similarity dimension factor of the current product.

[0046] In this embodiment, the current product refers to the component product selected or opened by the user in the current component library. The similarity dimension factors include factors of the dimensions of the component library's catalog attribution, classification category, physical properties, material and surface treatment, model geometry and physical quantities.

[0047] Specifically, when a user selects or opens a component product in the component library, the system automatically reads the catalog attribution information of the product in the library and determines the folder path or classification level where the product is located.

[0048] Obtain classification categories from the product's attribute information. For example, mechanical parts can be divided into transmission parts, supporting parts, etc.

[0049] Obtain the physical properties of the product, such as weight, hardness, etc., through sensors or data interfaces.

[0050] Read the product's material and surface treatment information, such as steel, aluminum alloy, and surface galvanizing.

[0051] Use 3D modeling software or measuring tools to obtain model geometric and physical quantities, such as the length, width, height, etc. of the model, and obtain the total area, total volume, and bounding box of the model through relevant calculations.

[0052] S200, converting the similarity dimension factor of the current product into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity.

[0053] In this embodiment, the similarity dimension factor of the current product is converted into a label reference quantity for comparison calculation in the subsequent step S500. The first similarity dimension factor quantity must include the classification category factor quantity and the material dimension factor quantity to ensure that the classification category and material of the target similar product have a high degree of similarity with the classification category and material of the current product, so as to recommend replacement and improve the accuracy of recommendation.

[0054] In a specific embodiment, the step S200 converts the similarity dimension factor of the current product into a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product, including the following steps:

[0055] S210 , labeling and quantifying the similarity dimension factor of the current product by a first similarity dimension factor amount, and obtaining a multi-dimensional label reference amount of the current product.

[0056] In this embodiment, labeling and quantification are performed based on factors of dimensions such as catalog affiliation, classification category, physical properties, material and surface treatment, model geometry and physical quantities of the library where the current product is located.

[0057] Specifically, the obtained directory ownership information is encoded, for example, each folder name in the path is represented by a specific combination of numbers or letters.

[0058] The classification categories are labeled, such as "C1" for transmission parts and "C2" for support parts, and so on, and a certain quantitative value is assigned according to its importance or other factors.

[0059] Information such as physical properties, materials and surface treatments is standardized and quantified, for example, weight ranges are divided into different grades and assigned corresponding values, and materials are quantified according to factors such as their cost or performance.

[0060] The model geometric and physical quantities are directly used as quantified values ​​to form label reference quantities.

[0061] S300: Filter a target similar product set from the parts library according to a preset filtering rule.

[0062] In this embodiment, a certain number of target similar products are preliminarily screened out in the parts library by using preset screening rules and classified into a target similar product set.

[0063] In a specific embodiment, the screening rule includes screening products in the same catalog and category as the current product and whose keyword matching degree is greater than a preset value. The step S300 screens a target similar product set from the parts library according to the preset screening rule, including the following steps:

[0064] S310: Filter out products from the parts library that are in the same catalog and category as the current product and whose keyword matching degree is greater than a preset value as target similar products, and classify them into a target similar product set.

[0065] In this embodiment, the preset screening rule includes screening out products in the same catalog, the same category and with a keyword matching degree greater than a preset value.

[0066] Specifically, the same catalog filtering rule is to search for products with the same path in the parts library according to the catalog attribution path of the current product. The same category filtering rule is to filter out products with the same label according to the classification category label of the current product. The keyword filtering rule is to search the entire parts library for fields such as product names and descriptions to find products containing keywords related to the current product. The products filtered out by these three filtering rules are combined to form the target product set.

[0067] S400, converting the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity and a model bounding box factor quantity.

[0068] In this embodiment, the similarity dimension factors of all target similar products are converted into label dimension quantities. Among them, the second similarity dimension factor quantity must include the model total area factor quantity, the model total volume factor quantity and the model bounding box factor quantity to ensure that the geometric shape and usage functionality of the target similar product have a high degree of similarity with the geometric shape and usage functionality of the current product, so as to recommend replacement. Of course, other factor quantities in the second similarity dimension factor quantity, such as the classification category factor quantity and the material dimension factor quantity, are consistent with the first similarity dimension factor quantity, thereby playing a double screening role and improving the accuracy of recommendation.

[0069] In a specific embodiment, the step S400 converts the second similarity dimension factor quantity of the target similar products in the target similar product set one by one to obtain the label dimension quantity of the target similar products, including the following steps:

[0070] S410 , labeling and quantifying the second similarity dimension factor quantity of the similarity dimension factors of the target similar products in the target similar product set one by one, and obtaining the multi-dimensional label dimension quantity of the target similar products.

[0071] In this embodiment, labeling and quantification are performed based on factors such as catalog affiliation, classification category, physical properties, material and surface treatment, model geometry and physical quantities of the library where the target similar products are located.

[0072] Specifically, for each target similar product in the target similar product set, labeling and quantification are performed in the same manner as step S200 to obtain label dimension quantities of each dimension thereof.

[0073] S500: Calculate the similarity between each of the target similar products and the current product based on the multi-dimensional label baseline quantity of the current product, the multi-dimensional label dimension quantity of the target similar product, and a preset similarity calculation formula.

[0074] In this embodiment, according to the similarity calculation formula, the label baseline quantity of the current product in multiple dimensions, the label dimension quantity of the target similar product in multiple dimensions and the similarity coefficient of the dimension factor quantity are substituted for calculation to obtain the similarity value between each target similar product and the current product.

[0075] In a specific embodiment, in step S500, the similarity calculation formula is:

[0076]

[0077] Among them, K a K is the similarity value between the a-th target similar product and the current product; 1j , K 2j , ..., K nj are the label reference quantities of the n dimensions of the current product; K 1a , K 2a , ..., K na are the label dimensions of the n dimensions of the a-th target similar product; η 1 , η 2 , ..., η n They are respectively the similarity coefficients of the n-dimensional factors of the a-th target similar product.

[0078] In this embodiment, the dimension factor similarity coefficient η n It can be set according to actual screening needs.

[0079] S600: Determine a recommendation result of a similar product to the current product according to the calculated similarity result.

[0080] In this embodiment, the similarity calculated for the screening target similar product set a, b, c...m is: K a , K b , K c , ..., K m , and then determine the recommendation results of similar products of the current product based on the similarity value. The higher the similarity, the more suitable the target similar product is to replace the current product.

[0081] In a specific embodiment, the step S600 determines the recommendation result of similar products of the current product according to the calculated similarity result, including the following steps:

[0082] S610: Recommend the target similar products in order from high similarity value to low similarity value according to the calculated similarity result, and display the similarity value of each target similar product.

[0083] In this embodiment, the calculated similarity values ​​of each target similar product are converted into percentages, and these percentages are sorted in descending order of similarity values. The sorting results are displayed to the user, and a recommendation result is given. The closer to 100%, the higher the similarity between the target similar product and the current product, and the more suitable it is for replacement. The user can select the most suitable component product for replacement according to the recommended order.

[0084] In summary, the embodiment of the present invention provides a similar product recommendation method based on a parts library, by converting the similarity dimension factor of the current product into a first similarity dimension factor quantity, obtaining the multi-dimensional label reference quantity of the current product, and converting the similarity dimension factor of the target similar product in the target similar product set into a second similarity dimension factor quantity one by one, obtaining the multi-dimensional label dimension quantity of the target similar product, wherein the first similarity dimension factor quantity at least includes the classification category factor quantity and the material dimension factor quantity, and the second similarity dimension factor quantity at least includes the model total area factor quantity, the model total volume factor quantity and the model bounding box factor quantity; then, according to the multi-dimensional label reference quantity of the current product, the multi-dimensional label dimension quantity of the target similar product and the preset similarity calculation formula, the similarity between the current product and each target similar product is calculated; finally, according to the calculated similarity result, the similar product recommendation result of the current product is determined. In this way, the present invention is not limited to text keywords and geometric similarity comparison, but also performs multi-dimensional calculation comparison in terms of product classification category, material and usage functionality, searches out target similar products with high similarity and closer to replaceable use, and the recommendation accuracy is higher. In addition, in the field of industrial product equipment development, the rapid selection of historical models or mature parts of other brands based on the parts library can not only shorten the selection cycle and control costs, but also improve product reliability and versatility, and promote product standardization and modularization.

[0085] See also Figure 2 , Figure 2 It is a structural schematic diagram of a similar product recommendation device based on a parts library provided by an embodiment of the present invention.

[0086] A similar product recommendation device based on a parts library according to an embodiment of the present invention includes:

[0087] A similarity dimension factor acquisition module is used to obtain the similarity dimension factor of the current product;

[0088] A label reference quantity conversion module is used to convert the similarity dimension factor of the current product into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity;

[0089] A target similar product set screening module is used to screen the target similar product set from the parts library according to preset screening rules;

[0090] A label dimension quantity conversion module is used to convert the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity and a model bounding box factor quantity;

[0091] A similarity calculation module, used to calculate the similarity between each target similar product and the current product according to the multi-dimensional label reference quantity of the current product, the multi-dimensional label dimension quantity of the target similar product and a preset similarity calculation formula;

[0092] The target similar product recommendation module is used to determine the similar product recommendation result of the current product according to the calculated similarity result.

[0093] In a specific embodiment, the label reference quantity conversion module is specifically used to:

[0094] The similarity dimension factor of the current product is labeled and quantified with a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product.

[0095] In a specific embodiment, the label dimension conversion module is specifically used to:

[0096] The similarity dimension factors of the target similar products in the target similar product set are labeled and quantified with a second similarity dimension factor quantity one by one to obtain multi-dimensional label dimension quantities of the target similar products.

[0097] An embodiment of the present invention provides a similar product recommendation device based on a parts library, which can execute all the steps and functions of a similar product recommendation method based on a parts library provided in any of the above embodiments, and the specific functions of the device are not described in detail herein.

[0098] See also Figure 3 , Figure 3 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention.

[0099] The terminal includes: a processor, a memory, and a computer program stored in the memory and configured to be run by the processor. When the processor executes the computer program, the steps of a similar product recommendation method based on a parts library in each of the above embodiments are implemented, for example Figure 1 Alternatively, the processor implements the functions of each module in the above-mentioned device embodiments when executing the computer program.

[0100] Exemplarily, the computer program may be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal. For example, the computer program may be divided into several modules, and the specific functions of each module have been described in detail in a similar product recommendation method based on a parts library provided in any of the above embodiments, and the specific functions of the device will not be repeated here.

[0101] The terminal may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal and does not constitute a limitation on a terminal. The terminal may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0102] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal, and uses various interfaces and lines to connect various parts of the entire terminal.

[0103] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the similar product recommendation method based on the parts library by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0104] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a similar product recommendation method based on a parts library in the above-mentioned embodiments.

[0105] If the terminal integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0106] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A similar product recommendation method based on a parts library, characterized in that: include: Get the similarity dimension factor of the current product; The similarity dimension factor of the current product is converted into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity; Filter the target similar product set from the parts library according to the preset filtering rules; Convert the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity, and a model bounding box factor quantity; Calculate the similarity between each of the target similar products and the current product according to the multi-dimensional label benchmark quantity of the current product, the multi-dimensional label dimension quantity of the target similar product, and a preset similarity calculation formula; According to the calculated similarity result, a similar product recommendation result of the current product is determined.

2. The method for recommending similar products based on a parts library according to claim 1, characterized in that: The converting the similarity dimension factor of the current product into a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product includes: The similarity dimension factor of the current product is labeled and quantified with a first similarity dimension factor amount to obtain a multi-dimensional label reference amount of the current product.

3. The method for recommending similar products based on a parts library according to claim 1, characterized in that: The screening rule includes screening products in the same catalog and category as the current product and whose keyword matching degree is greater than a preset value. The screening of a target similar product set from the parts library according to the preset screening rule includes: Products in the same catalog and category as the current product and with a keyword matching degree greater than a preset value are screened out from the parts library and determined as target similar products, and are classified into a target similar product set.

4. The method for recommending similar products based on a parts library according to claim 1, characterized in that: The converting the second similarity dimension factor quantity of the target similar products in the target similar product set one by one to obtain the label dimension quantity of the target similar products includes: The similarity dimension factors of the target similar products in the target similar product set are labeled and quantified with a second similarity dimension factor quantity one by one to obtain multi-dimensional label dimension quantities of the target similar products.

5. The method for recommending similar products based on a parts library according to claim 1, characterized in that: The similarity calculation formula is: Among them, K a K is the similarity value between the a-th target similar product and the current product; 1j , K 2j , ..., K nj are the label reference quantities of the n dimensions of the current product; K 1a , K 2a , ..., K na are the label dimensions of the n dimensions of the target similar product a; η1, η2, ..., η n They are respectively the similarity coefficients of the n-dimensional factors of the a-th target similar product.

6. The method for recommending similar products based on a parts library according to claim 1, characterized in that: Determining the recommendation result of similar products to the current product according to the calculated similarity result includes: According to the calculated similarity results, the target similar products are recommended in order from high similarity value to low similarity value, and the similarity value of each target similar product is displayed.

7. A similar product recommendation device based on a parts library, characterized in that: include: A similarity dimension factor acquisition module is used to obtain the similarity dimension factor of the current product; A label reference quantity conversion module is used to convert the similarity dimension factor of the current product into a first similarity dimension factor quantity to obtain a multi-dimensional label reference quantity of the current product; wherein the first similarity dimension factor quantity at least includes a classification category factor quantity and a material dimension factor quantity; A target similar product set screening module is used to screen the target similar product set from the parts library according to preset screening rules; A label dimension quantity conversion module is used to convert the similarity dimension factors of the target similar products in the target similar product set into second similarity dimension factor quantities one by one to obtain multi-dimensional label dimension quantities of the target similar products; wherein the second similarity dimension factor quantities at least include a model total area factor quantity, a model total volume factor quantity and a model bounding box factor quantity; A similarity calculation module, used to calculate the similarity between each target similar product and the current product according to the multi-dimensional label reference quantity of the current product, the multi-dimensional label dimension quantity of the target similar product and a preset similarity calculation formula; The target similar product recommendation module is used to determine the similar product recommendation result of the current product according to the calculated similarity result.

8. The similar product recommendation device based on the parts library according to claim 7, characterized in that: The label reference quantity conversion module is specifically used for: Labeling and quantifying the similarity dimension factor of the current product by a first similarity dimension factor amount to obtain a multi-dimensional label benchmark amount of the current product; The label dimension conversion module is specifically used for: The similarity dimension factors of the target similar products in the target similar product set are labeled and quantified with a second similarity dimension factor quantity one by one to obtain multi-dimensional label dimension quantities of the target similar products.

9. A terminal, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a similar product recommendation method based on a parts library as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a similar product recommendation method based on a parts library as described in any one of claims 1 to 6.

Images