Customized product difference comparison method and device and storage medium

Abstract

The invention discloses a difference comparison method and device for customized products and a storage medium, and the method comprises the steps: taking the product difference data as the product difference data finally matched with a product customization demand if the product difference data of a current version customized product is the same as the product difference data of a historical version customized product; training according to the product customization demand and the product difference data to obtain a difference matching model; if the product difference data of the current version of customized product is different from the product difference data of the historical version of customized product, inputting the product difference data of each version of customized product and the product customization demand into a difference matching model to obtain the product difference data which is output by the difference matching model and is finally matched with the product customization demand, the data utilization rate is improved, the product difference data finally matched with all the product customization requirements can be effectively identified, the product development effect is accurately analyzed, and the accuracy and efficiency of subsequent customized product development are conveniently improved.

Description

Technical Field

[0001] The present application relates to the technical field of product development, and in particular to a method, device and storage medium for comparing differences in customized products. Background Art

[0002] In enterprises with multiple varieties and small batches, there will be a large number of personalized customized products. R&D personnel customize the enterprise's baseline products according to the personalized needs of customers and generate corresponding customized products.

[0003] At present, the customization needs of products are mainly met by manually breaking down the needs and modifying the basic product data to generate customer customized product data. In the long run, a customization demand order requires a manual operation, which consumes a lot of manpower and material resources, and there is a possibility of errors in manual operation.

[0004] Therefore, how to determine the effect of product customization and development and improve the accuracy and efficiency of product customization and development is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The present application at least provides a method, device and storage medium for comparing differences in customized products.

[0006] The first aspect of the present application provides a method for comparing the differences of customized products, the method comprising: obtaining product structure information of each version of a basic product, and obtaining product structure information of each version of a customized product; wherein a customized product is obtained by customizing and developing a basic product of a corresponding version when creating a customized product based on product customization requirements, and using the basic product of the corresponding version when the customized product is created as the dependent basic product of the customized product; comparing the differences between the product structure information of the current version of the customized product and the product structure information of the dependent basic product corresponding to the current version of the customized product to obtain product difference data of the current version of the customized product; and comparing the product structure information of a historical version of a customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product. The product difference data of the historical version customized product is obtained by calculating the difference between them; wherein, the historical version refers to the version before the current version; if the product difference data of the current version customized product is the same as the product difference data of the historical version customized product, then the product difference data is used as the product difference data that finally matches the product customization demand, and the product customization demand is used as the input sample, and the product difference data is used as the sample label of the product customization demand to train a difference matching model; if the product difference data of the current version customized product is different from the product difference data of the historical version customized product, then the product difference data of each version customized product and the product customization demand are input into the difference matching model to obtain the product difference data that finally matches the product customization demand output by the difference matching model.

[0007] In one embodiment, the method also includes: if the current version is the first version, directly using the product difference data as the product difference data that is finally matched with the product customization requirements, and using the product customization requirements as input samples, and using the product difference data as sample labels of the product customization requirements to train a difference matching model.

[0008] In one embodiment, the first version is taken as the historical version; the differences between the product structure information of the historical version customized product and the product structure information of the dependent basic product corresponding to the historical version customized product are compared to obtain product difference data of the historical version customized product, including: comparing the differences between the product structure information of the first version customized product and the product structure information of the dependent basic product corresponding to the first version customized product to obtain product difference data of the first version customized product; the method also includes: detecting whether the product difference data of the current version customized product and the product difference data of the first version customized product are the same.

[0009] In one embodiment, if the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model to obtain the product difference data that ultimately matches the product customization requirements output by the difference matching model, including: if the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, then the differences between the product structure information of each version of the customized product and the product structure information of the dependent basic product corresponding to the customized product are compared to obtain the product difference data of each version; the product difference data of each version and the product customization requirements are input into the difference matching model to obtain the product difference data that ultimately matches the product customization requirements output by the difference matching model.

[0010] In one embodiment, all versions before the current version are taken as historical versions; the differences between the product structure information of the historical version customized product and the product structure information of the dependent basic product corresponding to the historical version customized product are compared to obtain product difference data of the historical version customized product, including: respectively comparing the differences between the product structure information of each historical version customized product and the product structure information of the dependent basic product corresponding to the historical version customized product to obtain product difference data of multiple historical versions; the method also includes: respectively detecting whether the product difference data of the current version customized product and the product difference data of each historical version are the same.

[0011] In one embodiment, the product difference data consists of one or more difference elements; the product difference data of each version of customized products and the product customization requirements are input into a difference matching model to obtain product difference data that is ultimately matched with the product customization requirements output by the difference matching model, including: inputting the product difference data of each version of customized products and the product customization requirements into the difference matching model to obtain an initial matching probability of each difference element in the product difference data of each version of customized products output by the difference matching model; calculating a target matching probability of the difference element based on all initial matching probabilities of the same difference element in each product difference data; selecting a difference element whose target matching probability meets a preset condition, and combining each selected difference element to obtain the product difference data that ultimately matches the product customization requirements.

[0012] In one embodiment, product difference data and product customization requirements of each version of customized products are input into a difference matching model to obtain product difference data output by the difference matching model that ultimately matches the product customization requirements, including: inputting the product difference data and product customization requirements of each version of customized products into the difference matching model to obtain a matching degree corresponding to the product difference data of each version of customized products output by the difference matching model; adding the product difference data of customized products whose matching degree is greater than a preset threshold to a difference list to obtain product difference data that ultimately matches the product customization requirements.

[0013] In one embodiment, the method further includes: obtaining product structure information of the current version of the basic product; combining the product structure information of the current version of the basic product and the product difference data that ultimately matches the product customization requirements to create the latest version of the customized product.

[0014] According to a second aspect of the present application, there is provided a device for comparing differences in customized products, the device comprising: an information acquisition module for acquiring product structure information of each version of a basic product, and acquiring product structure information of each version of a customized product; wherein a customized product is obtained by customizing and developing a basic product of a corresponding version when creating a customized product based on product customization requirements, and the basic product of the corresponding version when the customized product is created is used as a dependent basic product of the customized product; a difference comparison module for comparing the differences between the product structure information of a current version of a customized product and the product structure information of a dependent basic product corresponding to the current version of the customized product, to obtain product difference data of the current version of the customized product; and comparing the product structure information of a historical version of a customized product and the product structure information of a dependent basic product corresponding to the historical version of the customized product. The product difference data of the historical version customized product is obtained by calculating the difference between the two versions; wherein the historical version refers to the version before the current version; a model training module is used to, if the product difference data of the current version customized product is the same as the product difference data of the historical version customized product, use the product difference data as the product difference data that ultimately matches the product customization demand, and use the product customization demand as an input sample and the product difference data as a sample label of the product customization demand to train a difference matching model; a model matching module is used to, if the product difference data of the current version customized product is different from the product difference data of the historical version customized product, input the product difference data of each version customized product and the product customization demand into the difference matching model to obtain the product difference data that is output by the difference matching model and ultimately matches the product customization demand.

[0015] A third aspect of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned customized product difference comparison method.

[0016] A fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned customized product difference comparison method when the program instructions are executed by a processor.

[0017] The above scheme obtains the product difference data of the current version of the customized product by comparing the difference between the product structure information of the current version of the customized product and the product structure information of the dependent basic product corresponding to the current version of the customized product; and obtains the product difference data of the historical version of the customized product by comparing the difference between the product structure information of the historical version of the customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product; if the product difference data of the current version of the customized product is the same as the product difference data of the historical version of the customized product, the product difference data is used as the product difference data that is finally matched with the product customization demand, and the product customization demand is used as the input sample, and the product difference data is used as the sample label of the product customization demand, and the training is obtained. to the difference matching model, so that the difference matching model can effectively learn the correlation between mutually matching product difference data and product customization requirements, which is convenient for the subsequent effective distinction of different versions of product difference data, thereby realizing the effective use of data; if the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, then the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model, and the product difference data that finally matches the product customization requirements is obtained from the output of the difference matching model, which can effectively and accurately identify the product difference data that finally matches the product customization requirements, accurately analyze the product development effect, and facilitate improving the accuracy and efficiency of subsequent customized product development.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0020] Figure 1 is a schematic diagram of a solution implementation environment shown in an exemplary embodiment of the present application; Figure 2 is a flow chart of a method for comparing differences in customized products shown in an exemplary embodiment of the present application; Figure 3 It is a schematic diagram of version iteration of a basic product and a customized product shown in an exemplary embodiment of the present application; Figure 4 is a flow chart of a method for comparing differences in customized products shown in another exemplary embodiment of the present application; Figure 5 is a flow chart of a method for comparing differences in customized products shown in another exemplary embodiment of an exemplary embodiment of the present application; Figure 6is a block diagram of a device for comparing differences in customized products shown in an exemplary embodiment of the present application; Figure 7 is a schematic structural diagram of an electronic device shown in an exemplary embodiment of the present application; Figure 8 It is a schematic diagram of the structure of a computer-readable storage medium shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0021] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0022] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0023] The term "and / or" in this article is only an association information describing the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and next associated objects are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0024] The following is an explanation of the method for comparing the differences of customized products provided in the embodiments of the present application.

[0025] Please refer to Figure 1 , Figure 1 This is a schematic diagram of a solution implementation environment for an exemplary embodiment of the present application. The solution implementation environment may include a terminal 110 and a server 120, and the terminal 110 and the server 120 are in communication connection with each other.

[0026] The number of the terminal 110 may be one or more. The terminal 110 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart camera, etc., but is not limited thereto.

[0027] Server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0028] In one example, the server 120 stores product structure information of each version of the basic product and product structure information of each version of the customized product to compare the differences of the customized products and obtain product difference data that ultimately matches the product customization requirements. The server 120 can store the product difference data that ultimately matches the product customization requirements locally or transmit it to the terminal 110.

[0029] In one example, the terminal 110 stores product structure information of each version of the basic product and product structure information of each version of the customized product, and installs and runs a client of a target application, such as an application that provides customized product difference comparison, so as to perform customized product difference comparison and obtain product difference data that finally matches the product customization requirements. The server 120 may be a background server of the target application, used to provide background services for the client of the target application.

[0030] In the method for comparing the differences of customized products provided in the embodiment of the present application, the execution subject of each step can be the terminal 110, such as the client of the target application installed and running in the terminal 110, or the server 120, or the terminal 110 and the server 120 can interact and cooperate to execute, that is, part of the steps of the method are executed by the terminal 110 and the other part of the steps are executed by the server 120.

[0031] See also Figure 2 , Figure 2 is a flowchart of a method for comparing the differences of customized products shown in an exemplary embodiment of the present application. The method for comparing the differences of customized products can be applied to Figure 1 It should be understood that the method can also be applied to other exemplary implementation environments and be specifically executed by devices in other implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0032] like Figure 2 As shown, the method for comparing the difference of customized products at least includes steps S210 to S240, which are described in detail as follows: Step S210: Acquire product structure information of each version of the basic product, and acquire product structure information of each version of the customized product.

[0033] Among them, the customized product is obtained by customizing and developing the basic product of the corresponding version when the customized product is created based on the product customization requirements, and the basic product of the corresponding version when the customized product is created is used as the dependent basic product of the customized product.

[0034] Product customization requirements include personalized customization standards for basic products. Basic products include software products or hardware products. Product structure information is used to describe the composition structure of the product, such as using a bill of material (BOM) to store product structure information.

[0035] For example, if the basic product is a software product, the product structure information includes the code architecture of the software program; if the basic product is a hardware product, the product structure information includes all materials, components, quantities, specifications, and other information required to build the hardware.

[0036] The basic product is customized and developed according to the product customization requirements to obtain customized products.

[0037] Because a base product may have multiple versions, the base product of the corresponding version when the customized product is created is used as the dependent base product of the customized product.

[0038] For example, when a product customization requirement is received for the first version of the basic product, the first version of the basic product is customized and developed according to the product customization requirement to obtain the first version of the customized product. The dependent basic product of the first version of the customized product is the first version of the basic product; then, the first version of the basic product is subsequently iterated to obtain the second version of the basic product, and the customized product is also iterated. The second version of the basic product needs to be customized and developed according to the product customization requirement to obtain the second version of the customized product. The dependent basic product of the second version of the customized product is the second version of the basic product.

[0039] For another example, after a first version of a basic product is customized and developed according to product customization requirements to obtain a first version of a customized product, due to an update of the product customization requirements, the first version of the basic product is customized and developed again according to the updated product customization requirements to obtain a second version of a customized product. At this time, the dependent basic product of the second version of the customized product is the first version of the basic product.

[0040] It should also be noted that in actual application scenarios, the same basic product generally has multiple different product customization requirements. Different product customization requirements correspond to different customized products. Therefore, there are multiple customized product version iteration routes for the same basic product. For example, for the same basic product, there are product customization requirements provided by enterprise A and product customization requirements provided by enterprise B. The product customization requirements provided by enterprise A include A1 version customized products and A2 version customized products; the product customization requirements provided by enterprise B include B1 version customized products, B2 version customized products, and B3 version customized products.

[0041] Step S220: Compare the differences between the product structure information of the current version of the customized product and the product structure information of the dependent basic product corresponding to the current version of the customized product to obtain product difference data of the current version of the customized product; and compare the differences between the product structure information of the historical version of the customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product to obtain product difference data of the historical version of the customized product.

[0042] Among them, the historical version refers to the version before the current version.

[0043] The following is an example of the steps for comparing the differences of the current version of the customized product: Assuming that the product structure information of the current version of the customized product is (a', b, c, d), and the product structure information of the dependent basic product corresponding to the current version of the customized product is (a, b, c, d), then compare the difference between the two and obtain the product difference data (a').

[0044] Similarly, the product structure information of the historical version customized product and its corresponding dependent basic product is compared to obtain the product difference data of the historical version customized product.

[0045] Step S230: If the product difference data of the current version of the customized product is the same as the product difference data of the historical version of the customized product, the product difference data is used as the product difference data for the final match of the product customization demand, and the product customization demand is used as the input sample and the product difference data is used as the sample label of the product customization demand to train a difference matching model.

[0046] If the product difference data of the current version of the customized product is the same as the product difference data of the historical version of the customized product, it means that the probability of development errors occurring during the development of the customized product is small, and the degree of match with the product customization requirements is high. Therefore, the product difference data is directly used as the product difference data that is finally matched with the product customization requirements.

[0047] At the same time, the product customization demand is used as an input sample, and the product difference data is used as a sample label of the product customization demand, and a difference matching model is trained to enable the difference matching model to learn the correlation between the product customization demand and the product difference data with a high degree of matching.

[0048] Exemplarily, negative samples can be generated randomly, or negative samples can be generated based on the product difference data of the current version of customized products. For example, if the product difference data of the current version of customized products is (a', b'), then negative samples (a') or negative samples (b') can be generated. Then, the product difference data of the current version of customized products are used as positive samples, so that the product customization requirements, noise samples and positive samples are all input into the pre-trained neural network model. The pre-trained neural network model outputs the matching results of the product customization requirements, and the model training loss is calculated based on the matching results, so as to iteratively update the pre-trained neural network model to obtain the final trained difference matching model.

[0049] Exemplarily, the product difference data of the current version of customized products can be directly used as the true value label of the product customization requirements, and the product difference data of the current version of customized products and the product customization requirements can be input into the pre-trained neural network model. The pre-trained neural network model outputs the matching result between the product difference data of the current version of customized products and the product customization requirements, and calculates the model training loss based on the matching result to iteratively update the pre-trained neural network model to obtain the final trained difference matching model.

[0050] The above model training is only an example. In actual application scenarios, other model training methods can be selected to train a difference matching model, and this application does not limit this.

[0051] This application uses the product difference data of the current version of customized products and the historical version of customized products and their corresponding product customization requirements as training samples, so that the difference matching model can effectively learn the association between mutually matching product difference data and product customization requirements, facilitate the subsequent effective distinction of product difference data of different versions, and realize the effective use of data.

[0052] Step S240: If the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model to obtain the product difference data output by the difference matching model that ultimately matches the product customization requirements.

[0053] If the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, the difference matching model is used to determine the product difference data that ultimately matches the product customization requirements.

[0054] For example, the product difference data of the current version of the customized product is (a'), and the product difference data of the historical version of the customized product is (a', b'). Then, the product difference data (a'), the product difference data (a', b') and the product customization requirements are input into the difference matching model to obtain the product difference data output by the difference matching model that ultimately matches the product customization requirements.

[0055] Compared with the prior art that requires manual disassembly of customized requirements to obtain the difference data relative to the basic product, the present application obtains accurate product difference data by comparing the basic products and customized products of each version, and selects the same product difference data of each version as sample data for model training, so as to match the different product difference data of each version according to the trained model, effectively and accurately identify the product difference data that ultimately matches all product customization requirements, accurately analyze the product development effect, and facilitate improving the accuracy and efficiency of subsequent customized product development.

[0056] In some embodiments, after obtaining the product difference data that ultimately matches the product customization requirements, the product difference data that ultimately matches can be visualized and displayed to developers, so that the developers can clearly know the differences between the customization requirements and the basic products, and evaluate whether the currently developed customized products meet the product customization requirements. This also facilitates subsequent customized product development and improves the efficiency of customized product development.

[0057] In some embodiments, after obtaining the product difference data that ultimately matches the product customization requirements, the product structure information of the current version of the basic product can be obtained, and the product structure information of the current version of the basic product and the product difference data that ultimately matches the product customization requirements can be combined to create the latest version of the customized product, so as to automatically generate a customized product that meets the product customization requirements and improve the efficiency of customized product development.

[0058] It should be noted that the subsequent use method of the product difference data that is ultimately matched to the product customization requirements can be flexibly selected according to the specific application scenario, and this application does not limit this.

[0059] Next, some embodiments of the present application are described in detail.

[0060] In some embodiments, if the current version is the first version, the product difference data is directly used as the product difference data that is finally matched with the product customization requirements, and the product customization requirements are used as input samples, and the product difference data is used as the sample label of the product customization requirements to train a difference matching model.

[0061] In some embodiments, if the current version is not the first version, all versions before the current version are regarded as historical versions; the differences between the product structure information of each historical version of the customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product are compared to obtain product difference data of multiple historical versions; and the product difference data of the current version of the customized product and the product difference data of each historical version are respectively detected to see whether they are the same.

[0062] If the product difference data of the current version of the customized product is the same as the product difference data of each historical version of the customized product, the product difference data will be used as the product difference data for the final match of the product customization demand, and the product customization demand will be used as the input sample, and the product difference data will be used as the sample label of the product customization demand to train a difference matching model.

[0063] By comparing the product difference data of each version of the customized product, the accuracy of the product difference data comparison is improved.

[0064] In some embodiments, if the current version is not the first version, the first version is used as the historical version; the differences between the product structure information of the first version customized product and the product structure information of the dependent basic product corresponding to the first version customized product are compared to obtain the product difference data of the first version customized product; and it is detected whether the product difference data of the current version customized product and the product difference data of the first version customized product are the same.

[0065] If the product difference data of the current version of the customized product is the same as the product difference data of the first version of the customized product, the product difference data is used as the product difference data for the final match of the product customization demand, and the product customization demand is used as the input sample, and the product difference data is used as the sample label of the product customization demand to train a difference matching model.

[0066] By comparing the product difference data between the first version and the current version of the customized product, the algorithm execution efficiency can be effectively improved and the amount of calculation can be reduced.

[0067] For an example, see Figure 3 , Figure 3 A schematic diagram of version iteration of a basic product and a customized product is shown for an exemplary embodiment of the present application. Figure 3As shown, the basic products and customized products are iterated over time. The basic products include basic products from version S1 to version S5. In response to the product customization requirements provided by enterprise A, customized products from version A1 to version A5 are customized and developed. The current customized product is the customized product of version A5. The dependent basic product of the customized product of version A5 is the basic product of version S5. The product difference data between the product structure information of the customized product of version A5 and the product structure information of the basic product of version S5 is (a', a).

[0068] If version A1 is taken as the historical version, the dependent basic product of the customized product of version A1 is the basic product of version S1, and the product difference data between the product structure information of the customized product of version A1 and the product structure information of the basic product of version S1 is (a', a), which is the same as the product difference data (a', a) corresponding to the customized product of version A5.

[0069] If versions A1 to A4 are all regarded as historical versions, then the dependent basic product of the customized product of version A1 is the basic product of version S1, the dependent basic product of the customized product of version A2 is the basic product of version S2, the dependent basic product of the customized product of version A3 is the basic product of version S3, and the dependent basic product of the customized product of version A4 is the basic product of version S4. The product difference data corresponding to each version of the customized product are (a', a), which are the same as the product difference data (a', a) corresponding to the customized product of version A5.

[0070] Furthermore, in response to the product customization needs provided by enterprise B, customized products from version B1 to version B4 are customized and developed. The current version of the customized product is the version B4 customized product. The dependent basic product of the version B4 customized product is the version S5 basic product. The product difference data (a', a, b', c, d, f) between the product structure information of the version B4 customized product and the product structure information of the version S5 basic product.

[0071] If version B1 is taken as the historical version, the dependent basic product of the customized product of version B1 is the basic product of version S2, and the product difference data between the product structure information of the customized product of version B1 and the product structure information of the basic product of version S2 is (b', b), which is different from the product difference data (a', a, b', c, d, f) corresponding to the customized product of version B4.

[0072] If versions B1 to B3 are all regarded as historical versions, the product difference data between the customized product of version B2 and its dependent basic product (i.e., the basic product of version S2) is (a', a, b', b), and the product difference data between the customized product of version B3 and its dependent basic product (i.e., the basic product of version S4) is (a', a, c). The product difference data corresponding to the customized products of versions B1 to B3 are different from the product difference data corresponding to the customized product of version B4 (a', a, b', c, d, f).

[0073] If the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, then compare the differences between the product structure information of each version of the customized product and the product structure information of the dependent basic product corresponding to the customized product to obtain the product difference data of each version; input the product difference data of each version and the product customization requirements into the difference matching model to obtain the product difference data output by the difference matching model that ultimately matches the product customization requirements.

[0074] For example, the product customization requirements provided by enterprise B, Figure 3 The product difference data corresponding to the customized products from version B1 to version B4 are all input into the difference matching model to obtain the product difference data that is ultimately matched with the product customization requirements provided by enterprise B.

[0075] For an example, see Figure 4 , Figure 4 A flowchart of a method for comparing differences in customized products is shown as another exemplary embodiment of the present application. Figure 4 As shown, including: Step S401: Read the version number n of the current version of the customized product; Step S402: Determine whether the version number n is equal to 1, if not, execute step S403; if yes, execute step S409; Step S403: Compare the differences between the product structure information of the current version customized product and the product structure information of the dependent basic product corresponding to the current version customized product to obtain product difference data 1; Step S404: comparing the differences between the product structure information of the first version customized product and the product structure information of the dependent basic product corresponding to the first version customized product, to obtain product difference data 2; Step S405: determine whether the product difference data 1 is the same as the product difference data 2, if not, execute step S406, if yes, execute step S408; Step S406: Compare the differences between the product structure information of each version of the customized product and the product structure information of the dependent basic product corresponding to the customized product, and use the obtained product difference data of each version as verification data; Step S407: inputting the verification data and the product customization requirements into a difference matching model, and determining product difference data that ultimately matches the product customization requirements from the verification data based on the difference matching model; Step S408: using the product difference data as the product difference data that is finally matched with the product customization requirements; Step S409: Compare the differences between the product structure information of the current version customized product and the product structure information of the dependent basic product corresponding to the current version customized product to obtain product difference data that is ultimately matched to the product customization requirements.

[0076] In some embodiments, the product difference data and product customization requirements of each version of customized products are input into a difference matching model to obtain product difference data that ultimately matches the product customization requirements and is output by the difference matching model, including: inputting the product difference data and product customization requirements of each version of customized products into the difference matching model to obtain a matching degree corresponding to the product difference data of each version of customized products output by the difference matching model; adding the product difference data of customized products whose matching degree is greater than a preset threshold to a difference list to obtain product difference data that ultimately matches the product customization requirements.

[0077] For an example, see Figure 5 , Figure 5 A flowchart of a method for comparing differences in customized products is shown as another exemplary embodiment of the present application. Figure 5 As shown, including: Step S501: If the product difference data of the current version customized product is different from the product difference data of the historical version customized product, the product customization requirement is input into the difference matching model; Step S502: inputting product difference data corresponding to each version of customized product into a difference matching model in sequence, and obtaining a matching degree between the input product difference data and the product customization requirement; Step S503: determine whether the matching degree is greater than a preset threshold, if so, execute step S504, if not, execute step S507; Step S504: adding product difference data to the difference list; Step S505: Whether the product difference data corresponding to each version of the customized product is determined, if so, executing step S506, if not, executing step S502; Step S506: export the difference list to obtain product difference data that ultimately matches the product customization requirements; Step S507: Send the product difference data to a preset terminal to obtain a manual judgment result.

[0078] Among them, the manual judgment result is used to reflect whether the product difference data is the product difference data that ultimately matches the product customization requirements.

[0079] Of course, in addition to selecting the product difference data of customized products with a matching degree greater than a preset threshold as the final matching product difference data in the above embodiment, the matching degree corresponding to each product difference data can also be directly and comprehensively compared, and only the product difference data with the largest matching degree is selected as the final matching product difference data. This application does not limit this.

[0080] In some embodiments, the product difference data consists of one or more difference elements; the product difference data of each version of customized products and the product customization requirements are input into a difference matching model to obtain product difference data that is ultimately matched with the product customization requirements output by the difference matching model, including: inputting the product difference data of each version of customized products and the product customization requirements into the difference matching model to obtain an initial matching probability of each difference element in the product difference data of each version of customized products output by the difference matching model; calculating a target matching probability of the difference element based on all initial matching probabilities of the same difference element in each product difference data; selecting a difference element whose target matching probability meets a preset condition, and combining each selected difference element to obtain the product difference data that ultimately matches the product customization requirements.

[0081] Product variance data consists of one or more variance elements.

[0082] For example, if the product difference data is (a, b), it includes difference element a and difference element b respectively.

[0083] The product difference data of each version of customized products and the product customization requirements are input into the difference matching model to obtain the initial matching probability of each difference element in the product difference data of each version of customized products output by the difference matching model.

[0084] For example, the product difference data input into the difference matching model is (a, b), and the initial matching probability of the difference element a output by the difference matching model is 80%, and the initial matching probability of the difference element b is 50%.

[0085] Based on all initial matching probabilities of the same difference element in each product difference data, the target matching probability of the difference element is calculated.

[0086] For example, all initial matching probabilities of the same difference element may be summed up, and the summed result may be divided by the total number of product difference data to obtain the target matching probability of the difference element.

[0087] For another example, the weight corresponding to each difference element in each product difference data may be obtained, and then all initial matching probabilities of the same difference element in each product difference data may be weighted and summed to obtain the target matching probability of the difference element. The weight corresponding to the difference element may be pre-set, or may be flexibly set according to the total number of difference elements contained in the product difference data, and / or the version corresponding to the product difference data, and / or the importance of the product difference element in product development, etc. For example, the greater the total number of difference elements contained in the product difference data, the lower the weight of the difference element in the product difference data; and / or the closer the version corresponding to the product difference data is to the current version, the higher the weight of the difference element in the product difference data; and / or the higher the importance of the product difference element in product development, the higher the weight of the difference element in the product difference data.

[0088] For another example, all initial matching probabilities of the same difference element in each product difference data are obtained, and the maximum value, the middle value, or the average value of all the initial matching probabilities is selected as the target matching probability of the difference element.

[0089] It should be noted that the specific method of calculating the target matching probability of the difference element can be flexibly set according to the actual scenario, and this application does not limit this.

[0090] Take the product difference data input into the difference matching model as an example, including product difference data 1 (a, b), product difference data 2 (a, b, c), and product difference data 3 (b, c): Assume that the initial matching probability of difference element a in product difference data one (a, b) is 80%, and the initial matching probability of difference element b is 50%; the initial matching probability of difference element a in product difference data two (a, b, c) is 70%, the initial matching probability of difference element b is 60%, and the initial matching probability of difference element c is 90%; the initial matching probability of difference element b in product difference data three (b, c) is 50%, and the initial matching probability of difference element c is 85%.

[0091] For difference element a, its initial matching probabilities in each product difference data include 80% and 70%; for difference element b, its initial matching probabilities in each product difference data include 50%, 60%, and 50%; for difference element c, its initial matching probabilities in each product difference data include 90% and 85%.

[0092] Based on all initial matching probabilities of the same difference element in each product difference data, the target matching probability of the difference element is calculated.

[0093] For example, for difference element a, the mean of each initial matching probability is calculated, and the target matching probability is 75%; for difference element b, the mean of each initial matching probability is calculated, and the target matching probability is 53.3%; for difference element c, the mean of each initial matching probability is calculated, and the target matching probability is 87.5%.

[0094] Then, the difference elements whose target matching probability meets the preset conditions are selected, and each selected difference element is combined to obtain the product difference data that finally matches the product customization requirements.

[0095] Exemplarily, the difference elements in each product difference data may be flexibly combined according to preset conditions to obtain the final matching product difference data.

[0096] For example, each difference element is sorted in descending order according to the size of the target matching probability, and the first N difference elements in the sorting result are selected and combined to obtain the final matching product difference data.

[0097] For example, the target matching probability of difference element a is 75%, the target matching probability of difference element b is 53.3%, and the target matching probability of difference element c is 87.5%. The first two difference elements in the sorting results are selected and combined to obtain the final matching product difference data (a, c).

[0098] Among them, the value of N can be pre-set or flexibly calculated based on the total number of difference elements contained in each product difference data, and / or the minimum number and / or maximum number of difference elements contained in each product difference data, etc. This application does not limit this.

[0099] Of course, it is also possible to directly select and combine difference elements whose target matching probability is greater than a preset threshold to obtain final matching product difference data, which is not limited in this application.

[0100] Exemplarily, the matching degree of the product difference data can also be calculated based on the target matching probability of each difference element contained in the product difference data, and the product difference data whose matching degree meets the preset conditions can be selected to obtain the final matched product difference data, that is, each difference element contained in the product difference data whose matching degree meets the preset conditions is selected.

[0101] For example, the matching degree of the product difference data can be obtained by performing mean calculation, or weighted sum calculation, on the target matching probability of each difference element contained in the product difference data, or selecting the maximum value, or the middle value, or the average value of all target matching probabilities. The weights used in the weighted sum calculation can refer to the weight setting method corresponding to the difference element in the above embodiment, which will not be described in detail here.

[0102] For example, the product difference data input into the difference matching model include product difference data one (a, b), product difference data two (a, b, c), and product difference data three (b, c). The target matching probability of difference element a is 75%, the target matching probability of difference element b is 53.3%, and the target matching probability of difference element c is 87.5%. Then, the matching degree of product difference data one is (75%+53.3%) / 2=64.2%, the matching degree of product difference data two is (75%+53.3%+87.5%) / 3=71.9%, and the matching degree of product difference data three is (53.3%+87.5%) / 2=70.4%.

[0103] Then, each product difference data can be sorted in descending order according to the size of the matching degree, and the top M product difference data in the sorting result can be selected and combined to obtain the final matching product difference data; product difference data with a matching degree greater than a preset threshold can also be selected to obtain the final matching product difference data; or product difference data with the largest matching degree can be selected to obtain the final matching product difference data, and this application does not limit this.

[0104] Among them, the value of M can be pre-set or flexibly set, such as flexibly set according to the number of versions of the customized product, and this application does not limit this.

[0105] In the above embodiment, the final matching product difference data is selected from the dimension of difference elements, thereby improving the accuracy of the final matching product difference data.

[0106] The customized product difference comparison method provided in the present application obtains product difference data of the current version of the customized product by comparing the differences between the product structure information of the current version of the customized product and the product structure information of the dependent basic product corresponding to the current version of the customized product; and obtains product difference data of the historical version of the customized product by comparing the differences between the product structure information of the historical version of the customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product; if the product difference data of the current version of the customized product is the same as the product difference data of the historical version of the customized product, then the product difference data is used as the product difference data that is finally matched with the product customization demand, and the product customization demand is used as an input sample, and the product difference data is used as a sample of the product customization demand. Labels are used to train a difference matching model, so that the difference matching model can effectively learn the correlation between mutually matching product difference data and product customization requirements, which is convenient for subsequent effective distinction of different versions of product difference data, thereby realizing effective use of data; if the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model, and the product difference data that finally matches the product customization requirements is obtained from the output of the difference matching model, which can effectively and accurately identify the product difference data that finally matches the product customization requirements, accurately analyze the product development effect, and facilitate improving the accuracy and efficiency of subsequent customized product development.

[0107] Figure 6 FIG. 1 is a block diagram of a device for comparing differences in customized products shown in an exemplary embodiment of the present application. Figure 6 As shown, the exemplary customized product difference comparison device 600 includes: The information acquisition module 610 is used to acquire product structure information of each version of the basic product and to acquire product structure information of each version of the customized product; wherein the customized product is obtained by customizing and developing the basic product of the corresponding version when the customized product is created based on the product customization requirements, and the basic product of the corresponding version when the customized product is created is used as the dependent basic product of the customized product; The difference comparison module 620 is used to compare the differences between the product structure information of the current version customized product and the product structure information of the dependent basic product corresponding to the current version customized product, so as to obtain the product difference data of the current version customized product; and to compare the differences between the product structure information of the historical version customized product and the product structure information of the dependent basic product corresponding to the historical version customized product, so as to obtain the product difference data of the historical version customized product; wherein the historical version refers to the version before the current version; A model training module 630 is used to, if the product difference data of the current version of the customized product is the same as the product difference data of the historical version of the customized product, use the product difference data as the product difference data for the final matching of the product customization requirement, use the product customization requirement as an input sample, use the product difference data as a sample label of the product customization requirement, and train a difference matching model; Model matching module 640 is used to input the product difference data of each version of customized product and the product customization requirements into the difference matching model if the product difference data of the current version of customized product is different from the product difference data of the historical version of customized product, so as to obtain the product difference data output by the difference matching model that finally matches the product customization requirements.

[0108] It should be noted that the customized product difference comparison device provided in the above embodiment and the customized product difference comparison method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual applications, the customized product difference comparison device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0109] See also Figure 7 , Figure 7 7 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. The electronic device 700 includes a memory 701 and a processor 702, and the processor 702 is used to execute program instructions stored in the memory 701 to implement the steps in any of the above-mentioned embodiments of the method for comparing the difference of customized products. In a specific implementation scenario, the electronic device 700 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 700 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0110] Specifically, the processor 702 is used to control itself and the memory 701 to implement the steps in the above-mentioned embodiment of the difference comparison method of any customized product. The processor 702 can also be called a central processing unit (CPU). The processor 702 may be an integrated circuit chip with signal processing capabilities. The processor 702 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 702 can be implemented by an integrated circuit chip.

[0111] See also Figure 8 , Figure 8 The computer-readable storage medium 800 stores program instructions 810 that can be executed by a processor, and the program instructions 810 are used to implement the steps in any of the above-mentioned customized product difference comparison method embodiments.

[0112] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0113] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0115] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

Claims

1. A method for comparing differences in customized products, characterized in that: The method comprises: Obtain product structure information of each version of the basic product, and obtain product structure information of each version of the customized product; wherein the customized product is obtained by customizing and developing the basic product of the corresponding version when the customized product is created based on the product customization requirements, and the basic product of the corresponding version when the customized product is created is used as the dependent basic product of the customized product; Compare the differences between the product structure information of the current version of the customized product and the product structure information of the dependent basic product corresponding to the current version of the customized product to obtain product difference data of the current version of the customized product; and compare the differences between the product structure information of the historical version of the customized product and the product structure information of the dependent basic product corresponding to the historical version of the customized product to obtain product difference data of the historical version of the customized product; wherein the historical version refers to the version before the current version; If the product difference data of the current version customized product is the same as the product difference data of the historical version customized product, the product difference data is used as the product difference data finally matched by the product customization requirement, and the product customization requirement is used as an input sample, and the product difference data is used as a sample label of the product customization requirement to train a difference matching model; If the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model to obtain the product difference data output by the difference matching model that ultimately matches the product customization requirements.

2. The method according to claim 1, characterized in that The method further comprises: If the current version is the first version, the product difference data is directly used as the product difference data that is finally matched with the product customization demand, and the product customization demand is used as an input sample, and the product difference data is used as a sample label of the product customization demand to train a difference matching model.

3. The method according to claim 1, characterized in that The first version is used as the historical version; the product structure information of the historical version customized product is compared with the product structure information of the dependent basic product corresponding to the historical version customized product to obtain product difference data of the historical version customized product, including: Compare differences between product structure information of the first version customized product and product structure information of a dependent basic product corresponding to the first version customized product to obtain product difference data of the first version customized product; The method further comprises: It is detected whether the product difference data of the current version customized product is the same as the product difference data of the first version customized product.

4. The method according to claim 3, characterized in that If the product difference data of the current version customized product is different from the product difference data of the historical version customized product, the product difference data of each version customized product and the product customization requirement are input into the difference matching model to obtain the product difference data output by the difference matching model that finally matches the product customization requirement, including: If the product difference data of the current version of the customized product is different from the product difference data of the historical version of the customized product, then respectively compare the differences between the product structure information of each version of the customized product and the product structure information of the dependent basic product corresponding to the customized product to obtain the product difference data of each version; The product difference data of each version and the product customization requirements are input into the difference matching model to obtain the product difference data output by the difference matching model that finally matches the product customization requirements.

5. The method according to claim 1, characterized in that All versions before the current version are taken as historical versions; the product structure information of the historical version customized product is compared with the product structure information of the dependent basic product corresponding to the historical version customized product, and the product difference data of the historical version customized product is obtained, including: Compare the differences between the product structure information of each historical version customized product and the product structure information of the dependent basic product corresponding to the historical version customized product, and obtain product difference data of multiple historical versions; The method further comprises: It is respectively detected whether the product difference data of the current version of the customized product is the same as the product difference data of each historical version.

6. The method according to claim 1, characterized in that The product difference data is composed of one or more difference elements; the product difference data of each version of the customized product and the product customization requirements are input into the difference matching model to obtain the product difference data output by the difference matching model that finally matches the product customization requirements, including: Inputting the product difference data of each version of the customized product and the product customization requirements into the difference matching model, and obtaining the initial matching probability of each difference element in the product difference data of each version of the customized product output by the difference matching model; Based on all initial matching probabilities of the same difference element in each of the product difference data, a target matching probability of the difference element is calculated; The difference elements whose target matching probability meets the preset conditions are selected, and the product difference data that finally matches the product customization requirements are obtained by combining each selected difference element.

7. The method according to claim 1, characterized in that The step of inputting the product difference data of each version of the customized product and the product customization requirement into the difference matching model to obtain the product difference data output by the difference matching model and finally matching the product customization requirement includes: Inputting product difference data of each version of customized product and the product customization requirements into the difference matching model, and obtaining the matching degree corresponding to the product difference data of each version of customized product output by the difference matching model; The product difference data of the customized products whose matching degree is greater than a preset threshold are added to the difference list to obtain the product difference data that finally matches the product customization requirement.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Get the product structure information of the current version of the basic product; The latest version of the customized product is created by combining the product structure information of the current version of the basic product and the product difference data that is ultimately matched with the product customization requirements.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the processor is configured to execute program instructions stored in the memory to implement the steps in the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, and the program instructions can be executed by a processor to implement the steps in the method according to any one of claims 1 to 8.

Images