Data verification method, device and electronic equipment

Abstract

The present disclosure provides a data verification method, device and electronic device, which relate to the field of e-commerce technology. The data verification method includes: obtaining the product category and first configuration data of a standard product unit to be configured; determining a candidate standard product unit that has been successfully configured within a preset period before the current time point under the product category, and obtaining the second configuration data of the candidate standard product unit; determining the N reference standard product units with the highest reference degree among the candidate standard product units according to the similarity between the first configuration data and the second configuration data; and verifying the first configuration data according to the second configuration data of the reference standard product unit. The embodiments of the present disclosure can quickly and accurately implement integrity verification of large amounts of data.

Description

Background Art

[0002] SPU (Standard Product Unit) is the basic element of category management in e-commerce. One SPU includes multiple SKUs (Stock Keeping Units). For example, SPU can be "sports shoes", and its corresponding SKU can be "sports shoes-red-size 42". Before the SKU is put on the shelf, the SPU needs to be configured to achieve efficient management of the SKU. Since e-commerce needs to manage a large number of categories, the configuration and adjustment tasks are relatively arduous, and the SPU configuration is at a relatively front-end link. Once a mistake is made, the subsequent product management will have to be reworked, which will have serious consequences.

[0003] Therefore, it is necessary to ensure that the SPU configuration is accurate. Conventional inspection methods, such as manual inspection and data comparison using templates, are not efficient and accurate enough for the daily maintenance of massive data on e-commerce platforms. An efficient and accurate verification method is needed.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a data verification method, device and electronic device for improving the efficiency and accuracy of SPU configuration.

[0006] According to a first aspect of an embodiment of the present disclosure, a data verification method is provided, including: obtaining a product category and first configuration data of a standard product unit to be configured; determining a candidate standard product unit under the product category that has been successfully configured within a preset time period before a current time point, and obtaining second configuration data of the candidate standard product unit; determining N reference standard product units with the highest reference degree among the candidate standard product units according to a similarity between the first configuration data and the second configuration data; and verifying the first configuration data according to the second configuration data of the reference standard product unit.

[0007] According to a second aspect of an embodiment of the present disclosure, a data verification device is provided, including: a verification object determination module, configured to obtain a product category and first configuration data of a standard product unit to be configured; a candidate object determination module, configured to determine a candidate standard product unit under the product category that has been successfully configured within a preset time period before a current time point, and obtain second configuration data of the candidate standard product unit; a reference object determination module, configured to determine N reference standard product units with the highest reference degree among the candidate standard product units based on a similarity between the first configuration data and the second configuration data; and a verification module, configured to verify the first configuration data based on the second configuration data of the reference standard product unit.

[0008] According to a third aspect of the present disclosure, there is provided an electronic device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the methods described above based on instructions stored in the memory.

[0009] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a program is stored, and when the program is executed by a processor, the data verification method as described in any one of the above items is implemented.

[0010] The disclosed embodiment selects the most recently successfully configured candidate standard product units, selects the reference standard product unit with the highest reference degree from the candidate standard product units as the basis for data verification, and then verifies the first configuration data of the standard product unit to be configured. It can automatically adjust the current configuration data according to the configuration data of the most recent similar product. It is efficient and accurate compared to manual inspection. Compared to data comparison according to templates, it can reduce the risk of incomplete configuration due to outdated product templates, and timely provide the SPU configuration that best meets the current latest product characteristics.

[0011] 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 disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0013] Figure 1 is a flow chart of a data verification method in an exemplary embodiment of the present disclosure.

[0014] Figure 2It is a sub-flow chart of step S3 in one embodiment of the present disclosure.

[0015] Figure 3 It is a sub-flowchart of step S31 in one embodiment of the present disclosure.

[0016] Figure 4 It is a sub-flow chart of step S4 in one embodiment of the present disclosure.

[0017] Figure 5 It is a sub-flowchart of step S42 in one embodiment of the present disclosure.

[0018] Figure 6 It is a schematic diagram of an application scenario of method 100 in an embodiment of the present disclosure.

[0019] Figure 7 is a block diagram of a data verification device in an exemplary embodiment of the present disclosure.

[0020] Figure 8 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0022] In addition, the accompanying drawings are only schematic diagrams of the present disclosure, and the same reference numerals in the drawings represent the same or similar parts, so their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0023] The exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0024] Figure 1is a flow chart of a data verification method in an exemplary embodiment of the present disclosure.

[0025] refer to Figure 1 , the data verification method 100 may include:

[0026] Step S1, obtaining the product category and first configuration data of the standard product unit to be configured;

[0027] Step S2, determining a candidate standard product unit under the product category that has been successfully configured within a preset period before the current time point, and obtaining second configuration data of the candidate standard product unit;

[0028] Step S3, determining N reference standard product units with the highest reference degree among the candidate standard product units according to the similarity between the first configuration data and the second configuration data, where N≥1;

[0029] Step S4: verifying the first configuration data according to the second configuration data of the reference standard product unit.

[0030] The disclosed embodiment selects the most recently successfully configured candidate standard product units, selects the reference standard product unit with the highest reference degree from the candidate standard product units as the basis for data verification, and then verifies the first configuration data of the standard product unit to be configured. It can automatically adjust the current configuration data according to the configuration data of the most recent similar product. It is efficient and accurate compared to manual inspection. Compared to data comparison according to templates, it can reduce the risk of incomplete configuration due to outdated product templates, and timely provide the SPU configuration that best meets the current latest product characteristics.

[0031] SPU (Standard Product Unit) is the basic unit of commodity management. Its configuration data covers the core content of the commodity, such as commodity name, specification parameters, price positioning and detailed description, etc. It is the basis of SKU (Stock Keeping Unit). Based on SPU, multiple specific SKUs can be derived by further refining the specification information (such as color, size, capacity, etc.), simplifying the SKU creation process, because much of the basic information of SKU can be directly inherited from the corresponding SPU, and merchants only need to supplement the specific specification differences at the SKU level.

[0032] If the configuration data of SPU is wrong, it may cause a large number of SKUs to be displayed on the platform inconsistent with the actual products, such as errors or omissions in price, specifications, descriptions and other information, causing confusion in product management, making it impossible for the inventory management system to accurately track the inventory status of the products, leading to inventory backlogs or shortages. If the classification attribute of SPU is configured incorrectly, SKUs may be incorrectly classified into irrelevant categories, affecting consumers' search and purchasing experience.

[0033] Therefore, before listing SPU (Standard Product Unit), merchants must submit the configuration data of SPU for platform review. These configuration data include but are not limited to key attributes, sales attributes, ordering attributes, and general attributes. After the review is passed, the products corresponding to the SPU will be officially released to the platform for consumers to browse and purchase. In addition, in order to ensure the accuracy of the configuration data, after the SPU is listed, merchants also need to update and maintain the configuration data and submit it to the platform for re-review.

[0034] The method of the embodiment of the present disclosure can be applied to audit and verify the configuration data of the SPU.

[0035] Next, each step of the data verification method 100 is described in detail.

[0036] In step S1, the product category and first configuration data of the standard product unit to be configured are obtained.

[0037] In the embodiment of the present disclosure, the standard product unit to be configured (hereinafter referred to as the SPU to be configured) can be an SPU that has not been put on the shelf, or an SPU that has been put on the shelf for later maintenance.

[0038] Product category refers to the classification of the SPU to be configured under the commodity classification system. For example, mobile phones and smart watches belong to the electronic equipment or wearable device categories respectively.

[0039] The first configuration data is configuration data corresponding to the SPU to be configured, including multiple configuration items (configuration items are, for example, product price, model, etc.), each configuration item corresponds to an attribute type, and the attribute types include but are not limited to key attributes, sales attributes, ordering attributes, and general attributes, etc.

[0040] Key attributes are the core features used to define and distinguish different SPUs, and are the basis for the platform to classify, search, and recommend products. Key attributes can uniquely identify an SPU and distinguish it from other SPUs. For example, in the mobile phone category, brand and model are key attributes, and these two attributes can uniquely identify a mobile phone. After configuring key attributes, the platform can use these attributes to build indexes to improve the efficiency and accuracy of product searches. When consumers enter search keywords, the system can quickly match relevant SPUs. In addition, key attributes support consumers to compare between different SPUs.

[0041] Sales attributes refer to attributes directly related to the sale of goods. They determine the specific specifications and variants of goods, such as color, size, storage capacity, etc. By configuring sales attributes, the platform can provide a variety of product choices to meet the personalized needs of different consumers. For example, the same mobile phone can provide a variety of colors, storage capacities, and package options. Different combinations of sales attributes can form different SKUs (Stock Keeping Units). The platform can formulate different pricing strategies for different SKUs, so that consumers can choose the appropriate product specifications and variants according to their needs and budgets.

[0042] Order attributes include quantity, discount code, delivery address, etc., which are crucial to completing the product ordering process. The configuration of order attributes can ensure the accuracy of the order and avoid order problems caused by incomplete or incorrect information.

[0043] Common attributes refer to the common attributes applicable to all or most SPUs, such as product name, description, image, etc. The configuration of common attributes can improve user experience, enhance product credibility, support e-commerce platforms to display products on multiple sales channels, and ensure the consistency and coherence of product information on different channels.

[0044] In an exemplary embodiment, when obtaining the first configuration data of the standard product unit to be configured, the configuration items in the first configuration data can be referred to as first configuration items, and the configuration object (such as price, model) and attribute type (such as the attribute type corresponding to price is a sales attribute) of each first configuration item are determined.

[0045] In step S2, candidate standard product units under the product category that have been successfully configured within a preset period of time before the current time point are determined, and second configuration data of the candidate standard product units are obtained.

[0046] In the disclosed embodiment, an automatic verification method is used to improve the efficiency of configuration data review and verification. Conventional automatic verification methods usually use fixed templates for comparison, but due to the rapid product update speed, using fixed templates may not be able to verify whether the latest product is missing certain configuration items, or it is impossible to verify what attribute type a certain configuration item should correspond to.

[0047] For example, when the NFC function first appeared, the latest mobile phones supported the NFC function, but most mobile phones on the market do not support the NFC function. If the configuration data of the latest mobile phones is reviewed according to a fixed template, it is impossible to determine whether the configuration data of the mobile phone is missing the configuration items for the NFC function. Even if the configuration data of the mobile phone has the configuration items for the NFC function, it is impossible to determine whether the configuration items for the NFC function of the mobile phone are classified incorrectly. Alternatively, the fixed template includes the verification of the configuration items of the headphone jack of the mobile phone, but many mobile phones no longer have headphone jacks. According to the fixed template, it is impossible to determine whether the configuration data of the mobile phone has missed the configuration items for the headphone jack or whether the headphone jack is not set normally. If all similar doubts are reported as errors, it will cause multiple invalid reworks, greatly reducing the efficiency of SPU configuration.

[0048] Therefore, the embodiment of the present disclosure uses dynamic data to verify the first configuration data of the SPU to be configured, and determines multiple SPUs of the same category as the SPU to be configured from the SPUs that have been successfully configured (effective) within a preset time period before the current time point as candidate SPUs (candidate standard product units), selects N reference SPUs with the largest reference degrees based on the candidate SPUs, and compares and verifies the first configuration data based on the configuration data of the reference SPUs, so that the first configuration data can be efficiently and automatically reviewed and verified using the latest product information, greatly improving the accuracy of data verification.

[0049] The preset period can be determined based on the key information of the SPU to be configured, that is, the product category. For example, for the mobile phone category, the preset period can be set to one week, and for the refrigerator category, the preset period can be set to one month, etc. The above data is only an example and does not limit the actual value.

[0050] In an exemplary embodiment, the SPUs that have been successfully configured within the most recent preset period under the product category corresponding to the SPU to be configured can be determined as candidate SPUs, and the configuration data of the candidate SPUs is called second configuration data. The second configuration data of these candidate SPUs are all configuration data of the latest products on the shelves, and the settings of the configuration items are in line with the characteristics of recent products, and there will be no problem of template outdatedness.

[0051] Next, the candidate SPUs need to be further screened to improve the verification accuracy.

[0052] In step S3, N reference standard product units with the highest reference degree are determined from among the candidate standard product units according to the similarity between the first configuration data and the second configuration data.

[0053] Figure 2 It is a sub-flow chart of step S3 in one embodiment of the present disclosure.

[0054] refer to Figure 2 In an exemplary embodiment, step S3 may include:

[0055] Step S31, determining the similarity between the candidate standard product unit and the standard product unit to be configured according to the second configuration data and the first configuration data;

[0056] Step S32, determining the reference weight of the candidate standard product unit according to the activation success rate of the inventory unit corresponding to the candidate standard product unit;

[0057] Step S33, determining the reference degree of the candidate standard product unit according to the similarity and the reference weight;

[0058] Step S34, determining the complexity of the first configuration data, and determining a value N according to the complexity;

[0059] Step S35 , determining N reference standard product units with the highest reference degrees among the candidate standard product units.

[0060] In an exemplary embodiment, N SPUs that are similar and have high reference value can be further screened from SPUs of the same product type and that have been successfully configured recently, so as to improve the accuracy of the selected reference SPUs, reduce the risk of data errors caused by inaccurate data during the automatic verification process, and effectively improve the accuracy of the automatic verification results.

[0061] Among them, in step S31, the similarity between the candidate SPU and the SPU to be configured is calculated, and a reference target that is as close as possible to the SPU to be configured can be screened out. For example, the category of the SPU to be configured is a mobile phone, and the function includes a folding screen. When screening the candidate SPU, all the mobile phones that have been successfully configured recently may be determined as candidate SPUs. Then in step S31, based on the similarity information, it can be determined that the similarity of the folding screen mobile phone in the candidate SPU is greater, and the similarity of the straight screen mobile phone is smaller. When the reference SPU is determined later, the folding screen mobile phone is more likely to be determined as the reference SPU.

[0062] There are many methods for determining the similarity between the candidate SPU and the SPU to be configured, such as comparing the similarity between the configuration objects corresponding to the configuration items of the candidate SPU and the SPU to be configured, comparing whether certain configuration items of the candidate SPU and the SPU to be configured are exactly the same, etc., or calculating the similarity between the candidate SPU and the SPU to be configured based on partial information of the candidate SPU and the SPU to be configured, such as name, label, mapped SKU, key attributes and their values.

[0063] In an exemplary embodiment, in order to improve the accuracy of similarity, a similarity determination method based on the integration of text vector similarity and Jaccard coefficient is provided.

[0064] Figure 3 It is a sub-flowchart of step S31 in one embodiment of the present disclosure.

[0065] refer to Figure 3 In an exemplary embodiment, step S31 may include:

[0066] Step S311, determining the text vector similarity between the second configuration data and the first configuration data of the candidate standard product unit;

[0067] Step S312, determining the Jaccard coefficients of the second configuration data and the first configuration data of the candidate standard product unit;

[0068] Step S313, determining the similarity between the candidate standard product unit and the standard product unit to be configured based on the weighted sum of the text vector similarity and the Jaccard coefficient corresponding to the candidate standard product unit.

[0069] refer to Figure 3 , the first configuration data and the second configuration data can both be represented as text information, and the text vector similarity between the candidate SPU and the SPU to be configured can be calculated based on pre-trained models such as BERT, XLNet, etc., denoted as A; configuration items such as labels, mapped SKUs, key attributes + values, and other multiple data are relatively independent, and the Jaccard coefficient between the candidate SPU and the SPU to be configured can be calculated, denoted as B, that is, the ratio of the number of intersections and the number of unions of the configuration items of the candidate SPU and the SPU to be configured. The Jaccard coefficient measures the similarity between sets by the ratio of the size of the intersection and the union between sets. The larger the value of this coefficient, the higher the similarity between samples.

[0070] Combining the calculation results of the above two analysis methods, the similarity between each candidate SPU and the SPU to be configured can be obtained by weighted calculation. The similarity of the i-th candidate SPU is recorded as Si=αA+βB, α+β=1, where α and β are set according to the actual data calculation effect.

[0071] In addition to considering similarity, the embodiment of the present disclosure also considers the accuracy of the configuration data of the candidate SPU. In an exemplary embodiment, the reference weight of a candidate SPU is determined by the activation success rate of the SKU corresponding to the candidate SPU. The higher the activation success rate of the corresponding SKU, the more accurate the configuration data of the SPU. The activation success rate refers to the proportion of SKUs associated with the SPU that have been ordered and activated, that is, the activation success rate = the number of successful activations / the total number of orders, which is used as the reference weight C of the candidate SPU.

[0072] In addition, the number of reference SPUs needs to be determined. Figure 3 In the illustrated embodiment, in step S33, the complexity may be determined according to the number of items of the first configuration data, where the greater the number of items, the greater the complexity, and then a value N is determined according to the complexity, where the greater the complexity, the greater the value N.

[0073] The more configuration items of the SPU to be configured, the more reference SPUs there are, which can effectively improve the accuracy of automatic verification and prevent inaccurate data from being generated when automatic verification is performed using an inappropriately matching reference SPU due to the complexity of the configuration items of the SPU to be configured and the inability to match a completely similar reference SPU.

[0074] N can be calculated by substituting the number of items of the first configuration data into a preset formula, or the number of items of the first configuration data can be directly used as N, and the present disclosure does not impose any special restrictions on this.

[0075] In step S34, the reference degree of the candidate standard product unit is determined according to the similarity and the reference weight, for example, the reference degree of the ith candidate SPU is obtained by multiplying the similarity R=Si×Ci, where Ci is the reference weight of the ith candidate SPU.

[0076] In step S35, the N candidate SPUs with the highest reference degree are used as reference SPUs, that is, the most similar and most worthy of reference N candidate SPUs are selected as the basis for the subsequent automatic verification.

[0077] By combining the text vector similarity and the quantitative similarity between configuration items (Jaccard coefficient), candidate SPUs similar to the SPU to be configured are found. At the same time, the activation success rate of the SKU corresponding to the candidate SPU is used as its reference metric value to screen out N SPUs that are both similar and have high reference value, taking into account both the most similar and the most referenceable, thereby improving the availability of the selected reference SPU.

[0078] go through Figure 3The screening of the illustrated embodiment, which serves as the reference SPU based on automatic verification, has both verified accuracy (high activation success rate) and is relatively similar to the SPU to be configured (for example, they are all folding screen mobile phones, rather than using the configuration data of a straight-screen mobile phone to verify the configuration data of a folding screen mobile phone). It is also relatively timely, meets the characteristics of the latest products, and can provide accurate verification benchmark data.

[0079] In step S4, the first configuration data is verified according to the second configuration data of the reference standard product unit.

[0080] In some embodiments, the first configuration data can be directly verified based on the configuration data of the reference SPU to determine whether the first configuration data has missed some configuration items or has incorrectly set some configuration items. However, since each SPU is not exactly the same, the modification suggestions given based on different reference SPUs may be contradictory. Therefore, the exemplary embodiments of the present disclosure provide a solution for automatic verification using a reference SPU to further improve the accuracy of the verification.

[0081] Figure 4 It is a sub-flow chart of step S4 in one embodiment of the present disclosure.

[0082] refer to Figure 4 In an exemplary embodiment, step S4 may include:

[0083] Step S41, determining a plurality of first configuration items of the first configuration data and a configuration object corresponding to each first configuration item, and determining a plurality of second configuration items of the second configuration data and a configuration object corresponding to each second configuration item;

[0084] Step S42, determining the missing configuration item of the first configuration data according to the comparison result of the configuration object of the second configuration item and the configuration object of the first configuration item;

[0085] Step S43: determining the configuration items to be added in the first configuration data according to the missing configuration items corresponding to the N reference standard product units.

[0086] refer to Figure 4 The configuration items in the second configuration data are called second configuration items, which are distinguished from the first configuration items of the first configuration data. When determining whether the first configuration data misses some configuration items, modification suggestions may be firstly given based on each reference SPU.

[0087] For example, a reference SPU is compared with a SPU to be configured for configuration items. If a configuration item exists in the reference SPU but not in the SPU to be configured, the configuration item is set as a missing configuration item and recorded as the missing configuration item corresponding to the reference SPU.

[0088] Different reference SPUs may give different missing configuration items. Next, different sets of missing configuration items are integrated.

[0089] Figure 5 It is a sub-flowchart of step S43 in one embodiment of the present disclosure.

[0090] refer to Figure 5 In an exemplary embodiment, step S43 may include:

[0091] Step S431, determining the reference degree of the missing configuration item according to the missing configuration item corresponding to the reference standard product unit and the reference degree of the reference standard product unit;

[0092] Step S432, forming a missing configuration item set according to the missing configuration items corresponding to the N reference standard product units and the reference degree of each missing configuration item;

[0093] Step S433, merging identical missing configuration items in the missing configuration item set, and the reference degree of the missing configuration item after merging is the sum of the reference degrees before merging;

[0094] Step S434: determining the configuration item to be added in the first configuration data according to the reference degree of the missing configuration item.

[0095] refer to Figure 5 In an exemplary embodiment, the modification recommendation degree (reference degree) of each missing configuration item given by the reference SPU can be determined according to the reference degree of the reference SPU. Then, a missing configuration item set is formed according to the missing configuration items (labeled reference degrees) given by multiple reference SPUs to compare the missing configuration items given by all reference SPUs together. It can be understood that Figure 5 In the illustrated embodiment, the missing configuration items in the formed missing configuration item set are all second configuration items.

[0096] In the process of comparing the missing configuration items given by all reference SPUs, the same items are first merged, and the reference degree of the missing configuration items after merging is the sum of the reference degrees before merging.

[0097] In an exemplary embodiment, the same missing configuration items in the missing configuration item set may be merged first so that the missing configuration items in the missing configuration item set do not overlap, and then the reference degrees R of the N reference SPUs are superimposed as weights to obtain the reference degree DT of the missing configuration item j (j≥1):

[0098]

[0099] in Indicates whether the i-th reference SPU has given (can also be called corresponding) missing configuration item j. The value can only be 0 and 1. 0 means that the missing configuration item j is not given, and 1 means that the missing configuration item j is given.

[0100] For example, reference SPU1 gives missing configuration items A, B, and C, and the reference degree of reference SPU1 is 0.9; reference SPU2 gives missing configuration items B, C, and D, and the reference degree of reference SPU2 is 0.7; reference SPU3 gives missing configuration items C and D, and the reference degree of reference SPU3 is 0.6. Then, there are four missing configuration items A, B, C, and D in the final configuration item set. The reference degree corresponding to missing configuration item A is DTA=0.9×1+0+0=0.9, and the reference degree corresponding to missing configuration item B is DTB=0.9×1+0.7×1+0=1.6, and so on. The reference degree corresponding to the missing configuration item can also be called the modification recommendation degree.

[0101] See Table 1 for data relationships:

[0102] Table 1:

[0103]

[0104] Finally, they are arranged from high to low in terms of reference degree as C, B, D, and A.

[0105] A reference threshold of missing configuration items can be set to determine the configuration items added in the first configuration data from the missing configuration items. For example, if the reference threshold of missing configuration items is set to 1, then in the example of Table 1, the user can be prompted to add three configuration items B, C, and D so that the user can modify the configuration data. Alternatively, the three configuration items B, C, and D are automatically added to the first configuration data. In the scenario where the configuration item value needs to be filled in, the value of the configuration item can be set as blank and marked with a prompt mark to prompt the user to fill in the value corresponding to the configuration item.

[0106] pass Figure 5 The illustrated embodiment not only relies on the number of missing configuration items given by each reference SPU for judgment, but also considers the reliability of each reference SPU, that is, the reference degree. The final automatic verification result is tested experimentally, and the accuracy is greatly improved, thus avoiding a lot of useless rework and alarms.

[0107] In addition to verifying the missing configuration items of the SPU to be configured according to the configuration data of the reference SPU, it is also possible to verify whether each configuration item of the SPU to be configured is correctly filled out according to the configuration data of the reference SPU, for example, whether it is accurately classified.

[0108] In an exemplary embodiment, the attribute type of each first configuration item and the attribute type of each second configuration item can be determined; the attribute error configuration item in the first configuration item is determined based on the comparison result of the attribute type between the second configuration item with the same configuration object and the first configuration item; and the attribute error configuration item modified in the first configuration data is determined based on the attribute error configuration items corresponding to N reference standard product units.

[0109] Wherein, determining the attribute error configuration item in the first configuration item according to the comparison result of the attribute type between the second configuration item and the first configuration item having the same configuration object is to judge that the first configuration item may be an attribute error configuration item when the configuration objects of the first configuration item and the second configuration item are the same (for example, both are memory size) and the attribute types are different, or to judge that the first configuration item may be an attribute error configuration item when the configuration objects of the first configuration item and the second configuration item are similar (for example, one is memory size and the other is ROM size) and the attribute types are different.

[0110] In some embodiments, the process of determining attribute error configuration items can be the same as the process of determining missing configuration items. For example, both are based on the attribute error configuration items given by each reference SPU, and the configuration items whose attribute errors need to be modified in the first configuration data are given in combination with the reference values ​​of each reference SPU.

[0111] In other embodiments, if the attribute error configuration item is determined under the condition that the configuration objects of the first configuration item and the second configuration item are the same, it is also possible to directly determine that the configuration item is an attribute error configuration item without considering the reference value of the reference SPU.

[0112] In an exemplary embodiment, the second configuration items corresponding to the sales attributes, ordering attributes, and general attributes of the reference SPU may be classified and compared with the first configuration items corresponding to the three attributes of the SPU to be configured to determine missing configuration items and configuration items with incorrect attributes.

[0113] In addition to determining whether the above-mentioned configuration items are missing or the configuration item attribute types are filled in incorrectly, other aspects of the first configuration data of the SPU to be configured can also be verified based on the second configuration data of the reference SPU to determine whether they are correct, such as brand and model consistency, specification parameter accuracy, category attribution accuracy, price rationality, inventory accuracy, and the rationality of associated products (such as accessories and gifts).

[0114] In an exemplary embodiment, the brand and model in the first configuration data of the SPU to be configured can be directly compared with the corresponding fields in the second configuration data of the reference SPU to ensure that the brand name and model description are accurate and avoid errors caused by typos or formatting problems. For versions of the same brand in different markets or regions, there may be differences in model numbers. However, since the reference SPU and the SPU to be configured are more similar, the two are most likely versions of the same market or region, and accurate verification suggestions can be provided. However, when it comes to brand names and models, it is also possible to further use a reference SPU in the reference SPU whose brand name is exactly the same as that of the SPU to be configured to provide verification suggestions.

[0115] In an exemplary embodiment, the specification parameters (such as color, size, weight, material, etc.) of the SPU to be configured can be compared item by item with the corresponding parameters of the reference SPU to ensure that the specification parameters are detailed and accurate to avoid omissions or errors. For products of different batches or production dates, the specification parameters may vary, but since the reference SPUs are all recent products, the accuracy of the verification suggestions is unlikely to be affected by the batch or production date, and accurate verification suggestions can be provided.

[0116] In an exemplary embodiment, the category attribution of the SPU to be configured can be compared with the category attribution of the reference SPU to analyze whether there is a difference. Since the reference SPUs are all products of similar product type to the SPU to be configured, the possibility of the product type (category attribution) being judged to be wrong is small. However, if the reference degree of the reference SPU is low (for example, all lower than the preset value of 50%), or the number of missing items given is significantly greater than the preset threshold, it can be determined that the product type of the SPU to be configured, that is, the category attribution setting is wrong. For example, in most cases, the number of missing configuration items may be less than 10 items. If the number of missing configuration items is prompted to be 50, it means that the category setting is obviously unreasonable. For some cross-category or special category products, this phenomenon is very easy to occur. In this scenario, the verification value of the reference SPU screened according to the embodiment of the present disclosure is very high, and it can promptly discover unreasonable category attribution settings.

[0117] In an exemplary embodiment, a reasonable price range can be determined based on the prices of each reference SPU, and then it can be determined whether the price of the SPU to be configured is within the reasonable price range. If it is not within the reasonable price range, a modification suggestion can be generated. For example, based on the prices of multiple reference SPUs, it is determined that the reasonable price range of similar mobile phones is between 3,000 yuan and 5,000 yuan. If the price of the SPU (mobile phone) to be configured is 1, or the price is 999,999, it can be determined that the price is unreasonable, and a modification suggestion is generated.

[0118] In an exemplary embodiment, it is possible to determine whether the associated commodities of the SPU to be configured are reasonable based on the associated commodities of each reference SPU, such as accessories, gifts, etc. For example, it is determined based on the reference SPU that the associated commodities of a mobile phone are usually mobile phone cases, data cables, chargers, headphones, etc. If the associated commodities of a SPU to be configured (mobile phone) are sports shoes or refrigerators, it can be determined that the associated commodities are unreasonable and a modification suggestion is generated.

[0119] There are many other ways to use the reference SPU, and those skilled in the art can configure them according to the development of technology.

[0120] Figure 6 It is a schematic diagram of an application scenario of method 100 in an embodiment of the present disclosure.

[0121] refer to Figure 6 In an application scenario, the commodity configuration process 600 may include five processes: product category configuration 61, SPU configuration 62, SKU configuration 63, commodity combination configuration 64, and promotion activity configuration 65. The data verification link is located in SPU configuration 62.

[0122] The method of the embodiment of the present disclosure is used to perform data verification, determine the candidate SPU that has been successfully configured recently based on historical data, and then screen out N similar and referenceable reference SPUs, and verify the first configuration data of the SPU to be configured based on N second configuration data (second configuration data 1 to second configuration data N) of the N reference SPUs, and provide a verification result, wherein the configuration data includes multiple configuration items, and the attribute types of the configuration items include basic information, key attributes, subscription attributes, common attributes, etc.

[0123] The verification result can include modification suggestions or directly give the modification result for the user to confirm. The user can modify or confirm according to the verification result, or set some modification items as not to be modified, and then submit the modified configuration data again.

[0124] Considering the items that the user indicates do not need to be modified, the modified configuration data is automatically verified again, and the above process is repeated until there are no modification suggestions or modifications, and it is determined to have passed the verification. Next, the configuration data that has passed the verification can be put on the shelf, or put on the shelf after manual review.

[0125] Since the data verification method provided by the embodiment of the present disclosure has high accuracy, direct listing can maintain a high accuracy rate. Even if manual review is required, the amount of manual review can be greatly saved, greatly improving the management efficiency of the platform and the accuracy of information.

[0126] It should be noted that after the SPU to be configured is put on the shelf, the SPU is determined to be configured successfully, and its configuration data when it is put on the shelf may be used as second configuration data to participate in the reference SPU selection when other SPUs to be configured are subsequently verified.

[0127] To summarize, the disclosed embodiment selects the most recent and most valuable reference data based on recent historical data (including configuration data and subscription activation status), performs data verification on the configuration data of the SPU configuration link that is earlier in the entire process, and can output suggested modification items and modification recommendation degrees as feedback, so as to improve the SPU data as much as possible in the early stage of the process, improve the availability of SPU configuration data, and improve the efficiency of product listing.

[0128] Corresponding to the above method embodiments, the present disclosure also provides a data verification device, which can be used to execute the above method embodiments.

[0129] Figure 7 is a block diagram of a data verification device in an exemplary embodiment of the present disclosure.

[0130] refer to Figure 7 , the data verification device 700 may include:

[0131] A verification object determination module 71 is configured to obtain a product category and first configuration data of a standard product unit to be configured;

[0132] A candidate object determination module 72 is configured to determine a candidate standard product unit under the product category that has been successfully configured within a preset period before the current time point, and obtain second configuration data of the candidate standard product unit;

[0133] A reference object determination module 73, configured to determine N reference standard product units with the highest reference degree among the candidate standard product units according to the similarity between the first configuration data and the second configuration data;

[0134] The verification module 74 is configured to verify the first configuration data according to the second configuration data of the reference standard product unit.

[0135] In an exemplary embodiment of the present disclosure, the reference object determination module 73 is configured to: determine the similarity between the candidate standard product unit and the standard product unit to be configured based on the second configuration data and the first configuration data; determine the reference weight of the candidate standard product unit based on the activation success rate of the inventory unit corresponding to the candidate standard product unit; determine the reference degree of the candidate standard product unit based on the similarity and the reference weight; determine the complexity of the first configuration data, and determine a value N based on the complexity; and determine the N reference standard product units with the highest reference degrees among the candidate standard product units.

[0136] In an exemplary embodiment of the present disclosure, the reference object determination module 73 is configured to: determine the text vector similarity between the second configuration data and the first configuration data of the candidate standard product unit; determine the Jaccard coefficient between the second configuration data and the first configuration data of the candidate standard product unit; and determine the similarity between the candidate standard product unit and the standard product unit to be configured based on the weighted sum of the text vector similarity corresponding to the candidate standard product unit and the Jaccard coefficient.

[0137] In an exemplary embodiment of the present disclosure, the reference object determination module 73 is configured to: determine the complexity according to the number of items in the first configuration data, the more items, the greater the complexity; determine the value N according to the complexity, the greater the complexity, the greater the value N.

[0138] In an exemplary embodiment of the present disclosure, the verification module 74 is configured to: determine multiple first configuration items of the first configuration data and the configuration object corresponding to each first configuration item, determine multiple second configuration items of the second configuration data and the configuration object corresponding to each second configuration item; determine the missing configuration items of the first configuration data based on the comparison results of the configuration objects of the second configuration items and the configuration objects of the first configuration items; determine the configuration items to be added in the first configuration data based on the missing configuration items corresponding to N reference standard product units.

[0139] In an exemplary embodiment of the present disclosure, the verification module 74 is configured to: determine the reference degree of the missing configuration item based on the missing configuration item corresponding to the reference standard product unit and the reference degree of the reference standard product unit; form a missing configuration item set based on the missing configuration items corresponding to N reference standard product units and the reference degree of each missing configuration item; merge the same missing configuration items in the missing configuration item set, and the reference degree of the merged missing configuration item is the sum of the reference degrees before the merger; determine the configuration item to be added in the first configuration data based on the reference degree of the missing configuration item.

[0140] In an exemplary embodiment of the present disclosure, the verification module 74 is configured to: determine the attribute type of each first configuration item and the attribute type of each second configuration item; determine the attribute error configuration item in the first configuration item based on the comparison result of the attribute type between the second configuration item and the first configuration item with the same configuration object; determine the attribute error configuration item modified in the first configuration data based on the attribute error configuration items corresponding to N reference standard product units.

[0141] Since the functions of the device 700 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0142] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0143] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0144] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0145] Refer to the following Figure 8 An electronic device 800 according to this embodiment of the present invention will be described. Figure 8 The electronic device 800 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0146] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810).

[0147] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the method shown in the embodiment of the present disclosure.

[0148] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 8201 and / or a cache storage unit 8202 , and may further include a read-only storage unit (ROM) 8203 .

[0149] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0150] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0151] The electronic device 800 can also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be carried out through an input / output (I / O) interface 850. In addition, the electronic device 800 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter 860. As shown in the figure, the network adapter 860 communicates with other modules of the electronic device 800 through a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0152] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0153] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0154] The program product for implementing the above method according to an embodiment of the present invention can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0155] The program product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0156] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0157] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0158] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including programming languages ​​oriented to standard product units, such as Java, C++, etc., and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0159] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0160] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered exemplary only, and the true scope and concept of the present disclosure are indicated by the claims.

Claims

1. A data verification method, characterized in that: include: Acquire the product category and first configuration data of the standard product unit to be configured; Determine a candidate standard product unit under the product category that has been successfully configured within a preset period of time before the current time point, and obtain second configuration data of the candidate standard product unit; Determine N reference standard product units with the highest reference degree among the candidate standard product units according to the similarity between the first configuration data and the second configuration data, where N≥1, and the reference degree is determined according to the similarity between the candidate standard product unit and the standard product unit to be configured and the reference weight of the candidate standard product unit, and the reference weight is determined according to the activation success rate of the inventory unit corresponding to the candidate standard product unit; The first configuration data is verified according to the second configuration data of the reference standard product unit, and the verification includes determining missing configuration items and incorrectly set configuration items of the first configuration data.

2. The data verification method according to claim 1, characterized in that: Determining the N reference standard product units with the highest reference degree among the candidate standard product units according to the similarity between the first configuration data and the second configuration data comprises: Determining the similarity between the candidate standard product unit and the standard product unit to be configured according to the second configuration data and the first configuration data; Determining a reference weight of the candidate standard product unit according to an activation success rate of a stock quantity unit corresponding to the candidate standard product unit; Determining the reference degree of the candidate standard product unit according to the similarity and the reference weight; Determine the complexity of the first configuration data, and determine a value N according to the complexity; Determining the N reference standard product units with the highest reference degrees among the candidate standard product units; Among them, determining the complexity of the first configuration data and determining the numerical value N according to the complexity includes: determining the complexity according to the number of items in the first configuration data, the more items, the greater the complexity; determining the numerical value N according to the complexity, the greater the complexity, the greater the value N.

3. The data verification method according to claim 2, characterized in that: Determining the similarity between the candidate standard product unit and the to-be-configured standard product unit according to the second configuration data and the first configuration data includes: determining text vector similarity between the second configuration data of the candidate standard product unit and the first configuration data; determining a Jaccard coefficient of second configuration data of the candidate standard product unit and the first configuration data; The similarity between the candidate standard product unit and the standard product unit to be configured is determined according to a weighted sum of the text vector similarity corresponding to the candidate standard product unit and the Jaccard coefficient.

4. The data verification method according to any one of claims 1 to 3, characterized in that: Verifying the first configuration data according to the second configuration data of the reference standard product unit includes: Determine a plurality of first configuration items of the first configuration data and a configuration object corresponding to each of the first configuration items, and determine a plurality of second configuration items of the second configuration data and a configuration object corresponding to each of the second configuration items; Determine the missing configuration item of the first configuration data according to a comparison result of the configuration object of the second configuration item with the configuration object of the first configuration item; Determine the configuration items to be added in the first configuration data according to the missing configuration items corresponding to the N reference standard product units; The step of determining the configuration items to be added to the first configuration data according to the missing configuration items corresponding to the N reference standard product units includes: Determining the reference degree of the missing configuration item according to the missing configuration item corresponding to the reference standard product unit and the reference degree of the reference standard product unit; Forming a missing configuration item set according to the missing configuration items corresponding to the N reference standard product units and the reference degree of each of the missing configuration items; Merging identical missing configuration items in the missing configuration item set, where the reference degree of the missing configuration items after merging is the sum of the reference degrees before merging; The configuration item to be added to the first configuration data is determined according to the reference degree of the missing configuration item.

5. The data verification method according to claim 4, characterized in that: Verifying the first configuration data according to the second configuration data of the reference standard product unit further includes: Determine an attribute type of each of the first configuration items and an attribute type of each of the second configuration items; Determine an attribute error configuration item in the first configuration item according to a comparison result of the attribute types of the second configuration item and the first configuration item having the same configuration object; Determine, based on the attribute error configuration items corresponding to the N reference standard product units, to modify the attribute error configuration item in the first configuration data.

6. A data verification device, characterized in that: include: A verification object determination module, configured to obtain a product category and first configuration data of a standard product unit to be configured; A candidate object determination module, configured to determine a candidate standard product unit under the product category that has been successfully configured within a preset period before a current time point, and obtain second configuration data of the candidate standard product unit; a reference object determination module, configured to determine N reference standard product units with the highest reference degrees among the candidate standard product units according to the similarity between the first configuration data and the second configuration data, wherein the reference degrees are determined according to the similarity between the candidate standard product units and the standard product units to be configured and the reference weights of the candidate standard product units, and the reference weights are determined according to the activation success rates of the inventory units corresponding to the candidate standard product units; The verification module is configured to verify the first configuration data according to the second configuration data of the reference standard product unit, wherein the verification includes determining configuration items missing from the first configuration data and configuration items incorrectly set.

7. An electronic device, characterized in that: include: Memory; as well as A processor coupled to the memory, the processor being configured to execute the method according to any one of claims 1 to 5 based on instructions stored in the memory.

8. A computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images