Product information processing method, product recall method, device and server

Abstract

Embodiments of the present application provide a commodity information processing method, a commodity recall method, a device, a server and a computer readable storage medium. The commodity information processing method comprises: obtaining SKU codes of inventory units of a plurality of commodities in a commodity library; if the total number of SKU codes of commodities belonging to the same type in the plurality of commodities is greater than or equal to a preset threshold, performing a first bucketing operation on the SKU codes of the commodities belonging to the same type to obtain a plurality of first type buckets; distributing the commodities belonging to the same type into the plurality of first type buckets; performing a second bucketing operation on commodities having the same SKU code among the commodities belonging to the same type to obtain a plurality of second type buckets; and distributing the commodities belonging to the same type into the plurality of second type buckets. The embodiments of the present application can improve the diversity of recalled commodities.

Description

Technical Field

[0001] This application belongs to the field of Internet technology, specifically relating to the field of product search technology, and in particular to a product information processing method, product recall method, device, server, and computer-readable storage medium. Background Technology

[0002] With the rapid development of internet technology, e-commerce platforms are constantly launching new functions and services to meet the diverse consumption needs of users. For example, large-scale e-commerce platforms not only sell their own products but also provide sales interfaces for affiliated individual merchants. Some can even provide interfaces for individuals or businesses to sell second-hand goods, forming a unified sales platform that integrates product data from multiple sources.

[0003] When users enter search information on e-commerce platforms, the system returns a list of products including information on multiple items. However, because e-commerce platforms (especially second-hand e-commerce platforms) have too many sellers offering the same or similar products, the returned products are highly similar, resulting in high product duplication and poor diversity. For example, the product list may contain multiple items with the same model, attributes (such as color, size, condition, etc.), and price. This leads to a poor user experience and reduces user satisfaction. Summary of the Invention

[0004] In view of the above, this application proposes a product information processing method, a product recall method, an apparatus, a server, and a computer-readable storage medium to solve at least one of the above technical problems.

[0005] In a first aspect, embodiments of this application provide a product information processing method, including:

[0006] Retrieve the SKU code of multiple products in the product database to measure their inventory quantity;

[0007] If the total number of SKU codes of the same type of products among the multiple products is greater than or equal to a preset threshold, then the first binning operation is performed on the SKU codes of the same type of products to obtain multiple first-class bins;

[0008] The goods belonging to the same type are allocated into the plurality of first-type barrels;

[0009] A second binning operation is performed on products with the same SKU code belonging to the same type of products to obtain multiple second-category bins;

[0010] The goods belonging to the same type are allocated into the plurality of second-type barrels.

[0011] Secondly, embodiments of this application provide a product recall method, which is based on the product information processing method described above, and the product recall method includes:

[0012] Receive product search information;

[0013] If there are products matching the product search information in multiple first-class buckets, and there are also products matching the product search information in multiple second-class buckets, then select one first-class bucket from the multiple first-class buckets, and select one second-class bucket from the multiple second-class buckets.

[0014] Return the product information from the selected first and second type of buckets.

[0015] Thirdly, embodiments of this application provide a commodity information processing device, comprising:

[0016] The acquisition module is used to obtain the SKU code of the inventory quantity of multiple products in the product library;

[0017] The first binning operation module is used to perform a first binning operation on the SKU codes of the same type of goods among the multiple goods when the total number of SKU codes of the same type of goods is greater than or equal to a preset threshold, so as to obtain multiple first-class bins.

[0018] The first allocation module is used to allocate the goods of the same type to the plurality of first-type buckets;

[0019] The second binning operation module is used to perform a second binning operation on products with the same SKU code belonging to the same type of products, to obtain multiple second-type bins;

[0020] The second allocation module is used to allocate the goods belonging to the same type to the plurality of second-type buckets.

[0021] Fourthly, embodiments of this application provide a product recall device, which is based on the aforementioned product information processing method. The product recall device includes:

[0022] The receiving module is used to receive product search information;

[0023] The selection module is used to select one first-class bucket from the multiple first-class buckets and select one second-class bucket from the multiple second-class buckets when there are products matching the product search information in multiple first-class buckets and multiple second-class buckets.

[0024] The return module is used to return the product information from the selected first and second type of buckets.

[0025] Fifthly, this application provides a server, the server comprising: a processor and a memory storing computer program instructions; the server implements the method described above when executing the computer program instructions.

[0026] Sixthly, this application provides a computer storage medium, characterized in that the computer storage medium stores computer program instructions, which, when executed by a processor, implement the method described above.

[0027] The embodiments of this application perform two binning operations on the products. The two binning operations are binning of the same type of products at different granularities. The two binning operations are used in combination. When binning the same type of products, the situation of duplicate SKU codes and the clustering of homogeneous products under the same SKU code can be avoided to the greatest extent. Therefore, the diversity of the product list when recalling products can be improved and the duplication problem caused by the clustering of homogeneous products in the product list can be reduced. Attached Figure Description

[0028] The preferred embodiments of this application will now be described in further detail with reference to the accompanying drawings, wherein:

[0029] Figure 1 This is a flowchart of a product information processing method according to an embodiment of this application;

[0030] Figure 2 This is a flowchart of a product recall method according to an embodiment of this application;

[0031] Figure 3 This is a schematic diagram illustrating the process of performing two types of binning operations on goods according to the goods information processing method of this application embodiment;

[0032] Figure 4 This is a schematic diagram illustrating the process of returning a target product list according to the product recall method of this application embodiment;

[0033] Figure 5A and Figure 5B These are schematic diagrams showing statistical data of search results before and after applying the embodiments of this application;

[0034] Figure 6 This is a structural block diagram of a commodity information processing apparatus according to an embodiment of this application;

[0035] Figure 7 This is a structural block diagram of a product recall device according to an embodiment of this application;

[0036] Figure 8 This is a schematic diagram of a server used to implement the product information processing method or product recall method of the embodiments of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] In the following detailed description, reference can be made to the accompanying drawings, which form part of this application and illustrate specific embodiments of the present application. In the drawings, similar reference numerals describe substantially similar components in different figures. Specific embodiments of the present application are described in sufficient detail below to enable those skilled in the art to implement the technical solutions of the present application. It should be understood that other embodiments may also be utilized, or structural, logical, or electrical changes may be made to the embodiments of the present application.

[0039] To address the existing problems, this application proposes a product information processing method. First, the general concept of the solution is briefly described. Different users may use different search terms when searching for products of interest. When the search target is clear, they may directly search for keywords related to a specific brand or model. When the search target is unclear, they may only enter the product category as a search keyword. Therefore, while meeting the user's search needs, it is necessary to return as much diverse product information as possible, that is, to provide diverse choices. To this end, the inventors of this application have considered the following processing strategy:

[0040] ① When a user's search intent is clear, display products with multiple price points and attributes that match their search needs. For example, if a user searches for a specific model of mobile phone, their search intent is clear, and the returned product list can display mobile phones of that model with multiple attributes, such as different colors, capacities, conditions, and price points, thereby increasing the diversity of the product list.

[0041] ② When a user's search intent is unclear, display multiple models of products that match their search needs. For example, if a user only searches for "phones" and their search intent is unclear, the returned product list should display as many models (or types) of phones as possible to provide the user with diverse phone options, thereby increasing the diversity of the product list.

[0042] Additionally, regarding SKU codes, these typically refer to the codes for stockkeeping units (SKUs) generated based on product attributes. They can be abbreviated as SKU-ID or SKU. Products with the same attributes have the same SKU-ID, and products with the same SKU-ID are considered homogeneous. Since homogeneous products are essentially duplicates, it's important to avoid having a cluster of homogeneous products during product recalls.

[0043] Based on the above ideas, the product information processing solution designed in this application performs two types of binning operations on the products. The combination of the two binning operations helps to improve the diversity of recalled products and eliminate the duplication caused by homogeneous products, which can provide users with diversified choices and improve the user's product search experience.

[0044] refer to Figure 1 , Figure 1 A flowchart illustrating a product information processing method according to an embodiment of this application is shown, which includes:

[0045] S102, retrieve the SKU code of multiple products in the product library;

[0046] S104, If the total number of SKU codes of the same type of goods among the multiple goods is greater than or equal to a preset threshold, then perform a first binning operation on the SKU codes of the same type of goods to obtain multiple first-class bins;

[0047] S106, the goods belonging to the same type are allocated to the plurality of first-type barrels;

[0048] S108, perform a second binning operation on the products with the same SKU code belonging to the same type of products to obtain multiple second-category bins; and

[0049] S110, the goods belonging to the same type are allocated to the plurality of second-type barrels.

[0050] According to embodiments of this application, before binning the products in the product library, the SKU-IDs of different types of products in the product library can be obtained first. The SKU-IDs are then divided according to the product type to determine if there are too many SKU-IDs belonging to the same type of product (such as a certain model of watch or a certain model of mobile phone). Here, "belonging to the same type of product" can be divided differently depending on the product category. For example, for smart electronic products, products belonging to the same type can be smart devices of the same model or type; for automotive products, products belonging to the same type can be vehicles of the same model or type, and so on. If there are too many SKU-IDs for a certain type of product, it is easy to encounter situations where multiple products of that type are recalled in a concentrated manner, while other types of products are recalled less frequently or not at all. This results in a product list with a single product type after the user's search, suppressing the diversity of recalled products and failing to provide diverse choices.

[0051] According to an embodiment of this application, if the total number of SKU-IDs belonging to the same type of goods is greater than or equal to a preset threshold, a first bucketing operation is performed on the SKU codes of the same type of goods to obtain multiple first-class buckets, and the goods belonging to the same type are allocated to the multiple first-class buckets. That is, if the number of SKU-IDs of a certain type of goods is too large, then the goods of that type are bucketed, specifically the SKU-IDs of the goods of that type are bucketed so that the same SKU-ID will not enter the same bucket, i.e., the same type of goods are bucketed at the SKU granularity. According to the bucketing principle, the SKU-IDs of goods in a single first-class bucket are all different, that is, the product attributes are all different. Taking smartphones as an example, the first-class bucket contains multiple phones of the same model but with different other attributes. For example, for the model "Huawei P30", there are phones of this model in various colors, capacities, depreciation levels, and prices. Their attributes are different, and their SKU-IDs are all different.

[0052] Furthermore, in addition to binning SKU-IDs within the same product type, this application embodiment also bins homogeneous products with the same SKU-ID. According to this application embodiment, a second binning operation is performed on products with the same SKU code belonging to the same product type, resulting in multiple second-type bins. The products belonging to the same type are then assigned to these multiple second-type bins. In other words, homogeneous products under the same SKU-ID are binned, ensuring that products with completely identical attributes do not enter the same bin; that is, binning homogeneous products at the attribute granularity. According to the binning principle, multiple homogeneous products will not appear under each SKU-ID in a single second-type bin. Taking "Huawei P30" as an example, the second-type bins contain mobile phones of this model with the same and / or different SKU-IDs; no two or more homogeneous mobile phones with completely identical attributes will appear under each SKU-ID.

[0053] The embodiments of this application combine two-step binning operations, which can minimize the occurrence of duplicate SKU-IDs and clustering of homogeneous products under the same SKU-ID when binning similar products. Based on this, the diversity of the product list when recalling products can be improved, and the duplication problem caused by the clustering of homogeneous products in the product list can be reduced.

[0054] In some embodiments of this application, the two bucketing operations can be implemented in the following ways:

[0055] The first bucketing operation may include: determining the number of buckets of the first type using a hash bucketing method;

[0056] The second binning operation may include: determining the number of bins of the second type based on the number of products under the same SKU code.

[0057] On the one hand, regarding the first bucketing operation, the Hash bucketing method can be used to bucket different SKU-IDs of the same type of product.

[0058] As an example, after bucketing according to hash, the number of buckets m in the first type is:

[0059] m = Hash(SKU-ID) % mb + 1 ①

[0060] in,

[0061] Hash() is a hash function, which can be used to transform an input of arbitrary length to obtain an output of fixed length;

[0062] The symbol "%" represents the division operation of taking the remainder;

[0063] mb represents the total number of containers, which can be determined based on the inventory of the goods and the expected recall volume. The value of mb should be chosen to minimize the probability of empty containers.

[0064] Through the above processing, Hash(SKU-ID) is a hash operation performed on the SKU-ID. Based on the remainder of the resulting hash value divided by the total number of buckets (mb), the number of buckets (m) of the first category of the current product type can be obtained. Then, for example, m buckets can be randomly selected from the mb buckets as the first category of the current product type, thus ensuring that this type of product is distributed as evenly as possible among the mb buckets.

[0065] On the other hand, regarding the second binning operation, there may be multiple products under the same SKU-ID, and binning can be performed based on the number of products under the same SKU-ID.

[0066] As an example, the number of buckets g of the second type can be determined by the following formula:

[0067] g = Max(sku_b - s, 1) ②

[0068] In this context, Max() is the operation to select the maximum value, sku_b is the pre-defined total number of buckets, and s is the bucket number.

[0069] In other embodiments of this application, other suitable binning methods may be adopted to perform binning operations, thereby obtaining multiple first-type bins and multiple second-type bins.

[0070] In some embodiments of this application, if the total number of SKU codes for the same type of goods among the plurality of goods is less than the preset threshold, the number of the first type of buckets can be a preset number. Taking mobile phones in the product library as an example, if the number of SKU-IDs covered by a certain mobile phone model in the product library is small, the default number of buckets can be directly used as the number of buckets in the first type of buckets. For example, mb in formula ① can be used as the default number of buckets.

[0071] In some embodiments of this application, the preset threshold for the number of SKU codes (hereinafter referred to as t, where t is a positive integer) can be determined based on the number of SKU codes of the same type of goods in the product library and the inventory quantity of goods under each SKU code.

[0072] As mentioned earlier, if poor diversity occurs during product recall, it may be due to an excessive number of products of a certain type. This leads to a concentrated recall of certain types and models when selecting brands and models, while other models are recalled less frequently or not at all, failing to demonstrate diversity. To address this, the number of SKU-IDs for each product type and the average number of products per SKU-ID can be statistically analyzed. Without affecting product exposure, an appropriate SKU threshold can be chosen as a prerequisite for the first binning operation. In some embodiments of this application, when the size of the candidate product set is 2-3 times the size of the recalled products, it is possible to maintain high recalled product quality without affecting exposure. Therefore, the average number of products in each bin after implementing the first binning operation can be calculated. By examining whether the average number of products in each bin meets the above conditions, it can be determined whether the first binning operation should be implemented. When the above conditions are met, the first binning operation should be executed, and the corresponding number of SKU-IDs can be used as the threshold t. Based on this, it can be understood that the more products of the same type there are, the larger the value of t. Of course, in some embodiments, t can also be set to an appropriate value, such as estimating the t value of various types of goods based on historical data. For example, the t value corresponding to currently popular mobile phone models is larger, while the t value corresponding to unpopular mobile phone models is smaller.

[0073] In some embodiments of this application, the product library includes electronic products, such as smartphones, tablets, wearable devices, digital cameras, game consoles, etc. Products belonging to the same type refer to electronic products of the same model, such as a specific model of a mobile phone from a particular brand. Of course, the product library of this application may also include other types of products, such as clothing, food, general merchandise, bags, etc., all of which are applicable to the processing solutions provided in the embodiments of this application.

[0074] In some embodiments of this application, SKU-IDs can be generated using various attributes of the product, such as business attributes and basic attributes. Taking electronic products as an example, business attributes may include product type, the business to which the product belongs, and / or the overall product grade; basic attributes may include model, condition (new or used), memory, version (e.g., mainland China version, US version, Hong Kong version), network type, color, and price.

[0075] According to at least one embodiment of this application, product information can be processed according to product type, and two binning operations can be performed on products of the same type, so as to improve product diversity and eliminate duplication when recalling products by binning.

[0076] Corresponding to the above-described product information processing method, this application also provides a product recall method. Figure 2 This is a flowchart of a product recall method according to an embodiment of this application, the method including:

[0077] S202, Receive product search information;

[0078] S204, if there are products matching the product search information in multiple first-class buckets and products matching the product search information in multiple second-class buckets, then select one first-class bucket from the multiple first-class buckets and select one second-class bucket from the multiple second-class buckets.

[0079] S206, return the product information of the selected first and second type of buckets.

[0080] In this field, after receiving a user's product search information, the system filters and recalls products in the product database based on the search information, sorts them to form a product list, and returns it to the user for selection.

[0081] According to an embodiment of this application, the same type of goods are subject to two binning operations. During binning recall, the goods need to be recalled from the results of the two binning operations. Therefore, it is necessary to select one bin from multiple first-type bins and one bin from multiple second-type bins (e.g., randomly selected). The goods information in the two bins is then merged and returned to the user. Here, since the two binning operations are binning of the same type of goods at different granularities, the goods information recalled according to the two binning operations can improve product diversity and eliminate duplication, allowing more product attributes to be displayed to the user, which can improve user satisfaction to a certain extent.

[0082] In some embodiments of this application, before returning the product information from the selected first and second buckets, the product information from the selected first and second buckets can be merged into a product list, and the products in the product list can be reordered. During the reordering, the SKU codes of the products are broken down.

[0083] The reason for this approach is that if there are too many similar products with the same SKU-ID in the product database, binning and recalling cannot completely eliminate the occurrence of similar products. Therefore, after recalling, the products in the first and second bins are merged and then dispersed according to SKU-ID, so that products with the same SKU-ID will not be clustered together, effectively avoiding the phenomenon of similar products piling up.

[0084] In some embodiments of this application, the same product list is returned for the same product search information before the current user session ends. When a user enters product keywords to search, they may perform multiple searches for the same keywords. For the same keywords entered multiple times, in the embodiments of this application, when randomly selecting the first type of bucket and the second type of bucket, the bucket number of the first type of bucket selected in the two consecutive selections may be inconsistent, and / or the bucket number of the second type of bucket selected in the two consecutive selections may be inconsistent. This will lead to the situation where the same keyword is entered but the search results are inconsistent, which will confuse the user.

[0085] In this regard, according to the settings of the embodiments of this application, the same product list will be returned for the same keyword during the same session. For example, when searching for the same keyword multiple times, the same bucket number is selected when selecting the first bucket and the second bucket, thereby ensuring that the product list results of multiple searches are the same.

[0086] In this context, a session typically refers to the interaction process between a user and a network system over a period of time. For example, it can refer to a series of actions that a user takes from the start of a search to the end of the search, such as searching for products, browsing products, adding products to favorites, placing an order / purchasing, and logging out.

[0087] It should be noted that in the embodiments of this application, there are no timing requirements for the two binning operations. That is, the first binning operation can be performed first, followed by the second binning operation, or the second binning operation can be performed first, followed by the first binning operation. The two timing sequences have no overall impact on the implementation process and corresponding effects of the embodiments of this application.

[0088] The above describes various implementation methods of the embodiments of this application. The following describes the implementation process of the product information processing method and the product recall method of the embodiments of this application through specific examples.

[0089] Example 1

[0090] Figure 3 The illustration shows a schematic diagram of the process of performing two binning operations on products in the product database using the product information processing method based on the embodiments of this application. Figure 3 In this embodiment, the second binning operation is performed after the first binning operation. It should be understood that the second binning operation can also be performed before the first binning operation. This embodiment uses binning by mobile phone model as an example; for simplicity, the first binning operation is referred to as "model binning," and the second binning operation is referred to as "SKU binning."

[0091] refer to Figure 3 The general process of performing two types of bucketing on the target mobile phone model is as follows:

[0092] 1) Generate the SKU_ID for the product:

[0093] refer to Figure 3 The system updates product information in the product database, retrieves the attribute information of each product, and generates the product's SKU_ID based on the attribute information. For example, if a user posts an iPhone 11 on a second-hand trading system with attributes including: 128G, white, Chinese version, and 90% new, the system can generate the phone's SKU_ID based on these attributes.

[0094] 2) Divide the target mobile phone models into different buckets:

[0095] Determine if the number of SKU_IDs for all phones (different colors, different capacities, or different other attributes) under the target model (e.g., iPhone 12) in the product database is greater than or equal to t (e.g., t = 1000). If the number of SKU_IDs under this model is greater than or equal to t, determine the number of buckets for this model using the bucketing method of the hash function: m = Hash(SKU-ID) % mb + 1. If the number of SKU_IDs under this model is less than t, the default value for the number of buckets can be mb.

[0096] 3) Perform SKU bucketing for the target mobile phone model:

[0097] Query the inventory quantity s of each SKU_ID of the target mobile phone model, and calculate the number of buckets g = Max(sku_b-s,1).

[0098] 4) Write the products into m model buckets and g SKU buckets:

[0099] The target mobile phone model is written into m model buckets and g SKU buckets respectively. Similarly, other mobile phone models can also be written into m model buckets and g SKU buckets. A single model bucket contains mobile phones of multiple models to meet diverse needs, and a single SKU bucket contains mobile phones with different SKU_IDs. Homogeneous products under each SKU_ID have been deduplicated through bucketing operations.

[0100] In some embodiments of this application, since there may be multiple products under the same sku_id, the number of buckets required for the sku_id can be calculated based on the inventory s of the multiple products, i.e., g = max(sku_b-s, 1). When a new product is released under a sku_id, the number of buckets for the product is the total number of buckets sku_b, and the bucket number is 1, 2, ..., sku_b; when a new product is released, the bucket number is 1, 2, ..., (sku_b-1).

[0101] For example, if product A is released before product B, product A is placed in bins 1 through sku_b, while product B is placed in bins 1 through (sku_b-1). That is, the earlier a product is released, the more bins it has, and the later a product is released, the fewer bins it has, and the lower the probability of it being recalled. This aligns with the business requirement that products released earlier should be easier to sell. Even after product A is sold, the probability of product B being recalled is still relatively high. For the number of SKU bins, g = max(sku_b-s, 1), g bins can be randomly selected from bins 1 through sku_b. The more products there are, the lower the probability of empty bins. Assigning multiple products under the same sku_id to different bins based on inventory levels ensures a sufficient number of products can be recalled while reducing the number of homogeneous products and minimizing duplicate recalls.

[0102] Example 2

[0103] and Figure 3 Correspondingly, in the embodiments, Figure 4 The illustration shows a schematic diagram of the product recall method based on the embodiments of this application, in which the user is returned a list of target mobile phone models. During the product recall, only one model bucket and one SKU bucket of products for the target model are recalled. The recall process is described below.

[0104] When a user searches for products, a "model bucket number" and a "SKU bucket number" are generated for the user. These are used to match the "model bucket" and "SKU bucket" in the product database, respectively. The user's bucket number can be determined in several ways, i.e., the user's "model bucket number" and "SKU bucket number". For example, a model bucket number can be randomly selected from bucket numbers 1 to m of m model buckets. Similarly, an SKU bucket number can be randomly selected from bucket numbers 1 to g of g SKU buckets. Then, products from the corresponding buckets are selected to generate a product list.

[0105] In the embodiments of this application, in addition to randomly determining the two types of bucket numbers for users, other methods can also be used to determine the user's bucket number.

[0106] As an example, the following steps can be taken to generate two bucket numbers for a user: When a user starts searching for products, the user's current session is obtained, a hash transformation is performed using the current session, and the remainder of the hash value is calculated by dividing the product's device bucket number (e.g., m) and SKU bucket number (e.g., g) by the remainder value. Then, 1 is added to the remainder result (i.e., incremented by 1 after taking the remainder). The resulting values ​​are the user's device bucket number and SKU bucket number.

[0107] For example, suppose a user enters the search term "iPhone12". Searching for "iPhone12" in the product database will return all iPhone12 phones. These iPhone12 phones have already been binned by model and by SKU (refer to Example 1). Based on the user's iPhone12 search session, the user's model bin number and SKU bin number can be calculated. Let's assume the user's model bin number is 10 and their SKU bin number is 5. Then, the bin with bin number 10 should be matched among m model bins, and the bin with bin number 5 should be matched among g SKU bins. A product list is generated based on all iPhone12 phones in these two bins. The product list is then scrambled by SKU and returned to the user. It can be seen that the iPhone12 in the product list corresponds to model bin number 10 and SKU bin number 5.

[0108] Furthermore, the reason for dispersing SKUs in the product list is that products with the same SKU share the same important attributes, resulting in very similar ratings for these products in the model. These products are often grouped together, leading to repeated exposure. Therefore, separating products with the same SKU is crucial. Specific operational details can be implemented independently, but the goal is to separate products with the same SKU and avoid SKU clustering.

[0109] Regarding the effects, please refer to Figure 5A and Figure 5BThe examples illustrate, respectively, the process before applying the embodiments of this application ( Figure 5A ) and afterwards ( Figure 5B The statistics of search results for "mobile phone" are presented in a pie chart, showing the percentage of different mobile phone brands returned. For simplicity, different brands are labeled with a brand number in the chart. Figure 5B The number of brands included (19) is significantly more than Figure 5A The number of brands (13) indicates that using the embodiments of this application can not only eliminate the duplication caused by homogeneous products, but also improve the diversity of returned products, provide users with diverse choices, and enhance users' product search experience.

[0110] Corresponding to the above method embodiments, refer to Figure 6 and Figure 7 This application also provides a product information processing device 100 and a product recall device 200.

[0111] The product information processing device 100 in this application embodiment includes:

[0112] The acquisition module 110 is used to acquire the SKU code of the inventory quantity of multiple products in the product library;

[0113] The first binning operation module 120 is used to perform a first binning operation on the SKU codes of the same type of goods among the multiple goods when the total number of SKU codes of the goods belonging to the same type is greater than or equal to a preset threshold, so as to obtain multiple first-class bins.

[0114] The first allocation module 130 is used to allocate the goods of the same type to the plurality of first-type buckets;

[0115] The second binning operation module 140 is used to perform a second binning operation on products with the same SKU code belonging to the same type of products, to obtain multiple second-category bins;

[0116] The second allocation module 150 is used to allocate the goods belonging to the same type to the plurality of second-type buckets.

[0117] Optionally, the first bucketing operation module is used to determine the number of the first type of buckets using a hash bucketing method; and / or, the second bucketing operation module is used to determine the number of the second type of buckets based on the number of products under the same SKU code.

[0118] Optionally, the first binning operation module is further configured to determine the number of the first bins to be a predetermined number if the total number of SKU codes of the same type of goods among the multiple goods is less than the preset threshold.

[0119] Optionally, the preset threshold is determined based on the inventory quantity of goods of the same type in the product library.

[0120] Optionally, the product library includes electronic products, and the products belonging to the same type are electronic products belonging to the same model.

[0121] The product recall device 200 according to an embodiment of this application includes:

[0122] Receiver module 210 is used to receive product search information;

[0123] The selection module 220 is used to select one first-class bucket from the multiple first-class buckets and select one second-class bucket from the multiple second-class buckets when there are products matching the product search information in multiple first-class buckets and products matching the product search information in multiple second-class buckets.

[0124] The return module 230 is used to return the product information of the selected first and second type of buckets.

[0125] Optionally, the product recall device 200 further includes a scrambling processing module, used to merge the product information in the selected first type of bucket and the second type of bucket into a product list, reorder the products in the product list, and scramble the SKU codes of the products during the reordering process.

[0126] Optionally, before the current user session ends, the return module returns the same list of products for the same product search information.

[0127] In addition, this application also provides a server, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the product information processing method and the product recall method of any of the above embodiments.

[0128] Figure 8 A schematic diagram of the hardware structure of an embodiment of the server provided in this application is shown.

[0129] like Figure 8 As shown, the server may include a processor 601 and a memory 602 storing computer program instructions. The server may be a cloud server.

[0130] Specifically, the processor 601 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0131] Memory 602 may include mass storage for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 602 is non-volatile solid-state memory.

[0132] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0133] The processor 601 reads and executes computer program instructions stored in the memory 602 to implement any of the product information processing methods and product recall methods in the above embodiments.

[0134] In one example, the server may also include a communication interface 603 and a bus 610. Wherein, as... Figure 8 As shown, the processor 601, memory 602, and communication interface 603 are connected through bus 610 and complete communication with each other.

[0135] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0136] Bus 610 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 610 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0137] Furthermore, in conjunction with the product information processing method and product recall method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any one of the product information processing method and product recall method in the above embodiments.

[0138] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0139] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Machine-readable media can include non-transitory computer-readable storage media, such as electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, and can also include radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0140] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0141] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0142] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

[0143] The above embodiments are for illustrative purposes only and are not intended to limit the scope of this application. Those skilled in the art can make various changes and modifications without departing from the scope of this application. Therefore, all equivalent technical solutions should also fall within the scope of this application.

Claims

1. A commodity information processing method characterized by comprising: include: Retrieve the SKU code of multiple products in the product database to measure their inventory quantity; If the total number of SKU codes of products belonging to the same type among the multiple products is greater than or equal to a preset threshold, then the first binning operation is performed on the SKU codes of products belonging to the same type to obtain multiple first-class bins, wherein the SKU codes of products in a single first-class bin are different from each other. The goods belonging to the same type are allocated into the plurality of first-type barrels; The number of second-type barrels corresponding to a given SKU code is determined based on the inventory quantity of the goods under the same SKU code; A second binning operation is performed on products with the same SKU code belonging to the same type of products to obtain multiple second-category bins; The goods belonging to the same type are allocated to the plurality of second-type bins, wherein the first binning operation and the second binning operation are binning the goods belonging to the same type at different granularities; Receive product search information; If there are products matching the product search information in the plurality of first-class buckets, and there are also products matching the product search information in the plurality of second-class buckets, then select one first-class bucket from the plurality of first-class buckets, and select one second-class bucket from the plurality of second-class buckets. A product list is generated and returned based on the product information from the selected first and second type of buckets.

2. The method according to claim 1, characterized in that, The first bucketing operation includes: using a hash bucketing method to determine the number of buckets of the first type.

3. The method according to claim 1, characterized in that, If the total number of SKU codes for products of the same type among the multiple products is less than the preset threshold, then the number of the first type of buckets is a predetermined number.

4. The method according to claim 1, characterized in that, The preset threshold is determined based on the number of SKU codes of the same type of goods in the product library and the inventory quantity of goods under each SKU code.

5. The method according to any one of claims 1-4, characterized in that, The product database includes electronic products, and the products belonging to the same type are electronic products belonging to the same model.

6. A product recall method characterized by, The product recall method is based on the product information processing method as described in any one of claims 1-5, and the product recall method includes: Receive product search information; If there are products matching the product search information in multiple first-class buckets, and there are also products matching the product search information in multiple second-class buckets, then select one first-class bucket from the multiple first-class buckets, and select one second-class bucket from the multiple second-class buckets. Return the product information from the selected first and second type of buckets.

7. The method according to claim 6, characterized in that, Before returning the product information from the selected first and second type of bins, the method further includes: The product information from the selected first and second buckets is merged into a single product list. The products in the product list are then reordered, and the SKU codes of the products are broken down during the reordering process.

8. The method according to claim 6, characterized in that, The same product list will be returned for the same product search information until the current user session ends.

9. A commodity information processing device, characterized in that, include: The acquisition module is used to obtain the SKU code of the inventory quantity of multiple products in the product library; The first binning operation module is used to perform a first binning operation on the SKU codes of the same type of products when the total number of SKU codes of the products in the multiple products is greater than or equal to a preset threshold, so as to obtain multiple first bins, wherein the SKU codes of the products in a single first bin are different from each other. The first allocation module is used to allocate the goods of the same type to the plurality of first-type buckets; The second binning operation module determines the number of second-category bins corresponding to the same SKU code based on the inventory quantity of the goods under the same SKU code, and performs the second binning operation on the goods with the same SKU code belonging to the same type of goods to obtain multiple second-category bins; The second allocation module is used to allocate the goods of the same type to the plurality of second-type bins, wherein the first binning operation and the second binning operation are binning the goods of the same type at different granularities; The information receiving module is used to receive product search information; If there are products matching the product search information in both the plurality of first-class buckets and the plurality of second-class buckets, then one first-class bucket is selected from the plurality of first-class buckets, and one second-class bucket is selected from the plurality of second-class buckets; a product list is generated based on the product information in the selected first-class bucket and second-class bucket and returned.

10. The apparatus according to claim 9, characterized in that, The first bucketing operation module is used to determine the number of the first type of buckets using the hash bucketing method.

11. The apparatus according to claim 9, characterized in that, The first binning operation module is also used to determine the number of the first type of bins to be a predetermined number when the total number of SKU codes of products of the same type among the multiple products is less than the preset threshold.

12. The apparatus according to claim 9, characterized in that, The preset threshold is determined based on the inventory quantity of goods of the same type in the product library.

13. The apparatus according to any one of claims 9-12, characterized in that, The product database includes electronic products, and the products belonging to the same type are electronic products belonging to the same model.

14. A product recall device, characterized in that, The product recall device is based on the product information processing method as described in any one of claims 1-5, and the product recall device includes: The receiving module is used to receive product search information; The selection module is used to select one first-class bucket from the multiple first-class buckets and select one second-class bucket from the multiple second-class buckets when there are products matching the product search information in multiple first-class buckets and multiple second-class buckets. The return module is used to return the product information from the selected first and second type of buckets.

15. The apparatus according to claim 14, characterized in that, The device further includes: The scrambling module is used to merge the product information from the selected first and second category buckets into a product list, reorder the products in the product list, and scramble the SKU codes of the products during the reordering process.

16. The apparatus according to claim 15, characterized in that, Before the current user session ends, the return module returns the same list of products for the same product search information.

17. A server, characterized in that, The server includes a processor and a memory storing computer program instructions; when the server executes the computer program instructions, it implements the method as described in any one of claims 1-8.

18. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method as described in any one of claims 1-8.

Images