Product sorting methods, devices, electronic equipment, and storage media

Abstract

This disclosure provides a product ranking method, apparatus, electronic device, and storage medium. A product ranking method includes: acquiring characteristic information of a target user and characteristic information of a target product, wherein the target product includes one or more SPUs; each SPU has one or more SKUs; determining the estimated purchase rate of SKUs when different prior characteristics are met based on the characteristic information of the target user and the characteristic information of the target product; and determining the ranking of SKUs based on the estimated purchase rates of SKUs when different prior characteristics are met. The method of this disclosure can increase the purchase rate of target products by target users.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to a product sorting method, apparatus, electronic device, and storage medium. Background Technology

[0002] Multi-style products refer to a single product (usually denoted as SPU, Standard Product Unit) that has different styles and specifications (usually denoted as SKU, StockKeeping Unit) with subtle differences in color, material, etc. For example, a piece of clothing is an SPU, and styles with different colors are denoted as SKUs; or a piece of jewelry is an SPU, and styles made of different materials are denoted as SKUs. Summary of the Invention

[0003] This disclosure provides a product sorting method, apparatus, electronic device, and storage medium.

[0004] The following technical solution is adopted in this disclosure.

[0005] In some embodiments, this disclosure provides a product sorting method, including:

[0006] Obtain characteristic information of target users and characteristic information of target products, wherein the target products include one or more SPUs; each SPU has one or more SKUs;

[0007] Based on the characteristic information of the target user and the characteristic information of the target product, determine the estimated purchase rate of the SKU when different prior characteristics are met;

[0008] The SKUs are ranked according to their estimated purchase rate when different prior characteristics are met.

[0009] In some embodiments, this disclosure provides a product sorting apparatus, comprising:

[0010] The acquisition unit is used to acquire feature information of the target user and feature information of the target product, wherein the target product includes one or more SPUs; each of the SPUs has one or more SKUs;

[0011] The control unit is used to determine the estimated purchase rate of the SKU when different prior characteristics are met, based on the characteristic information of the target user and the characteristic information of the target product.

[0012] The control unit is also configured to determine the order of the SKUs based on the estimated purchase rate of the SKUs when different prior characteristics are met.

[0013] In some embodiments, this disclosure provides an electronic device, including: at least one memory and at least one processor;

[0014] The memory is used to store program code, and the processor is used to call the program code stored in the memory to execute the above method.

[0015] In some embodiments, this disclosure provides a computer-readable storage medium for storing program code that, when run by a processor, causes the processor to perform the methods described above.

[0016] The method provided in this disclosure takes into account the target user's preferences for different SKUs, and calculates the estimated purchase rate of each SKU when different prior features are met (i.e., different ranking scenarios), thereby making the product recommendation order more conducive to product purchase, promoting transaction completion, and increasing the purchase rate of the target user for the target product. Attached Figure Description

[0017] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0018] Figure 1 This is a flowchart of a product sorting method according to an embodiment of the present disclosure.

[0019] Figure 2 This is a schematic diagram illustrating the determination of the estimated purchase rate according to an embodiment of this disclosure.

[0020] Figure 3 This is a schematic diagram illustrating the determination of the target SKU according to an embodiment of this disclosure.

[0021] Figure 4 This is a schematic diagram of a neural network model according to an embodiment of the present disclosure.

[0022] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0023] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0024] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0025] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0026] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0027] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be understood that the various steps described in the method embodiments of this disclosure can be performed in sequence and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0030] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the use of the word "a" in this disclosure is illustrative rather than restrictive, and those skilled in the art should understand that it should be understood as "one or more" unless otherwise expressly indicated in the context.

[0033] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0034] The solutions provided by the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0035] The same product may have different specifications and styles, and a single SKU can have multiple SKUs. When recommending products, directly recommending by SKU will result in a lack of segmentation based on SKU color and material preferences, leading to a decrease in recommendation effectiveness. Recommending by SKU may also cause multiple SKUs under the same SKU to appear together, wasting exposure opportunities.

[0036] like Figure 1 As shown, Figure 1 This is a flowchart of a product sorting method according to an embodiment of the present disclosure, which includes the following steps.

[0037] S11. Obtain the characteristic information of the target user and the characteristic information of the target product.

[0038] In some embodiments, the execution end of the method proposed in this disclosure can be a terminal, specifically a mobile phone, tablet, computer, server, etc. The method proposed in this disclosure can be used for product sorting, specifically for sorting products in shopping software, or for sorting products in automated promotion software, such as the sorting performed on a search page when a user searches for a certain type of product, or the sorting of products on a promotional page. The target user is a single user, which can be the user currently using the terminal, such as the user performing the product search, or the logged-in user of the software containing the promotional page. In some embodiments, the characteristic information of the target user may include, for example, the target user's purchase preference data, which can be obtained by analyzing the target user's historical purchase behavior for various products. The characteristic information of the target product may include: the style and / or performance parameters of each SKU, and the style information such as color and material of each SKU. The target product includes one or more SPUs (Standard Product Units). The target product can be a single product or multiple different products. For example, the target product can be one or more of shoes, clothing, furniture, etc. Multiple SPUs can be of the same type or different types. For example, multiple SPUs can all be shoes or all be clothing, or some can be clothing and some can be shoes. Each SPU has one or more SKUs (Stock Keeping Units). For example, a piece of clothing can have different colors and styles. This piece of clothing is an SPU, and the different styles of this piece of clothing are individual SKUs.

[0039] S12. Based on the characteristic information of the target user and the characteristic information of the target product, determine the estimated purchase rate of the SKU when different prior characteristics are met.

[0040] In some embodiments, the preceding features include: feature information of preceding SKUs that have already been displayed at a preceding position and belong to the same SPU as the SKU currently used to calculate the estimated purchase rate; in some embodiments, the estimated purchase rate is: given that the preceding features are satisfied, if an additional SKU is displayed (at a position after the preceding position), the probability that the target audience will purchase that SKU is then. In some embodiments, for each SKU under any SPU, different preceding features indicate that different numbers and / or different preceding SKUs belonging to the same SPU have already been displayed at the preceding position. In some embodiments, preceding SKUs refer to other SKUs belonging to the same SPU as the SKU currently used to calculate the estimated purchase rate, which have already been displayed at the preceding position in the scenario described by the current feature. For example, ... Figure 2As shown, the target product includes product A (A is an SPU, not shown in the figure). Product A has three SKUs: a, b, and c. The different "precedence" characteristics include: 0, 1, or 2 SKUs belonging to the same SPU have already been displayed above (i.e., the previous position, representing the previous position on the same page, such as in a list). Furthermore, for the case where 1 or 2 SKUs are displayed in the previous position, different sub-cases are further subdivided based on the different SKUs displayed. Figure 2 The 'a, b, and / or c' items following 'already shown above' in the middle and right sections represent the preceding SKUs. When determining the estimated purchase rate for a particular SKU, the probability of that SKU being purchased by the target user is calculated when a different number and / or different SKUs belonging to the same SKU as that SKU have already been shown in the preceding positions, and then the SKU is added later. For example, when calculating the estimated purchase rate for each SKU of product A, if... Figure 2 As shown on the left, when the preceding feature indicates that no SKU under the same SPU is displayed in the preceding position, the probability that the increased display of a, b, or c will be purchased by the target audience is calculated. For example... Figure 2 As shown in the middle and right sections, when the "preceding feature" indicates that one or two SKUs under a SPU are displayed in the preceding position, the estimated purchase rate of each SKU is calculated when different SKUs are displayed in the preceding position. The process is similar for SKUs under other SPUs. In some embodiments, when determining the estimated purchase rate of an SKU satisfying different preceding features, only other SKUs under the SPU to which the SKU currently calculating the estimated purchase rate belongs may be considered, without considering other SKUs not belonging to the same SPU as the SKU currently calculating the estimated purchase rate. Specifically, if there are two SPUs, product A and product B, when calculating the estimated purchase rate of SKUs under product A satisfying different preceding features, the SKU of product B displayed in the preceding position may not be considered. Similarly, when calculating the estimated purchase rate of SKUs under product B satisfying different preceding features, the SKU of product A displayed in the preceding position may not be considered.

[0041] S13. Determine the SKU ranking based on the estimated purchase rate of SKUs when different prior characteristics are met.

[0042] In some embodiments, step S12 can obtain the estimated purchase rate of each SKU under different prior characteristics, which represents the probability that the target user will purchase each SKU under different circumstances. At this time, the SKUs can be sorted and displayed in descending order of estimated purchase rate. For example, as... Figure 2As shown, for product A, the estimated purchase rate of each SKU was calculated for the following scenarios: when product A was not yet displayed in the first position, when one SKU was displayed, or when two SKUs were displayed. This yielded the estimated purchase rate of each SKU under different SKUs displayed in the first position. In this case, if only product A is displayed, the SKU with the highest estimated purchase rate can be displayed in one position when product A was not yet displayed in the first position, in a later position when one SKU of product A was displayed in the first position, and in an even later position when two SKUs of product A were displayed in the first position.

[0043] In some embodiments of this disclosure, a sorting method is provided for recommendation scenarios of multi-style products. This method fully considers the target user's preference for the different attributes of different SKUs. By calculating the estimated purchase rate of each SKU when different prior features are met (i.e., under different sorting scenarios), the order of product recommendations is more conducive to product purchase and promotes transaction completion. Compared with related recommendation sorting methods, this method can improve the purchase rate of target users for target products.

[0044] In some embodiments of this disclosure, determining the estimated purchase rate of the SKU when different preceding characteristics are met includes: determining the estimated purchase rate of the SKU when 0 to x preceding SKUs belonging to the same SPU as the SKU for which the estimated purchase rate is currently being calculated have already been displayed in the preceding position; wherein x is equal to the total number of SKUs under the SPU to which the SKU for which the estimated purchase rate is currently being calculated minus one.

[0045] In some embodiments, for any SPU, when determining the estimated purchase rate of each SKU under it, the total number of SKUs under that SPU can be determined first. This total number minus one equals x. In the scenarios described by the previous features, there are a total of (x+1) types, i.e., 0, 1, ..., x SKUs in the first few scenarios. Then, the estimated purchase rate of each SKU under that SPU is calculated for each scenario described by the previous features. For example... Figure 2 As shown, product A has three SKUs: a, b, and c. Therefore, the estimated purchase rates of a, b, and c were calculated for scenarios described by the preceding features, where the preceding SKUs are 0, 1, and 2, respectively. In this way, by listing a total of (x+1) scenarios, all possible cases can be listed when calculating the estimated purchase rate of each SKU under any SPU, avoiding omissions.

[0046] In some embodiments of this disclosure, determining the SKU ranking based on the estimated purchase rate of the SKU when different prior characteristics are met includes: determining the purchase score of the SKU based on the estimated purchase rate of the SKU when different prior characteristics are met; arranging the SKUs in descending order of their purchase scores; wherein the purchase score of the SKU increases as the estimated purchase rate of the SKU increases.

[0047] In some embodiments, after obtaining the estimated purchase rate of SKUs under different scenarios described by different prior features, a purchase score can be assigned to each SKU. This purchase score can be roughly proportional to the estimated purchase rate. For example, the estimated purchase rate can be directly used as the purchase score, and then the SKUs can be sorted in descending order of purchase scores to be displayed to the target user. In some embodiments, instead of calculating the purchase score for all SKUs, the order of SKUs under an SPU can be determined first, and then the purchase score of the SKUs under that order can be determined. This is because the order of SKUs under an SPU affects the final transaction. Therefore, an optimal order can be determined first, and then the purchase score of each SKU under that order can be determined. This reduces the computational load while providing transaction possibilities and avoids user waiting.

[0048] In some embodiments of this disclosure, the purchase score of each SKU under each SPU is determined based on the estimated purchase rate of the SKU when different prior characteristics are met. This includes: for any target SPU in the SPU, determining the target SKU corresponding to the number of prior SKUs displayed in the prior position and its corresponding estimated purchase rate, respectively; determining the purchase score of each target SPU based on the estimated purchase rate of each target SPU, wherein the target SKU is determined based on the number of prior SKUs and the estimated purchase rate, and different numbers of prior SKUs correspond to different target SKUs, and the purchase score of the target SKU increases with the increase of its estimated purchase rate.

[0049] In some embodiments, the target product includes one or more SPUs. The evaluation of the purchase rating of SKUs under any SPU (denoted as the target SPU) can be achieved by first determining the number of top SKUs in the scenario described by each preceding feature, and then determining the target SKUs corresponding to each number of top SKUs in ascending order of their count. For example, as... Figure 2 As shown, product A has three SKUs: a, b, or c. After determining... Figure 2 The estimated purchase rate for each SKU in each scenario described above is shown below. Figure 3As shown, the number of initial SKUs can be 0, 1, or 2. Following the increasing order of the number of initial SKUs, the target SKUs are first determined when there are 0 initial SKUs, then when there is 1 initial SKU, and finally when there are 2 initial SKUs. This results in 3 target SKUs and their corresponding estimated purchase rates. The number of target SKUs under a SKU can be the same as the number of SKUs under that SKU; that is, each SKU under that SKU is a target SKU. This embodiment assigns a corresponding number of initial SKUs to each SKU. Because different SKUs actually have multiple estimated purchase rates, corresponding to different initial features, but calculating their purchase score requires determining which estimated purchase rate to use, this embodiment determines which estimated purchase rate to use for calculating the purchase score for each SKU.

[0050] In some embodiments of this disclosure, determining the target SKU corresponding to the number of preceding SKUs and its corresponding estimated purchase rate includes: if the number of preceding SKUs is 0, determining that when no SKU of the target SPU has been displayed in the preceding position, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU; if the number of preceding SKUs is n and n is not 0, determining that when the preceding SKUs displayed in the preceding position are n target SKUs arranged in ascending order of the number of preceding SKUs, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU.

[0051] In some embodiments, with appendix Figure 3 For example, product A has three SKUs: a, b, and c. First, when the number of existing SKUs is zero, the SKU with the highest estimated purchase rate is selected as the target SKU corresponding to the zero-count count. Figure 3 Let 'b' in the left-hand column be the target SKU. Then, for cases where the number of preceding SKUs is not zero, the calculation is performed in ascending order of the number of preceding SKUs. First, the calculation is performed when the number of preceding SKUs is 1. In this case, there are multiple scenarios, and the preceding SKU is selected as the scenario where the target SKUs that have been determined and arranged in a predetermined order are selected. Figure 3The example selected the case where SKU b was already displayed in the first few rows. The estimated purchase rate of displaying either a or c was calculated, and c, with the highest estimated purchase rate, was selected as the target SKU when there was one SKU in the first few rows. This process was repeated until there were two SKUs in the first few rows. The SKU with the highest estimated purchase rate when b and c were displayed in sequence was selected as c, and it became the target SKU when there were two SKUs in the first few rows. As can be seen, this embodiment considers not only the magnitude of the estimated purchase rate but also the order of the first few SKUs, selecting the order with the highest estimated purchase rate. Therefore, the target SKUs are ordered according to the highest estimated purchase rate. The order of the SKUs under this SPU is based on the determined order of the target SKUs. It is important to note that since there can be multiple SPUs, although the SKUs under a single SPU are ordered according to the determined target SKU order, the SKUs under a single SPU do not necessarily have to be ordered consecutively. For example... Figure 3 In product A, SKUs a, b, and c are ordered in the order b, c, and a. However, there can be SKUs from other SPUs between b and c, and between c and a, such as SKUs from product B. In some embodiments of this disclosure, the SKU order is determined based on the estimated purchase rate of the SKUs when different prior characteristics are met. This can be done without distinguishing which SKU belongs to which SKU, and all SKUs (which may belong to different SPUs) are sorted in descending order according to their purchase ratings and displayed to the target audience.

[0052] In some embodiments of this disclosure, a pre-trained neural network model is used to determine the estimated purchase rate of each SKU when different prior features are satisfied; wherein, the input of the neural network model includes: user feature information, product feature information, and prior features; the output of the neural network model includes: the estimated purchase rate of the user purchasing the SKU in the input product when the prior features of the input are satisfied.

[0053] In some embodiments, such as Figure 4The diagram illustrates the structure of a neural network model, which can be a binary classification model used to predict the probability of a user purchasing an SKU. The neural network model needs to be trained before use. During training, different users can be used to calculate the probability of purchasing each SKU under different prior features. The neural network model's input includes user features (user_feature), product features (item_feature), and prior features (sku_context_feature). It can output the estimated purchase rate of a user (a user satisfying the input user features) purchasing the input product's SKU, given that the prior features are satisfied. In some embodiments of this disclosure, different pre-set prior features are also included. By changing the input prior features, the estimated purchase rate of each SKU under different prior features can be calculated.

[0054] In some embodiments of this disclosure, the SKU currently used to calculate the estimated purchase rate is different from the SKUs displayed in the previous positions. In some embodiments, the SKUs displayed in the previous positions are all different. In some embodiments, each SKU under a SPU is displayed only once on the display page (the page displaying the sorted SKUs) and is not displayed repeatedly. Therefore, there cannot be duplicate SKUs in the previous positions, nor can they be the same as the SKU currently used to calculate the estimated purchase rate.

[0055] In some embodiments of this disclosure, a product sorting apparatus is provided, comprising:

[0056] The acquisition unit is used to acquire the characteristic information of the target user and the characteristic information of the target product, wherein the target product includes one or more SPUs (Standard Product Units); each of the SPUs has one or more SKUs (Stock Keeping Units).

[0057] The control unit is used to determine the estimated purchase rate of the SKU when different prior characteristics are met, based on the characteristic information of the target user and the characteristic information of the target product.

[0058] The control unit is also configured to determine the order of the SKUs based on the estimated purchase rate of the SKUs when different prior characteristics are met.

[0059] In some embodiments, the preceding features include: feature information of preceding SKUs that have been displayed in the preceding position and belong to the same SPU as the SKU currently used to calculate the estimated purchase rate;

[0060] The estimated purchase rate is the probability that, given the preceding characteristics, an additional SKU will be displayed and purchased by the target audience.

[0061] In some embodiments, determining the estimated purchase rate of the SKU when different prior characteristics are met includes:

[0062] When it is determined that 0 to x SKUs belonging to the same SPU as the SKU currently used to calculate the estimated purchase rate have been displayed in the previous position, the estimated purchase rate of the SKU is determined;

[0063] Where x equals the total number of SKUs under the SPU to which the SKU for which the estimated purchase rate is currently calculated minus one.

[0064] In some embodiments, the SKU ranking is determined based on the estimated purchase rate of the SKU when different prior characteristics are met, including:

[0065] The purchase score of the SKU is determined based on the estimated purchase rate of the SKU when different prior characteristics are met.

[0066] Sort the SKUs in descending order of their purchase ratings;

[0067] The purchase rating of a SKU increases as the estimated purchase rate of that SKU increases.

[0068] In some embodiments, the purchase score of the SKU is determined based on the estimated purchase rate of the SKU when different prior characteristics are met, including:

[0069] For any target SPU in the SPU, the target SKU corresponding to the number of the first SKUs displayed in the first position and its corresponding estimated purchase rate are determined respectively, according to the increasing order of the number of the first SKUs. The target SKU is determined based on the number of the first SKUs and the estimated purchase rate.

[0070] Based on the estimated purchase rate of each target SKU, the purchase score of each target SKU is determined, wherein different numbers of top SKUs correspond to different target SKUs.

[0071] In some embodiments, determining the target SKU corresponding to the number of preceding SKUs and its corresponding estimated purchase rate includes:

[0072] If the number of SKUs in the front position is 0, and it is determined that no SKU under the target SPU has been displayed in the front position, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU;

[0073] If the number of the first SKUs is n and n is not 0, when the first SKUs displayed in the first position are n target SKUs arranged in ascending order of the number of the corresponding first SKUs, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU.

[0074] In some embodiments, a pre-trained neural network model is used to determine the estimated purchase rate of each SKU when different prior features are satisfied; wherein, the input of the neural network model includes: user feature information, product feature information, and prior features; the output of the neural network model includes: the estimated purchase rate of the user purchasing the SKU in the input product when the prior features of the input are satisfied.

[0075] In some embodiments, the SKU currently used to calculate the estimated purchase rate is different from the SKU displayed in the previous position.

[0076] In some embodiments, the individual SKUs displayed in the first position are different.

[0077] For embodiments of the apparatus, since they basically correspond to the method embodiments, relevant details can be found in the descriptions of the method embodiments. The apparatus embodiments described above are merely illustrative, and the modules described as separate modules may or may not be separate. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0078] The methods and apparatus of this disclosure have been described above based on embodiments and application examples. Furthermore, this disclosure also provides an electronic device and a computer-readable storage medium, which are described below.

[0079] The following is for reference. Figure 5 The figure illustrates a structural schematic of an electronic device (e.g., a terminal device or server) 800 suitable for implementing embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in the figure is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present disclosure.

[0080] Electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 802 or a program loaded from storage device 808 into random access memory (RAM) 803. RAM 803 also stores various programs and data required for the operation of electronic device 800. The processing device 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0081] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although an electronic device 800 with various devices is shown in the figure, it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0082] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by a processing device 801, it performs the functions defined in the methods of embodiments of this disclosure.

[0083] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0084] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0085] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0086] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods of the present disclosure.

[0087] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0089] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0090] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0091] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0092] According to one or more embodiments of this disclosure, a product sorting method is provided, comprising: acquiring characteristic information of a target user and characteristic information of a target product, wherein the target product includes one or more SPUs (Standard Product Units); each of the SPUs has one or more SKUs (Stock Keeping Units).

[0093] Based on the characteristic information of the target user and the characteristic information of the target product, determine the estimated purchase rate of the SKU when different prior characteristics are met;

[0094] The SKUs are ranked according to their estimated purchase rate when different prior characteristics are met.

[0095] According to one or more embodiments of this disclosure, a product sorting method is provided to determine the estimated purchase rate of the SKU when different prior characteristics are met, including:

[0096] When it is determined that 0 to x SKUs belonging to the same SPU as the SKU currently used to calculate the estimated purchase rate have been displayed in the previous position, the estimated purchase rate of the SKU is determined;

[0097] Where x equals the total number of SKUs under the SPU to which the SKU for which the estimated purchase rate is currently calculated minus one.

[0098] According to one or more embodiments of this disclosure, a product sorting method is provided, which determines the sorting of SKUs based on the estimated purchase rate of the SKUs when different prior characteristics are met, including:

[0099] The purchase score of the SKU is determined based on the estimated purchase rate of the SKU when different prior characteristics are met.

[0100] Sort the SKUs in descending order of their purchase ratings;

[0101] The purchase rating of a SKU increases as the estimated purchase rate of that SKU increases.

[0102] According to one or more embodiments of this disclosure, a product sorting method is provided, which determines the purchase score of an SKU based on the estimated purchase rate of the SKU when different prior characteristics are met, including:

[0103] For any target SPU in the SPU, the target SKU corresponding to the number of the first SKUs displayed in the first position and its corresponding estimated purchase rate are determined respectively, according to the increasing order of the number of the first SKUs. The target SKU is determined based on the number of the first SKUs and the estimated purchase rate.

[0104] Based on the estimated purchase rate of each target SKU, the purchase score of each target SKU is determined, wherein different numbers of top SKUs correspond to different target SKUs.

[0105] According to one or more embodiments of this disclosure, a product sorting method is provided to determine the target SKU corresponding to the number of top SKUs and its corresponding estimated purchase rate, including:

[0106] If the number of SKUs in the front position is 0, and it is determined that no SKU of the target SPU has been displayed in the front position, the SKU with the highest estimated purchase rate under the target SPU shall be the target SKU;

[0107] If the number of the first SKUs is n and n is not 0, when the first SKUs displayed in the first position are n target SKUs arranged in ascending order of the number of the corresponding first SKUs, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU.

[0108] According to one or more embodiments of this disclosure, a product sorting method is provided, which uses a pre-trained neural network model to determine the estimated purchase rate of each SKU when different prior features are met.

[0109] The inputs to the neural network model include: user feature information, product feature information, and prior features;

[0110] The output of the neural network model includes: the estimated purchase rate of SKUs in the input product when the preceding features of the input are satisfied.

[0111] According to one or more embodiments of this disclosure, a product sorting method is provided where the SKU currently used to calculate the estimated purchase rate differs from the SKUs displayed in the previous positions; and / or,

[0112] The SKUs displayed in the first position are all different.

[0113] According to one or more embodiments of the present disclosure, a product sorting apparatus is provided, characterized in that it includes:

[0114] The acquisition unit is used to acquire the characteristic information of the target user and the characteristic information of the target product, wherein the target product includes one or more SPUs (Standard Product Units); each of the SPUs has one or more SKUs (Stock Keeping Units).

[0115] The control unit is used to determine the estimated purchase rate of the SKU when different prior characteristics are met, based on the characteristic information of the target user and the characteristic information of the target product.

[0116] The control unit is also configured to determine the order of the SKUs based on the estimated purchase rate of the SKUs when different prior characteristics are met.

[0117] According to one or more embodiments of the present disclosure, an electronic device is provided, including: at least one memory and at least one processor;

[0118] The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute the method described in any one of the above.

[0119] According to one or more embodiments of the present disclosure, a computer-readable storage medium is provided for storing program code that, when executed by a processor, causes the processor to perform the methods described above.

[0120] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0121] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0122] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A product sorting method, characterized in that, include: Obtain characteristic information of target users and characteristic information of target products, wherein the target products include one or more SPUs (Standard Product Units); each SPU has one or more SKUs (Stock Keeping Units). Based on the characteristic information of the target user and the characteristic information of the target product, determine the estimated purchase rate of the SKU when different prior characteristics are met; The SKUs are ranked according to their estimated purchase rate when different prior characteristics are met. The preceding features include: feature information of the preceding SKUs that have already been displayed in the preceding position and belong to the same SPU as the SKU for which the estimated purchase rate is currently calculated; the estimated purchase rate is: the probability that the target object will purchase the SKU if an additional SKU is displayed, given that the preceding features are satisfied.

2. The method according to claim 1, characterized in that, Determine the estimated purchase rate of the SKU when different prior characteristics are met, including: When it is determined that 0 to x SKUs belonging to the same SPU as the SKU currently used to calculate the estimated purchase rate have been displayed in the previous position, the estimated purchase rate of the SKU is determined; Where x equals the total number of SKUs under the SPU to which the SKU for which the estimated purchase rate is currently calculated minus one.

3. The method according to claim 1, characterized in that, The SKU ranking is determined based on the estimated purchase rate of the SKU when different prior characteristics are met, including: The purchase score of the SKU is determined based on the estimated purchase rate of the SKU when different prior characteristics are met. Sort the SKUs in descending order of their purchase ratings; The purchase rating of a SKU increases as the estimated purchase rate of that SKU increases.

4. The method according to claim 3, characterized in that, Based on the estimated purchase rate of the SKU when different prior characteristics are met, the purchase score of the SKU is determined, including: For any target SPU in the SPU, the target SKU corresponding to the number of the first SKUs displayed in the first position and its corresponding estimated purchase rate are determined respectively, according to the increasing order of the number of the first SKUs. The target SKU is determined based on the number of the first SKUs and the estimated purchase rate. Based on the estimated purchase rate of each target SKU, the purchase score of each target SKU is determined, wherein different numbers of top SKUs correspond to different target SKUs.

5. The method according to claim 4, characterized in that, Determine the target SKUs corresponding to the number of preceding SKUs and their corresponding estimated purchase rates, including: If the number of SKUs in the front position is 0, and it is determined that no SKU under the target SPU has been displayed in the front position, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU; If the number of the first SKUs is n and n is not 0, when the first SKUs displayed in the first position are n target SKUs arranged in ascending order of the number of the corresponding first SKUs, the SKU with the highest estimated purchase rate under the target SPU is taken as the target SKU.

6. The method according to claim 1, characterized in that, A pre-trained neural network model is used to determine the estimated purchase rate of each SKU when different prior features are satisfied; wherein, the input of the neural network model includes: user feature information, product feature information, and prior features; the output of the neural network model includes: the estimated purchase rate of the user purchasing the SKU in the input product when the prior features of the input are satisfied; And / or, the SKU currently used to calculate the estimated purchase rate is different from the SKU displayed in the previous position; And / or, The SKUs displayed in the first position are all different.

7. A product sorting device, characterized in that, include: The acquisition unit is used to acquire feature information of the target user and feature information of the target product, wherein the target product includes one or more SPUs; each of the SPUs has one or more SKUs; The control unit is used to determine the estimated purchase rate of the SKU when different prior characteristics are met, based on the characteristic information of the target user and the characteristic information of the target product. The control unit is also configured to determine the order of the SKUs based on the estimated purchase rate of the SKUs when different prior characteristics are met; The preceding features include: feature information of the preceding SKUs that have already been displayed in the preceding position and belong to the same SPU as the SKU for which the estimated purchase rate is currently calculated; the estimated purchase rate is: the probability that the target object will purchase the SKU if an additional SKU is displayed, given that the preceding features are satisfied.

8. An electronic device, comprising: At least one memory and at least one processor; The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute the method of any one of claims 1 to 6.

9. A computer-readable storage medium for storing program code that, when executed by a processor, causes the processor to perform the method of any one of claims 1 to 6.

Images