User preference analysis method, device, equipment and computer storage medium

Abstract

An embodiment of the present application proposes a user preference analysis method, device, electronic device and computer storage medium, the method comprising: obtaining historical added purchase data within a first set time period and historical order data within a second set time period for each user among multiple users; the second set time period represents a specified time period after the first set time period; for each user, determining a mapping relationship between the added purchase items in the historical added purchase data and the order items in the historical order data within the specified time period; the product category of the added purchase items and the order items is the same; from at least one product dimension, comparing and analyzing the added purchase items and the order items that satisfy the mapping relationship to determine preference information of the multiple users.

Description

Technical Field

[0001] The present application relates to the field of computer network data technology, and in particular to a user preference analysis method, device, electronic device and computer storage medium. Background Art

[0002] With the rapid growth of brand sales data on websites and increasingly fierce brand competition, brands are in urgent need of understanding user preferences and improving brand competitiveness. However, the existing data can only count transaction data such as the number of users, sales volume, and sales revenue under the category or brand dimension, and can only simply analyze user distribution under the brand and category dimensions. There is a lack of analysis of user purchase interests, making it difficult to deeply explore user preferences, and thus unable to achieve the goal of deeply exploring potential users, reducing product competitiveness. Summary of the invention

[0003] The present application provides a user preference analysis method, device, electronic device and computer storage medium, which can deeply explore user preferences and improve product competitiveness.

[0004] The technical solution of this application is implemented as follows:

[0005] The present application provides a method for analyzing user preferences, the method comprising:

[0006] Acquire historical additional purchase data within a first set time period and historical order data within a second set time period for each of a plurality of users; the second set time period represents a specified time period after the first set time period;

[0007] For each user, determining a mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period; the added-purchase items and the ordered items are of the same commodity category;

[0008] From at least one product dimension, a comparative analysis is performed on the additional products and the ordered products that satisfy the mapping relationship to determine preference information of the multiple users.

[0009] In some embodiments, determining the mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period includes:

[0010] Determine a first time difference between the purchase time of the additional product in the historical additional purchase data and a reference time, and a second time difference between the order time of the order product in the historical order data and the reference time; the reference time is earlier than or equal to the additional purchase time;

[0011] According to the numerical relationship between the first time difference and the specified time period, a grouping method is used to determine the group number of the group to which the additional purchase product belongs; according to the numerical relationship between the second time difference and the specified time period, a grouping method is used to determine the group number of the group to which the order product belongs;

[0012] When it is determined that the user of the added purchased item is the same as the user of the ordered item, the product category of the added purchased item is the same as that of the ordered item, and the group number of the added purchased item and the group number of the ordered item satisfy a set relationship, a mapping relationship between the added purchased item and the ordered item within the specified time period is determined.

[0013] In some embodiments, the step of determining the group number of the group to which the additional purchase item belongs by setting a grouping method according to the numerical relationship between the first time difference and the specified time period includes:

[0014] According to the numerical relationship between the first time difference and the specified time period, the quotient of the first time difference divided by the specified time period is used as the group number of the group to which the additional purchase product belongs;

[0015] The step of determining the group number of the group to which the ordered product belongs by setting a grouping method according to the numerical relationship between the second time difference and the specified time period includes:

[0016] According to the numerical relationship between the second time difference and the specified time period, the quotient of the second time difference divided by the specified time period is used as the group number of the group to which the order product belongs.

[0017] In some embodiments, the method further comprises:

[0018] When it is determined that the group number of the additional purchase item is the same as the group number of the order item or the group number of the additional purchase item is equal to the group number of the order item minus 1, it is determined that the group number of the additional purchase item satisfies a set relationship with the group number of the order item.

[0019] In some embodiments, determining the mapping relationship between the additional purchase item and the order item within the specified time period includes:

[0020] Based on the restriction condition, a mapping relationship between the added purchase item and the order item within the specified time period is determined; the restriction condition includes: an order time of the order item is greater than a purchase time of the added purchase item, and a difference in days between the order time and the added purchase time is less than or equal to the specified time period.

[0021] In some embodiments, the at least one product dimension includes at least one of the following: product brand, product price range, and product physical properties.

[0022] The embodiment of the present application also proposes a user preference analysis device, which includes an acquisition module, a first determination module and a second determination module, wherein:

[0023] An acquisition module, used to acquire historical additional purchase data of each user in a first set time period and historical order data in a second set time period; the second set time period represents a specified time period after the first set time period;

[0024] A first determination module is used to determine, for each user, a mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period; the added-purchase items and the ordered items are of the same commodity category;

[0025] The second determination module is used to compare and analyze the additional purchase items and the order items that satisfy the mapping relationship from at least one item dimension to determine the preference information of the multiple users.

[0026] An embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the user preference analysis method provided by one or more of the aforementioned technical solutions when executing the program.

[0027] An embodiment of the present application provides a computer storage medium, which stores a computer program; after the computer program is executed, it can implement the user preference analysis method provided by one or more of the above-mentioned technical solutions.

[0028] An embodiment of the present application proposes a user preference analysis method, device, electronic device and computer storage medium, the method comprising: obtaining historical added purchase data within a first set time period and historical order data within a second set time period for each user among multiple users; the second set time period represents a specified time period after the first set time period; for each user, determining a mapping relationship between the added purchase items in the historical added purchase data and the order items in the historical order data within the specified time period; the product category of the added purchase items and the order items is the same; from at least one product dimension, comparing and analyzing the added purchase items and the order items that satisfy the mapping relationship to determine preference information of the multiple users.

[0029] It can be seen that the embodiment of the present application can obtain the user's behavior data from adding items to purchasing items of the same category (order items) within a certain period of time by acquiring the user's historical added-to-cart data and historical order data; then, by comparing and analyzing the user's behavior data of adding items to cart and ordering items from at least one product dimension, such as product brand, product price range, etc., the user's sensitivity to product prices and product brands can be determined, thereby achieving the purpose of in-depth exploration of user preferences; in this way, subsequent adjustments can be made to promotional activities or new product development to be closer to user preferences, thereby achieving sales growth while improving product competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1a is a flowchart of a user preference analysis method in an embodiment of the present application;

[0031] Figure 1b is a schematic diagram of determining user preferences in an embodiment of the present application;

[0032] Figure 2a A flowchart of determining user preferences according to an embodiment of the present application;

[0033] Figure 2b A flowchart of another method for analyzing user preferences according to an embodiment of the present application;

[0034] Figure 3 is a schematic diagram of the structure of a user preference analysis device according to an embodiment of the present application;

[0035] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The present application will be further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the embodiments provided herein are only used to explain the present application and are not intended to limit the present application. In addition, the embodiments provided below are partial embodiments for implementing the present application, rather than providing all embodiments for implementing the present application. In the absence of conflict, the technical solutions recorded in the embodiments of the present application can be implemented in any combination.

[0037] It should be noted that, in the embodiments of the present application, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or apparatus including a series of elements includes not only the elements explicitly recorded, but also includes other elements not explicitly listed, or also includes elements inherent to the implementation of the method or apparatus. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other related elements (such as steps in a method or units in a device, for example, a unit may be a portion of a circuit, a portion of a processor, a portion of a program or software, etc.) in the method or apparatus including the element.

[0038] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, I and / or J can represent the three situations that I exists alone, I and J exist at the same time, and J exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of I, J, and R can represent including any one or more elements selected from the set consisting of I, J, and R.

[0039] For example, the user preference analysis method provided in the embodiment of the present application includes a series of steps, but the user preference analysis method provided in the embodiment of the present application is not limited to the recorded steps. Similarly, the user preference analysis device provided in the embodiment of the present application includes a series of modules, but the user preference analysis device provided in the embodiment of the present application is not limited to including the modules explicitly recorded, and may also include modules required to obtain relevant task data or perform processing based on task data.

[0040] The present application can be implemented based on an electronic device, where the electronic device can be a thin client, a thick client, a handheld or laptop device, a microprocessor-based system, a set-top box, a programmable consumer electronic product, a network personal computer, a small computer system, and the like.

[0041] Electronic devices can implement corresponding functions through the execution of program modules. Generally, program modules can include routines, programs, target programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, in which tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0042] In the related technologies, only transaction data such as the number of users, sales volume, and sales revenue can be counted under the category or brand dimension through existing data, which can only be used for simple sales analysis. There is a lack of analysis on users' purchasing interests and the advantages of the products themselves. It is impossible to mine user preferences from the trajectory from the exposure of products to users, to arousing users' interest, and then to the conversion from added-to-cart products to ordered products over a period of time. In other words, there is no method to analyze users' behavior from adding-to-cart products to ordering products, and to deeply mine user preferences. Therefore, it is difficult to achieve the goal of increasing sales and enhancing product competitiveness.

[0043] In view of the above technical problems, the following embodiments are proposed.

[0044] In some embodiments of the present application, the user preference analysis method can be implemented using a processor in a user preference analysis device, and the above-mentioned processor can be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor.

[0045] Figure 1a is a flowchart of a user preference analysis method in an embodiment of the present application, such as Figure 1a As shown, the method comprises the following steps:

[0046] Step 100: Obtain historical additional purchase data within a first set time period and historical order data within a second set time period for each user among a plurality of users; the second set time period represents a specified time period after the first set time period.

[0047] In an embodiment of the present application, historical purchase data represents the behavior data of users adding items to the shopping cart within a first set time period; historical order data represents the behavior data of users submitting order items for payment within a second set time period; here, the items can represent any type of items traded by an e-commerce platform or seller through the Internet; for example, they can be clothing items, food items, etc., and can also be virtual items, etc.

[0048] Exemplarily, the setting of the first set time period is related to the category to which the product belongs. For example, for products in the electrical appliance category, the first set time period can be set relatively longer, for example, 6 months, 1 year, etc.; and for products in the food category, the first set time period can be set relatively shorter, for example, 1 month, 2 months, etc.

[0049] Exemplarily, the second set time period represents a prescribed time period after the first set time period; here, the setting of the prescribed time period can be determined according to actual conditions, and the embodiments of the present application do not limit this; for example, when the first set time period is 6 months, the prescribed time period can be 14 days or 20 days after 6 months.

[0050] Exemplarily, the first set time period and the second set time period both represent historical time periods; since the historical purchase data and historical order data generated recently by the user can more accurately determine the user's current preference information than those generated in the early stage, the time periods closer to the current time can be preferentially selected as the first set time period and the second set time period; for example, the first set time period may be the past 6 months, and the second set time period may be 14 days after the past 6 months.

[0051] Exemplarily, before obtaining historical added purchase data and historical order data, a added purchase data table related to the historical added purchase data and an order data table related to the historical order data can be pre-constructed; here, Table 1 lists a table structure of an added purchase data table. Referring to Table 1, it can be seen that the added purchase data table includes fields such as product code, user pin and added purchase time.

[0052]

[0053] Table 1

[0054] Table 2 lists the table structure of an order data table. Referring to Table 2, it can be seen that the order data table includes fields such as product code, user pin, order code, sales amount, sales volume and order time.

[0055]

[0056] Table 2

[0057] For example, in addition to constructing the above-mentioned purchase data table and order data table, a product brand category table is also constructed. Table 3 lists a table structure of a product brand category table. Referring to Table 3, it can be seen that the product brand category table includes fields such as sku code, sku name, brand code, brand name, first-level category code and first-level category name; here, sku code represents the product code after deduplication.

[0058]

[0059] Table 3

[0060] It should be noted that the fields included in Table 1, Table 2 and Table 3 can be flexibly changed and can be determined according to the actual scenario. The embodiments of the present application do not limit this. For example, the field "Number of additional purchases" can be added to Table 1, the field "Number of orders" can be added to Table 2, and the fields "First-level category code" and "Second-level category name" can be added to Table 2.

[0061] It can be seen that for any user, each time an additional purchase behavior occurs, the additional purchase data corresponding to the additional purchase behavior will be stored in the corresponding field in the additional purchase data table, and the brand and category of the additional purchase product will be stored in the corresponding field in the product brand category table; similarly, each time an order for a product occurs, the order data corresponding to the order behavior will be stored in the corresponding field in the order data table, and the brand and category of the order product will be stored in the corresponding field in the product brand category table; in this way, after setting the first set time period, the historical additional purchase data of each user in the first set time period can be directly obtained from the additional purchase data table; after setting the second set time period, the historical order data of each user in the second set time period can be directly obtained from the order data table.

[0062] Step 101: for each user, determine the mapping relationship between the added-to-purchase items in the historical added-to-purchase data and the ordered items in the historical order data within a specified time period; the added-to-purchase items and the ordered items are of the same product category.

[0063] In the embodiment of the present application, after the historical added purchase data and historical order data of each user are obtained according to step 100, since the category of the added purchase goods included in the historical added purchase data and the category of the order goods included in the historical order data may be the same or may be different; here, when it is determined that the category of the added purchase goods is the same as the category of the order goods, a mapping relationship between the added purchase goods and the order goods within the second set time period is established for each user.

[0064] For example, suppose a user purchased a dress the day before yesterday and placed an order for another dress yesterday, that is, the two dresses belong to the same product category, both women's clothing; if it is determined that the user's purchase time and order time are within the second set time period, at this time, a mapping relationship between the purchased dress and the ordered dress within the second set time period can be established for the user.

[0065] In some embodiments, determining the mapping relationship between purchased items in historical purchased data and ordered items in historical order data within a specified time period may include: determining a first time difference between the purchase time of the purchased items in the historical purchased data and a reference time, and a second time difference between the order time of the order items in the historical order data and the reference time; the reference time is earlier than or equal to the purchased time; according to the numerical relationship between the first time difference and the specified time period, using a set grouping method to determine the group number of the group to which the purchased items belong; according to the numerical relationship between the second time difference and the specified time period, using a set grouping method to determine the group number of the group to which the order items belong; when it is determined that the user of the purchased items is the same as the user of the ordered items, the product category of the purchased items is the same as that of the ordered items, and the group number of the purchased items and the group number of the order items satisfy the set relationship, determining the mapping relationship between the purchased items and the order items within the specified time period.

[0066] Here, the reference time may be a preset time point, which may be earlier than the earliest purchase time when the user purchases the product, or the same as the earliest purchase time when the user purchases the product.

[0067] For example, assuming that within the first set time period, a user first purchases product A in the food category at time point 2021 / 5 / 2, and then first purchases product B in the food category at time point 2021 / 5 / 3; then, at time point 2021 / 5 / 5, the user purchases product A in the food category again. At this time, the time point 2021 / 5 / 2 can be used as the reference time, or a time point earlier than the time point 2021 / 5 / 2, such as the time point 2021 / 5 / 1, can be used as the reference time.

[0068] Exemplarily, after determining the above-mentioned reference time, the purchase time of each added item can be obtained based on the historical added purchase data of each user, and then, the first time difference between the purchase time of each added item and the reference time can be determined; similarly, the order time of each order item can be obtained based on the historical order data of each user, and then, the second time difference between the order time of each order item and the reference time can be determined.

[0069] For example, assuming that the pre-set reference time is 2021 / 5 / 1 12:00, the user's purchase time for product C in the food category is 2021 / 5 / 11 12:00, and the user's order time for product D in the food category is 2021 / 5 / 16 12:00, then the first time difference between the purchase time corresponding to product C and the reference time is 10 days, and the second time difference between the order time corresponding to product D and the reference time is 15 days.

[0070] Exemplarily, after determining the first time difference between the purchase time of the added purchased items in the historical purchased data and the reference time, as well as the second time difference between the order time of the order items in the historical order data and the reference time for each user, a grouping method is set to group the added purchased items and the order items respectively, and obtain the group number of the group where the added purchased items are located and the group number of the group where the added purchased items are located.

[0071] In some embodiments, based on the numerical relationship between the first time difference and the specified time period, a grouping method is set to determine the group number of the group where the added purchase items are located, which may include: based on the numerical relationship between the first time difference and the specified time period, taking the quotient of the first time difference divided by the specified time period as the group number of the group where the added purchase items are located.

[0072] Here, the method of grouping the added purchase items is the same as the method of grouping the order items, and the grouping is performed according to the numerical relationship between the first time difference and the specified time period; specifically, when the first time difference and the specified time period corresponding to the added purchase item are obtained, the quotient of the first time difference divided by the specified time period can be used as the group number of the group to which the added purchase item belongs.

[0073] For example, assuming that the specified time period is 14 days, the additional product is product C, and its corresponding first time difference is 10 days, at this time, the quotient of the first time difference of 10 days divided by the specified time period of 14 days, 0, can be used as the group number of the group to which product C belongs, that is, the group number of the group to which the additional product (product C) belongs is 0.

[0074] In some embodiments, based on the numerical relationship between the second time difference and the specified time period, a grouping method is set to determine the group number of the group to which the order product belongs, which may include: based on the numerical relationship between the second time difference and the specified time period, taking the quotient of the second time difference divided by the specified time period as the group number of the group to which the order product belongs.

[0075] For example, assuming that the specified time period is 14 days, the order product is the above-mentioned product D, and its corresponding second time difference is 15 days, at this time, the quotient 1 of the second time difference 15 days divided by the specified time period 14 days can be used as the group number of the group to which product D belongs, that is, the group number of the group to which the order product (product D) belongs is 1.

[0076] In some embodiments, the above method may further include: when it is determined that the group number of the added item is the same as the group number of the order item or the group number of the added item is equal to the group number of the order item minus 1, determining that the group number of the added item and the group number of the order item satisfy a set relationship.

[0077] Exemplarily, assuming that user 1 purchases additional goods of category L, and the group number of the additional goods is 1, and user 1 subsequently purchases goods of category L, and the group number of the order goods is also 1, then it is determined that the group number of the additional goods and the group number of the order goods satisfy the set relationship; or, assuming that user 2 purchases additional goods of category L, and the group number of the additional goods is 1, and user 2 subsequently purchases goods of category L, and the group number of the order goods is 2, then it is determined that the group number of the additional goods and the group number of the order goods also satisfy the set relationship.

[0078] In some embodiments, if it is determined that the group number of the additional product and the group number of the order product satisfy a set relationship, a mapping relationship between the additional product and the order product within a specified time period is determined based on the restriction condition.

[0079] In an embodiment of the present application, the restriction conditions may include: the order time of the ordered product is greater than the purchase time of the added product, and the difference in days between the order time and the added purchase time is less than or equal to the specified time period.

[0080] For example, by setting restriction conditions, limiting the order time of the order items to be greater than the purchase time of the added items, and the difference in days between the order time and the added purchase time is within the specified time period, the amount of data calculation can be reduced and the time for determining the mapping relationship can be saved.

[0081] In an embodiment of the present application, after obtaining the group number of the group where the added purchase item is located and the group number of the group where the order item is located according to the above-mentioned grouping method, if it is determined that the user of the added purchase item and the order item is the same user, the commodity category corresponding to the added purchase item and the order item is the same category, and the group number of the group where the added purchase item is located is equal to the serial number of the group where the order item is located, the mapping relationship between the added purchase item and the order item within the specified time period is determined through the above-mentioned restriction conditions; or, if it is determined that the user of the added purchase item and the order item is the same user, the commodity category corresponding to the added purchase item and the order item is the same category, and the group number of the group where the added purchase item is located is equal to the group number of the group where the order item is located minus 1, the mapping relationship between the added purchase item and the order item within the specified time period is determined through the above-mentioned restriction conditions.

[0082] Table 4 lists a mapping relationship between added-to-cart items and ordered items for different users. Here, the product category of each user's added-to-cart items is the same as the product category of the ordered items. Referring to Table 4, it can be seen that for each user from user 1 to user 4, a mapping relationship between added-to-cart items and ordered items can be obtained.

[0083]

[0084]

[0085] Table 4

[0086] For example, after obtaining the mapping relationship between the added-purchase items and the order items within the second set time period for each user, the number of added-purchase items, the converted order quantity, the converted amount, the converted sales volume and other data of each user can be counted according to the added-purchase item dimension and the order item dimension. Here, the converted order quantity refers to the number of order items of the same product category converted from the added-purchase items; the converted amount refers to the amount of order items of the same product category converted from the added-purchase items; and the converted sales volume refers to the sales volume of order items of the same product category converted from the added-purchase items.

[0087] Step 102: From at least one product dimension, comparative analysis is performed on the additional purchase products and the order products that satisfy the mapping relationship to determine preference information of multiple users.

[0088] In some embodiments, at least one product dimension may include at least one of the following: product brand, product price range, and product physical properties; here, the product physical properties refer to the physical properties of the product itself, such as product color, product size, or product weight, etc., which is not limited to this embodiment of the present application.

[0089] In an embodiment of the present application, after obtaining the added-to-cart items and the ordered items that satisfy the mapping relationship for each user, a comparative analysis can be performed on the added-to-cart items and the ordered items from at least one product dimension; illustratively, when the product dimensions are product brand and product price range, a comparative analysis can be performed on the two product dimensions of product brand and product price range corresponding to the added-to-cart items and the ordered items at the same time, so as to determine the user's preference information for product brand and product price range.

[0090] Exemplarily, the data such as the conversion order volume, conversion amount, and conversion sales volume of the added-to-cart items and the order items that satisfy the mapping relationship can also be compared and analyzed from at least one product dimension to determine the preference information of multiple users.

[0091] Figure 1b is a schematic diagram of determining user preferences in an embodiment of the present application, which shows a comparative analysis result diagram of multiple users when adding to cart and placing orders for the same category of goods, such as Figure 1b As shown in the figure, the vertical direction of the figure represents the price range when multiple users purchase two different brands of goods (a certain brand and a competing product), and the horizontal direction of the figure represents the price range when multiple users place orders for two different brands of goods; from the horizontal direction, each percentage under a certain price band in the figure represents the sales volume distribution of the brand of goods actually purchased by multiple users in different price bands after they purchase a certain brand of goods; it can be seen that Figure 1b It is the result of a comparative analysis of the conversion sales of added-to-cart items and order items that satisfy the mapping relationship from the two product dimensions of product brand and product price range.

[0092] From 1b, we can see that the competitiveness of a certain brand (target brand) in the price range of 1K-1.5K and 2K-2.5K needs to be solved urgently. In the data of these two price ranges, from the perspective of add-to-cart conversion, the sales volume of a certain brand of goods added to the cart and converted into the corresponding order goods of the same price range only accounted for 13% and 11% of the sales volume of the converted order goods of the added-to-cart goods in the price range, while the sales volume of the competing products accounted for 30% and 18% respectively. It can be seen that the competitiveness of the target brand is relatively weak compared with the competing products. In addition, from the perspective of users who hesitated in the previous price range of 1.5K-2K and 2.5K-3K, only 4% and 2% were converted from the previous price range of the added-to-cart goods (1.5K-2K and 2.5K-3) to the next price range (1K-1.5K and 2K-2.5K), while the sales volume of the competing products was 19% and 14% from the previous price range of the added-to-cart goods.

[0093] It can be seen that in the embodiments of the present application, by comparing and analyzing the data such as the conversion order volume, conversion amount and conversion sales volume of the user's added purchase and ordered products from at least one product dimension, for example, product brand, product price range, product physical properties, etc., the user's sensitivity to product price, product brand, and product physical properties can be determined, thereby achieving the purpose of in-depth exploration of user preferences; in this way, subsequent adjustments can be made to promotional activities or new product development to be more in line with user preferences, thereby achieving sales growth while improving product competitiveness.

[0094] The embodiment of the present application proposes a user preference analysis method, device, electronic device and computer storage medium, the method comprising: obtaining historical purchase data of each user in a first set time period and historical order data in a second set time period; the second set time period represents a specified time period after the first set time period; for each user, determining the mapping relationship between the purchased items in the historical purchase data and the ordered items in the historical order data within the specified time period; the purchased items and the ordered items are of the same commodity category; from at least one commodity dimension, the purchased items and the ordered items that satisfy the mapping relationship are compared and analyzed to determine the preference information of multiple users. It can be seen that the embodiment of the present application can obtain the user's behavior data from purchasing purchased items to purchasing the same category of goods (order goods) within a certain time period by obtaining the user's historical purchase data and historical order data; then, by comparing and analyzing the user's purchase data and order data from at least one commodity dimension, such as commodity brand, commodity price range, etc., the user's sensitivity to commodity price and commodity brand can be determined, so as to achieve the purpose of in-depth mining of user preferences; in this way, the subsequent promotion activities or new product development can be adjusted to be closer to user preferences, so as to achieve sales growth and improve commodity competitiveness.

[0095] In order to better reflect the purpose of the present application, further explanation is given based on the above embodiments of the present application.

[0096] This application involves a multi-level combined analysis business intelligence (BI) report model solution. Figure 2a This is a flow chart of determining user preferences according to an embodiment of the present application. Figure 2a As shown, the process may include three layers: a basic layer, a core computing layer, and an analysis layer; wherein the core computing layer includes an intermediate layer and an integration layer.

[0097] Exemplarily, the basic layer obtains valid data, that is, obtains the historical added purchase data of each user within a first set time period and the historical order data within a second set time period; for example, the added purchase data of the past 6 months (representing the above-mentioned first time period, which can be adjusted according to different product categories, here, 6 months is taken as an example) and the order data of the past 6 months plus 14 days are obtained; the core computing layer determines the mapping relationship of each user's added purchase products into order products of the same category, and integrates the data by matching the added purchase products and order products with product brands, price ranges, and physical properties. The analysis layer performs multi-dimensional report analysis based on the mapping relationship of the core computing layer and the data integration results.

[0098] Figure 2b FIG. 1 is a flow chart of another method for analyzing user preferences according to an embodiment of the present application. Figure 2b As shown, for each user, the purchase time of the added purchase items in the historical added purchase data, the order time of the order items in the historical order data, and the base time are determined; a first time difference between the added purchase time and the base time is calculated, and the quotient of the first time difference divided by 14 (indicating that the duration of the above-mentioned specified time period is 14 days) is used as the group number of the group to which the added purchase items belong; similarly, a second time difference between the order time and the base time is calculated, and the quotient of the second time difference divided by 14 is used as the group number of the group to which the order items belong; when it is determined that the user of the added purchase items is the same as the user of the order items, the product category of the added purchase items is the same as that of the order items, and the group number of the added purchase items is the same as that of the order items or the group number of the added purchase items is equal to the group number of the order items minus 1, based on the fact that the order time of the order items is greater than the purchase time of the added purchase items, and the difference in days between the order time and the added purchase time is less than or equal to 14 days, the mapping relationship between the added purchase items and the order items in the past 15 days is determined.

[0099] Next, for the mapping relationship between added-to-cart items and ordered items, the relevant data such as the number of added-to-cart items, converted order volume, converted amount, converted sales volume, etc. for each user are counted according to the dimensions of added-to-cart items and order items. The price, brand, and physical properties of the items purchased by users and the actual purchases are compared from the product dimensions such as product brand, product price range, and product physical properties, and the user's preferences for price, brand, and attributes are analyzed.

[0100] Figure 3 is a schematic diagram of the structure of the user preference analysis device according to an embodiment of the present application. Figure 3 As shown, the device includes: an acquisition module 300, a first determination module 301 and a second determination module 302, wherein:

[0101] The acquisition module 300 is used to acquire the historical additional purchase data of each user in a first set time period and the historical order data in a second set time period; the second set time period is a specified time period after the first set time period;

[0102] The first determination module 301 is used to determine, for each user, a mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period; the added-purchase items and the ordered items are of the same commodity category;

[0103] The second determining module 302 is used to compare and analyze the added-to-cart products and the ordered products that satisfy the mapping relationship from at least one product dimension to determine the preference information of the multiple users.

[0104] In some embodiments, the first determining module 301 is used to determine the mapping relationship between the added purchase items in the historical added purchase data and the ordered items in the historical order data within the specified time period, including:

[0105] Determine a first time difference between the purchase time of the additional product in the historical additional purchase data and a reference time, and a second time difference between the order time of the order product in the historical order data and the reference time; the reference time is earlier than or equal to the additional purchase time;

[0106] According to the numerical relationship between the first time difference and the specified time period, a grouping method is used to determine the group number of the group to which the additional purchase product belongs; according to the numerical relationship between the second time difference and the specified time period, a grouping method is used to determine the group number of the group to which the order product belongs;

[0107] When it is determined that the user of the added purchased item is the same as the user of the ordered item, the product category of the added purchased item is the same as that of the ordered item, and the group number of the added purchased item and the group number of the ordered item satisfy a set relationship, a mapping relationship between the added purchased item and the ordered item within the specified time period is determined.

[0108] In some embodiments, the first determining module 301 is used to determine the group number of the group where the additional purchase product is located according to the numerical relationship between the first time difference and the specified time period, using a set grouping method, including:

[0109] According to the numerical relationship between the first time difference and the specified time period, the quotient of the first time difference divided by the specified time period is used as the group number of the group to which the additional purchase product belongs;

[0110] The first determination module 301 is used to determine the group number of the group to which the ordered product belongs according to the numerical relationship between the second time difference and the specified time period by setting a grouping method, including:

[0111] According to the numerical relationship between the second time difference and the specified time period, the quotient of the second time difference divided by the specified time period is used as the group number of the group to which the order product belongs.

[0112] In some embodiments, the first determining module 301 is further configured to:

[0113] When it is determined that the group number of the additional purchase item is the same as the group number of the order item or the group number of the additional purchase item is equal to the group number of the order item minus 1, it is determined that the group number of the additional purchase item satisfies a set relationship with the group number of the order item.

[0114] In some embodiments, the first determining module 301 is further configured to:

[0115] After determining that the group number of the added purchase item and the group number of the order item satisfy a set relationship, based on restriction conditions, determine a mapping relationship between the added purchase item and the order item within the specified time period; the restriction conditions include: the order time of the order item is greater than the purchase time of the added purchase item, and the difference in days between the order time and the added purchase time is less than or equal to the specified time period.

[0116] In some embodiments, the at least one product dimension includes at least one of the following: product brand, product price range, and product physical properties.

[0117] In practical applications, the acquisition module 300, the first determination module 301, the second determination module 302 and the allocation module can all be implemented by a processor located in an electronic device, and the processor can be at least one of an ASIC, a DSP, a DSPD, a PLD, a FPGA, a CPU, a controller, a microcontroller, and a microprocessor.

[0118] In addition, each functional module in this embodiment can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or software functional modules.

[0119] If the integrated unit is implemented in the form of a software function module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment is essentially or the part that contributes to the relevant technology or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method of this embodiment. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc. Various media that can store program codes.

[0120] Specifically, the computer program instructions corresponding to a user preference analysis method in this embodiment can be stored on a storage medium such as a CD, a hard disk, or a USB flash drive. When the computer program instructions corresponding to a user preference analysis method in the storage medium are read or executed by an electronic device, any user preference analysis method in the aforementioned embodiments is implemented.

[0121] Based on the same technical concept as the above embodiments, see Figure 4 , which shows an electronic device 400 provided in an embodiment of the present application, which may include: a memory 401 and a processor 402; wherein,

[0122] Memory 401, used for storing computer programs and data;

[0123] The processor 402 is configured to execute a computer program stored in the memory to implement any one of the user preference analysis methods in the foregoing embodiments.

[0124] In practical applications, the memory 401 may be a volatile memory, such as RAM; or a non-volatile memory, such as ROM, flash memory, hard disk drive (HDD) or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 402.

[0125] The processor 402 may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. It is understandable that for different audit management platforms, the electronic device used to implement the processor function may also be other, which is not specifically limited in the embodiments of the present application.

[0126] In some embodiments, the functions or modules included in the device provided in the embodiments of the present application can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0127] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0128] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0129] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0130] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0132] The present application is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, and the combination of the process and / or box in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0134] The above are only preferred embodiments of the present application and are not intended to limit the protection scope of the present application.

Claims

1. A user preference analysis method, characterized in that: The method comprises: Acquire historical additional purchase data within a first set time period and historical order data within a second set time period for each of a plurality of users; the second set time period represents a specified time period after the first set time period; For each user, determining a mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period; the added-purchase items and the ordered items are of the same commodity category; performing comparative analysis on the additional purchase items and the order items that satisfy the mapping relationship from at least one product dimension to determine preference information of the multiple users; Wherein, the determining of the mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period includes: Determine a first time difference between the purchase time of the additional product in the historical additional purchase data and a reference time, and a second time difference between the order time of the order product in the historical order data and the reference time; the reference time is earlier than or equal to the additional purchase time; According to the numerical relationship between the first time difference and the specified time period, a grouping method is used to determine the group number of the group to which the additional purchase product belongs; according to the numerical relationship between the second time difference and the specified time period, a grouping method is used to determine the group number of the group to which the order product belongs; When it is determined that the user of the added purchased item is the same as the user of the ordered item, the product category of the added purchased item is the same as that of the ordered item, and the group number of the added purchased item and the group number of the ordered item satisfy a set relationship, a mapping relationship between the added purchased item and the ordered item within the specified time period is determined.

2. The method according to claim 1, characterized in that The step of determining the group number of the group to which the additional purchase product belongs by setting a grouping method according to the numerical relationship between the first time difference and the specified time period includes: According to the numerical relationship between the first time difference and the specified time period, the quotient of the first time difference divided by the specified time period is used as the group number of the group to which the additional purchase product belongs; The step of determining the group number of the group to which the ordered product belongs by setting a grouping method according to the numerical relationship between the second time difference and the specified time period includes: According to the numerical relationship between the second time difference and the specified time period, the quotient of the second time difference divided by the specified time period is used as the group number of the group to which the order product belongs.

3. The method according to claim 1, characterized in that The method further comprises: When it is determined that the group number of the additional purchase item is the same as the group number of the order item or the group number of the additional purchase item is equal to the group number of the order item minus 1, it is determined that the group number of the additional purchase item satisfies a set relationship with the group number of the order item.

4. The method according to claim 2 or 3, characterized in that: The method further comprises: After determining that the group number of the added purchase item and the group number of the order item satisfy a set relationship, based on restriction conditions, determine a mapping relationship between the added purchase item and the order item within the specified time period; the restriction conditions include: the order time of the order item is greater than the purchase time of the added purchase item, and the difference in days between the order time and the added purchase time is less than or equal to the specified time period.

5. The method according to claim 1, characterized in that The at least one product dimension includes at least one of the following: product brand, product price range, and product physical attribute.

6. A user preference analysis device, characterized in that: The device comprises: An acquisition module, used to acquire historical additional purchase data of each user in a first set time period and historical order data in a second set time period; the second set time period represents a specified time period after the first set time period; A first determination module is used to determine, for each user, a mapping relationship between the added-purchase items in the historical added-purchase data and the ordered items in the historical order data within the specified time period; the added-purchase items and the ordered items are of the same commodity category; A second determining module is used to compare and analyze the additional purchase products and the ordered products that satisfy the mapping relationship from at least one product dimension to determine the preference information of the multiple users; Wherein, the first determining module is further used for: Determine a first time difference between the purchase time of the additional product in the historical additional purchase data and a reference time, and a second time difference between the order time of the order product in the historical order data and the reference time; the reference time is earlier than or equal to the additional purchase time; According to the numerical relationship between the first time difference and the specified time period, a grouping method is used to determine the group number of the group to which the additional purchase product belongs; according to the numerical relationship between the second time difference and the specified time period, a grouping method is used to determine the group number of the group to which the order product belongs; When it is determined that the user of the added purchased item is the same as the user of the ordered item, the product category of the added purchased item is the same as that of the ordered item, and the group number of the added purchased item and the group number of the ordered item satisfy a set relationship, a mapping relationship between the added purchased item and the ordered item within the specified time period is determined.

7. An electronic device, characterized in that: The device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the method according to any one of claims 1 to 5 is implemented when the processor executes the program.

8. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images