Electronic commerce promotion method based on cloud computing

Abstract

The invention relates to the technical field of cloud computing, and discloses an e-commerce promotion method based on cloud computing, which comprises the following steps: acquiring behavior data of a user on an e-commerce platform; screening the users according to the user registration time and the behavior data to obtain a target user set; purchasing records of the target users in the target user set are extracted; calculating the purchase frequency, the purchase amount and the browsing duration of the target user according to the purchase record and the specific data value in the browsing history, and taking the purchase frequency, the purchase amount and the browsing duration as target features; calculating a matching result of the target commodity and the target user according to the target feature, and determining the commodity with the highest matching degree with the target user; and according to the commodity with the highest matching degree with the target user, popularizing the corresponding commodity on the e-commerce platform for the target user. According to the e-commerce promotion method based on cloud computing provided by the invention, the users are screened according to the behavior data of the users, and the corresponding commodities are matched for the users for promotion, so that accurate recommendation of the commodities is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and in particular to an e-commerce promotion method based on cloud computing. Background Art

[0002] With the popularity of smart phones and mobile Internet, more and more consumers choose to shop on their phones or tablets. Therefore, online shopping in the future will be more mobile. For online shopping e-commerce platforms, merchants need to optimize the mobile shopping experience and provide more convenient and friendly mobile shopping services. Not only that, social media platforms have become an indispensable part of people's daily lives, and many consumers look for shopping inspiration on social media. Therefore, the future e-commerce platform will be more socialized, and merchants can carry out marketing activities through social media platforms, interact with consumers, and increase brand awareness and sales.

[0003] The data content on the e-commerce platform includes consumers' browsing information, product feature information, consumer comments and basic information of consumers. Processing and further mining e-commerce data can improve consumers' loyalty to the e-commerce platform, create more value and enhance the competitiveness of e-commerce. In the context of big data, e-commerce platforms must meet the personalized needs of consumers. They cannot simply display products on the platform, but should use certain means to enable consumers to quickly access products and provide products that they may be interested in, so as to improve consumers' efficiency in selecting products and increase their experience value. Traditional e-commerce product promotion generally has problems such as low personalization of recommendation results, low coverage, low popularity of recommendation results, and poor real-time performance, which seriously affects users' experience of product search. Summary of the invention

[0004] The present invention provides an e-commerce promotion method based on cloud computing, which screens users according to their behavior data and matches corresponding commodities for users for promotion, thereby achieving accurate recommendation of commodities.

[0005] The present invention provides a method for promoting e-commerce based on cloud computing, comprising:

[0006] Obtaining user behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments;

[0007] The users are screened according to the user registration time and the behavior data to obtain a target user set;

[0008] Extracting the purchase records of target users in the target user set, and counting the specific data values ​​in the purchase records and browsing histories;

[0009] Calculate the target user's purchase frequency, purchase amount, and browsing time based on the specific data values ​​in the purchase records and browsing history, and use the purchase frequency, purchase amount, and browsing time as target features;

[0010] Calculate the matching result between the target product and the target user according to the target feature, and determine the product with the highest matching degree with the target user;

[0011] According to the product with the highest matching degree with the target user, the corresponding product is promoted for the target user on the e-commerce platform.

[0012] Furthermore, the step of screening the users according to the user registration time and the behavior data to obtain the target user set includes:

[0013] Obtain the user's registration time, calculate the registration duration based on the registration time, and determine whether the registration duration exceeds the set duration;

[0014] If the registration duration does not exceed the set duration, the user's data will be deleted;

[0015] If the registration duration exceeds the set duration, the user's data will be recorded, and the user's search history and click behavior will be counted. If there are both search records and click behaviors, it will be recorded as a valid search;

[0016] When the ratio of effective search time to registration time exceeds the set ratio, the user is recorded as a target user;

[0017] Traverse all users and get the target user set.

[0018] Further, the step of calculating the target user's purchase frequency, purchase amount, and browsing time according to the specific data values ​​in the purchase record, and using the purchase frequency, purchase amount, and browsing time as target features includes:

[0019] Counting specific data values ​​in the purchase records and browsing histories, including the number of times a product was purchased, the amount of money spent on the product, and the duration of browsing the product;

[0020] The formula for calculating the target user’s purchase frequency, purchase amount, and browsing time is:

[0021]

[0022] T(x)=∑t(x i )

[0023] Among them, f(x) represents the purchase frequency of x-type products; n(x) represents the purchase frequency of x-type products in T n The number of times x-type products are purchased within a certain time frame; C(x) represents the purchase amount of x-type products; c(xi ) represents the purchase amount of any specific product in category x; m(x i ) represents the total purchase amount of any specific product in category x; T(x) represents the browsing time of products in category x; t(x i ) represents the browsing time of any specific product in category x;

[0024] Purchase frequency, purchase amount, and browsing time are used as target features.

[0025] Furthermore, in the step of calculating the matching result between the target product and the target user according to the target feature, and determining the product with the highest matching degree with the target user, the matching result between the target product and the target user is calculated according to the target feature, and the calculation formula is:

[0026]

[0027] Among them, G(x,y) represents the matching result between product attributes and user product preferences; T(x→y) represents the matching coefficient between product browsing time and product y, which mainly determines the type consistency between the product and the user's product preferences; f(x∩y) represents the matching coefficient between product purchase frequency and product y consumption frequency, which mainly determines the consumption habit consistency between the product and the user's product preferences; C(x∩y) represents the matching coefficient between product purchase amount and product y price, which mainly determines the consumption capacity consistency between the product and the user's product preferences.

[0028] Furthermore, in the step of calculating the matching result between the target product and the target user according to the target feature, and determining the product with the highest matching degree with the target user, determining the product with the highest matching degree with the target user includes:

[0029] According to the matching results, the products are sorted in descending order. When the matching results of two or more products are the same, the two or more products are placed in the same order.

[0030] The first ranked product is regarded as the product with the highest matching degree with the target user. If there are multiple first ranked products, all of them are regarded as the products with the highest matching degree with the target user.

[0031] Furthermore, the step of promoting the corresponding product on the e-commerce platform for the target user according to the product with the highest matching degree with the target user includes:

[0032] The product with the highest matching degree with the target user is used as the target product, and the product category of the target product is obtained;

[0033] Acquire related products under the product category that are related to the target product;

[0034] The target product of another brand is promoted to the target user, and the related product is promoted to the target user.

[0035] The present invention also provides a device for promoting e-commerce based on cloud computing, comprising:

[0036] An acquisition module is used to acquire the user's behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments;

[0037] A screening module, used to screen the users according to the user registration time and the behavior data to obtain a target user set;

[0038] An extraction module is used to extract the purchase records of target users in the target user set and to count the specific data values ​​in the purchase records and browsing histories;

[0039] A calculation module, used to calculate the purchase frequency, purchase amount, and browsing time of the target user according to the specific data values ​​in the purchase record and browsing history, and use the purchase frequency, purchase amount, and browsing time as target features;

[0040] A matching module, used to calculate the matching result between the target product and the target user according to the target feature, and determine the product with the highest matching degree with the target user;

[0041] The promotion module is used to promote corresponding commodities for the target users on the e-commerce platform according to the commodities with the highest matching degree with the target users.

[0042] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0043] The present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.

[0044] The beneficial effects of the present invention are:

[0045] The present invention obtains the behavior data of users on the e-commerce platform; and screens the users according to the user registration time and behavior data to obtain the target user set; counts the specific data values ​​in the purchase records and browsing history, calculates the purchase frequency, purchase amount, and browsing time of the target user; and then calculates the matching result between the target product and the target user, and promotes the corresponding product for the target user on the e-commerce platform. According to the consumer's shopping history, browsing behavior and other information, personalized product promotion is provided to consumers to improve the consumer's shopping experience and satisfaction. Cloud computing is used to mine and analyze massive data to provide consumers with more accurate and valuable product recommendations, thereby achieving accurate recommendations for products and having good application effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The figure is a schematic diagram of a method flow according to an embodiment of the present invention.

[0047] Figure 2 FIG. 1 is a schematic diagram of a device structure according to an embodiment of the present invention.

[0048] Figure 3 The figure is a schematic diagram of the internal structure of a computer device according to an embodiment of the present invention.

[0049] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0051] like Figure 1 As shown, the present invention provides a method for promoting e-commerce based on cloud computing, comprising:

[0052] S1. Obtaining user behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments;

[0053] When analyzing user behavior, the user's product preferences are the goal orientation. Therefore, the collected data is mainly the user's behavior data on online platforms such as shopping websites or applications, mainly including browsing history, search history, purchase history, click behavior, ratings and comments, etc. On this basis, the data is processed through the cloud computing platform.

[0054] Through the background records, we can count the user's browsing history and understand which products the user has browsed. Through the user's search history, we can understand which products the user is interested in recently. Through the purchase record, we can understand which products the user has a high demand for recently. Through click behavior, ratings and comments, we can understand the user's purchasing interest behavior, that is, whether the user is good at browsing products and whether he is keen on evaluating products, so as to predict the user's purchasing tendency.

[0055] S2. Screening the users according to the user registration time and the behavior data to obtain a target user set;

[0056] Step S2 specifically includes:

[0057] S21, obtaining the user's registration time, and calculating the registration duration according to the registration time, and determining whether the registration duration exceeds the set duration;

[0058] The registration time is the user's account registration time, and the time from the registration time to the present is the registration duration. For example, if the registration time is November 25, 2023, the user's registration duration is one year. A set duration is set to evaluate the user's account attributes. If the registration time is too short and there are not many purchase records, the account may be an inactive account or may no longer be used, and there is no need for further promotion.

[0059] S22. If the registration duration does not exceed the set duration, deleting the user's data;

[0060] All accounts with a registration period of more than 6 months (the set period can be adjusted as needed and is not limited here) will be deleted, that is, the data of this account will not be counted.

[0061] S23. If the registration duration exceeds the set duration, the user's data is recorded, and the user's search history and click behavior are counted. When there are both search records and click behaviors, it is recorded as a valid search;

[0062] When a user's registration time exceeds 6 months, the user's account may be an active account, so data is recorded for the account, and search records and click behaviors are counted. When there is a search record and there is a click on the result under the search record, it is determined that the user is interested in the product, and it is counted as a valid search.

[0063] S24. When the ratio of effective search time to registration time exceeds a set ratio, the user is recorded as a target user;

[0064] S25. Traverse all users to obtain the target user set.

[0065] The ratio of effective search and registration time is calculated, that is, A = effective search times / registration time. When the registration time is in years, the user's annual search frequency A is obtained. When the registration time is in months / weeks / days, the user's monthly / weekly / day search frequency A is obtained. When the value of A exceeds the set ratio (set according to specific needs, not limited here), the user is recorded as a target user. Finally, all recorded users are traversed according to steps S21-S24 to obtain the target user set.

[0066] S3, extracting the purchase records of the target users in the target user set, and counting the specific data values ​​in the purchase records and browsing histories;

[0067] S4, calculating the target user's purchase frequency, purchase amount, and browsing time based on the specific data values ​​in the purchase records and browsing history, and using the purchase frequency, purchase amount, and browsing time as target features;

[0068] Step S4 specifically includes:

[0069] S41, counting specific data values ​​in the purchase records and browsing history, including the number of times the product was purchased, the amount of the product purchased, and the browsing time of the product;

[0070] S42. Calculate the purchase frequency, purchase amount, and browsing time of the target user. The formula is:

[0071]

[0072] T(x)=Σt(x i )

[0073] Among them, f(x) represents the purchase frequency of x-type products; n(x) represents the purchase frequency of x-type products in T n The number of times x-type products are purchased within a certain time frame; C(x) represents the purchase amount of x-type products; c(x i ) represents the purchase amount of any specific product in category x; m(x i ) represents the total purchase amount of any specific product in category x; T(x) represents the browsing time of category x products; t(xi) represents the browsing time of any specific product in category x products; According to the above method, cloud computing is used to analyze user behavior and determine the user's product preference.

[0074] S43. Purchase frequency, purchase amount, and browsing time are used as target features.

[0075] S5, calculating the matching result between the target product and the target user according to the target feature, and determining the product with the highest matching degree with the target user;

[0076] S51, the calculation formula for calculating the matching result between the target product and the target user according to the target feature is:

[0077]

[0078] Among them, G(x,y) represents the matching result between product attributes and user product preferences; T(x→y) represents the matching coefficient between product browsing time and product y, which mainly determines the type consistency between the product and the user's product preferences; f(x∩y) represents the matching coefficient between product purchase frequency and product y consumption frequency, which mainly determines the consumption habit consistency between the product and the user's product preferences; C(x∩y) represents the matching coefficient between the product purchase amount and the product y price, which mainly determines the consumption capacity consistency between the product and the user's product preferences. It should be noted that the above parameters are all quantitative results and are calculable parameter values ​​in the context of cloud computing. For some products, there may be situations where the characteristic indicators are difficult to directly quantify and calculate. At this time, the frequency parameter can be introduced to convert it into data for subsequent analysis and calculation.

[0079] S52: Sort the commodities in descending order according to the matching results. When the matching results of two or more commodities are the same, the two or more commodities are placed in the same order.

[0080] S53: The first ranked product is used as the product with the highest matching degree with the target user. If there are multiple first ranked products, all of them are used as the products with the highest matching degree with the target user.

[0081] According to the above calculation method, the matching results are sorted in ascending order, and the top products are selected as the preferred recommendation objects. The corresponding recommendation quantity is set according to actual needs to maximize the reliability of the recommendation results and user satisfaction.

[0082] S6. Promote corresponding products on the e-commerce platform for the target user according to the products with the highest matching degree with the target user.

[0083] Step S6 specifically includes:

[0084] S61, taking the product with the highest matching degree with the target user as the target product, and obtaining the product category of the target product;

[0085] S62, obtaining related products under the product category that are related to the target product;

[0086] For example, if the product that has the highest matching degree with the target user is diapers, the product category of diapers is obtained as maternal and child products, and then other products related to diapers (such as diaper cream) under maternal and child products are obtained.

[0087] S63: promoting the target product of another brand that is the same as the target product to the target user, and promoting the associated product to the target user.

[0088] The present invention obtains the behavior data of users on the e-commerce platform; and screens the users according to the user registration time and behavior data to obtain the target user set; counts the specific data values ​​in the purchase records and browsing history, calculates the purchase frequency, purchase amount, and browsing time of the target user; and then calculates the matching result between the target product and the target user, and promotes the corresponding product for the target user on the e-commerce platform. According to the consumer's shopping history, browsing behavior and other information, personalized product promotion is provided to consumers to improve the consumer's shopping experience and satisfaction. Cloud computing is used to mine and analyze massive data to provide consumers with more accurate and valuable product recommendations, thereby achieving accurate recommendations for products and having good application effects.

[0089] like Figure 2 As shown, the present invention also provides an e-commerce promotion device based on cloud computing, comprising:

[0090] Acquisition module 1 is used to acquire the user's behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments;

[0091] Screening module 2, used to screen the users according to the user registration time and the behavior data to obtain a target user set;

[0092] Extraction module 3, used to extract the purchase records of target users in the target user set, and count the specific data values ​​in the purchase records and browsing history;

[0093] Calculation module 4, used to calculate the purchase frequency, purchase amount, and browsing time of the target user according to the specific data values ​​in the purchase record and browsing history, and use the purchase frequency, purchase amount, and browsing time as target features;

[0094] A matching module 5 is used to calculate the matching result between the target product and the target user according to the target feature, and determine the product with the highest matching degree with the target user;

[0095] The promotion module 6 is used to promote the corresponding commodity for the target user on the e-commerce platform according to the commodity with the highest matching degree with the target user.

[0096] In one embodiment, the screening module 2 comprises:

[0097] A registration time acquisition unit, used to acquire the user's registration time, calculate the registration duration according to the registration time, and determine whether the registration duration exceeds the set duration;

[0098] A deleting unit, used to delete the user's data when the registration duration does not exceed the set duration;

[0099] A statistical unit, used to record the user's data when the registration duration exceeds the set duration, and to count the user's search history and click behavior. When there are both search records and click behaviors, it is recorded as a valid search;

[0100] A recording unit, used for recording the user as a target user when the ratio of effective search time to registration time exceeds a set ratio;

[0101] The traversal unit is used to traverse all users and obtain the target user set.

[0102] In one embodiment, the calculation module 4 includes:

[0103] A data statistics unit, used to count specific data values ​​in the purchase records and browsing history, including the number of times a product is purchased, the amount of the product purchased, and the browsing time of the product;

[0104] The calculation unit is used to calculate the purchase frequency, purchase amount, and browsing time of the target user. The formula is:

[0105]

[0106] T(x)=∑t(x i )

[0107] Among them, f(x) represents the purchase frequency of x-type products; n(x) represents the purchase frequency of x-type products in T n The number of times the product of category x is purchased within a certain time frame; c(x) represents the purchase amount of the product of category x; c(x i ) represents the purchase amount of any specific product in category x; m(x i ) represents the total purchase amount of any specific product in category x; T(x) represents the browsing time of products in category x; t(x i ) represents the browsing time of any specific product in category x;

[0108] As a unit, it is used to take purchase frequency, purchase amount, and browsing time as target features.

[0109] In one embodiment, in the matching module 5, the matching result between the target product and the target user is calculated according to the target feature, and the calculation formula is:

[0110]

[0111] Among them, C(x,y) represents the matching result between product attributes and user product preferences; T(x→y) represents the matching coefficient between product browsing time and product y, which mainly determines the type consistency between the product and the user's product preferences; f(x∩y) represents the matching coefficient between product purchase frequency and product y consumption frequency, which mainly determines the consumption habit consistency between the product and the user's product preferences; C(x∩y) represents the matching coefficient between product purchase amount and product y price, which mainly determines the consumption capacity consistency between the product and the user's product preferences.

[0112] In one embodiment, in the matching module 5, determining the product with the highest matching degree with the target user includes:

[0113] A sorting unit, used to sort the commodities in descending order according to the matching results, and when the matching results of two or more commodities are the same, the two or more commodities are placed in the same order;

[0114] The selection unit is used to select the first ranked product as the product with the highest matching degree with the target user. If there are multiple first ranked products, all of them are selected as the products with the highest matching degree with the target user.

[0115] In one embodiment, the promotion module 6 includes:

[0116] A category acquisition unit, used to take the product with the highest matching degree with the target user as the target product, and acquire the product category of the target product;

[0117] A related product acquisition unit, used to acquire related products under the product category that are related to the target product;

[0118] A promotion unit is used to promote other brands of the same target product to the target user, and to promote the associated products to the target user.

[0119] The above modules and units are used to execute the corresponding steps in the above cloud computing-based e-commerce promotion method. The specific implementation method thereof is described in the above method embodiment and will not be repeated here.

[0120] like Figure 3 As shown, the present invention also provides a computer device, which can be a server, and its internal structure can be as shown in Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the method for promoting e-commerce based on cloud computing. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the method for promoting e-commerce based on cloud computing is implemented.

[0121] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0122] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any of the above-mentioned methods for promoting e-commerce based on cloud computing is implemented.

[0123] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0124] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0125] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for promoting e-commerce based on cloud computing, characterized in that: include: Obtaining user behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments; The users are screened according to the user registration time and the behavior data to obtain a target user set; Extracting the purchase records of the target users in the target user set, and counting the specific data values ​​in the purchase records and browsing histories; Calculate the target user's purchase frequency, purchase amount, and browsing time based on the specific data values ​​in the purchase records and browsing history, and use the purchase frequency, purchase amount, and browsing time as target features; Calculate the matching result between the target product and the target user according to the target feature, and determine the product with the highest matching degree with the target user; According to the product with the highest matching degree with the target user, the corresponding product is promoted for the target user on the e-commerce platform.

2. The method for promoting e-commerce based on cloud computing according to claim 1, characterized in that: The step of screening the users according to the user registration time and the behavior data to obtain the target user set includes: Obtain the user's registration time, calculate the registration duration based on the registration time, and determine whether the registration duration exceeds the set duration; If the registration duration does not exceed the set duration, the user's data will be deleted; If the registration duration exceeds the set duration, the user's data will be recorded, and the user's search history and click behavior will be counted. If there are both search records and click behaviors, it will be recorded as a valid search; When the ratio of effective search time to registration time exceeds the set ratio, the user is recorded as a target user; Traverse all users and get the target user set.

3. The method for promoting e-commerce based on cloud computing according to claim 1, characterized in that: The step of calculating the target user's purchase frequency, purchase amount, and browsing time according to the specific data values ​​in the purchase record, and using the purchase frequency, purchase amount, and browsing time as target features includes: Counting specific data values ​​in the purchase records and browsing histories, including the number of times a product was purchased, the amount of money spent on the product, and the duration of browsing the product; The formula for calculating the target user’s purchase frequency, purchase amount, and browsing time is: T(x)=∑t(x i ) Among them, f(x) represents the purchase frequency of x-type products; n(x) represents the purchase frequency of x-type products in T n The number of times x-type products are purchased within a certain time frame; C(x) represents the purchase amount of x-type products; c(x i ) represents the purchase amount of any specific product in category x; m(x i ) represents the total purchase amount of any specific product in category x; T(x) represents the browsing time of products in category x; t(x i ) represents the browsing time of any specific product in category x; Purchase frequency, purchase amount, and browsing time are used as target features.

4. The method for promoting e-commerce based on cloud computing according to claim 1, characterized in that: In the step of calculating the matching result between the target product and the target user according to the target feature, and determining the product with the highest matching degree with the target user, the matching result between the target product and the target user is calculated according to the target feature, and the calculation formula is: Among them, G(x,y) represents the matching result between product attributes and user product preferences; T(x→y) represents the matching coefficient between product browsing time and product y, which mainly determines the type consistency between the product and the user's product preferences; f(x∩y) represents the matching coefficient between product purchase frequency and product y consumption frequency, which mainly determines the consumption habit consistency between the product and the user's product preferences; C(x∩y) represents the matching coefficient between product purchase amount and product y price, which mainly determines the consumption capacity consistency between the product and the user's product preferences.

5. The method for promoting e-commerce based on cloud computing according to claim 4, characterized in that: In the step of calculating the matching result between the target product and the target user according to the target feature, and determining the product with the highest matching degree with the target user, determining the product with the highest matching degree with the target user includes: According to the matching results, the products are sorted in descending order. When the matching results of two or more products are the same, the two or more products are placed in the same order. The first ranked product is regarded as the product with the highest matching degree with the target user. If there are multiple first ranked products, all of them are regarded as the products with the highest matching degree with the target user.

6. The method for promoting e-commerce based on cloud computing according to claim 1, characterized in that: The step of promoting the corresponding product on the e-commerce platform for the target user according to the product with the highest matching degree with the target user includes: The product with the highest matching degree with the target user is used as the target product, and the product category of the target product is obtained; Acquire related products under the product category that are related to the target product; The target product of another brand is promoted to the target user, and the related product is promoted to the target user.

7. A device for promoting e-commerce based on cloud computing, characterized in that: include: An acquisition module is used to acquire the user's behavior data on the e-commerce platform; wherein the behavior data includes browsing history, search history, purchase history, click behavior, ratings and comments; A screening module, used to screen the users according to the user registration time and the behavior data to obtain a target user set; An extraction module is used to extract the purchase records of target users in the target user set and to count the specific data values ​​in the purchase records and browsing histories; A calculation module, used to calculate the purchase frequency, purchase amount, and browsing time of the target user according to the specific data values ​​in the purchase record and browsing history, and use the purchase frequency, purchase amount, and browsing time as target features; A matching module, used to calculate the matching result between the target product and the target user according to the target feature, and determine the product with the highest matching degree with the target user; The promotion module is used to promote corresponding commodities for the target users on the e-commerce platform according to the commodities with the highest matching degree with the target users.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images