Commodity recommendation method and device based on big data

By analyzing regional information and shopping preferences and generating shopping recommendation models, the problem of difficulty in recommending products in cross-border e-commerce platforms is solved, and information utilization and promotion effect are improved.

CN117934113BActive Publication Date: 2024-11-08GUANGZHOU THOUSAND POINT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410082245.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-19
Publication Date
2024-11-08
Estimated Expiration
2044-01-19

AI Technical Summary

Technical Problem

The existing product recommendation methods are difficult to personalize the folk customs needs of different regions in cross-border e-commerce platforms, resulting in information overload and low utilization.

Method used

By collecting and analyzing regional information (such as habits, popular festivals, and climates) and shopping preferences, a shopping recommendation model is generated, combining the shopping time preferences of target customers, targeted recommended products, and a recommendation page is generated.

Benefits of technology

Targeted product recommendations for different regions and time nodes have been realized, information utilization and promotion effect have been improved, and can better match the needs of local residents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117934113B_ABST
    Figure CN117934113B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a commodity recommendation method and device based on big data. The embodiment collects the local regional information and shopping preferences of the sales place in advance, including collecting regional habits, popular festivals and climate, and associates the collected regional information and shopping preferences at the same time node, so as to know the shopping products that the local residents are more keen on corresponding to the local regional information at different time nodes, and then generate a shopping recommendation model, and count the shopping time preferences of target customers, understand the time nodes when the target customers are keen on shopping, and then recommend corresponding recommended products through the shopping recommendation model at the corresponding time nodes, and generate a push page to display to the target customers. The embodiment can recommend products in combination with the local customs and folkways of cross-border sales, which is more targeted and can match with most local residents, with a wider audience and higher acceptance, and can achieve better promotion effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of commodity recommendation, and in particular to a commodity recommendation method and device based on big data. Background Art

[0002] With the rapid development of network communication and information technology around the world, traditional business models are changing. E-commerce is gradually taking the leading position in modern business, and many e-commerce platforms have been born, among which cross-border e-commerce platforms are one of them. Cross-border e-commerce refers to an international business activity in which trading entities in different customs territories reach transactions through e-commerce platforms, make payment settlements, and complete transactions through cross-border logistics. The emergence of cross-border e-commerce platforms has not only created new growth points for my country's foreign trade, but also brought new opportunities to my country's logistics companies.

[0003] However, the increase in the amount of information has reduced the utilization rate of information, making it more difficult for users to find the information they need, resulting in information overload. Currently, personalized product recommendations are generally considered to be one of the most effective tools to solve this problem. Personalized recommendations analyze user behavior habits and recommend effective information to users, saving users time in screening information and improving the effective utilization rate of information.

[0004] Currently, product recommendations mainly adopt the method of directly matching and comparing a single user with a single product. With tens of millions of types of products and tens of millions of users, it is difficult to provide product recommendations that meet the local folk customs. Summary of the invention

[0005] In response to the above-mentioned defects, an embodiment of the present invention discloses a commodity recommendation method and device based on big data, which provides product recommendations that meet local needs in a targeted manner according to local customs and practices across borders.

[0006] The first aspect of the embodiment of the present invention discloses a commodity recommendation method based on big data, comprising:

[0007] Collecting local regional information and shopping preferences, including regional customs, popular festivals and climate;

[0008] Generate a shopping recommendation model for the local area based on regional information and shopping preferences;

[0009] Acquire the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model;

[0010] A recommendation page for the recommended product is generated and displayed to the target customer.

[0011] As an optional implementation, in the first aspect of the embodiment of the present invention, the collecting of the local geographical information and shopping preferences of the selling place includes:

[0012] Collect and sell local customs, popular festivals and climate, and arrange the collected customs, popular festivals and climate in chronological order;

[0013] Collect and sell the shopping hobby lists of local residents at each time point, and obtain shopping preferences based on the shopping hobby lists.

[0014] As an optional implementation manner, in the first aspect of the embodiment of the present invention, acquiring shopping preferences according to the shopping hobby list includes:

[0015] Select the top M popular products with the highest purchase volume at each time point in the shopping hobby list;

[0016] Analyze the correlation scores between popular products and the current corresponding time nodes;

[0017] According to the relevance score, the top N popular products are selected as shopping preferences.

[0018] As an optional implementation manner, in the first aspect of the embodiment of the present invention, generating a shopping recommendation model includes:

[0019] The regional information and shopping preferences arranged in time sequence are matched one by one to generate a function curve with time nodes as independent variables and recommended products as dependent variables.

[0020] As an optional implementation, in the first aspect of the embodiment of the present invention, analyzing the correlation score between the popular product and the current corresponding time node includes:

[0021] Evaluate whether popular products are exclusive products at the corresponding time point;

[0022] Evaluate whether popular products are seasonal products at the corresponding time point;

[0023] Assign different weight coefficients to exclusive products, non-exclusive products, seasonal products and non-seasonal products, and calculate the relevance score based on the weight coefficient of each popular product.

[0024] As an optional implementation manner, in the first aspect of the embodiment of the present invention, it also includes:

[0025] Obtain target customers’ historical shopping preferences;

[0026] The historical shopping preference information is divided according to the time nodes, and the historical shopping preference information with a repetition rate reaching a preset threshold at the same time node is selected to generate recommended shopping.

[0027] As an optional implementation manner, in the first aspect of the embodiment of the present invention, it also includes:

[0028] Compare the recommended shopping and recommended products to see if they are repeated at the same time node. If they are repeated, remove the recommended shopping corresponding to the time node. If they are not repeated, assign the recommended shopping a first display time and the recommended product a second display time, where the first display time is greater than the second display time.

[0029] A second aspect of an embodiment of the present invention discloses a commodity recommendation device based on big data, comprising:

[0030] Information collection module: used to collect local regional information and shopping preferences, including regional habits, popular festivals and climate;

[0031] Model generation module: used to generate a shopping recommendation model for the local area based on regional information and shopping preferences;

[0032] Product recommendation module: used to obtain the shopping time preference of target customers, and output recommended products for the target customers at different set time nodes according to the shopping time preference and the shopping recommendation model;

[0033] Product display module: used to generate the recommended product recommendation page and display it to the target customer

[0034] As an optional implementation, in the second aspect of the embodiment of the present invention, the collecting of the local geographical information and shopping preferences of the selling place includes:

[0035] Collect and sell local customs, popular festivals and climate, and arrange the collected customs, popular festivals and climate in chronological order;

[0036] Collect and sell the shopping hobby lists of local residents at each time point, and obtain shopping preferences based on the shopping hobby lists.

[0037] As an optional implementation, in the second aspect of the embodiment of the present invention, acquiring shopping preferences according to the shopping hobby list includes:

[0038] Select the top M popular products with the highest purchase volume at each time point in the shopping hobby list;

[0039] Analyze the correlation scores between popular products and the current corresponding time nodes;

[0040] According to the relevance score, the top N popular products are selected as shopping preferences.

[0041] As an optional implementation manner, in the second aspect of the embodiment of the present invention, generating a shopping recommendation model includes:

[0042] The regional information and shopping preferences arranged in time sequence are matched one by one to generate a function curve with time nodes as independent variables and recommended products as dependent variables.

[0043] As an optional implementation, in the second aspect of the embodiment of the present invention, analyzing the correlation score between the popular products and the current corresponding time node includes:

[0044] Evaluate whether popular products are exclusive products at the corresponding time point;

[0045] Evaluate whether popular products are seasonal products at the corresponding time point;

[0046] Assign different weight coefficients to exclusive products, non-exclusive products, seasonal products and non-seasonal products, and calculate the relevance score based on the weight coefficient of each popular product.

[0047] As an optional implementation manner, in the second aspect of the embodiment of the present invention, it also includes:

[0048] Obtain target customers’ historical shopping preferences;

[0049] The historical shopping preference information is divided according to the time nodes, and the historical shopping preference information with a repetition rate reaching a preset threshold at the same time node is selected to generate recommended shopping.

[0050] As an optional implementation manner, in the second aspect of the embodiment of the present invention, it also includes:

[0051] Compare the recommended shopping and recommended products to see if they are repeated at the same time node. If they are repeated, remove the recommended shopping corresponding to the time node. If they are not repeated, assign the recommended shopping a first display time and the recommended product a second display time, where the first display time is greater than the second display time.

[0052] The third aspect of an embodiment of the present invention discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the big data-based product recommendation method disclosed in the first aspect of the embodiment of the present invention.

[0053] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the commodity recommendation method based on big data disclosed in the first aspect of an embodiment of the present invention.

[0054] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0055] In the embodiment of the present invention, the local regional information and shopping preferences of the sales place are collected in advance, including collecting regional habits, popular festivals and climate. By associating the collected regional information and shopping preferences at the same time node, it is possible to obtain shopping products that local residents are more keen on corresponding to the local regional information at different time nodes, and then generate a shopping recommendation model, and count the shopping time preferences of target customers, understand the time nodes when target customers are keen on shopping, and then recommend corresponding recommended products through the shopping recommendation model at the corresponding time nodes, and generate a push page to display to the target customers. The embodiment can recommend products in combination with local customs and folkways of cross-border sales, which is more targeted and can match with most local residents, with a wider audience and higher acceptance, and can achieve better promotion effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 It is a flowchart of a commodity recommendation method based on big data disclosed in an embodiment of the present invention;

[0058] Figure 2 It is a flowchart of another commodity recommendation method based on big data disclosed in an embodiment of the present invention;

[0059] Figure 3 is a schematic diagram of a process of obtaining shopping preferences according to the shopping hobby list disclosed in an embodiment of the present invention;

[0060] Figure 4 It is a flowchart of another commodity recommendation method based on big data disclosed in an embodiment of the present invention;

[0061] Figure 5 It is a structural schematic diagram of a commodity recommendation device based on big data provided by an embodiment of the present invention;

[0062] Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] It should be noted that the terms "first", "second", "third", "fourth", etc. in the specification and claims of the present invention are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0065] The embodiment of the present invention discloses a commodity recommendation method, device, electronic device and storage medium based on big data. In the embodiment, the local regional information and shopping preferences of the sales place are collected in advance, including collecting regional habits, popular festivals and climate. The collected regional information and shopping preferences are associated at the same time node, so that the shopping products that local residents are more keen on corresponding to the local regional information at different time nodes can be known, and then a shopping recommendation model is generated, and the shopping time preferences of target customers are counted to understand the time nodes when the target customers are keen on shopping, and then at the corresponding time nodes, the corresponding recommended products can be recommended through the shopping recommendation model, and a push page is generated to display to the target customers. The embodiment can recommend products in combination with the local customs and folkways of cross-border sales, which is more targeted and can match with most local residents, with a wider audience and higher acceptance, and can achieve better promotion effects.

[0066] Embodiment 1

[0067] See also Figure 1 , Figure 1It is a flow chart of the commodity recommendation method based on big data disclosed in the embodiment of the present invention. Among them, the execution subject of the method described in the embodiment of the present invention is an execution subject composed of software and / or hardware, and the execution subject can receive relevant information by wired or / and wireless means, and can send certain instructions. Of course, it can also have certain processing functions and storage functions. The execution subject can control multiple devices, such as a remote physical server or cloud server and related software, or it can be a local host or server and related software that performs related operations on a device placed somewhere. In some scenarios, multiple storage devices can also be controlled, and the storage devices can be placed in the same place or different places as the devices. For example Figure 1 As shown, the commodity recommendation method based on big data includes the following steps:

[0068] 101. Collect and sell local regional information and shopping preferences, wherein the regional information includes regional customs, popular festivals and climate.

[0069] One of the application scenarios of the embodiment is cross-border e-commerce. As there is a long distance between merchants and customers, merchants can only rely on online searches, past experience, and customers’ voluntary shopping needs to determine the main product direction to be sold. Usually, there is a delay, and it is impossible to obtain timely information to provide effective promotion to potential customers in advance. The embodiment starts from the sale of local regional information, where regional customs refer to, for example, special festivals that are loved by the local area, local favorite foods, etc. Popular festivals are major festivals that are more popular in the local area throughout the year. Climate mainly refers to the temperature and humidity of the local area in different seasons. Different corresponding products can be promoted for different regional information.

[0070] 102. Generate a shopping recommendation model for the local area based on the regional information and shopping preferences.

[0071] The embodiment generates a shopping recommendation model based on the collected regional information and shopping preferences, and uses the collected regional information and shopping preferences as input data. Specifically, a part of the collected regional information and shopping preferences can be selected as input data to generate the shopping recommendation model, and another part can be used as correction data to correct the shopping recommendation model. When a time node is input into the generated shopping recommendation model, the regional information and shopping preferences corresponding to the time node correspond to each other, so the recommended products can be output in a targeted manner.

[0072] 103. Obtain the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model.

[0073] In the embodiment, the target customer is the user that the merchant intends to recommend, and can be an existing customer of the merchant's own store or a potential customer of the merchant. The target customer's shopping time preference can be collected by screening the target customer's historical shopping list. For example, the target customer will buy a large number of Christmas-related items during Christmas every year, and the Christmas-related items purchased can be treated as shopping time preference due to the large quantity.

[0074] 104. Generate a recommendation page for the recommended product and display it to the target customer.

[0075] In an embodiment, the recommended products are displayed to the target customers in the form of a recommendation page. The recommendation page can be a small window. The recommendation page can be set to pop up automatically when the user opens the shopping application, or when the user browses the shopping application, the recommendation page can be popped up after a period of time. The display time of the recommendation page can also be limited. The user can learn about the recommended product and further purchase it by clicking on the recommendation page.

[0076] Figure 2 A flowchart of another commodity recommendation method based on big data disclosed in an embodiment of the present application is shown. Figure 2 As shown, the commodity recommendation method based on big data includes:

[0077] 201. Collect and sell local customs, popular festivals and climate, and arrange the collected customs, popular festivals and climate in chronological order.

[0078] In this step, the region information of the mobile phone is sorted according to different time nodes in the order of the calendar of the natural year.

[0079] 202. Collect and sell the shopping hobby list of local residents at each time point, and obtain shopping preferences according to the shopping hobby list, wherein the regional information includes regional habits, popular festivals and climate.

[0080] In this step, the shopping hobby list is the products that the local residents are more keen to buy at the time node. For example, in the cold winter, the purchase quantity of down jackets increases significantly, then corresponding to the time node, down jackets are included in the shopping hobby list.

[0081] Specifically, the process of acquiring shopping preferences according to the shopping preference list in the embodiment is as follows: Figure 3 As shown, including:

[0082] 2021. Select the top M popular products in terms of purchase volume at each time node in the shopping hobby list.

[0083] 2022. Analyze the correlation scores between popular products and the current corresponding time nodes.

[0084] 2023. According to the relevance score, the top N popular products are selected as shopping preferences.

[0085] In the embodiment, M and N are both natural numbers, and the relevance refers to the relevance between the popular products and the corresponding time nodes. For example, summer and watermelon are defined as having a large relevance, while summer and down jackets are defined as having a small relevance. From the perspective of relevance, the embodiment can avoid recommending items with a very low relevance to the corresponding time nodes, thereby ensuring that the recommended products are more popular and more targeted.

[0086] Specifically, analyzing the correlation scores between popular products and the current corresponding time nodes includes evaluating whether the popular products are exclusive products for the corresponding time nodes; evaluating whether the popular products are seasonal products for the corresponding time nodes; assigning different weight coefficients to exclusive products, non-exclusive products, seasonal products and non-seasonal products, and calculating the correlation scores based on the weight coefficients of each popular product.

[0087] Exemplarily, the corresponding time node is Christmas. It should be noted that Christmas in this time node is not limited to Christmas Day, but several days before and after Christmas can be set as the time node of Christmas. In this time node, exclusive products are represented as Christmas-related products, such as Christmas trees, Christmas decorations, etc. Since Christmas is in winter, the corresponding seasonal products can be, for example, cotton clothes, down jackets, ski suits and other cold-resistant equipment. At this time, the seasonal products are also non-exclusive products. Therefore, in this example, there are also cases where non-exclusive products are seasonal products. At the same time, there is also a product that is both a non-exclusive product and a non-seasonal product. There can also be other situations, depending on the actual situation. There are as many combinations as possible. The weight set for exclusive products is the heaviest, and the weight of seasonal products is second. For seasonal products defined as non-exclusive products, only the weight of seasonal products is retained. For exclusive products defined as non-seasonal products, only the weight of exclusive products is retained. If the non-exclusive products and non-seasonal products are neither exclusive products nor seasonal products, the weight coefficient is set to 0.

[0088] 203. Generate a shopping recommendation model for the local area based on the regional information and shopping preferences.

[0089] In this step, the regional information and shopping preferences arranged in the order of time nodes are matched one by one to generate a function curve with the time node as the independent variable and the recommended product as the dependent variable. That is, in this embodiment, when a time node is input, the corresponding recommended product can be output accordingly. Taking the time node as the horizontal axis as an example, the vertical axis corresponding to each time node corresponds to different shopping preferences, so the recommended product can be output in combination with the shopping preferences.

[0090] 204. Obtain the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model.

[0091] 205. Generate a recommendation page for the recommended product and display it to the target customer.

[0092] Figure 4 A flowchart of another commodity recommendation method based on big data disclosed in an embodiment of the present application is shown. Figure 4 As shown, the commodity recommendation method based on big data includes:

[0093] 401. Collect and sell local regional information and shopping preferences, wherein the regional information includes regional customs, popular festivals and climate.

[0094] 402. Generate a shopping recommendation model for the local area based on the regional information and shopping preferences.

[0095] 403. Obtain the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model.

[0096] 404. Generate a recommendation page for the recommended product and display it to the target customer.

[0097] 405. Obtain the target customer’s historical shopping preference information.

[0098] 406. Divide the historical shopping preference information by time nodes, and select the historical shopping preference information with a repetition rate at the same time node reaching a preset threshold to generate recommended shopping.

[0099] In addition to considering the promotion of products that are more popular and have a wider audience based on the local customs and folkways of the products being sold, this embodiment also conducts targeted promotion in combination with the personalized shopping interests of the target customers. By collecting the historical shopping information of the target customers and sorting out the time nodes, the shopping preferences of the target customers at different time nodes are generated. For example, taking Children's Day every year as an example, the target customers buy more children's school supplies at this time node every year on Children's Day, so the school supplies can be recommended as a shopping hobby. In another example, still taking Children's Day as an example, the target customers only bought toys on Children's Day in one year, and there was no information about buying toys on Children's Day in other years, so toys cannot be used as a shopping hobby on Children's Day.

[0100] More specifically, the embodiment can also compare whether the recommended shopping and recommended products are repeated at the same time node. If they are repeated, the recommended shopping corresponding to the time node is eliminated. If they are not repeated, the recommended shopping is assigned a first display time and the recommended product is assigned a second display time, wherein the first display time is greater than the second display time.

[0101] Embodiment 2

[0102] See also Figure 5 , Figure 5 Schematic diagram of a commodity recommendation device based on big data disclosed in an embodiment of the present invention. Figure 5 As shown, the commodity recommendation device based on big data may include: an information collection module 501, a model generation module 502, a product recommendation module 503 and a product display module 504, wherein the information collection module 501 is used to collect the local geographical information and shopping preferences of the selling place, and the local information includes regional habits, popular festivals and climate; the model generation module 502 is used to generate a shopping recommendation model for the selling place based on the regional information and shopping preferences; the product recommendation module 503 is used to obtain the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model; the product display module 504 is used to generate a recommendation page for the recommended product and display it to the target customer.

[0103] Specifically, in the information collection module 501, the local regional customs, popular festivals and climate are collected and arranged in order of time nodes; the shopping hobby list of the local residents at each time node is collected, and the shopping preferences are obtained according to the shopping hobby list. Further, the shopping preferences are obtained according to the shopping hobby list, including: selecting the top M popular products with purchase volume corresponding to each time node in the shopping hobby list; analyzing the correlation score between the popular products and the current corresponding time node; and selecting the top N popular products with correlation scores as shopping preferences according to the correlation score height.

[0104] The above analysis of the correlation score between the popular products and the current corresponding time node includes: evaluating whether the popular products are exclusive products for the corresponding time node; evaluating whether the popular products are seasonal products for the corresponding time node; allocating different weight coefficients to exclusive products, non-exclusive products, seasonal products and non-seasonal products, and calculating the correlation score based on the weight coefficient of each popular product.

[0105] The model generation module 502 specifically matches the regional information and shopping preferences arranged in the order of time nodes one by one, and generates a function curve with the time node as the independent variable and the recommended product as the dependent variable.

[0106] The embodiment may further include a customer information collection module and a personalized recommendation module. The customer information collection module is used to obtain the historical shopping preference information of the target customers. The personalized recommendation module is used to divide the historical shopping preference information according to time nodes, and select the historical shopping preference information with a repetition rate at the same time node reaching a preset threshold to generate recommended shopping.

[0107] Furthermore, based on the above, it is also possible to compare whether the recommended shopping and recommended products are repeated at the same time node. If they are repeated, the recommended shopping corresponding to the time node is eliminated. If they are not repeated, the recommended shopping is assigned a first display time and the recommended product is assigned a second display time, where the first display time is greater than the second display time.

[0108] Embodiment 3

[0109] See also Figure 6 , Figure 6 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. The electronic device may be a computer, a server, etc. Of course, in certain circumstances, it may also be a smart device such as a mobile phone, a tablet computer, a monitoring terminal, and an image acquisition device with processing functions. Figure 6 As shown, the electronic device may include:

[0110] A memory 601 storing executable program codes;

[0111] a processor 602 coupled to the memory 601;

[0112] The processor 602 calls the executable program code stored in the memory 601 to execute part or all of the steps in the commodity recommendation method based on big data in the first embodiment.

[0113] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute part or all of the steps in the commodity recommendation method based on big data in the first embodiment.

[0114] The embodiment of the present invention further discloses a computer program product, wherein when the computer program product is run on a computer, the computer is enabled to execute part or all of the steps in the commodity recommendation method based on big data in the first embodiment.

[0115] An embodiment of the present invention further discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes part or all of the steps in the big data-based product recommendation method in embodiment one.

[0116] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the method described in each embodiment of the present invention.

[0120] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0121] A person of ordinary skill in the art can understand that some or all of the steps in the various methods of the embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0122] The above is a detailed introduction to the big data-based commodity recommendation method, device, electronic device and storage medium disclosed in the embodiments of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A commodity recommendation method based on big data, characterized in that: include: Collect and sell local customs, popular festivals and climate, and arrange the collected customs, popular festivals and climate in chronological order; Collect the shopping preference lists of local residents at each time point, and select the top M popular products with the highest purchase volume at each time point in the shopping preference lists; analyze the correlation scores between popular products and the current corresponding time point; select the top N popular products with the highest correlation scores as shopping preferences according to the correlation scores. Regional information includes regional habits, popular festivals and climate; Match the regional information and shopping preferences arranged in time sequence one by one, and generate a function curve with time nodes as independent variables and recommended products as dependent variables; Acquire the shopping time preference of the target customer, and output the recommended products for the target customer at different set time nodes according to the shopping time preference and the shopping recommendation model; Generating a recommendation page for the recommended product and displaying it to the target customer; Acquire historical shopping preference information of target customers; divide the historical shopping preference information by time nodes, and select historical shopping preference information whose repetition rate at the same time node reaches a preset threshold to generate recommended shopping; Compare the recommended shopping and recommended products to see if they are repeated at the same time node. If they are repeated, remove the recommended shopping corresponding to the time node. If they are not repeated, assign the recommended shopping a first display time and the recommended product a second display time, where the first display time is greater than the second display time.

2. The commodity recommendation method according to claim 1, characterized in that: Analyze the correlation scores between popular products and the current corresponding time nodes, including: Evaluate whether popular products are exclusive products at the corresponding time point; Evaluate whether popular products are seasonal products at the corresponding time point; Assign different weight coefficients to exclusive products, non-exclusive products, seasonal products and non-seasonal products, and calculate the relevance score based on the weight coefficient of each popular product.

3. A commodity recommendation device based on big data, characterized in that: include: Information collection module: used to collect and sell local regional customs, popular festivals and climate, and arrange the collected regional customs, popular festivals and climate in chronological order; Collect the shopping preference lists of local residents at each time point, and select the top M popular products with the highest purchase volume at each time point in the shopping preference lists; analyze the correlation scores between popular products and the current corresponding time point; select the top N popular products with the highest correlation scores as shopping preferences according to the correlation scores. Regional information includes regional habits, popular festivals and climate; Model generation module: used to generate a shopping recommendation model for the local area based on regional information and shopping preferences; Product recommendation module: used to obtain the shopping time preference of target customers, and output recommended products for the target customers at different set time nodes according to the shopping time preference and the shopping recommendation model; Product display module: used to generate a recommendation page for the recommended product and display it to the target customer; Customer information collection module: used to obtain the target customers’ historical shopping preference information; Personalized recommendation module: used to divide the historical shopping preference information according to the time nodes, and select the historical shopping preference information with a repetition rate reaching a preset threshold at the same time node to generate recommended shopping; Compare the recommended shopping and recommended products to see if they are repeated at the same time node. If they are repeated, remove the recommended shopping corresponding to the time node. If they are not repeated, assign the recommended shopping a first display time and the recommended product a second display time, where the first display time is greater than the second display time.

4. An electronic device, characterized in that: include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the commodity recommendation method based on big data as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the commodity recommendation method based on big data as described in any one of claims 1 to 2.