Commodity recommendation management system and method based on big data analysis

Abstract

The invention relates to the technical field of commodity recommendation, in particular to a commodity recommendation management system and method based on big data analysis, and the method comprises the steps: obtaining user position data, offline retail channel distribution data and commodity attribute data; based on the user position data and the offline retail channel distribution data, analyzing the offline shopping place distribution condition of the area where the user is located, and evaluating the offline shopping convenience of the user; generating an online commodity recommendation list based on the offline shopping convenience of the user; on the basis of the commodity attribute data, analyzing online and offline purchase convenience differences of the commodities to obtain online purchase weight information of the commodities; and optimizing an online commodity recommendation list based on the commodity online purchase weight information, and pushing the optimized online commodity recommendation list to the user. According to the method, the accuracy and the individuation level of commodity recommendation are effectively improved by quantifying the offline shopping convenience of the user and the difference between the online purchasing convenience and the offline purchasing convenience of the commodity.

Description

Technical Field

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

[0002] With the booming development of e-commerce and the advent of the big data era, the rapid growth of product information has caused online shopping users to face difficulties in choosing products. Against this background, product recommendation systems have come into being. They provide users with products of interest based on clarifying and understanding users' needs and preferences, becoming one of the core technologies to alleviate information overload problems and improve user experience.

[0003] Traditional product recommendation systems make personalized recommendations based on user historical behavior data such as user historical purchase data and virtual community feedback. Although this system can meet user needs to a certain extent, it ignores the differences in users' offline shopping environments and the differences in convenience between online and offline product purchases.

[0004] In actual shopping scenarios, the convenience of users' offline shopping has an important impact on their online shopping decisions. For example, for users who have difficulty in offline shopping, online platforms should give priority to recommending daily necessities to meet users' high-frequency needs. For users who have convenient offline shopping, online platforms should meet users' diverse needs by recommending special products including imported goods and niche brands. At the same time, the delivery timeliness and transportation fragility of online shopping will also affect users' purchasing preferences. Existing technologies lack a comprehensive analysis of users' offline shopping convenience and the convenience of online purchase of goods, resulting in insufficient accuracy and practicality of recommendation results, which cannot fully meet users' real needs. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the prior art, the present application provides a product recommendation management system and method based on big data analysis, which effectively improves the accuracy and personalization of product recommendations by quantifying the convenience of users' offline shopping and the difference in the convenience of purchasing products online and offline.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a product recommendation management method based on big data analysis, comprising the following steps:

[0008] Obtain user location data, offline retail channel distribution data, and product attribute data;

[0009] Analyze the distribution of offline shopping places in the user's area based on user location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for users;

[0010] Generate a list of online product recommendations based on the user's offline shopping convenience;

[0011] Analyze the difference in online and offline purchase convenience based on product attribute data to obtain online purchase weight information of products;

[0012] The online product recommendation list is optimized based on the product online purchase weight information, and the optimized online product recommendation list is pushed to the user.

[0013] Optionally, the specific steps of evaluating the convenience of offline shopping for users include:

[0014] Obtain user location data and offline retail channel distribution data, and use the user location as the center and the area within a preset radius as the user activity area;

[0015] Determine offline retail channel data within the user activity area and determine the distribution density and average distance of different types of offline retail channels within the user activity area;

[0016] The distribution density and average distance of different types of offline retail channels are normalized, and the weighted sum of the normalized distribution density and the inverse of the average distance of different types of offline retail channels is taken to obtain the user offline shopping convenience index, which is used to evaluate the convenience of user offline shopping.

[0017] Optionally, the specific step of determining the distribution density and average distance of different types of offline retail channels in the user activity area includes:

[0018] Obtain offline retail channel data within the user's activity area, where the offline retail channel data includes the number of different types of offline retail channels and the locations of offline retail channels;

[0019] Determine the distribution density of different types of offline retail channels in the user activity area through the number of offline retail channels. The distribution density of offline retail channels is the ratio of the number of offline retail channels of the same type in the user activity area to the area of ​​the user activity area.

[0020] The average distance between different types of offline retail channels and the user's location in the user's activity area is determined through the offline retail channel location.

[0021] Optionally, the specific steps of generating an online product recommendation list based on the user's offline shopping convenience include:

[0022] Obtain the user's offline shopping convenience index, product attribute data, and user historical behavior data;

[0023] The products are divided into a daily necessities set and a special products set according to the product purchase cycle in the product attribute data, and the user preference value of the product is determined based on the user historical behavior data;

[0024] The user preference value of the product is optimized by the user's offline shopping convenience index, and all products are sorted in descending order according to the optimized user preference value to obtain an online product recommendation list.

[0025] Optionally, the specific steps of optimizing the user preference value of a product by using the user offline shopping convenience index include:

[0026] When the user's offline shopping convenience index is greater than the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the featured product set are optimized, and the user preference values ​​of the products in the daily necessities set remain unchanged. When the user's offline shopping convenience index is less than or equal to the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the daily necessities set are optimized, and the user preference values ​​of the products in the featured product set remain unchanged. The calculation formula for the optimized user preference value is:

[0027] U′=U×(1+CI);

[0028] Among them, U is the user preference value before optimization, CI is the user offline shopping convenience index, and U′ is the user preference value after optimization.

[0029] Optionally, the specific steps of obtaining the commodity online purchase weight information include:

[0030] Obtain product attribute data, including product weight, product volume, product purchase cycle, and the transportation time and transportation damage rate required for online product purchases;

[0031] The convenience of carrying goods purchased offline is evaluated by the weight and volume of the goods. The reciprocal of the weighted sum of the weight influence factor and the volume influence factor is used as the offline portability coefficient of the goods. The weight influence factor is the ratio of the weight of the goods to the average weight of the goods, and the volume influence factor is the ratio of the volume of the goods to the average volume of the goods.

[0032] The timeliness and fragility of online purchases of goods are evaluated by the transportation time and transportation damage rate required for online purchases of goods, and the online timeliness coefficient and online fragility coefficient of the goods are obtained, wherein the online timeliness coefficient is the ratio of the average transportation time required for online purchases of all goods to the transportation time required for online purchases of the current goods, and the online fragility coefficient is the ratio of the average transportation damage rate of all online purchases of goods to the transportation damage rate of the current online purchase of goods;

[0033] The inverse of the offline portability coefficient, the inverse of the online fragility coefficient and the online timeliness coefficient are weighted and summed to obtain the online purchase weight information of the product.

[0034] Optionally, the specific steps of optimizing the online product recommendation list based on the product online purchase weight information include:

[0035] Obtain product online purchase weight information and online product recommendation list;

[0036] The product of the user preference value of the product in the online product recommendation list and the corresponding product online purchase weight information is used as the optimized user preference value;

[0037] Arrange the products in descending order according to the optimized user preference values ​​to obtain an optimized online product recommendation list.

[0038] In a second aspect, the present application provides a commodity recommendation management system based on big data analysis, comprising:

[0039] Data acquisition module, used to obtain user location data, offline retail channel distribution data and product attribute data;

[0040] The convenience evaluation module is used to analyze the distribution of offline shopping places in the user's area based on the user's location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for users;

[0041] A product recommendation list generation module is used to generate an online product recommendation list based on the convenience of offline shopping for users;

[0042] The difference evaluation module is used to analyze the difference in the convenience of online and offline purchase of goods based on the commodity attribute data, and obtain the online purchase weight information of the goods;

[0043] The product recommendation list optimization module is used to optimize the online product recommendation list based on the product online purchase weight information, and push the optimized online product recommendation list to the user.

[0044] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a product recommendation management method based on big data analysis by calling the computer program stored in the memory.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a product recommendation management method based on big data analysis.

[0046] Compared with the prior art, this application has the following advantages and beneficial effects:

[0047] This application first analyzes the distribution of offline shopping places in the user's area to quantitatively evaluate the convenience of offline shopping for users, then quantifies the online purchase weight of products by analyzing the difference in purchase convenience between online and offline products, and finally optimizes the user preference value of products by comprehensively considering the convenience of offline shopping for users and the online purchase weight of products, thereby effectively improving the accuracy and personalization level of product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0049] Figure 1 This is a schematic diagram of the overall process of a commodity recommendation management method based on big data analysis provided in an embodiment of the present application;

[0050] Figure 2 It is a structural diagram of a commodity recommendation management system based on big data analysis provided by an embodiment of the present application;

[0051] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0053] See also Figure 1 , Figure 1 This is a schematic diagram of the overall process of a commodity recommendation management method based on big data analysis provided by an embodiment of the present application, which specifically includes the following steps:

[0054] S1: Obtain user location data, offline retail channel distribution data, and product attribute data.

[0055] S2: Analyze the distribution of offline shopping places in the user's area based on user location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for users;

[0056] By analyzing the density and coverage of offline retail channels such as supermarkets and convenience stores, the offline shopping convenience in the user's area can be accurately judged. If the offline retail channels in the user's area are scarce, it means that it is inconvenient for the user to shop offline. The online platform should give priority to recommending daily necessities to meet the user's high-frequency needs. If the offline retail channels near the user are dense, it means that the user is convenient for offline shopping. The online platform can give priority to recommending special products that are difficult to buy offline, such as imported products and niche brands, to give full play to the unique advantages of online shopping. The recommendation strategy based on the convenience of offline shopping can more accurately meet user needs, improve user experience and platform conversion rate. The specific steps to evaluate the convenience of offline shopping for users include:

[0057] Obtain user location data and offline retail channel distribution data, and use the user location as the center and the area within a preset radius as the user activity area;

[0058] Determine offline retail channel data within the user activity area and determine the distribution density and average distance of different types of offline retail channels within the user activity area;

[0059] The distribution density and average distance of different types of offline retail channels are normalized, wherein the calculation formula of the normalized distribution density can be:

[0060]

[0061] Where P(i) is the distribution density of the i-th type of offline retail channels in the user activity area, P max is the maximum value of the distribution density of different types of offline retail channels in the user activity area, P min is the minimum value of the distribution density of different types of offline retail channels in the user activity area, and P′(i) is the distribution density of the i-th type of offline retail channels after normalization;

[0062] The calculation formula of the normalized average distance can be:

[0063]

[0064] in, is the average distance between the i-th type of offline retail channel and the user’s location, is the maximum value of the average distance between different types of offline retail channels and user locations, is the minimum value of the average distance between different types of offline retail channels and user locations, is the normalized average distance between the ith type of offline retail channel and the user’s location;

[0065] The user offline shopping convenience index is obtained by taking the weighted sum of the normalized distribution density of different types of offline retail channels and the inverse of the average distance. The user offline shopping convenience index is used to evaluate the convenience of user offline shopping. The calculation formula of the user offline shopping convenience index can be:

[0066]

[0067] Among them, α i is the distribution density weight of the i-th type of offline retail channel, β i is the average distance weight between the ith type of offline retail channel and the user’s location, n is the number of types of offline retail channels, and CI is the user’s offline shopping convenience index;

[0068] The specific steps to determine the distribution density and average distance of different types of offline retail channels in the user activity area include:

[0069] Obtain offline retail channel data within the user's activity area, where the offline retail channel data includes the number of different types of offline retail channels and the locations of offline retail channels;

[0070] The distribution density of different types of offline retail channels in the user activity area is determined by the number of offline retail channels. The distribution density of offline retail channels is the ratio of the number of offline retail channels of the same type in the user activity area to the area of ​​the user activity area. The calculation formula for the distribution density can be:

[0071]

[0072] Among them, N i is the number of offline retail channels of the i-th type in the user activity area, S is the area of ​​the user activity area, and P(i) is the distribution density of offline retail channels of the i-th type in the user activity area;

[0073] The average distance between different types of offline retail channels and the user's location in the user's activity area is determined by the offline retail channel location. The calculation formula for the average distance can be:

[0074]

[0075] Among them, x 0 is the horizontal coordinate of the user's position, y 0 is the vertical coordinate of the user's position, x i,j is the horizontal coordinate of the jth channel position in the i-th type of offline retail channel in the user's activity area, y i,j is the ordinate of the jth channel position in the i-th type of offline retail channel in the user's activity area, is the average distance between the i-th type of offline retail channel and the user's location.

[0076] S3: Generates a list of online product recommendations based on the user's offline shopping convenience;

[0077] By combining the user's offline shopping convenience index, product attribute data and user historical behavior data, the recommendation priority of products is dynamically adjusted to provide users with more accurate and personalized product recommendations. Specifically, first, according to the offline shopping convenience of the user's area, it is determined whether the user is more inclined to buy daily necessities or special products. For users in convenient shopping areas, the recommendation weight of special products is increased, while for users in inconvenient shopping areas, daily necessities are recommended first. The specific steps of generating an online product recommendation list based on the user's offline shopping convenience include:

[0078] Obtain the user's offline shopping convenience index, product attribute data, and user historical behavior data. The user's historical behavior data includes the user's historical purchase records, historical browsing records, historical collection records, historical search records, and historical evaluation records;

[0079] According to the commodity purchase cycle in the commodity attribute data, the commodities are divided into a set of daily necessities and a set of special commodities, and the user preference value of the commodity is determined based on the user's historical behavior data. The process of ensuring the user preference value includes: obtaining the user's historical behavior data, assigning behavior weights, calculating the behavior score and normalizing it. The normalized behavior score is used as the user preference value of the commodity. The higher the user preference value, the higher the user's preference for the commodity.

[0080] Optimize the user preference value of the product through the user's offline shopping convenience index, and sort all the products in descending order according to the optimized user preference value to obtain an online product recommendation list;

[0081] The specific steps to optimize the user preference value of a product through the user's offline shopping convenience index include:

[0082] When the user's offline shopping convenience index is greater than the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the featured product set are optimized, and the user preference values ​​of the products in the daily necessities set remain unchanged. When the user's offline shopping convenience index is less than or equal to the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the daily necessities set are optimized, and the user preference values ​​of the products in the featured product set remain unchanged. The calculation formula for the optimized user preference value is:

[0083] U′=U×(1+CI);

[0084] Among them, U is the user preference value before optimization, CI is the user offline shopping convenience index, and U′ is the user preference value after optimization.

[0085] S4: Analyze the difference in online and offline purchase convenience based on product attribute data to obtain online purchase weight information of the product;

[0086] By analyzing the convenience of carrying goods offline, the timeliness of online purchases, and the fragility of transportation, the convenience difference between online and offline purchases of goods is quantified. The offline portability coefficient reflects the convenience of users carrying goods after offline purchases. The online timeliness coefficient and fragility coefficient respectively evaluate the delivery efficiency and transportation risk of online purchases of goods. The online purchase weight information of goods is then comprehensively generated, which is conducive to the platform to more accurately judge whether the goods are suitable for online recommendations, and then optimize the recommendation strategy. The specific steps to obtain the online purchase weight information of goods include:

[0087] Obtain product attribute data, including product weight, product volume, product purchase cycle, and the transportation time and transportation damage rate required for online product purchases;

[0088] The convenience of carrying after the user purchases the goods offline is evaluated by the weight and volume of the goods. The reciprocal of the weighted sum of the weight influence factor and the volume influence factor is taken as the offline portability coefficient of the goods. Among them, the weight influence factor is the ratio of the weight of the goods to the average weight of the goods, and the volume influence factor is the ratio of the volume of the goods to the average volume of the goods. The calculation formula of the offline portability coefficient can be:

[0089]

[0090] Where W is the weight of the product, is the average weight of all commodities, V is the volume of commodities, is the average volume of all commodities, w 1 is the weight of the product, w 2 is the product volume weight, K p is the offline portability coefficient;

[0091] The timeliness and fragility of online purchases of goods are evaluated by the transportation time and transportation damage rate required for online purchases of goods, and the online timeliness coefficient and online fragility coefficient of the goods are obtained, wherein the online timeliness coefficient is the ratio of the average transportation time required for online purchases of all goods to the transportation time required for online purchases of the current goods, and the online fragility coefficient is the ratio of the average transportation damage rate of all online purchases of goods to the transportation damage rate of the current online purchase of goods;

[0092] The inverse of the offline portability coefficient, the inverse of the online fragility coefficient and the online timeliness coefficient are weighted and summed to obtain the online purchase weight information of the product.

[0093] S5: Optimize the online product recommendation list based on the product online purchase weight information, and push the optimized online product recommendation list to the user;

[0094] By combining the online purchase weight information of the product and the user's preference value, the online product recommendation list is further optimized to ensure that the products recommended to the user are in line with their personal interests and have more advantages in online purchase, thereby providing users with more reasonable and targeted product recommendations. The specific steps for optimizing the online product recommendation list based on the online purchase weight information of the product include:

[0095] Obtain product online purchase weight information and online product recommendation list;

[0096] The product of the user preference value of the product in the online product recommendation list and the corresponding product online purchase weight information is used as the optimized user preference value;

[0097] Arrange the products in descending order according to the optimized user preference values ​​to obtain an optimized online product recommendation list.

[0098] It should be noted that the setting parameters in the embodiments of the present application, such as the preset radius, the preset user offline shopping convenience threshold, and the distribution density weight, the average distance weight, the commodity weight weight, the commodity volume weight and other weighted weights, are obtained in the following manner: a data set is constructed by acquiring user location data, offline retail channel distribution data and commodity attribute data, and the user's offline shopping convenience index and the commodity online purchase weight information are substituted into the data, and the expert's recommendation results for the commodity are obtained. The user's offline shopping convenience index, the commodity online purchase weight information and the recommendation results are imported into the fitting software, and the preset radius, the preset user offline shopping convenience threshold and the distribution density weight, the average distance weight, the commodity weight weight, the commodity volume weight and other weighted weights that meet the maximum judgment accuracy are output.

[0099] See also Figure 2 , Figure 2 : is a structural diagram of a commodity recommendation management system based on big data analysis provided by an embodiment of the present application. This embodiment provides a commodity recommendation management system based on big data analysis, including:

[0100] Data acquisition module 210, used to acquire user location data, offline retail channel distribution data and product attribute data;

[0101] Convenience evaluation module 220, used to analyze the distribution of offline shopping places in the user's area based on the user's location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for the user;

[0102] A product recommendation list generation module 230, for generating an online product recommendation list based on the user's offline shopping convenience;

[0103] The difference evaluation module 240 is used to analyze the difference in the convenience of online and offline purchase of commodities based on commodity attribute data, and obtain the online purchase weight information of commodities;

[0104] The commodity recommendation list optimization module 250 is used to optimize the online commodity recommendation list based on the commodity online purchase weight information, and push the optimized online commodity recommendation list to the user.

[0105] In the embodiment of the present application, the convenience evaluation module 220 is used to analyze the distribution of offline shopping places in the user's area based on the user's location data and the offline retail channel distribution data, and evaluate the convenience of the user's offline shopping. The specific steps of evaluating the convenience of the user's offline shopping include:

[0106] Obtain user location data and offline retail channel distribution data, and use the user location as the center and the area within a preset radius as the user activity area;

[0107] Determine offline retail channel data within the user activity area and determine the distribution density and average distance of different types of offline retail channels within the user activity area;

[0108] The distribution density and average distance of different types of offline retail channels are normalized, and the weighted sum of the normalized distribution density and the inverse of the average distance of different types of offline retail channels is taken to obtain the user offline shopping convenience index, which is used to evaluate the user's offline shopping convenience;

[0109] The specific steps to determine the distribution density and average distance of different types of offline retail channels in the user activity area include:

[0110] Obtain offline retail channel data within the user's activity area, where the offline retail channel data includes the number of different types of offline retail channels and the locations of offline retail channels;

[0111] Determine the distribution density of different types of offline retail channels in the user activity area through the number of offline retail channels. The distribution density of offline retail channels is the ratio of the number of offline retail channels of the same type in the user activity area to the area of ​​the user activity area.

[0112] The average distance between different types of offline retail channels and the user's location in the user's activity area is determined through the offline retail channel location.

[0113] In the embodiment of the present application, the commodity recommendation list generation module 230 is used to generate an online commodity recommendation list based on the convenience of offline shopping for users. The specific steps of generating an online commodity recommendation list based on the convenience of offline shopping for users include:

[0114] Obtain the user's offline shopping convenience index, product attribute data, and user historical behavior data;

[0115] The products are divided into a daily necessities set and a special products set according to the product purchase cycle in the product attribute data, and the user preference value of the product is determined based on the user historical behavior data;

[0116] Optimize the user preference value of the product through the user's offline shopping convenience index, and sort all the products in descending order according to the optimized user preference value to obtain an online product recommendation list;

[0117] The specific steps to optimize the user preference value of a product through the user's offline shopping convenience index include:

[0118] When the user's offline shopping convenience index is greater than the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the featured product set are optimized, and the user preference values ​​of the products in the daily necessities set remain unchanged. When the user's offline shopping convenience index is less than or equal to the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the daily necessities set are optimized, and the user preference values ​​of the products in the featured product set remain unchanged. The calculation formula for the optimized user preference value is:

[0119] U′=U×(1+CI);

[0120] Among them, U is the user preference value before optimization, CI is the user offline shopping convenience index, and U′ is the user preference value after optimization.

[0121] In the embodiment of the present application, the difference evaluation module 240 is used to analyze the difference in online and offline purchase convenience of commodities based on commodity attribute data to obtain online purchase weight information of commodities. The specific steps of obtaining online purchase weight information of commodities include:

[0122] Obtain product attribute data, including product weight, product volume, product purchase cycle, and the transportation time and transportation damage rate required for online product purchases;

[0123] The convenience of carrying goods purchased offline is evaluated by the weight and volume of the goods. The reciprocal of the weighted sum of the weight influence factor and the volume influence factor is used as the offline portability coefficient of the goods. The weight influence factor is the ratio of the weight of the goods to the average weight of the goods, and the volume influence factor is the ratio of the volume of the goods to the average volume of the goods.

[0124] The timeliness and fragility of online purchases of goods are evaluated by the transportation time and transportation damage rate required for online purchases of goods, and the online timeliness coefficient and online fragility coefficient of the goods are obtained, wherein the online timeliness coefficient is the ratio of the average transportation time required for online purchases of all goods to the transportation time required for online purchases of the current goods, and the online fragility coefficient is the ratio of the average transportation damage rate of all online purchases of goods to the transportation damage rate of the current online purchase of goods;

[0125] The inverse of the offline portability coefficient, the inverse of the online fragility coefficient and the online timeliness coefficient are weighted and summed to obtain the online purchase weight information of the product.

[0126] In the embodiment of the present application, the product recommendation list optimization module 250 is used to optimize the online product recommendation list based on the product online purchase weight information, and push the optimized online product recommendation list to the user. The specific steps of optimizing the online product recommendation list based on the product online purchase weight information include:

[0127] Obtain product online purchase weight information and online product recommendation list;

[0128] The product of the user preference value of the product in the online product recommendation list and the corresponding product online purchase weight information is used as the optimized user preference value;

[0129] Arrange the products in descending order according to the optimized user preference values ​​to obtain an optimized online product recommendation list.

[0130] The above-mentioned parameters and steps for each unit module to implement corresponding functions in a product recommendation management system based on big data analysis of the present application can refer to the parameters and steps in the embodiment of a product recommendation management method based on big data analysis above, and will not be repeated here.

[0131] Please refer to Figure 3 The embodiment of the present invention further provides an electronic device 300, including a memory 310, a processor 320 and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores a commodity recommendation management method based on big data analysis as provided in the above embodiment, which can be loaded and executed by the processor 320.

[0132] The memory 310 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 310 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing a commodity recommendation management method based on big data analysis provided in the above embodiment, etc.; the data storage area may store data involved in a commodity recommendation management method based on big data analysis provided in the above embodiment, etc.

[0133] The processor 320 may include one or more processing cores. The processor 320 calls the data stored in the memory 310 by running or executing the instructions, programs, code sets or instruction sets stored in the memory 310, and performs various functions and processes data of the present application. The processor 320 may 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. It is understandable that for different devices, the electronic device used to implement the above-mentioned processor 320 function can also be other, and the embodiment of the present application is not specifically limited.

[0134] The communication bus 330 may include a path to transmit information between the above components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus 330 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one double arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0135] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a commodity recommendation management method based on big data analysis as provided in the above embodiment.

[0136] In an embodiment of the present application, a computer-readable storage medium may be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, a computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0137] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0138] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A commodity recommendation management method based on big data analysis, characterized in that: The steps include: Obtain user location data, offline retail channel distribution data, and product attribute data; Analyze the distribution of offline shopping places in the user's area based on user location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for users; Generate a list of online product recommendations based on the user's offline shopping convenience; Analyze the difference in online and offline purchase convenience based on product attribute data to obtain online purchase weight information of products; The online product recommendation list is optimized based on the product online purchase weight information, and the optimized online product recommendation list is pushed to the user.

2. A commodity recommendation management method based on big data analysis according to claim 1, characterized in that: The specific steps of evaluating the convenience of offline shopping for users include: Obtain user location data and offline retail channel distribution data, and use the user location as the center and the area within a preset radius as the user activity area; Determine offline retail channel data within the user activity area and determine the distribution density and average distance of different types of offline retail channels within the user activity area; The distribution density and average distance of different types of offline retail channels are normalized, and the weighted sum of the normalized distribution density and the inverse of the average distance of different types of offline retail channels is taken to obtain the user offline shopping convenience index, which is used to evaluate the convenience of user offline shopping.

3. The commodity recommendation management method based on big data analysis according to claim 2, characterized in that: The specific steps of determining the distribution density and average distance of different types of offline retail channels in the user activity area include: Obtain offline retail channel data within the user's activity area, where the offline retail channel data includes the number of different types of offline retail channels and the locations of offline retail channels; Determine the distribution density of different types of offline retail channels in the user activity area through the number of offline retail channels. The distribution density of offline retail channels is the ratio of the number of offline retail channels of the same type in the user activity area to the area of ​​the user activity area. The average distance between different types of offline retail channels and the user's location in the user's activity area is determined through the offline retail channel location.

4. The commodity recommendation management method based on big data analysis according to claim 1, characterized in that: The specific steps of generating an online product recommendation list based on the user's offline shopping convenience include: Obtain the user's offline shopping convenience index, product attribute data, and user historical behavior data; The products are divided into a daily necessities set and a special products set according to the product purchase cycle in the product attribute data, and the user preference value of the product is determined based on the user historical behavior data; The user preference value of the product is optimized by the user's offline shopping convenience index, and all products are sorted in descending order according to the optimized user preference value to obtain an online product recommendation list.

5. A commodity recommendation management method based on big data analysis according to claim 4, characterized in that: The specific steps of optimizing the user preference value of a product through the user offline shopping convenience index include: When the user's offline shopping convenience index is greater than the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the featured product set are optimized, and the user preference values ​​of the products in the daily necessities set remain unchanged. When the user's offline shopping convenience index is less than or equal to the preset user's offline shopping convenience threshold, the user preference values ​​of the products in the daily necessities set are optimized, and the user preference values ​​of the products in the featured product set remain unchanged. The calculation formula for the optimized user preference value is: U′=U×(1+CI); Among them, U is the user preference value before optimization, CI is the user offline shopping convenience index, and U′ is the user preference value after optimization.

6. The commodity recommendation management method based on big data analysis according to claim 1, characterized in that: The specific steps of obtaining the online purchase weight information of the product include: Obtain product attribute data, including product weight, product volume, product purchase cycle, and the transportation time and transportation damage rate required for online product purchases; The convenience of carrying goods purchased offline is evaluated by the weight and volume of the goods. The reciprocal of the weighted sum of the weight influence factor and the volume influence factor is used as the offline portability coefficient of the goods. The weight influence factor is the ratio of the weight of the goods to the average weight of the goods, and the volume influence factor is the ratio of the volume of the goods to the average volume of the goods. The timeliness and fragility of online purchases of goods are evaluated by the transportation time and transportation damage rate required for online purchases of goods, and the online timeliness coefficient and online fragility coefficient of the goods are obtained, wherein the online timeliness coefficient is the ratio of the average transportation time required for online purchases of all goods to the transportation time required for online purchases of the current goods, and the online fragility coefficient is the ratio of the average transportation damage rate of all online purchases of goods to the transportation damage rate of the current online purchase of goods; The inverse of the offline portability coefficient, the inverse of the online fragility coefficient and the online timeliness coefficient are weighted and summed to obtain the online purchase weight information of the product.

7. The commodity recommendation management method based on big data analysis according to claim 1, characterized in that: The specific steps of optimizing the online product recommendation list based on the product online purchase weight information include: Obtain product online purchase weight information and online product recommendation list; The product of the user preference value of the product in the online product recommendation list and the corresponding product online purchase weight information is used as the optimized user preference value; Arrange the products in descending order according to the optimized user preference values ​​to obtain an optimized online product recommendation list.

8. A commodity recommendation management system based on big data analysis, applied to a commodity recommendation management method based on big data analysis as claimed in any one of claims 1 to 7, characterized in that: The system comprises: Data acquisition module, used to obtain user location data, offline retail channel distribution data and product attribute data; The convenience evaluation module is used to analyze the distribution of offline shopping places in the user's area based on the user's location data and offline retail channel distribution data, and evaluate the convenience of offline shopping for users; A product recommendation list generation module is used to generate an online product recommendation list based on the convenience of offline shopping for users; The difference evaluation module is used to analyze the difference in the convenience of online and offline purchase of goods based on the commodity attribute data, and obtain the online purchase weight information of the goods; The product recommendation list optimization module is used to optimize the online product recommendation list based on the product online purchase weight information, and push the optimized online product recommendation list to the user.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes a commodity recommendation management method based on big data analysis as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a commodity recommendation management method based on big data analysis as described in any one of claims 1 to 7.

Images