A commodity recommendation management system and method based on big data analysis

Abstract

The application relates to the technical field of commodity recommendation, in particular to a commodity recommendation management system and method based on big data analysis, the steps of the method comprising the following steps: acquiring user position data, offline retail channel distribution data and commodity attribute data; analyzing the offline shopping place distribution situation of the region where the user is located based on the user position data and the offline retail channel distribution data, and evaluating the offline shopping convenience of the user; generating an online commodity recommendation list based on the offline shopping convenience of the user; analyzing the purchase convenience difference between online and offline of commodities based on the commodity attribute data, and obtaining commodity online purchase weight information; and optimizing the online commodity recommendation list based on the commodity online purchase weight information, and pushing the optimized online commodity recommendation list to the user. The offline shopping convenience of the user and the purchase convenience difference between online and offline of commodities are quantified, and the accuracy and the individualization level of commodity recommendation are effectively improved.

Description

Technical Field

[0001] This application relates to the field of product recommendation technology, and in particular to a product recommendation management system and method based on big data analysis. Background Technology

[0002] With the booming development of e-commerce and the arrival of the big data era, the rapid growth of product information has led to difficulties in choosing products for online shoppers. Against this backdrop, product recommendation systems have emerged. Based on a clear understanding of users' needs and preferences, these systems provide users with products they are interested in, becoming one of the core technologies for alleviating information overload and improving user experience.

[0003] Traditional product recommendation systems make personalized recommendations based on users' historical purchase data, feedback from virtual communities, and other user behavior data. While this can meet user needs to some extent, it ignores the differences in users' offline shopping environments and the differences in convenience between online and offline purchases.

[0004] In real-world shopping scenarios, the convenience of offline shopping significantly impacts users' online shopping decisions. For example, for users who find offline shopping inconvenient, online platforms should prioritize recommending daily necessities to meet their frequent needs. Conversely, for users who find offline shopping convenient, online platforms should recommend specialty products, including imported goods and niche brands, to meet their diverse needs. Furthermore, the delivery timeliness and the fragility of online shopping also influence users' purchasing preferences. Current technology lacks a comprehensive analysis of the convenience of offline shopping and the convenience of online purchasing, resulting in insufficient accuracy and practicality in recommendation results, failing to fully meet users' actual needs. Summary of the Invention

[0005] To overcome the shortcomings and deficiencies of existing technologies, this application provides a product recommendation management system and method based on big data analysis. By quantifying the convenience of offline shopping for users and the differences in the convenience of purchasing products online and offline, it effectively improves the accuracy and personalization of product recommendations.

[0006] To achieve the above objectives, this application adopts the following technical solution:

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

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

[0009] Based on user location data and offline retail channel distribution data, we analyze the distribution of offline shopping venues in the user's area and assess the convenience of offline shopping for the user.

[0010] An online product recommendation list is generated based on the convenience of users' offline shopping.

[0011] Based on the analysis of product attribute data, the differences in the convenience of purchasing products online and offline are obtained to obtain the weight information of online purchase of products;

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

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

[0014] Acquire user location data and offline retail channel distribution data, and use the user's location as the center to define the area within a preset radius as the user's activity area;

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

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

[0017] Optionally, the specific steps for determining the distribution density and average distance of different types of offline retail channels within the user's activity area include:

[0018] Acquire offline retail channel data within the user's activity area. The offline retail channel data includes the number of different types of offline retail channels and their locations.

[0019] The distribution density of different types of offline retail channels within a user's 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 the same type of offline retail channels within the user's activity area to the area of ​​the user's activity area.

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

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

[0022] Acquire user offline shopping convenience index, product attribute data, and user historical behavior data;

[0023] Based on the product purchase cycle in the product attribute data, the products are divided into a set of daily necessities and a set of featured products, and the user preference value of the products is determined based on the user's historical behavior data;

[0024] The user preference value of products is optimized by using 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 for optimizing the user preference value of goods through the user's offline shopping convenience index include:

[0026] When the user's offline shopping convenience index is greater than the preset user offline shopping convenience threshold, the user preference value of the products in the featured products set is optimized, while the user preference value of the products in the daily necessities set remains unchanged. When the user's offline shopping convenience index is less than or equal to the preset user offline shopping convenience threshold, the user preference value of the products in the daily necessities set is optimized, while the user preference value of the products in the featured products set remains unchanged. The optimized user preference value is calculated using the following formula:

[0027] U′=U×(1+CI);

[0028] Where U represents the user preference value before optimization, CI represents the user's offline shopping convenience index, and U′ represents the user preference value after optimization.

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

[0030] Obtain product attribute data, which includes product weight, product volume, product purchase cycle, and the shipping time and shipping damage rate required for online purchase.

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

[0032] The timeliness and fragility of online purchases are assessed by evaluating the shipping time and damage rate required for online purchases, resulting in an online timeliness coefficient and an online fragility coefficient. The online timeliness coefficient is the ratio of the average shipping time required for all online purchases to the shipping time required for the current online purchase, and the online fragility coefficient is the ratio of the average damage rate of all online purchases to the damage rate of the current online purchase.

[0033] The online purchase weight information of a product is obtained by weighting and summing the reciprocal of the offline portability coefficient, the reciprocal of the online fragility coefficient, and the online timeliness coefficient.

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

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

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

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

[0038] Secondly, this application provides a product recommendation management system based on big data analysis, comprising:

[0039] The data acquisition module is used to acquire user location data, offline retail channel distribution data, and product attribute data;

[0040] The convenience assessment module is used to analyze the distribution of offline shopping venues in the user's area based on user location data and offline retail channel distribution data, and to assess the convenience of offline shopping for the user.

[0041] The product recommendation list generation module is used to generate an online product recommendation list based on the convenience of users' offline shopping.

[0042] The difference assessment module is used to analyze the differences in purchase convenience between online and offline based on product attribute data, and to obtain online purchase weight information for products.

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

[0044] Thirdly, this application provides an electronic device, including: 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] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform 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 venues in the user's area to quantitatively assess the convenience of offline shopping. Then, it analyzes the difference in convenience between online and offline purchases of goods to quantify the weight of online purchases. Finally, it optimizes the user preference value of goods by combining the convenience of offline shopping and the weight of online purchases, effectively improving the accuracy and personalization of product recommendations. Attached Figure Description

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

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

[0050] Figure 2 This is a schematic diagram of the structure of a product recommendation management system based on big data analysis provided in an embodiment of this application;

[0051] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

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

[0053] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of a product recommendation management method based on big data analysis provided in an embodiment of this 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 venues in the user's area based on user location data and offline retail channel distribution data, and assess the convenience of offline shopping for the user;

[0056] By analyzing the density and coverage of offline retail channels such as supermarkets and convenience stores, the convenience of offline shopping in a user's area can be accurately determined. If offline retail channels are scarce in a user's area, it indicates that offline shopping is inconvenient for the user. In this case, the online platform should prioritize recommending daily necessities to meet the user's high-frequency needs. If offline retail channels are abundant near the user, it indicates that offline shopping is convenient for the user. In this case, the online platform can prioritize recommending unique products that are difficult to purchase offline, such as imported goods and niche brands, to leverage the unique advantages of online shopping. A recommendation strategy based on the convenience of offline shopping can more accurately meet user needs, improve user experience and platform conversion rates. The specific steps for assessing the convenience of offline shopping for users include:

[0057] Acquire user location data and offline retail channel distribution data, and use the user's location as the center to define the area within a preset radius as the user's activity area;

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

[0059] The distribution density and average distance of different types of offline retail channels are normalized. The formula for calculating the normalized distribution density can be:

[0060]

[0061] Where P(i) is the distribution density of the i-th type of offline retail channel within the user's activity area, P max P represents the maximum distribution density of different types of offline retail channels within the user's activity area. min P′(i) represents the minimum distribution density of different types of offline retail channels within the user's activity area, and P′(i) represents the distribution density of the i-th type of offline retail channel after normalization.

[0062] The formula for calculating the normalized average distance can be:

[0063]

[0064] in, Let be the average distance between the i-th type of offline retail channel and the user's location. This represents the maximum average distance between different types of offline retail channels and the user's location. This represents the minimum average distance between different types of offline retail channels and user locations. This represents the average distance between the i-th type of offline retail channel and the user's location after normalization.

[0065] The offline shopping convenience index is obtained by weighting and summing the distribution density of different types of offline retail channels after normalization with the inverse of the average distance. This index is used to assess the convenience of offline shopping for users. The formula for calculating the offline shopping convenience index can be:

[0066]

[0067] Where, α i Let β be the distribution density weight of the i-th type of offline retail channel. i is the average distance weight between the i-th 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 for determining the distribution density and average distance of different types of offline retail channels within a user's activity area include:

[0069] Acquire offline retail channel data within the user's activity area. The offline retail channel data includes the number of different types of offline retail channels and their locations.

[0070] The distribution density of different types of offline retail channels within a user's 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 the same type of offline retail channels within the user's activity area to the area of ​​the user's activity area. The formula for calculating the distribution density can be:

[0071]

[0072] Where, N i Let S be the number of offline retail channels of type i within the user's activity area, S be the area of ​​the user's activity area, and P(i) be the distribution density of offline retail channels of type i within the user's activity area.

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

[0074]

[0075] Where x0 is the x-coordinate of the user's location, y0 is the y-coordinate of the user's location, and x i,j Let y be the x-coordinate of the j-th channel location within the i-th type of offline retail channel in the user's activity area. i,j Let be the ordinate of the j-th channel location within the i-th type of offline retail channel in the user's activity area. Let be the average distance between the i-th type of offline retail channel and the user's location.

[0076] S3: Generate an online product recommendation list based on the convenience of offline shopping for users;

[0077] By combining user 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, firstly, based on the offline shopping convenience of the user's area, it is determined whether the user prefers to buy daily necessities or specialty products. For users in areas with convenient shopping, the recommendation weight of specialty products is increased, while for users in areas with inconvenient shopping, daily necessities are recommended first. The specific steps for generating an online product recommendation list based on the user's offline shopping convenience include:

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

[0079] Based on the product purchase cycle in the product attribute data, the products are divided into a set of daily necessities and a set of featured products. The user preference value of the product is determined based on the user's historical behavior data. The process of ensuring the user preference value includes: obtaining user historical behavior data, allocating behavior weights, calculating behavior scores and normalizing the data. The normalized behavior score is used as the user preference value of the product. The higher the user preference value, the higher the user's preference for the product.

[0080] The user preference value of products 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;

[0081] The specific steps to optimize user preference values ​​for products based on the user's offline shopping convenience index include:

[0082] When the user's offline shopping convenience index is greater than the preset user offline shopping convenience threshold, the user preference value of the products in the featured products set is optimized, while the user preference value of the products in the daily necessities set remains unchanged. When the user's offline shopping convenience index is less than or equal to the preset user offline shopping convenience threshold, the user preference value of the products in the daily necessities set is optimized, while the user preference value of the products in the featured products set remains unchanged. The optimized user preference value is calculated using the following formula:

[0083] U′=U×(1+CI);

[0084] Where U represents the user preference value before optimization, CI represents the user's offline shopping convenience index, and U′ represents the user preference value after optimization.

[0085] S4: Analyze the differences in purchase convenience between online and offline channels based on product attribute data to obtain online purchase weight information for products;

[0086] By analyzing the convenience of carrying goods offline, the timeliness of online purchase, and the fragility of transportation, the differences in convenience between online and offline purchases are quantified. The offline portability coefficient reflects the ease with which users can carry goods after offline purchase, while the online timeliness and fragility coefficients assess the delivery efficiency and transportation risk of online purchases, respectively. This comprehensive analysis generates online purchase weight information for goods, enabling the platform to more accurately determine whether a product is suitable for online recommendation and thus optimize its recommendation strategy. The specific steps to obtain online purchase weight information for goods include:

[0087] Obtain product attribute data, which includes product weight, product volume, product purchase cycle, and the shipping time and shipping damage rate required for online purchase.

[0088] The ease of carrying goods purchased offline is assessed by considering both weight and volume. The reciprocal of the weighted sum of the weight and volume factors is used as the offline portability coefficient. Here, the weight factor is the ratio of the product's weight to its mean weight, and the volume factor is the ratio of its volume to its mean volume. The formula for calculating the offline portability coefficient can be:

[0089]

[0090] Where W is the weight of the product. V is the average weight of all items, and V is the volume of the items. The average volume of all items, w1 is the item weight weight, w2 is the item volume weight, and K is the average volume of all items. p Portability factor for offline use;

[0091] The timeliness and fragility of online purchases are assessed by evaluating the shipping time and damage rate required for online purchases, resulting in an online timeliness coefficient and an online fragility coefficient. The online timeliness coefficient is the ratio of the average shipping time required for all online purchases to the shipping time required for the current online purchase, and the online fragility coefficient is the ratio of the average damage rate of all online purchases to the damage rate of the current online purchase.

[0092] The online purchase weight information of a product is obtained by weighting and summing the reciprocal of the offline portability coefficient, the reciprocal of the online fragility coefficient, and the online timeliness coefficient.

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

[0094] By combining online purchase weight information of products with user preference values, the online product recommendation list is further optimized to ensure that the recommended products not only match the user's personal interests but also have a greater advantage in online purchasing. This provides users with more reasonable and targeted product recommendations. The specific steps for optimizing the online product recommendation list based on online purchase weight information include:

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

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

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

[0098] It should be noted that the setting parameters in this application embodiment, such as the preset radius, the preset user offline shopping convenience threshold, and the weighted weights such as distribution density weight, average distance weight, product weight weight, and product volume weight, are determined as follows: A dataset is constructed by acquiring user location data, offline retail channel distribution data, and product attribute data. This dataset is then used to calculate the user offline shopping convenience index and the product online purchase weight information. Expert recommendations for the products are obtained. The user offline shopping convenience index, the product 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 weighted weights such as distribution density weight, average distance weight, product weight weight, and product volume weight that meet the maximum judgment accuracy are output.

[0099] Please see Figure 2 , Figure 2 This is a schematic diagram of a product recommendation management system based on big data analysis provided in this application embodiment. This embodiment provides a product recommendation management system based on big data analysis, including:

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

[0101] The convenience assessment module 220 is used to analyze the distribution of offline shopping venues in the user's area based on user location data and offline retail channel distribution data, and to assess the convenience of offline shopping for the user.

[0102] The product recommendation list generation module 230 is used to generate an online product recommendation list based on the convenience of offline shopping for users;

[0103] The difference assessment module 240 is used to analyze the differences in the convenience of purchasing goods online and offline based on product attribute data, and to obtain the online purchase weight information of goods.

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

[0105] In this embodiment, the convenience assessment module 220 is used to analyze the distribution of offline shopping venues in the user's area based on user location data and offline retail channel distribution data, and to assess the convenience of offline shopping for the user. The specific steps for assessing the convenience of offline shopping for the user include:

[0106] Acquire user location data and offline retail channel distribution data, and use the user's location as the center to define the area within a preset radius as the user's activity area;

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

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

[0109] The specific steps for determining the distribution density and average distance of different types of offline retail channels within a user's activity area include:

[0110] Acquire offline retail channel data within the user's activity area. The offline retail channel data includes the number of different types of offline retail channels and their locations.

[0111] The distribution density of different types of offline retail channels within a user's 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 the same type of offline retail channels within the user's activity area to the area of ​​the user's activity area.

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

[0113] In this embodiment, the product recommendation list generation module 230 is used to generate an online product recommendation list based on the user's convenience of offline shopping. The specific steps for generating the online product recommendation list based on the user's convenience of offline shopping include:

[0114] Acquire user offline shopping convenience index, product attribute data, and user historical behavior data;

[0115] Based on the product purchase cycle in the product attribute data, the products are divided into a set of daily necessities and a set of featured products, and the user preference value of the products is determined based on the user's historical behavior data;

[0116] The user preference value of products 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;

[0117] The specific steps to optimize user preference values ​​for products based on the user's offline shopping convenience index include:

[0118] When the user's offline shopping convenience index is greater than the preset user offline shopping convenience threshold, the user preference value of the products in the featured products set is optimized, while the user preference value of the products in the daily necessities set remains unchanged. When the user's offline shopping convenience index is less than or equal to the preset user offline shopping convenience threshold, the user preference value of the products in the daily necessities set is optimized, while the user preference value of the products in the featured products set remains unchanged. The optimized user preference value is calculated using the following formula:

[0119] U′=U×(1+CI);

[0120] Where U represents the user preference value before optimization, CI represents the user's offline shopping convenience index, and U′ represents the user preference value after optimization.

[0121] In this embodiment, the difference assessment module 240 is used to analyze the differences in purchase convenience between online and offline channels based on product attribute data, and to obtain online purchase weight information. The specific steps for obtaining the online purchase weight information include:

[0122] Obtain product attribute data, which includes product weight, product volume, product purchase cycle, and the shipping time and shipping damage rate required for online purchase.

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

[0124] The timeliness and fragility of online purchases are assessed by evaluating the shipping time and damage rate required for online purchases, resulting in an online timeliness coefficient and an online fragility coefficient. The online timeliness coefficient is the ratio of the average shipping time required for all online purchases to the shipping time required for the current online purchase, and the online fragility coefficient is the ratio of the average damage rate of all online purchases to the damage rate of the current online purchase.

[0125] The online purchase weight information of a product is obtained by weighting and summing the reciprocal of the offline portability coefficient, the reciprocal of the online fragility coefficient, and the online timeliness coefficient.

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

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

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

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

[0130] The parameters and steps for implementing the corresponding functions of each unit module in the product recommendation management system based on big data analysis described above can be referred to the parameters and steps in the embodiments of the product recommendation management method based on big data analysis above, and will not be repeated here.

[0131] Please refer to Figure 3 The present invention also 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 product recommendation management method based on big data analysis, which can be loaded and executed by the processor 320 as provided in the above embodiments.

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

[0133] Processor 320 may include one or more processing cores. Processor 320 executes instructions, programs, code sets, or instruction sets stored in memory 310, and calls data stored in memory 310 to perform various functions and process data as described in this application. Processor 320 may be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 320 may also be other types, and this application embodiment does not specifically limit the specific devices used.

[0134] The communication bus 330 may include a path for transmitting information between the aforementioned components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 330 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double arrow, but this does not mean that there is only one bus or one type of bus.

[0135] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, a product recommendation management method based on big data analysis.

[0136] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. A computer-readable storage medium can 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 can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

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

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

Claims

1. A commodity recommendation management method based on big data analysis, characterized by, The method comprises the following steps: Obtaining user location data, offline retail channel distribution data and commodity attribute data; Analyzing the distribution of offline shopping places in the area where the user is located based on the user location data and the offline retail channel distribution data, and evaluating the offline shopping convenience of the user; Generating an online commodity recommendation list based on the offline shopping convenience of the user; Analyzing the difference in purchase convenience between online and offline of commodities based on the commodity attribute data, and obtaining commodity online purchase weight information; Optimizing the online commodity recommendation list based on the commodity online purchase weight information, and pushing the optimized online commodity recommendation list to the user; The specific steps of evaluating the offline shopping convenience of the user include: Obtaining user location data and offline retail channel distribution data, taking the user location as the center, and taking the area within a preset radius as the user activity area; Determining the offline retail channel data in the user activity area and determining the distribution density and average distance of different types of offline retail channels in the user activity area; Normalizing the distribution density and average distance of different types of offline retail channels, and weighting and summing the distribution density and average distance of different types of offline retail channels after normalization to obtain a user offline shopping convenience index, which is used to evaluate the offline shopping convenience of the user; The specific steps of generating an online commodity recommendation list based on the offline shopping convenience of the user include: Obtaining user offline shopping convenience index, commodity attribute data and user historical behavior data; Dividing commodities into a daily necessity set and a specialty commodity set according to the commodity purchase cycle in the commodity attribute data, and determining the user preference value of the commodity based on the user historical behavior data; Optimizing the user preference value of the commodity through the user offline shopping convenience index, and arranging all commodities in descending order according to the optimized user preference value to obtain an online commodity recommendation list; The specific steps of obtaining commodity online purchase weight information include: Obtaining commodity attribute data, which includes commodity weight, commodity volume, commodity purchase cycle, and transportation time and transportation damage rate required for online purchase of the commodity; Evaluating the carrying convenience of the user after offline purchase of the commodity through the commodity weight and the commodity volume, and taking the weighted sum of the inverse of the commodity weight influence factor and the commodity volume influence factor as the offline portability coefficient of the commodity, wherein the commodity weight influence factor is the ratio of the commodity weight to the average commodity weight, and the commodity volume influence factor is the ratio of the commodity volume to the average commodity volume; Evaluating the timeliness and vulnerability of online purchase of the commodity through the transportation time and transportation damage rate required for online purchase of the commodity, and obtaining the online timeliness coefficient and the online vulnerability coefficient of the commodity, wherein the online timeliness coefficient is the ratio of the average transportation time required for online purchase of all commodities to the transportation time required for online purchase of the current commodity, and the online vulnerability coefficient is the ratio of the average transportation damage rate for online purchase of all commodities to the transportation damage rate for online purchase of the current commodity; Weighting and summing the inverse of the offline portability coefficient, the inverse of the online vulnerability coefficient and the online timeliness coefficient to obtain the commodity online purchase weight information. 2.The commodity recommendation management method based on big data analysis of claim 1, wherein, The specific steps of determining the distribution density and average distance of different types of offline retail channels in the user activity area include: Obtaining offline retail channel data in the user activity area, the offline retail channel data including the number of different types of offline retail channels and the location of the offline retail channels; Determining 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 being 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; Determining the average distance between different types of offline retail channels and user locations in the user activity area through the location of the offline retail channels. 3.The commodity recommendation management method based on big data analysis of claim 1, wherein, The specific steps of optimizing the user preference value of the goods based on the user offline shopping convenience index include: When the user offline shopping convenience index is greater than a preset user offline shopping convenience threshold, optimizing the user preference value of the goods in the special goods set, and keeping the user preference value of the goods in the daily necessities set unchanged; when the user offline shopping convenience index is less than or equal to the preset user offline shopping convenience threshold, optimizing the user preference value of the goods in the daily necessities set, and keeping the user preference value of the goods in the special goods set unchanged, the optimized user preference value being calculated according to the formula: ； wherein, is the user preference value before optimization, is the user offline shopping convenience index, is the user preference value after optimization. 4.The commodity recommendation management method based on big data analysis of claim 1, wherein, The specific steps of optimizing the online goods recommendation list based on the online purchase weight information of the goods include: Obtaining the online purchase weight information of the goods and the online goods recommendation list; Taking the product of the user preference value of the goods in the online goods recommendation list and the corresponding online purchase weight information of the goods as the optimized user preference value; Arranging the goods in descending order according to the optimized user preference value to obtain the optimized online goods recommendation list. 5.A commodity recommendation management system based on big data analysis, applied to the commodity recommendation management method based on big data analysis in any one of claims 1-4, characterized in that, The system includes: A data acquisition module for acquiring user location data, offline retail channel distribution data, and goods attribute data; A convenience evaluation module for evaluating the offline shopping convenience of a user based on user location data and offline retail channel distribution data; A goods recommendation list generation module for generating an online goods recommendation list based on the offline shopping convenience of a user; A difference evaluation module for analyzing the purchase convenience difference between online and offline goods based on goods attribute data to obtain online purchase weight information of the goods; A goods recommendation list optimization module for optimizing the online goods recommendation list based on the online purchase weight information of the goods and pushing the optimized online goods recommendation list to the user.

6. 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 kind of based on big data analysis's goods recommendation management method of claim 1-4 by calling the computer program stored in the memory.

7. A computer readable storage medium characterized by An instruction is stored, when the instruction runs on the computer, make the computer execute a kind of based on big data analysis's goods recommendation management method of claim 1-4.

Images