Electronic product online sales recommendation system based on big data analysis
Through the online sales recommendation system of electronic products analyzed by big data, combined with users and product itself evaluation, the problem of unreasonable information acquisition and recommendation in online electronic products sales is solved, the recommendation efficiency and success rate are improved, and sales display is optimized.
Patent Information
- Application Number
- CN202411054677.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In online electronic product sales, it is difficult for users to obtain product information in a timely manner, which affects sales volume, and cannot reasonably recommend and display based on market demand and its own impact, resulting in poor sales.
Using an online sales recommendation system for electronic products based on big data analysis, through recommendation division and supervision analysis of sales data, combined with evaluation from product users and their own perspectives, a discount intensity, demand and heat evaluation coefficient is generated, and recommendation integration evaluation is carried out to optimize recommendations. deal with.
It improves the rationality and success rate of electronic product recommendations, optimizes recommendation efficiency, and enhances sales display effect.
Smart Images

Figure CN118917919A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of online sales recommendation, and in particular to an online sales recommendation system for electronic products based on big data analysis. Background Art
[0002] With the continuous development of society, electronic products are increasingly used in people's lives, and the development of electronic products is also becoming more and more rapid. With the improvement of the intelligence of electronic products, they have gradually become a window for people to understand the world. In the current society, online shopping has become an important choice for people to buy goods. In the network environment, people can directly select electronic products online through the Internet. After the selection is completed, they can pay directly, and the goods will be mailed to the address set by the buyer.
[0003] With the rapid development of online shopping, more and more offline product shopping stores have set up online shopping brands to maintain online and offline product sales simultaneously. However, when selling electronic products online, due to the large number of electronic products, users often cannot obtain the desired product information in the first time, which in turn affects the sales volume of electronic products. In addition, it is impossible to make sales recommendations based on the market demand of electronic products and their own influence, which is not conducive to the rational recommendation and sales display of online electronic products.
[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention
[0005] The purpose of the present invention is to provide an online sales recommendation system for electronic products based on big data analysis to solve the technical defects mentioned above. The present invention performs electronic product recommendation classification supervision analysis on sales data so as to preliminarily recommend and classify each electronic product to improve the rationality of electronic product recommendations, and conducts in-depth analysis on the main electronic products, that is, analysis from the two perspectives of product users and the product itself to understand the demand situation of the main electronic products and the impact of recommendation sales, so as to provide data support for subsequent recommendation analysis, which helps to improve the comprehensiveness of data analysis, and conducts recommendation fusion evaluation feedback analysis through information feedback to reasonably recommend each main electronic product, optimize the efficiency of the recommendation of the main electronic products, improve the success rate of the recommendation of the main electronic products, and better display the recommended sales of the main electronic products.
[0006] The object of the present invention can be achieved by the following technical solutions: an online sales recommendation system for electronic products based on big data analysis, comprising an online sales recommendation platform, a product information unit, a pre-processing division unit, a product demand evaluation unit, a product self-evaluation unit, and a recommendation matching evaluation unit;
[0007] The product information unit is used to collect sales information of the plurality of electronic products, and send the sales information to the preprocessing and classification unit. After receiving the sales data, the preprocessing and classification unit immediately performs electronic product recommendation and classification supervision analysis on the sales data, and compares and analyzes the obtained discount strength evaluation values to obtain the main recommended electronic products and the secondary recommended electronic products;
[0008] The product demand evaluation unit is used to collect product base information of the main electronic products, perform product demand supervision feedback analysis on the product base information, and send the obtained demand evaluation coefficient Sg to the recommendation matching evaluation unit;
[0009] The product self-evaluation unit is used to collect product popularity information of the main electronic product, and perform product recommendation impact feedback operation on the product popularity information, and send the obtained product popularity evaluation coefficient Zg to the recommendation matching evaluation unit;
[0010] Upon receiving the demand evaluation coefficient Sg and the product popularity evaluation coefficient Zg, the recommendation matching evaluation unit immediately performs a recommendation fusion evaluation feedback analysis and sends the obtained sorted sales recommendation evaluation coefficient ZTg to the online sales recommendation platform.
[0011] Preferably, the electronic product recommendation division supervision analysis process of the pre-processing division unit is as follows:
[0012] Collect multiple electronic product sales periods and set them as time thresholds to obtain sales information of each electronic product within the time threshold. The sales information includes sales status and current sales price. The sales status indicates discount status and non-discount status, and then preliminarily determine the sales status of each electronic product:
[0013] If the electronic product is in a discount state, the electronic product corresponding to the discount state is set as the primary selected electronic product;
[0014] If the electronic product is in a non-discount state, the electronic product corresponding to the discount state is set as a normal electronic product.
[0015] Preferably, the initial selling price of each preliminarily selected electronic product within the time threshold is obtained, and at the same time, the current selling price of each preliminarily selected electronic product within the time threshold is obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is further obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is set as the discount strength evaluation value. It should be noted that the larger the value of the discount strength evaluation value is, the higher the main push demand for the current preliminarily selected electronic product is;
[0016] Compare and analyze the discount strength evaluation value with the preset discount strength evaluation value threshold stored in the internal storage:
[0017] If the discount strength evaluation value is greater than or equal to the preset discount strength evaluation value threshold, the corresponding preliminary selected electronic product will be set as the main recommended electronic product;
[0018] If the discount strength evaluation value is less than the preset discount strength evaluation value threshold, the corresponding initially selected electronic product will be set as the second recommended electronic product.
[0019] Preferably, the product demand supervision feedback analysis process of the product demand assessment unit is as follows:
[0020] Obtain the product cardinality information of each main electronic product within the time threshold. The product cardinality information includes the user evaluation value and the demand evaluation value. The main electronic product is labeled as g, where g is a natural number greater than zero. The user evaluation value and the demand evaluation value are labeled as YPg and XPg respectively. Substitute the user evaluation value YPg and the demand evaluation value XPg into the formula The demand assessment coefficient of each main electronic product is obtained, where a1 and a2 are the preset proportional factor coefficients of the user evaluation value YPg and the demand assessment value XPg respectively, a3 is the preset correction factor coefficient, and its value is 2.218. Both a1 and a2 are greater than zero, and Sg is the demand assessment coefficient of each main electronic product.
[0021] Preferably, the analysis process of the user evaluation value is as follows: obtaining user information of each main electronic product within a time threshold, the user information including the actual number of users and the attention evaluation value, the attention evaluation value represents the sum of the values corresponding to the daily browsing average and the daily search average of the main electronic product, and setting the product value obtained by multiplying the actual number of users by the value corresponding to the attention evaluation value as the user evaluation value;
[0022] The analysis process of the demand assessment value is as follows: obtain the total online reservations and the average reservation growth rate of each main electronic product within the time threshold, and set the value obtained by multiplying the corresponding values of the total online reservations and the average reservation growth rate after data normalization as the demand assessment value.
[0023] Preferably, the product recommendation impact feedback operation process of the product self-evaluation unit is as follows:
[0024] Obtain product popularity information of each main electronic product within the time threshold, the product popularity information includes electronic product information value and sales evaluation coefficient, and the electronic product information value and sales evaluation coefficient are labeled as DCg and XSg respectively;
[0025] According to the formula The product heat evaluation coefficient of each main electronic product is obtained, where f1 and f2 are the preset weight factor coefficients of the electronic product information value and the sales evaluation coefficient respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, and Zg is the product heat evaluation coefficient of each main electronic product.
[0026] Preferably, the electronic product information value represents the value obtained by dividing the number of registered users of the brand corresponding to each main electronic product by the brand image evaluation value after data normalization, and the brand image evaluation value represents the proportion of users who have given more than two negative reviews to the total number of users who have given negative reviews to each main electronic product;
[0027] The sales evaluation coefficient represents the ratio between the effective sales coefficient and the corresponding value of the total sales evaluation value. The total sales evaluation value represents the sum of the total online sales volume and the total offline sales volume corresponding to each main electronic product. The effective sales coefficient represents the value obtained by deducting the number of returns of each main electronic product from the total sales evaluation value.
[0028] Preferably, the recommendation fusion evaluation feedback analysis process of the recommendation matching evaluation unit is as follows:
[0029] Obtain the demand evaluation coefficient Sg of each main electronic product within the time threshold, obtain the product popularity evaluation coefficient Zg of each main electronic product within the time threshold, and obtain the discount strength evaluation value of each main electronic product within the time threshold, and label the discount strength evaluation value as ZDg, and substitute the demand evaluation coefficient Sg, the product popularity evaluation coefficient Zg and the discount strength evaluation value as ZDg into the formula ZTg=(Sg×Zg×ZDg) 2 ×v1 to obtain the sales recommendation evaluation coefficient of each main electronic product, where v1 is the preset influence ratio coefficient, v1 is greater than zero, and ZTg is the sales recommendation evaluation coefficient of each main electronic product. The sales recommendation evaluation coefficient ZTg is sorted in order from large to small.
[0030] The beneficial effects of the present invention are as follows:
[0031] (1) The present invention analyzes the sales data for electronic product recommendation and classification, so as to make preliminary recommendation and classification for each electronic product, thereby improving the rationality of electronic product recommendation, and further refines the classification from the perspective of discount, so as to divide the electronic products into main recommended electronic products and secondary recommended electronic products;
[0032] (2) The present invention conducts an in-depth analysis of the main electronic products, that is, analyzes from the perspectives of product users and the products themselves, so as to understand the demand situation of the main electronic products and the impact of recommendation sales, so as to provide data support for subsequent recommendation analysis, which helps to improve the comprehensiveness of data analysis, and conducts recommendation fusion evaluation feedback analysis through information feedback, so as to reasonably recommend each main electronic product, optimize the efficiency of the recommendation of the main electronic products, improve the success rate of the recommendation of the main electronic products, and better display the recommended sales of the main electronic products. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The present invention will be further described below in conjunction with the accompanying drawings;
[0034] Figure 1 It is a flowchart of the system of the present invention;
[0035] Figure 2 This is a local analysis diagram of Example 1 of the present invention. DETAILED DESCRIPTION
[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0037] Embodiment 1:
[0038] See also Figure 1 to Figure 2 As shown, the present invention is an online sales recommendation system for electronic products based on big data analysis, including an online sales recommendation platform, a product information unit, a preprocessing division unit, a product demand evaluation unit, a product self-evaluation unit and a recommendation matching evaluation unit, the online sales recommendation platform is in a one-way communication connection with the product information unit, the product information unit is in a one-way communication connection with the preprocessing division unit, the preprocessing division unit is in a one-way communication connection with the online sales recommendation platform, the online sales recommendation platform is in a one-way communication connection with the product demand evaluation unit and the product self-evaluation unit, the product demand evaluation unit and the product self-evaluation unit are both in a one-way communication connection with the recommendation matching evaluation unit, and the recommendation matching evaluation unit is in a one-way communication connection with the online sales recommendation platform;
[0039] When the online sales recommendation platform monitors the sales of multiple electronic products, it generates an operation management instruction and sends the operation management instruction to the product information unit, wherein the electronic products include but are not limited to: mobile phones, watches, tablet computers. After receiving the operation management instruction, the product information unit immediately collects the sales information of the multiple electronic products and sends the sales information to the pre-processing division unit. After receiving the sales data, the pre-processing division unit immediately performs an electronic product recommendation division supervision analysis on the sales data, so as to preliminarily recommend and divide each electronic product to improve the rationality of the recommendation of the electronic products. The specific electronic product recommendation division supervision analysis process is as follows:
[0040] Collect multiple electronic product sales periods and set them as time thresholds to obtain sales information of each electronic product within the time threshold. The sales information includes sales status and current sales price. The sales status indicates discount status and non-discount status, and then preliminarily determine the sales status of each electronic product:
[0041] If the electronic product is in a discount state, the electronic product corresponding to the discount state is set as the primary selected electronic product;
[0042] If the electronic product is in a non-discount state, the electronic product corresponding to the discount state is set as a normal electronic product;
[0043] The initial selling price of each preliminarily selected electronic product within the time threshold is obtained, and the current selling price of each preliminarily selected electronic product within the time threshold is obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is further obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is set as the discount strength evaluation value. It should be noted that the larger the value of the discount strength evaluation value is, the higher the main push demand for the current preliminarily selected electronic product is;
[0044] Compare and analyze the discount strength evaluation value with the preset discount strength evaluation value threshold stored in the internal storage:
[0045] If the discount strength evaluation value is greater than or equal to the preset discount strength evaluation value threshold, the corresponding preliminary selected electronic product will be set as the main recommended electronic product;
[0046] If the discount strength evaluation value is less than the preset discount strength evaluation value threshold, the corresponding preliminarily selected electronic product is set as the second recommended electronic product, and the main recommended electronic product and the second recommended electronic product are sent to the online sales recommendation platform, and the online sales recommendation platform divides the main recommended electronic product and the second recommended electronic product;
[0047] The product demand assessment unit is used to collect product base information of the main electronic products and conduct product demand supervision feedback analysis on the product base information, that is, to analyze from the user's perspective to understand the demand situation of the main electronic products, so as to provide data support for subsequent recommendation analysis. The specific product demand supervision feedback analysis process is as follows:
[0048] Obtain the product cardinality information of each main electronic product within the time threshold. The product cardinality information includes the user evaluation value and the demand evaluation value. The main electronic product is labeled as g, where g is a natural number greater than zero. The user evaluation value and the demand evaluation value are labeled as YPg and XPg respectively. Substitute the user evaluation value YPg and the demand evaluation value XPg into the formula Obtain the demand assessment coefficient of each main electronic product, where a1 and a2 are preset proportional factor coefficients of the user evaluation value YPg and the demand assessment value XPg, respectively. The proportional factor coefficient is used to correct the deviation of various parameters in the formula calculation process, so as to make the calculation result more accurate. a3 is the preset correction factor coefficient, which is 2.218. Both a1 and a2 are greater than zero. Sg is the demand assessment coefficient of each main electronic product. The demand assessment coefficient Sg is sent to the recommendation matching evaluation unit.
[0049] In the embodiment of the present invention, the analysis process of the user evaluation value is as follows: the user information of each main electronic product within the time threshold is obtained, the user information includes the actual user volume and the attention evaluation value, the attention evaluation value represents the sum of the values corresponding to the daily browsing average and the daily search average of the main electronic product, and the product value obtained by multiplying the actual user volume and the value corresponding to the attention evaluation value is set as the user evaluation value. It should be noted that the user base of the main electronic product can be understood by analyzing from the perspective of the user volume;
[0050] In an embodiment of the present invention, the analysis process of the demand assessment value is as follows: the total online reservation amount and the average reservation growth rate of each main electronic product within the time threshold are obtained, and the value obtained by multiplying the corresponding values of the total online reservation amount and the average reservation growth rate after data normalization processing is set as the demand assessment value. It should be noted that the demand assessment value reflects the influencing parameters of the demand status of the main electronic product.
[0051] Embodiment 2:
[0052] The product self-evaluation unit is used to collect the product popularity information of the main electronic products, and perform product recommendation impact feedback operations on the product popularity information, that is, to analyze from the perspective of the product itself to understand the impact of the main electronic products themselves on recommended sales, so as to provide data support for subsequent recommendation analysis. The specific product recommendation impact feedback operation process is as follows:
[0053] Obtain product popularity information of each main electronic product within the time threshold, the product popularity information includes electronic product information value and sales evaluation coefficient, and the electronic product information value and sales evaluation coefficient are labeled as DCg and XSg respectively;
[0054] In the embodiment of the present invention, the electronic product information value represents the value obtained by dividing the number of registered users of the brand corresponding to each main electronic product by the brand image evaluation value after data normalization processing, and the brand image evaluation value represents the proportion of the number of users who have given more than two negative reviews to the total number of users who have given negative reviews to each main electronic product. It should be noted that the analysis is conducted from the perspective of the main electronic product itself to understand the influence of the popularity of the main electronic product itself on the recommendation;
[0055] In the embodiment of the present invention, the sales evaluation coefficient represents the ratio between the effective sales coefficient and the corresponding value of the sales evaluation total value, the sales evaluation total value represents the sum of the total online sales volume and the total offline sales volume corresponding to each main electronic product, and the effective sales coefficient represents the value obtained by subtracting the number of returns of each main electronic product from the sales evaluation total value. It should be noted that the analysis is performed from the perspective of the effective sales of the product itself to ensure the validity of the analysis data;
[0056] According to the formula Obtain the product heat evaluation coefficient of each main electronic product, wherein f1 and f2 are respectively the preset weight factor coefficients of the electronic product information value and the sales evaluation coefficient, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, Zg is the product heat evaluation coefficient of each main electronic product, and the product heat evaluation coefficient Zg is sent to the recommendation matching evaluation unit;
[0057] After receiving the demand evaluation coefficient Sg and the product popularity evaluation coefficient Zg, the recommendation matching evaluation unit immediately performs recommendation fusion evaluation feedback analysis to reasonably recommend each main electronic product, optimize the efficiency of product recommendation, improve the success rate of product recommendation, and enhance user experience. The specific recommendation fusion evaluation feedback analysis process is as follows:
[0058] Obtain the demand evaluation coefficient Sg of each main electronic product within the time threshold, obtain the product popularity evaluation coefficient Zg of each main electronic product within the time threshold, and obtain the discount strength evaluation value of each main electronic product within the time threshold, and label the discount strength evaluation value as ZDg, and substitute the demand evaluation coefficient Sg, the product popularity evaluation coefficient Zg and the discount strength evaluation value as ZDg into the formula ZTg=(Sg×Zg×ZDg) 2×v1 to obtain the sales recommendation evaluation coefficient of each main electronic product, where v1 is the preset influence ratio coefficient, v1 is greater than zero, and ZTg is the sales recommendation evaluation coefficient of each main electronic product. The sales recommendation evaluation coefficient ZTg is sorted in order from large to small, and the sorted sales recommendation evaluation coefficient ZTg is sent to the online sales recommendation platform. After receiving the sales recommendation evaluation coefficient ZTg, the online sales recommendation platform immediately displays the electronic products corresponding to the sorted sales recommendation evaluation coefficient ZTg in sequence and recommends them to users for purchase, thereby optimizing the efficiency of product recommendation, improving the success rate of product recommendation, and better recommending and displaying electronic products for sale;
[0059] In summary, the present invention performs electronic product recommendation classification supervision and analysis on sales data so as to make preliminary recommendation classification for each electronic product to improve the rationality of electronic product recommendation, and further performs detailed classification from the discount perspective to divide the electronic products into main electronic products and secondary electronic products, and performs in-depth analysis on the main electronic products, that is, analyzes from the two perspectives of product users and the product itself to understand the demand situation of the main electronic products and the impact of recommendation sales, so as to provide data support for subsequent recommendation analysis, which helps to improve the comprehensiveness of data analysis, and performs recommendation fusion evaluation feedback analysis through information feedback to reasonably recommend each main electronic product, optimize the efficiency of the recommendation of the main electronic product, improve the success rate of the recommendation of the main electronic product, and better recommend the sales display of the main electronic product.
[0060] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.
[0061] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.
Claims
1. An electronic product online sales recommendation system based on big data analysis, characterized by: It includes an online sales recommendation platform, a product information unit, a pre-processing division unit, a product demand evaluation unit, a product self-evaluation unit, and a recommendation matching evaluation unit; The product information unit is used to collect sales information of the plurality of electronic products, and send the sales information to the preprocessing and classification unit. After receiving the sales data, the preprocessing and classification unit immediately performs electronic product recommendation and classification supervision analysis on the sales data, and compares and analyzes the obtained discount strength evaluation values to obtain the main recommended electronic products and the secondary recommended electronic products; The product demand evaluation unit is used to collect product base information of the main electronic products, perform product demand supervision feedback analysis on the product base information, and send the obtained demand evaluation coefficient Sg to the recommendation matching evaluation unit; The product self-evaluation unit is used to collect product popularity information of the main electronic product, and perform product recommendation impact feedback operation on the product popularity information, and send the obtained product popularity evaluation coefficient Zg to the recommendation matching evaluation unit; Upon receiving the demand evaluation coefficient Sg and the product popularity evaluation coefficient Zg, the recommendation matching evaluation unit immediately performs a recommendation fusion evaluation feedback analysis and sends the obtained sorted sales recommendation evaluation coefficient ZTg to the online sales recommendation platform.
2. The electronic product online sales recommendation system based on big data analysis according to claim 1 is characterized in that: The electronic product recommendation division supervision analysis process of the pre-processing division unit is as follows: Collect multiple electronic product sales periods and set them as time thresholds to obtain sales information of each electronic product within the time threshold. The sales information includes sales status and current sales price. The sales status indicates discount status and non-discount status, and then preliminarily determine the sales status of each electronic product: If the electronic product is in a discount state, the electronic product corresponding to the discount state is set as the primary selected electronic product; If the electronic product is in a non-discount state, the electronic product corresponding to the discount state is set as a normal electronic product.
3. The electronic product online sales recommendation system based on big data analysis according to claim 2 is characterized in that: The initial selling price of each preliminarily selected electronic product within the time threshold is obtained, and the current selling price of each preliminarily selected electronic product within the time threshold is obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is further obtained, and the ratio between the value obtained by subtracting the current selling price from the initial selling price and the initial selling price is set as the discount strength evaluation value. It should be noted that the larger the value of the discount strength evaluation value is, the higher the main push demand for the current preliminarily selected electronic product is; Compare and analyze the discount strength evaluation value with the preset discount strength evaluation value threshold stored in the internal storage: If the discount strength evaluation value is greater than or equal to the preset discount strength evaluation value threshold, the corresponding preliminary selected electronic product will be set as the main recommended electronic product; If the discount strength evaluation value is less than the preset discount strength evaluation value threshold, the corresponding initially selected electronic product will be set as the second recommended electronic product.
4. The electronic product online sales recommendation system based on big data analysis according to claim 1, characterized in that: The product demand supervision feedback analysis process of the product demand assessment unit is as follows: Obtain the product cardinality information of each main electronic product within the time threshold. The product cardinality information includes the user evaluation value and the demand evaluation value. The main electronic product is labeled as g, where g is a natural number greater than zero. The user evaluation value and the demand evaluation value are labeled as YPg and XPg respectively. Substitute the user evaluation value YPg and the demand evaluation value XPg into the formula The demand assessment coefficient of each main electronic product is obtained, where a1 and a2 are the preset proportional factor coefficients of the user evaluation value YPg and the demand assessment value XPg respectively, a3 is the preset correction factor coefficient, and its value is 2.
218. Both a1 and a2 are greater than zero, and Sg is the demand assessment coefficient of each main electronic product.
5. The electronic product online sales recommendation system based on big data analysis according to claim 4 is characterized in that: The analysis process of the user evaluation value is as follows: obtaining user information of each main electronic product within a time threshold, the user information including the actual number of users and the attention evaluation value, the attention evaluation value represents the sum of the values corresponding to the daily average browsing value and the daily average search value of the main electronic product, and setting the product value obtained by multiplying the actual number of users by the value corresponding to the attention evaluation value as the user evaluation value; The analysis process of the demand assessment value is as follows: obtain the total online reservations and the average reservation growth rate of each main electronic product within the time threshold, and set the value obtained by multiplying the corresponding values of the total online reservations and the average reservation growth rate after data normalization as the demand assessment value.
6. The electronic product online sales recommendation system based on big data analysis according to claim 1, characterized in that: The product recommendation impact feedback operation process of the product self-evaluation unit is as follows: Obtain product popularity information of each main electronic product within the time threshold, the product popularity information includes electronic product information value and sales evaluation coefficient, and the electronic product information value and sales evaluation coefficient are labeled as DCg and XSg respectively; According to the formula The product heat evaluation coefficient of each main electronic product is obtained, where f1 and f2 are the preset weight factor coefficients of the electronic product information value and the sales evaluation coefficient respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, and Zg is the product heat evaluation coefficient of each main electronic product.
7. The electronic product online sales recommendation system based on big data analysis according to claim 6, characterized in that: The electronic product information value represents the value obtained by dividing the number of registered users of the brand corresponding to each main electronic product by the brand image evaluation value after data normalization processing; the brand image evaluation value represents the proportion of users who have given more than two negative reviews to the total number of users who have given negative reviews to each main electronic product; The sales evaluation coefficient represents the ratio between the effective sales coefficient and the corresponding value of the total sales evaluation value. The total sales evaluation value represents the sum of the total online sales volume and the total offline sales volume corresponding to each main electronic product. The effective sales coefficient represents the value obtained by deducting the number of returns of each main electronic product from the total sales evaluation value.
8. The electronic product online sales recommendation system based on big data analysis according to claim 1, characterized in that: The recommendation fusion evaluation feedback analysis process of the recommendation matching evaluation unit is as follows: Obtain the demand evaluation coefficient Sg of each main electronic product within the time threshold, obtain the product popularity evaluation coefficient Zg of each main electronic product within the time threshold, and obtain the discount strength evaluation value of each main electronic product within the time threshold, and label the discount strength evaluation value as ZDg, and substitute the demand evaluation coefficient Sg, the product popularity evaluation coefficient Zg and the discount strength evaluation value as ZDg into the formula ZTg=(Sg×Zg×ZDg) 2 ×v1 to obtain the sales recommendation evaluation coefficient of each main electronic product, where v1 is the preset influence ratio coefficient, v1 is greater than zero, and ZTg is the sales recommendation evaluation coefficient of each main electronic product. The sales recommendation evaluation coefficient ZTg is sorted in order from large to small.
