Hot-sell product intelligent transaction method based on Internet

Abstract

The invention relates to the field of commodity transaction, and discloses an internet-based hot-sell product intelligent transaction method, which comprises the steps of constructing a hot-sell product information base containing product names, prices, classifications, goods sources and grades, calculating the grades of the products according to the grades of the products by shoppers, and making a product recommendation strategy to realize the intelligent transaction of the hot-sell products. And recommending products to different shoppers by adopting the first matching strategy and the second matching strategy in combination with the shopping habits of the shoppers. Wherein the first matching strategy is suitable for a first-time purchasing user and performs similarity matching and product pushing by analyzing browsing and clicking behaviors and personal signs of a shopper, and the second matching strategy is suitable for a multi-time purchasing user and performs association search, screening and pushing high-rating products by extracting keywords of interested products. The order pushing time is set according to the purchasing frequency and period of the shopper, so that the user can place an order quickly and conveniently.

Description

Technical Field

[0001] The present invention relates to the field of commodity trading technology, and in particular to a monitoring system and method for environmental protection equipment. Background Art

[0002] With the rapid development of Internet technology, e-commerce has become an important part of modern business. Consumers are increasingly inclined to buy hot-selling products online and enjoy a convenient shopping experience. However, faced with a large number of online products, consumers often need to spend a lot of time searching and comparing to find suitable products. In addition, due to the lack of personalized shopping guidance, consumers may miss out on hot-selling products that really suit their needs.

[0003] In existing online trading platforms, the display of product information is usually relatively simple, mainly including product pictures, descriptions and user reviews, etc. Although this information helps consumers understand the product, it often cannot fully reflect the characteristics and applicability of the product. At the same time, although the user rating system provides a certain reference value, it lacks in-depth analysis and application, and fails to fully play its role in product recommendations and trading decisions.

[0004] Although personalized recommendation systems have alleviated the problem of consumers' difficulty in choosing products to a certain extent, most systems are still based on simple algorithms, such as collaborative filtering or content recommendation, which often ignore the personalized needs of users and the complexity of shopping behaviors. Moreover, for the intelligent transaction management of consumables, existing technologies have not yet provided effective solutions to help consumers achieve automated and intelligent repeated purchases. In terms of the choice of transaction methods, most e-commerce platforms usually only provide one mode of online transactions, and fail to provide flexible and diverse transaction methods based on consumers' geographical locations and actual needs. This has limited consumers' shopping choices to a certain extent, and has failed to give full play to the convenience of offline transactions and the flexibility of online transactions.

[0005] In response to these problems, it is necessary to develop a new type of intelligent transaction method for hot-selling products based on the Internet. This method should have the following characteristics: comprehensive product information database construction, intelligent user rating system application, personalized product recommendation strategy, and flexible transaction methods combining online and offline. Through this method, the automation and efficiency of hot-selling product transactions can be improved, consumers can reduce the time and energy investment in product selection and transaction processes, improve shopping experience, and provide merchants with more accurate market positioning and marketing strategies.

[0006] Therefore, how to develop an intelligent trading method that can integrate multi-dimensional product information, deeply mine the value of user ratings, provide personalized recommendations and flexible trading methods has become an urgent problem to be solved in the field of e-commerce. This can not only greatly enhance consumers' shopping satisfaction, but also promote the innovation and development of e-commerce platform service models. Therefore, developing such an efficient, intelligent and personalized intelligent trading method for hot-selling products has become an important direction of e-commerce technology research. Summary of the invention

[0007] The present invention provides an Internet-based intelligent transaction method for hot-selling products, which is used to promote the solution of the problems mentioned in the above background technology.

[0008] The present invention provides the following technical solution: an intelligent transaction method for hot-selling products based on the Internet,

[0009] Optional,

[0010] Build a hot-selling product information database;

[0011] The hot-selling product information database contains the following information:

[0012] Hot-selling product names, hot-selling product price ranges, hot-selling product categories, hot-selling product sources and hot-selling product ratings;

[0013] The hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product, with a score range of [0,100] points;

[0014] Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product;

[0015] Get the total score of hot-selling products and calculate the average score of hot-selling products;

[0016] Get the keywords in the names of hot-selling products and record them as hot-selling product keywords;

[0017] Build a database of shoppers’ personal information;

[0018] The shopper personal information database contains the following information:

[0019] Shopper contact information, shopping behavior, and personal characteristics;

[0020] Develop product recommendation strategies to recommend products to shoppers based on their shopping habits;

[0021] Two transaction methods are set up, divided into online transactions and offline transactions.

[0022] Optionally, the hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product, with a score range of [0,100] points, including:

[0023] Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product;

[0024] Get the total score of hot-selling products and calculate the average score of hot-selling products;

[0025] The formula is: A = B / C;

[0026] Among them, A is the average score of the best-selling products, B is the total score of the best-selling products, and C is the number of times the best-selling products are evaluated;

[0027] Get the average score of hot-selling products and rate them as follows:

[0028] Set the score range corresponding to the evaluation level:

[0029] The corresponding score range for a five-star rating is [90,100] points;

[0030] The corresponding score range for a four-star rating is [70,89] points;

[0031] The corresponding score range for three-star rating is [50,69] points;

[0032] The corresponding score range for a two-star rating is [30,49] points;

[0033] The corresponding score range for a one-star rating is [0,29].

[0034] Furthermore, a product recommendation strategy is developed to recommend products to shoppers based on their shopping habits, including:

[0035] The product recommendation strategy is a first matching strategy and a second matching strategy;

[0036] If the shopper is a first-time buyer of a hot-selling product, the shopper is recorded as the first user and the first matching strategy is executed;

[0037] The first matching strategy is:

[0038] Get the shopping behavior of the shopper;

[0039] Shopping behavior specifically includes: the length of time shoppers browse the best-selling product page and the number of times they click on the best-selling product details interface;

[0040] If the shopper stays on the hot-selling product page for ≥15 seconds or clicks on the hot-selling product page ≥3 times, the hot-selling product will be marked as an interested product;

[0041] According to the personal information database, obtain the shopper's personal physical characteristics;

[0042] Personal signs include:

[0043] the shopper’s height, weight, age, and occupation;

[0044] Based on the shopper's personal characteristics, similarity matching is performed with other shoppers in the personal information database;

[0045] Get the products that shoppers with high matching degree are interested in during their shopping behavior;

[0046] Filter products of interest and obtain five-star and four-star reviews;

[0047] Push the screened products to the first user;

[0048] If the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed.

[0049] Furthermore, if the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed, including:

[0050] The second matching strategy is to obtain the product of interest according to the shopping behavior of the second user;

[0051] Extract keywords from the product names of the products of interest and record them as related keywords;

[0052] Perform a related search for hot-selling products;

[0053] The hot-selling product related search is to obtain the hot-selling products containing the related keywords among the hot-selling products according to the related keywords, and record them as keyword matching products;

[0054] Filter keyword matching products to obtain five-star and four-star rating products;

[0055] Push the filtered products to the second user.

[0056] Optional,

[0057] Identify popular items ordered by shoppers and assign them as consumable or non-consumable;

[0058] If the hot-selling item ordered by the shopper is a consumable item and it is purchased for the second time, the hot-selling item will be recorded as a recommended item for ordering, and the automatic recommended ordering strategy will be implemented;

[0059] Provide shoppers with the option to select this automatic recommended ordering method;

[0060] If the shopper refuses, the automatic recommended ordering strategy will not be executed;

[0061] If the shopper agrees, the automatic recommended ordering strategy is executed.

[0062] Furthermore, the automatically recommended order placement strategies include:

[0063] The specific steps are:

[0064] S1: Obtain recommended order items and identify the purchase time and purchase frequency of the items based on the purchaser's purchase behavior;

[0065] S2: Define the purchase time series, let T = {t 1 ,t 2 ,t 3 ,.....,t n} is the time point set when the shopper purchased the hot-selling product, where t i represents the time point of the i-th purchase;

[0066] S3: Calculate the purchase time interval ΔT = {Δt 1 ,Δt 2 ,......,Δt n-1}; where Δt i =t i+1 -t i represents the time difference between the i-th purchase and the i+1-th purchase;

[0067] S4: Calculate the purchase frequency f, the formula is:

[0068]

[0069] S5: Calculate the purchase cycle P, the formula is:

[0070] S6: Get the time point T when the buyer recently purchased the hot-selling product i ;

[0071] According to the obtained purchase cycle P, set the push order time to T i +P;

[0072] S7: Setting a recent order time interval, wherein the recent order time interval is from the order time point pushed by the system to the last order time point of the shopper;

[0073] S8: If the shopper has placed ≥ 3 orders in the recent order time interval, the number of orders in the recent order time interval is recorded and recorded as B;

[0074] Record the time point of the first order placed in the recent order time interval as the start time point;

[0075] Record the time point of the last order in the recent order time interval as the end time point;

[0076] Obtain the time duration of the recent order placement time interval, denoted as A;

[0077] Calculate the purchase cycle P, and the formula is:

[0078] S9: If the number of orders placed by the shopper within the recent order placement time interval is < 3 times, then record the shopper's order placement time and execute S1 - S6.

[0079] Optionally, the two trading methods are set, namely online trading and offline trading, including:

[0080] Obtain the shopper's contact information;

[0081] The shopper's contact information includes: the shopper's receiving address and contact phone number;

[0082] The time when the shopper places an order for the best-selling product is recorded as the first time;

[0083] The time when the shopper determines the trading method is recorded as the second time;

[0084] Execute the trading method selection strategy:

[0085] Starting from the first time, obtain the source location of the best-selling product that has been ordered;

[0086] Calculate the distance between the shopper's receiving address and the source location of the best-selling product, and generate a distance set, {S 1 , S 2 , ……, S n};

[0087] Sort the set in ascending order;

[0088] The sorted set is {S (1) , S (2) , ……, S (n)};

[0089] Obtain the shortest distance S (1) , and set a distance threshold M;

[0090] If the shortest distance S (1) ≥M, then recommend that the purchaser use the online trading method;

[0091] If the shortest distance S (1) <M, then recommend that the purchaser use both online and offline trading methods;

[0092] The present invention has the following beneficial effects:

[0093] 1. This is an Internet-based intelligent trading method for hot-selling products. By building a detailed hot-selling product information database, it integrates multi-dimensional information such as product name, price range, classification, source of goods and rating, and provides consumers with comprehensive product data support. Star rating is conducted based on this, which enhances the objectivity and accuracy of product ratings and helps consumers make more informed purchasing decisions.

[0094] 2. This is an Internet-based smart transaction method for hot-selling products. It determines the rating of hot-selling products by combining the scores of all shoppers and calculating the average score, which improves the accuracy of the rating. It also provides consumers with a more detailed product feedback reference through detailed star rating standards. It encourages consumers to make more intelligent purchasing choices, while motivating merchants to improve product quality and service levels, thereby improving consumer satisfaction.

[0095] 3. This is an Internet-based intelligent transaction method for hot-selling products. By distinguishing between first-time buyers and repeat buyers, different matching strategies are implemented to ensure that the recommendation results are more in line with the personalized needs of users, thereby improving user satisfaction and purchase conversion rate. The first matching strategy analyzes shopping behavior and personal signs to perform similarity matching on first-time buyers, ensuring that the recommended products are in line with the user's explicit behavior and implicit preferences, providing a more considerate shopping experience. The second matching strategy is for repeat buyers. By extracting keywords of products of interest and performing related searches, accurate product push is achieved, helping users quickly discover new products of potential interest. Through refined and personalized recommendation strategies, users are provided with more abundant and satisfactory shopping choices, while creating greater value for merchants and platforms.

[0096] 4. This is a hot-selling product online intelligent consultation feedback management method. By recording and analyzing the purchase time and frequency of buyers in detail, it can identify consumers' purchasing patterns and provide data support for personalized services. By calculating the purchase time series and time intervals, it is possible to predict consumers' purchase cycles, so as to push order reminders more accurately and improve the timeliness of recommendations. By setting the push order time according to the purchase cycle, this method can actively remind consumers before they need to buy again, thereby enhancing the initiative of the service. By setting the recent order time interval, the push strategy is dynamically adjusted, and the push time point is adjusted according to the consumer's purchase frequency to avoid excessive interruption. By recording and analyzing the number of orders and time points, it is possible to provide consumers with a more humane shopping experience and reduce the inconvenience caused by forgetting to buy. The automatic recommendation order strategy reduces the cumbersomeness of repeated purchases and increases users' dependence on the platform. Intelligent order reminders can effectively improve the success rate of transactions, increase platform sales, and improve consumers' purchasing efficiency. If the number of orders placed by consumers in the time interval is less than three times, the system will re-analyze the purchase behavior and update the recommendation strategy to ensure the continued accuracy and relevance of the recommendation. It provides consumers with a more intelligent and personalized shopping experience, while improving transaction efficiency and the platform's sales performance.

[0097] 5. This is an Internet-based intelligent transaction method for hot-selling products. By calculating the distance between the delivery address and the source of goods and setting a distance threshold, it can recommend the most suitable transaction method for shoppers based on geographical distance to improve logistics efficiency. If the shortest distance is less than the threshold, online and offline transaction methods are recommended, which increases shopping flexibility and enables consumers to choose the best transaction method based on personal preferences and actual conditions. By considering the location of consumers, distance-based transaction method recommendations are provided, which improves consumers' shopping satisfaction and loyalty. Recommending the shortest distance transaction method helps reduce logistics costs and improve delivery efficiency, while also reducing the loss of goods that may be caused by long-distance transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0099] 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.

[0100] Embodiment 1, combined with Figure 1, an intelligent transaction method for hot-selling products based on the Internet, comprising:

[0101] Build a hot-selling product information database;

[0102] The hot-selling product information database contains the following information:

[0103] Hot-selling product names, hot-selling product price ranges, hot-selling product categories, hot-selling product sources and hot-selling product ratings;

[0104] The hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product, with a score range of [0,100] points;

[0105] Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product;

[0106] Get the total score of hot-selling products and calculate the average score of hot-selling products;

[0107] Get the keywords in the names of hot-selling products and record them as hot-selling product keywords;

[0108] Build a database of shoppers’ personal information;

[0109] The shopper personal information database contains the following information:

[0110] Shopper contact information, shopping behavior, and personal characteristics;

[0111] Develop product recommendation strategies to recommend products to shoppers based on their shopping habits;

[0112] Two transaction methods are set up, divided into online transactions and offline transactions.

[0113] Optionally, the hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product, with a score range of [0,100] points, including:

[0114] Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product;

[0115] Get the total score of hot-selling products and calculate the average score of hot-selling products;

[0116] The formula is: A = B / C;

[0117] Among them, A is the average score of the best-selling products, B is the total score of the best-selling products, and C is the number of times the best-selling products are evaluated;

[0118] Get the average score of hot-selling products and rate them as follows:

[0119] Set the score range corresponding to the evaluation level:

[0120] The corresponding score range for a five-star rating is [90,100] points;

[0121] The corresponding score range for a four-star rating is [70,89] points;

[0122] The corresponding score range for three-star rating is [50,69] points;

[0123] The corresponding score range for a two-star rating is [30,49] points;

[0124] The corresponding score range for a one-star rating is [0,29].

[0125] Furthermore, a product recommendation strategy is developed to recommend products to shoppers based on their shopping habits, including:

[0126] The product recommendation strategy is a first matching strategy and a second matching strategy;

[0127] If the shopper is a first-time buyer of a hot-selling product, the shopper is recorded as the first user and the first matching strategy is executed;

[0128] The first matching strategy is:

[0129] Get the shopping behavior of the shopper;

[0130] Shopping behavior specifically includes: the length of time shoppers browse the best-selling product page and the number of times they click on the best-selling product details interface;

[0131] If the shopper stays on the hot-selling product page for ≥15 seconds or clicks on the hot-selling product page ≥3 times, the hot-selling product will be marked as an interested product;

[0132] According to the personal information database, obtain the shopper's personal physical characteristics;

[0133] Personal signs include:

[0134] the shopper’s height, weight, age, and occupation;

[0135] Based on the shopper's personal characteristics, similarity matching is performed with other shoppers in the personal information database;

[0136] Get the products that shoppers with high matching degree are interested in during their shopping behavior;

[0137] Filter products of interest and obtain five-star and four-star reviews;

[0138] Push the screened products to the first user;

[0139] If the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed.

[0140] Furthermore, if the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed, including:

[0141] The second matching strategy is to obtain the product of interest according to the shopping behavior of the second user;

[0142] Extract keywords from the product names of the products of interest and record them as related keywords;

[0143] Perform a related search for hot-selling products;

[0144] The hot-selling product related search is to obtain the hot-selling products containing the related keywords among the hot-selling products according to the related keywords, and record them as keyword matching products;

[0145] Filter keyword matching products to obtain five-star and four-star rating products;

[0146] Push the filtered products to the second user.

[0147] Optional,

[0148] Identify popular items ordered by shoppers and assign them as consumable or non-consumable;

[0149] If the hot-selling item ordered by the shopper is a consumable item and it is purchased for the second time, the hot-selling item will be recorded as a recommended item for ordering, and the automatic recommended ordering strategy will be implemented;

[0150] Provide shoppers with the option to select this automatic recommended ordering method;

[0151] If the shopper refuses, the automatic recommended ordering strategy will not be executed;

[0152] If the shopper agrees, the automatic recommended ordering strategy is executed.

[0153] Furthermore, the automatically recommended order placement strategies include:

[0154] The specific steps are:

[0155] S1: Obtain recommended order items and identify the purchase time and purchase frequency of the items based on the purchaser's purchase behavior;

[0156] S2: Define the purchase time series, let T = {t 1 ,t 2 ,t 3 ,.....,t n} is the time point set when the shopper purchased the hot-selling product, where t i represents the time point of the i-th purchase;

[0157] S3: Calculate the purchase time interval ΔT = {Δt1 ,Δt 2 ,......,Δt n-1}; where Δt i =t i+1 -t i represents the time difference between the i-th purchase and the i+1-th purchase;

[0158] S4: Calculate the purchase frequency f, the formula is:

[0159]

[0160] S5: Calculate the purchase cycle P, the formula is:

[0161] S6: Get the time point T when the buyer recently purchased the hot-selling product i ;

[0162] According to the obtained purchase cycle P, set the push order time to T i +P;

[0163] S7: Setting a recent order time interval, wherein the recent order time interval is from the order time point pushed by the system to the last order time point of the shopper;

[0164] S8: If the shopper has placed ≥ 3 orders in the recent order time interval, the number of orders in the recent order time interval is recorded and recorded as B;

[0165] Record the time point of the first order placed in the recent order time interval as the start time point;

[0166] Record the time point of the last order in the recent order time interval as the end time point;

[0167] Get the duration of the recent order time interval, recorded as A;

[0168] Calculate the purchase cycle P, the formula is:

[0169] S9: If the shopper has placed orders less than 3 times in the recent order time interval, the shopper's order time is recorded and S1-S6 are executed.

[0170] Optionally, the two transaction methods are set, namely online transaction and offline transaction, including:

[0171] Get shopper contact information;

[0172] The shopper's contact information includes: the shopper's delivery address and contact number;

[0173] The time when shoppers place orders for hot-selling products is recorded as the first time;

[0174] The time when the shopper determines the transaction method is recorded as the second time;

[0175] Execute the transaction method selection strategy:

[0176] Starting from the first time, obtain the source locations of the hot-selling products that have been ordered;

[0177] Calculate the distance between the shopper's receiving address and the source locations of the hot-selling products, generate a distance set, {S 1 , S 2 , ……, S n};

[0178] Sort the set in ascending order;

[0179] The sorted set is {S (1) , S (2) , ……, S (n)};

[0180] Obtain the shortest distance S (1) , and set a distance threshold M;

[0181] If the shortest distance S (1) ≥M, then recommend that the purchaser use the online transaction method;

[0182] If the shortest distance S (1) <M, then recommend that the purchaser use both online and offline transaction methods;

[0183] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0184] The above is only the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent transaction method for hot-selling products based on the Internet, comprising: Build a hot-selling product information database; The hot-selling product information database contains the following information: Hot-selling product names, hot-selling product price ranges, hot-selling product categories, hot-selling product sources and hot-selling product ratings; The hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product, with a score range of [0,100] points; Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product; Get the total score of hot-selling products and calculate the average score of hot-selling products; Get the keywords in the names of hot-selling products and record them as hot-selling product keywords; Build a database of shoppers’ personal information; The shopper personal information database contains the following information: Shopper contact information, shopping behavior, and personal characteristics; Develop product recommendation strategies to recommend products to shoppers based on their shopping habits; Two transaction methods are set up, divided into online transactions and offline transactions.

2. The hot-selling product intelligent transaction method based on the Internet according to claim 1 is characterized in that: The hot-selling product rating is a score given to the hot-selling product by shoppers based on their usage after purchasing the hot-selling product. The score range is [0,100] points, including: Add up all the shopper ratings of the hot-selling product and record it as the total score of the hot-selling product; Get the total score of hot-selling products and calculate the average score of hot-selling products; The formula is: A = B / C; Among them, A is the average score of the best-selling products, B is the total score of the best-selling products, and C is the number of times the best-selling products are evaluated; Get the average score of hot-selling products and rate them as follows: Set the score range corresponding to the evaluation level: The corresponding score range for a five-star rating is [90,100] points; The corresponding score range for a four-star rating is [70,89] points; The corresponding score range for three-star rating is [50,69] points; The corresponding score range for a two-star rating is [30,49] points; The corresponding score range for a one-star rating is [0,29].

3. The hot-selling product intelligent transaction method based on the Internet according to claim 1 is characterized in that: Develop product recommendation strategies to recommend products to shoppers based on their shopping habits, including: The product recommendation strategy is a first matching strategy and a second matching strategy; If the shopper is a first-time buyer of a hot-selling product, the shopper is recorded as the first user and the first matching strategy is executed; The first matching strategy is: Get the shopping behavior of the shopper; Shopping behavior specifically includes: the length of time shoppers browse the best-selling product page and the number of times they click on the best-selling product details interface; If the shopper stays on the hot-selling product page for ≥15 seconds or clicks on the hot-selling product page ≥3 times, the hot-selling product will be marked as an interested product; Obtain the shopper's personal information based on the personal information database; Personal signs include: the shopper’s height, weight, age, and occupation; Based on the shopper's personal characteristics, similarity matching is performed with other shoppers in the personal information database; Get the products that shoppers with high matching degree are interested in during their shopping behavior; Filter products of interest and obtain five-star and four-star reviews; Push the screened products to the first user; If the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed.

4. The hot-selling product intelligent transaction method based on the Internet according to claim 3 is characterized in that: If the shopper is a user who has purchased the hot-selling product multiple times, the shopper is recorded as the second user and the second matching strategy is executed, including: The second matching strategy is to obtain the product of interest according to the shopping behavior of the second user; Extract keywords from the product names of the products of interest and record them as related keywords; Perform a related search for hot-selling products; The hot-selling product related search is to obtain the hot-selling products containing the related keywords among the hot-selling products according to the related keywords, and record them as keyword matching products; Filter keyword matching products to obtain five-star and four-star rating products; Push the filtered products to the second user.

5. The Internet-based hot-selling product intelligent transaction method according to claim 1 is characterized by: Identify popular items ordered by shoppers and assign them as consumable or non-consumable; If the hot-selling item ordered by the shopper is a consumable item and it is purchased for the second time, the hot-selling item will be recorded as a recommended item for ordering, and the automatic recommended ordering strategy will be implemented; Provide shoppers with the option to select this automatic recommended ordering method; If the shopper refuses, the automatic recommended ordering strategy will not be executed; If the shopper agrees, the automatic recommended ordering strategy is executed.

6. The method for intelligent trading of hot-selling products based on the Internet according to claim 5, characterized in that: The automatically recommended order strategies include: The specific steps are: S1: Obtain recommended order items and identify the purchase time and purchase frequency of the items based on the purchaser's purchase behavior; S2: Define the purchase time series, let T = {t1, t2, t3, ....., t n } is the time point set when the shopper purchased the hot-selling product, where t i represents the time point of the i-th purchase; S3: Calculate the purchase time interval ΔT = {Δt1, Δt2, ..., Δt n-1 }; where Δt i =t i+1 -t i represents the time difference between the i-th purchase and the i+1-th purchase; S4: Calculate the purchase frequency f, the formula is: S5: Calculate the purchase cycle P, the formula is: S6: Get the time point T when the buyer recently purchased the hot-selling product i ; According to the obtained purchase cycle P, set the push order time to T i +P; S7: Setting a recent order time interval, wherein the recent order time interval is from the order time point pushed by the system to the last order time point of the shopper; S8: If the shopper has placed ≥ 3 orders in the recent order time interval, the number of orders in the recent order time interval is recorded and recorded as B; Record the time point of the first order placed in the recent order time interval as the start time point; Record the time point of the last order in the recent order time interval as the end time point; Get the duration of the recent order time interval, recorded as A; Calculate the purchase cycle P, the formula is: S9: If the shopper has placed orders less than 3 times in the recent order time interval, the shopper's order time is recorded and S1-S6 are executed.

7. The hot-selling product intelligent transaction method based on the Internet according to claim 1 is characterized by: The two transaction methods are set, namely online transaction and offline transaction, including: Get shopper contact information; The shopper's contact information includes: the shopper's delivery address and contact number; The time when shoppers place orders for hot-selling products is recorded as the first time; The time when the shopper determines the transaction method is recorded as the second time; Execution of trading method selection strategy: Get the source of the hot-selling products that have been ordered at the first time; Calculate the distance between the shopper's delivery address and the source of the hot-selling product, and generate a distance set, {S1, S2, ..., S n }; Sort the collection in ascending order; The sorted set is {S (1) , S (2) , ..., S (n) }; Get the shortest distance S (1) , set the distance threshold M; If the shortest distance S (1) ≥M, it is recommended that buyers use online transactions; If the shortest distance S (1) <M, it is recommended that the purchaser use online and offline trading methods.

Images