Automatic order generation method and system based on information analysis and storage medium

Abstract

The invention discloses an automatic order generation method and system based on information analysis, and a storage medium, and relates to the technical field of automatic order generation, and the method comprises the steps: obtaining the shopping related information of a user; the method comprises the following steps: firstly, determining a user consumption upper limit value, secondly, analyzing products which are frequently purchased according to user historical shopping information, determining a frequently purchased product set and a purchase time set corresponding to the frequently purchased product set, then, carrying out preferential analysis on user shopping cart information, determining preferential product combination information, and finally, carrying out statistical analysis on the preferential product combination information. And performing consumption upper limit analysis on the consumption upper limit value of the user, the frequently purchased product set, the purchase time set and the preferential product combination information to determine an optimal supplement product so as to obtain an optimal preferential product combination, so that the consumption upper limit value of the user can be determined, and the consumption amount is the psychological price of the user; in addition, the user can purchase favorite products, and in addition, the shopping time of the user is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic order generation, and specifically relates to a method, system and storage medium for automatic order generation based on information analysis. Background Art

[0002] An order form is a purchase voucher sent by an enterprise's purchasing department to a supplier, covering the entire procurement process of finished products, raw materials, fuels, spare parts, office supplies, services, etc.

[0003] Coupons are issued irregularly in shopping APPs. When users use coupons for shopping, they can reduce expenses. However, the coupons that can be used for each product may be different, and the combined purchased products will also be different. If users combine and make up orders for the coupons of each product, it will take a lot of time. In addition, when users shop, they have a psychological price threshold and need to match their psychological price threshold according to the product price, which will also waste a lot of time. Summary of the Invention

[0004] To solve the above technical problems, a method, system and storage medium for automatic order generation based on information analysis are provided. This technical solution solves the problem proposed in the above background art that coupons are issued irregularly in shopping APPs. When users use coupons for shopping, they can reduce expenses. However, the coupons that can be used for each product may be different, and the combined purchased products will also be different. If users combine and make up orders for the coupons of each product, it will take a lot of time. In addition, when users shop, they have a psychological price threshold and need to match their psychological price threshold according to the product price, which will also waste a lot of time.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for automatic order generation based on information analysis, comprising: Obtaining user shopping-related information, wherein the user shopping-related information is obtained from the user's shopping APP, and the user shopping-related information includes user shopping cart information and user historical shopping information; Based on a data analysis terminal, analyzing and processing the user historical shopping information to determine user consumption characteristic information, where the user consumption characteristic information includes the user's consumption upper limit value, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products; Based on a data analysis terminal, performing a preferential analysis on the user shopping cart information to determine preferential product combination information; Based on a data analysis terminal, performing a judgment process on the preferential product combination information and the user's consumption upper limit value to determine a set of preferential products that meet the criteria; Based on the data analysis terminal, product supplementation processing is performed on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase time corresponding to the set of frequently purchased products, to determine the best combination of preferential products.

[0006] Preferably, the data analysis terminal analyzes and processes the user's historical shopping information to determine the user's consumption characteristic information, which specifically includes the following steps: Based on the data analysis terminal, classify and process the user's historical shopping information with payment information as the feature to obtain several groups of user's historical shopping consumption information; Based on the data analysis terminal, plot discrete points of several groups of user's historical shopping consumption information in a two-dimensional rectangular coordinate system to obtain several groups of user's historical shopping consumption points. The X-axis parameter of the two-dimensional rectangular coordinate system is the consumption date, and the Y-axis parameter is the consumption amount; Based on the data analysis terminal, perform dispersion analysis on several groups of user's historical shopping consumption points to determine the standard straight line of the user's historical shopping consumption; Based on the data analysis terminal, screen several groups of user's historical shopping consumption points with the standard straight line of the user's historical shopping consumption as the feature to obtain multiple groups of consumption points higher than the standard straight line of the user's historical shopping consumption. The specific process of screening several groups of user's historical shopping consumption points is to screen out the user's historical shopping consumption points above the standard straight line of the user's historical shopping consumption; Based on the data analysis terminal, judge and process multiple groups of consumption points higher than the standard straight line of the user's historical shopping consumption to determine the user's consumption upper limit value; Based on the data analysis terminal, classify and process the user's historical shopping information with the number of product purchases as the feature to determine the set of frequently purchased products and the set of purchase time corresponding to the set of frequently purchased products.

[0007] Preferably, the data analysis terminal judges and processes multiple groups of consumption points higher than the standard straight line of the user's historical shopping consumption to determine the user's consumption upper limit value, which specifically includes the following steps: Based on the data analysis terminal, merge multiple groups of consumption points higher than the standard straight line of the user's historical shopping consumption with a preset consumption amount interval as the feature to obtain several groups of consumption intervals higher than the standard straight line of the user's historical shopping consumption; Based on the data analysis terminal, count the consumption points within several groups of consumption intervals higher than the standard straight line of the user's historical shopping consumption to obtain the number of consumption points within different consumption intervals; Based on the data analysis terminal, compare and judge the number of consumption points within different consumption intervals with the set consumption point number threshold; If the number of consumption points within different consumption ranges is less than the set consumption point number threshold, the consumption range does not meet the user consumption standard; If the number of consumption points within different consumption ranges is greater than or equal to the set consumption point number threshold, record the consumption range, set it as the standard consumption range, and the number of the standard consumption ranges is at least one; Based on the data analysis terminal, perform data reading and processing on the standard consumption ranges to determine the user consumption upper limit. If the number of standard consumption ranges is one, set the consumption amount corresponding to the maximum consumption point in the standard consumption range as the user consumption upper limit value. If the number of standard consumption ranges is greater than one, set the consumption amount corresponding to the maximum consumption point in the standard consumption range with the largest upper limit value as the user consumption upper limit value.

[0008] Preferably, the data analysis terminal classifies the user's historical shopping information by taking the number of product purchases as a feature, and determining the frequently purchased product set and the purchase time set corresponding to the frequently purchased product set specifically includes the following steps: Based on the data analysis terminal, perform product count processing on the user's historical shopping information to obtain the number of purchases of different types of products; Based on the data analysis terminal, compare and judge the number of purchases of different types of products with the set product purchase number threshold; If the number of purchases of different types of products is less than the set product purchase number threshold, the number of purchases of this product does not meet the frequently purchased product standard, and discard the number of purchases of this type of product; If the number of purchases of different types of products is greater than or equal to the set product purchase number threshold, the number of purchases of this product meets the frequently purchased product standard, and perform a collection process on the products corresponding to the frequently purchased product standard to obtain the frequently purchased product set; Based on the data analysis terminal, calculate the shopping time in the user's historical shopping information with the products in the frequently purchased product set as features, and determine the purchase time set, and the purchase time set is specifically the purchase time interval of each product in the frequently purchased product set.

[0009] Preferably, the data analysis terminal performs preferential analysis on the user's shopping cart information to determine the preferential product combination information, which specifically includes the following steps: Based on the data analysis terminal, perform an intersection process on the preferential information of all products in the user's shopping cart information to determine the products with the same preferential information; Based on the data analysis terminal, combine the products with the same preferential information to determine the preferential product combination information, and the number of the preferential product combination information is at least one; Among them, the specific calculation formula for performing an intersection process on the preferential information of all products in the user's shopping cart information is: ; In the formula, the are products with the same preferential information; the is the preferential information of a certain product in the user's shopping cart information; the is the preferential information of the products in the user's shopping cart information that do not include corresponding products; the i is the specific quantity of products with the same preferential information; the j is the quantity of all products in the user's shopping cart information; the k = j - 1; the .

[0010] Preferably, the data analysis terminal judges and processes the preferential product combination information and the user's consumption upper limit value to determine the set of preferential products that meet the standards, which specifically includes the following steps: Based on the data analysis terminal, perform amount calculation processing on the preferential product combination information to obtain the amount spent on the preferential product combination, and the quantity of the amount spent on the preferential product combination is at least one; Based on the data analysis terminal, judge and process the amount spent on the preferential product combination and the user's consumption upper limit value; If the amount spent on the preferential product combination is greater than the user's consumption upper limit value, the amount spent on the preferential product combination does not meet the user's shopping consumption standard, and discard the preferential product combination information corresponding to the amount spent on the preferential product combination; If the amount spent on the preferential product combination is equal to the user's consumption upper limit value, the amount spent on the preferential product combination meets the user's shopping consumption standard, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the best preferential product combination and generate order information to be sent to the user's electronic device; If the amount spent on the preferential product combination is less than the user's consumption upper limit value, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the set of preferential products that meet the standards.

[0011] Preferably, the data analysis terminal performs product supplementation processing on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products to determine the best preferential product combination, which specifically includes the following steps: Based on the data analysis terminal, perform a difference calculation on the amount spent corresponding to the set of preferential products that meet the standards and the user's consumption upper limit value to obtain the amount to be supplemented; Based on the data analysis terminal, match the amount of each product in the set of frequently purchased products with the amount to be supplemented as a feature to determine the set of frequently purchased products that meet the amount standard; Based on the data analysis terminal, product selection processing is performed on the set of frequently purchased products that meet the amount standard, using the set of purchase times corresponding to the set of frequently purchased products as features, to determine the best supplementary products; Based on the data analysis terminal, the best supplementary products are filled into the set of preferential products that meet the standards, the best preferential product combination is determined, and the best preferential product combination is generated into order information and sent to the user's electronic device.

[0012] Preferably, the above-mentioned data analysis terminal performs product selection processing on the set of frequently purchased products that meet the amount standard, using the set of purchase times corresponding to the set of frequently purchased products as features, to determine the best supplementary products, which specifically includes the following steps: Obtain real-time time information; Based on the data analysis terminal, data extraction processing is performed on the user's historical shopping information to obtain the user's last shopping time; Based on the data analysis terminal, a difference calculation is performed on the real-time time information and the user's last shopping time to obtain the shopping time interval; Based on the data analysis terminal, data screening processing is performed on the set of purchase times corresponding to the set of frequently purchased products, with each product in the set of frequently purchased products that meet the amount standard as a feature, to obtain the product purchase time interval that meets the amount standard; Based on the data analysis terminal, judgment processing is performed on the shopping time interval and the product purchase time interval that meets the amount standard; If the shopping time interval is less than the product purchase time interval that meets the amount standard and the products frequently purchased by the user have not been used up, the set of preferential products that meet the standards is set as the best preferential product combination, and the best preferential product combination is generated into order information and sent to the user's electronic device; If the shopping time interval is greater than or equal to the product purchase time interval that meets the amount standard, the product corresponding to the largest product purchase time interval in the product purchase time interval that meets the amount standard is set as the best supplementary product.

[0013] Furthermore, an order automatic generation system based on information analysis is proposed, which is used to implement an order automatic generation method based on information analysis as described above, including: A data analysis terminal, which is used to perform type analysis, preferential analysis, and product analysis on the user's shopping-related information to determine the best preferential product combination; A user shopping APP, which is used to store the user's shopping cart information and the user's historical shopping information, and the user shopping APP is used to realize the user's online shopping; Among them, the following are integrated inside the data analysis terminal: A central control module, which is used to control data transmission and information interaction among various modules; A data reading module, which is used to read data from the user's shopping APP; A classification module, which classifies the user's historical shopping information based on payment information; A consumption upper limit value determination module, which is used to perform dispersion analysis, consumption point screening, and consumption point judgment on several groups of user historical shopping consumption points to determine the user's consumption upper limit value; A frequently purchased product determination module, which is used to count the number of product purchases and judge the number of purchases in the user's historical shopping information to determine the set of frequently purchased products and the set of purchase times corresponding to the set of frequently purchased products; A preferential analysis module, which is used to analyze the preferential information in the user's shopping cart to determine the preferential product combination information; A consumption amount comparison module, which is used to judge the preferential product combination information and the user's consumption upper limit value to determine the set of preferential products that meet the standards; A product selection module, which is used to select products from the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products to determine the best preferential product combination.

[0014] Furthermore, a storage medium is proposed, on which a computer program is stored. When the computer program is called and run, it executes an order automatic generation method based on information analysis as described above.

[0015] Compared with the prior art, the present invention provides an order automatic generation method, system and storage medium based on information analysis, which has the following beneficial effects: The present invention first analyzes the consumption upper limit of the user's historical shopping information to determine the user's consumption upper limit value. Secondly, it analyzes the products frequently purchased in the user's historical shopping information again to determine the set of frequently purchased products and the set of purchase times corresponding to the set of frequently purchased products. Then, it analyzes the preferential information in the user's shopping cart to determine the preferential product combination information. Finally, it performs consumption upper limit analysis on the user's consumption upper limit value, the set of frequently purchased products, the set of purchase times, and the preferential product combination information to determine the best supplementary products, and then obtains the best preferential product combination. The above method can not only determine the user's consumption upper limit value, making the consumption amount the user's psychological price, but also enable the user to buy their favorite products. In addition, it also shortens the user's shopping time. Description of the Drawings

[0016] Figure 1 Flow diagram of steps S100 - S500 in an order automatic generation method based on information analysis proposed by the present invention; Figure 2 Flow diagram of steps S201 - S206 in an order automatic generation method based on information analysis proposed by the present invention; Figure 3 Flow diagram of steps S2051 - S2056 in an order automatic generation method based on information analysis proposed by the present invention; Figure 4 Flow diagram of steps S2061 - S2065 in an order automatic generation method based on information analysis proposed by the present invention; Figure 5 Flow diagram of steps S301 - S302 in an order automatic generation method based on information analysis proposed by the present invention; Figure 6 Flow diagram of steps S401 - S405 in an order automatic generation method based on information analysis proposed by the present invention; Figure 7 Flow diagram of steps S501 - S504 in an order automatic generation method based on information analysis proposed by the present invention; Figure 8 Flow diagram of steps S5031 - S5037 in an order automatic generation method based on information analysis proposed by the present invention; Figure 9 Block diagram of the structure of an order automatic generation method, system and storage medium based on information analysis proposed by the present invention. Detailed implementation manners

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0018] Refer to Figure 1 As shown, an order automatic generation method based on information analysis includes: S100. Obtain user shopping - related information, where the user shopping - related information is obtained from the user shopping APP, and the user shopping - related information includes user shopping cart information and user historical shopping information; S200. Based on the data analysis terminal, analyze and process the user historical shopping information to determine user consumption characteristic information, where the user consumption characteristic information includes the user consumption upper limit value, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products; S300. Based on the data analysis terminal, conduct a preferential analysis on the user's shopping cart information to determine the preferential product combination information; S400. Based on the data analysis terminal, conduct a judgment process on the preferential product combination information and the user's consumption upper limit value to determine the set of preferential products that meet the standards; S500. Based on the data analysis terminal, conduct a product supplementation process on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase time corresponding to the set of frequently purchased products to determine the best preferential product combination; Those skilled in the art can understand that coupons have a time limit. When the usage time of the coupon expires, the coupon will expire and cannot be used. In addition, some coupons require different products to be combined to meet the usage standards of the coupon. When users match products according to the coupon matching standards, it will waste a lot of time. And each user has an expected price for each shopping. Therefore, when users need to match products according to their expected prices, it will also waste a certain amount of time. Therefore, in order to shorten the user's shopping time, analyze the user's historical shopping information to determine the user's consumption upper limit value. Then, conduct a comprehensive analysis of the preferential information of each product and the user's consumption upper limit value to determine the best set of preferential products. The above method can not only quickly select the user's favorite products, but also meet the usage standards of the coupon and reach the user's expected consumption amount (i.e., the user's consumption upper limit value). In addition, it can also greatly save the user's shopping time.

[0019] Refer to Figure 2 As shown in the figure, based on the data analysis terminal, conduct an analysis process on the user's historical shopping information to determine the user's consumption characteristic information, which specifically includes the following steps: S201. Based on the data analysis terminal, classify the user's historical shopping information with payment information as the feature to obtain several groups of user's historical shopping consumption information; It can be understood that each user's consumption has an expected amount, and the predicted amounts of each consumption will not vary much. Therefore, classify the user's historical shopping information through the payment information; S202. Based on the data analysis terminal, plot discrete points of several groups of user's historical shopping consumption information in a two-dimensional rectangular coordinate system to obtain several groups of user's historical shopping consumption points. The X-axis parameter of the two-dimensional rectangular coordinate system is the consumption date, and the Y-axis parameter of the two-dimensional rectangular coordinate system is the consumption amount; It can be understood that in order to eliminate the data with too large consumption amounts, analyze the dispersion degree of the discrete points to eliminate those discrete points with larger dispersion degrees, that is, the records with too large consumption amounts; S203. Based on the data analysis terminal, perform a dispersion analysis on several groups of users' historical shopping consumption points to determine the standard straight line of users' historical shopping consumption; It can be understood that the dispersion of users' historical shopping consumption points can be calculated through the interquartile range, and the value calculated through the interquartile range is a straight line in the two-dimensional rectangular coordinate system (i.e., the standard straight line of users' historical shopping consumption); S204. Based on the data analysis terminal, perform a screening process on several groups of users' historical shopping consumption points with the standard straight line of users' historical shopping consumption as a feature to obtain multiple groups of consumption points higher than the standard straight line of users' historical shopping consumption. The specific process of performing a screening process on several groups of users' historical shopping consumption points is to screen out the users' historical shopping consumption points above the standard straight line of users' historical shopping consumption; It can be understood that the data on the standard straight line of users' historical shopping consumption is the expected consumption amount that users can accept. It should be noted that this situation is after removing those points with large dispersions. In order to obtain a more accurate upper limit value of users' consumption, the points on the standard straight line of users' historical shopping consumption are screened; S205. Based on the data analysis terminal, perform a judgment process on multiple groups of consumption points higher than the standard straight line of users' historical shopping consumption to determine the upper limit value of users' consumption; S206. Based on the data analysis terminal, classify the users' historical shopping information with the number of product purchases as a feature to determine the set of frequently purchased products and the set of purchase times corresponding to the set of frequently purchased products; In this embodiment, in order to determine the upper limit value of users' consumption, the users' historical shopping information is classified according to the payment information. Because each time a user shops and consumes, there is a psychological price. Therefore, classifying the users' historical shopping information according to the payment information to obtain the users' historical shopping consumption information. However, the amount spent by the user each time shopping does not fluctuate within a certain range. When purchasing a relatively expensive product, the consumption amount for that time will increase. However, this situation is only a special case. In order to accurately obtain the expected consumption price of the user, this special case needs to be screened out. Therefore, by performing a dispersion analysis on the users' historical consumption information, removing the data with large dispersions, and analyzing the remaining data, a relatively accurate upper limit value of users' consumption can be obtained.

[0020] Refer to Figure 3 As shown, based on the data analysis terminal, performing a judgment process on multiple groups of consumption points higher than the standard straight line of users' historical shopping consumption to determine the upper limit value of users' consumption specifically includes the following steps: S2051. Based on the data analysis terminal, merge multiple sets of consumption points above the straight line of the user's historical shopping consumption standard with the preset consumption amount interval as the feature to obtain several consumption intervals above the straight line of the user's historical shopping consumption standard; It can be understood that the amount of each user consumption may be different, but the difference is not too large. If all consumption points are counted, the calculation amount will be increased. To reduce the calculation amount, these consumption points are merged through the preset consumption amount interval. When the preset consumption amount interval is set to , the consumption points within this interval are classified into this interval. It should be noted that there are many sets of preset consumption amount intervals, not just one set; S2052. Based on the data analysis terminal, count the consumption points within several consumption intervals above the straight line of the user's historical shopping consumption standard to obtain the number of consumption points within different consumption intervals; It can be understood that not all consumption intervals meet the user's psychological expectations. Therefore, by judging the number of consumption points within the consumption interval, determine the consumption interval that meets the user's psychological consumption expectations; S2053. Based on the data analysis terminal, compare and judge the number of consumption points within different consumption intervals with the set consumption point number threshold; S2054. If the number of consumption points within a different consumption interval is less than the set consumption point number threshold, this consumption interval does not meet the user's consumption standard; S2055. If the number of consumption points within a different consumption interval is greater than or equal to the set consumption point number threshold, record this consumption interval and set it as the standard consumption interval, and the number of the standard consumption intervals is at least one; S2056. Based on the data analysis terminal, perform data reading processing on the standard consumption interval to determine the user's consumption upper limit. If the number of standard consumption intervals is one, set the consumption amount corresponding to the maximum consumption point in the standard consumption interval as the user's consumption upper limit value. If the number of standard consumption intervals is greater than one, set the consumption amount corresponding to the maximum consumption point in the standard consumption interval with the largest upper limit value as the user's consumption upper limit value; In this embodiment, the points on the straight line of the user's historical shopping consumption standard all meet the standard, but they do not necessarily meet the user's psychological expectations. Only the consumption amount that appears the most times among the points that meet the standard meets the user's psychological expectations. Therefore, by counting the consumption points on the straight line of the user's historical shopping consumption standard, the interval of the consumption point that appears the most is the user's psychological expectation (i.e., the standard consumption interval). Since there may be more than one standard consumption interval, by comparing the upper limit values of the standard consumption intervals, the interval with the largest upper limit value in the standard consumption intervals is the interval we need, and the consumption amount corresponding to the largest consumption point in it is the consumption upper limit value that the user can accept.

[0021] Referring to Figure 4 As shown, based on the data analysis terminal, classifying the user's historical shopping information by taking the number of product purchases as a feature, and determining the frequently purchased product set and the purchase time set corresponding to the frequently purchased product set specifically include the following steps: S2061. Based on the data analysis terminal, perform a product count process on the user's historical shopping information to obtain the number of purchases of different types of products; It can be understood that users will frequently purchase some products to maintain normal life, and these frequently purchased products are good products for order aggregation when users shop; S2062. Based on the data analysis terminal, compare and judge the number of purchases of different types of products with the set product purchase threshold; S2063. If the number of purchases of different types of products is less than the set product purchase threshold, the number of purchases of this product does not meet the frequently purchased product standard, and the number of purchases of this type of product is discarded; S2064. If the number of purchases of different types of products is greater than or equal to the set product purchase threshold, the number of purchases of this product meets the frequently purchased product standard, and perform a collection process on the products corresponding to the frequently purchased product standard to obtain the frequently purchased product set; S2065. Based on the data analysis terminal, calculate the shopping time in the user's historical shopping information by taking the products in the frequently purchased product set as features, and determine the purchase time set, where the purchase time set is specifically the purchase time interval of each product in the frequently purchased product set; In this embodiment, users may purchase the same products online at regular intervals (i.e., the frequently purchased product set), such as tissues, oil, salt, soy sauce, and vinegar. In order to enable users to purchase more products without exceeding the user consumption limit value, it is necessary to analyze the consumption amount. Therefore, order aggregation is involved. The products frequently purchased by users are excellent order aggregation products. Therefore, by judging the number of purchased products in the user's historical shopping information, the products frequently purchased by users are determined. In addition, users purchase frequently purchased products at regular time intervals. For example, the time for a user to consume a bottle of soy sauce is fixed (i.e., the purchase time interval for each product in the frequently purchased product set). In order to make the order aggregation products more to the user's liking, it is necessary to know the purchase time interval for each product in the frequently purchased product set. When order aggregation is required, it is possible to determine which frequently purchased products the user is about to run out of and combine them into the user's purchase list.

[0022] Refer to Figure 5 As shown, based on the data analysis terminal, the preferential analysis of the user's shopping cart information is carried out, and the specific steps for determining the preferential product combination information are as follows: S301. Based on the data analysis terminal, perform an intersection process on the preferential information of all products in the user's shopping cart information to determine the products with the same preferential information; S302. Based on the data analysis terminal, combine the products with the same preferential information to determine the preferential product combination information, and the number of the preferential product combination information is at least one; Among them, the specific calculation formula for performing an intersection process on the preferential information of all products in the user's shopping cart information is: ; In the formula, the are the products with the same preferential information; the is the preferential information of a certain product in the user's shopping cart information; the is the preferential information of the products in the user's shopping cart information excluding the products corresponding to ; i is the specific number of products with the same preferential information; j is the number of all products in the user's shopping cart information; k = j - 1; the ; In this embodiment, different products may be able to use the same coupon, or may not be able to use the same coupon. Therefore, a matching analysis is performed on the preferential information of all products in the user's shopping cart information to determine the products that can be combined and used preferentially.

[0023] Refer to Figure 6As shown, based on the data analysis terminal, the preferential product combination information and the user's consumption upper limit value are judged and processed to determine the set of preferential products that meet the standards, which specifically includes the following steps: S401. Based on the data analysis terminal, perform amount calculation processing on the preferential product combination information to obtain the amount spent on the preferential product combination, and the number of the amounts spent on the preferential product combination is at least one; It can be understood that although some product combinations can meet the usage conditions of the coupon, their consumption amount may exceed the user's psychological expectation. Therefore, it is necessary to screen the amount spent on the preferential product combination to determine the preferential product combination information that meets the user's psychological expectation; S402. Based on the data analysis terminal, judge and process the amount spent on the preferential product combination and the user's consumption upper limit value; S403. If the amount spent on the preferential product combination is greater than the user's consumption upper limit value, the amount spent on the preferential product combination does not meet the user's shopping consumption standard, and discard the preferential product combination information corresponding to the amount spent on the preferential product combination; S404. If the amount spent on the preferential product combination is equal to the user's consumption upper limit value, the amount spent on the preferential product combination meets the user's shopping consumption standard, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the best preferential product combination and generate order information to be sent to the user's electronic device; S405. If the amount spent on the preferential product combination is less than the user's consumption upper limit value, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the set of preferential products that meet the standards; In this embodiment, the amount spent on some preferential product combinations may exceed the user's consumption upper limit value. In order to enable the user to place an order to purchase products, the preferential product combinations that exceed the user's consumption upper limit value are excluded, and the preferential product combinations that meet the user's consumption upper limit value are left. Because when the price of some products meets the user's psychological expectation, the user will have the desire to place an order. Therefore, the preferential product combination information is screened by the user's consumption upper limit value.

[0024] Refer to Figure 7 As shown, based on the data analysis terminal, perform product supplementation processing on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products to determine the best preferential product combination, which specifically includes the following steps: S501. Based on the data analysis terminal, perform a difference calculation on the amount spent corresponding to the set of preferential products that meet the standards and the user's consumption upper limit value to obtain the amount to be supplemented; S502. Based on the data analysis terminal, perform matching processing on the amount of each product in the set of frequently purchased products with the amount to be supplemented as a feature to determine the set of frequently purchased products that meet the amount standard; It is understandable that the products that users frequently purchase are the best products to complete the order. Therefore, the products in the frequently purchased product set are filtered by the amount to be replenished to obtain the frequently purchased products that do not exceed the user's consumption upper limit. S503, based on the data analysis terminal, selecting products from the frequently purchased product set that meets the amount standard based on the purchase time set corresponding to the frequently purchased product set as a feature, and determining the best supplementary product; S504, based on the data analysis terminal, adding the best supplementary product to the preferential product set that meets the standard, determining the best preferential product combination, and generating order information for the best preferential product combination and sending it to the user's electronic device; In this embodiment, the consumption amount corresponding to some preferential product combination information is still a little short of the user's consumption upper limit. In order to make the user spend more money to buy products, some preferential product combination information is supplemented with products so that the amount spent on the supplemented preferential product combination information is closer to the user's consumption upper limit. However, not all supplemented products meet the user's wishes. For example, the user just bought a bottle of soy sauce a few days ago, and then the supplementary product is also a bottle of soy sauce, which may cause the user to not want to buy it. Therefore, the above frequently purchased product set is introduced, and the purchase time set corresponding to the frequently purchased product set is analyzed to determine the products that the user will use recently, set them as supplementary products, and increase the user's desire to buy.

[0025] Reference Figure 8 As shown, based on the data analysis terminal, the frequently purchased product set that meets the amount standard is selected based on the purchase time set corresponding to the frequently purchased product set as a feature, and the optimal supplementary product is determined, which specifically includes the following steps: S5031. Obtain real-time time information; S5032. Based on the data analysis terminal, extract and process the user's historical shopping information to obtain the user's last shopping time; S5033. Based on the data analysis terminal, calculate the difference between the real-time information and the user's last shopping time to obtain the shopping time interval; S5034. Based on the data analysis terminal, data screening is performed on the purchase time set corresponding to the frequently purchased product set by taking each product in the frequently purchased product set that meets the monetary standard as a feature to obtain the purchase time interval of the products that meet the monetary standard. S5035. Based on the data analysis terminal, determine and process the shopping time interval and the time interval for purchasing products that meet the amount standard; S5036. If the shopping time interval is less than the product purchase time interval that meets the amount standard, and the frequently purchased products by the user have not been used up, set the set of preferential products that meet the standard as the best preferential product combination, and generate order information for the best preferential product combination and send it to the user's electronic device; S5037. If the shopping time interval is greater than or equal to the product purchase time interval that meets the amount standard, set the product corresponding to the largest product purchase time interval in the product purchase time intervals that meet the amount standard as the best supplementary product; In this embodiment, the products for order aggregation should be selected from the set of frequently purchased products. However, products that meet the user's preference need to be chosen. For example, if the user just bought tissues the day before yesterday, the product for order aggregation today should not be tissues. Therefore, it is necessary to select according to the time interval of the products purchased by the user, determine the products that the user will soon run out of or use the most, and set them as the best supplementary products.

[0026] Refer to Figure 9 As shown in the figure, an order automatic generation system based on information analysis is used to implement an order automatic generation method based on information analysis as described above, including: A data analysis terminal, which is used to perform type analysis, preferential analysis, and product analysis on user shopping-related information to determine the best preferential product combination; A user shopping APP, which is used to store user shopping cart information and user historical shopping information, and is used to implement the user's online shopping; Among them, the following are integrated inside the data analysis terminal: A central control module, which is used to control data transmission and information interaction between each module; A data reading module, which is used to read data from the user shopping APP; A classification module, which classifies and processes user historical shopping information based on payment information; A consumption upper limit value determination module, which is used to perform dispersion analysis, consumption point screening, and consumption point judgment on several groups of user historical shopping consumption points to determine the user's consumption upper limit value; A frequently purchased product determination module, which is used to perform product purchase times counting processing and purchase times judgment processing on user historical shopping information to determine the set of frequently purchased products and the corresponding purchase time set of the set of frequently purchased products; A preferential analysis module, which is used to perform preferential analysis on user shopping cart information to determine preferential product combination information; A consumption amount comparison module, which is used to judge and process the preferential product combination information and the user's consumption upper limit value to determine a set of preferential products that meet the standards; A product selection module, which is used to select products from the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products to determine the best preferential product combination.

[0027] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An order automatic generation method based on information analysis, characterized in that, Including: Obtain user shopping-related information, where the user shopping-related information is obtained from the user's shopping APP, and the user shopping-related information includes user shopping cart information and user historical shopping information; Based on a data analysis terminal, analyze and process the user historical shopping information to determine user consumption characteristic information, where the user consumption characteristic information includes the user's consumption upper limit value, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products; Based on a data analysis terminal, conduct a preferential analysis on the user shopping cart information to determine preferential product combination information; Based on a data analysis terminal, judge and process the preferential product combination information and the user's consumption upper limit value to determine a set of preferential products that meet the standards; Based on a data analysis terminal, conduct product supplementation processing on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase times corresponding to the set of frequently purchased products to determine the best preferential product combination.

2. The automatic order generation method based on information analysis according to claim 1, wherein The step of analyzing and processing the user historical shopping information based on a data analysis terminal to determine the user consumption characteristic information specifically includes the following steps: Based on a data analysis terminal, classify the user historical shopping information with payment information as a feature to obtain several groups of user historical shopping consumption information; Based on a data analysis terminal, plot discrete points of several groups of user historical shopping consumption information in a two-dimensional rectangular coordinate system to obtain several groups of user historical shopping consumption points. The X-axis parameter of the two-dimensional rectangular coordinate system is the consumption date, and the Y-axis parameter of the two-dimensional rectangular coordinate system is the consumption amount; Based on a data analysis terminal, conduct a dispersion analysis on several groups of user historical shopping consumption points to determine the user historical shopping consumption standard line; Based on a data analysis terminal, screen several groups of user historical shopping consumption points with the user historical shopping consumption standard line as a feature to obtain multiple groups of consumption points above the user historical shopping consumption standard line. The step of screening several groups of user historical shopping consumption points specifically is to screen out the user historical shopping consumption points above the user historical shopping consumption standard line; Based on a data analysis terminal, judge and process multiple groups of consumption points above the user historical shopping consumption standard line to determine the user's consumption upper limit value; Based on a data analysis terminal, classify the user historical shopping information with the number of product purchases as a feature to determine the set of frequently purchased products and the set of purchase times corresponding to the set of frequently purchased products.

3. The automatic order generation method based on information analysis according to claim 2, wherein The step of judging and processing multiple groups of consumption points above the user historical shopping consumption standard line based on a data analysis terminal to determine the user's consumption upper limit value specifically includes the following steps: Based on a data analysis terminal, merge multiple groups of consumption points above the user historical shopping consumption standard line with a preset consumption amount interval as a feature to obtain several groups of consumption intervals above the user historical shopping consumption standard line; Based on a data analysis terminal, count the consumption points inside several groups of consumption intervals above the user historical shopping consumption standard line to obtain the number of consumption points inside different consumption intervals; Based on the data analysis terminal, compare and judge the number of consumption points within different consumption ranges with the set threshold of the number of consumption points. If the number of consumption points within different consumption ranges is less than the set threshold of the number of consumption points, this consumption range does not meet the user's consumption standard. If the number of consumption points within different consumption ranges is greater than or equal to the set threshold of the number of consumption points, record this consumption range and set it as the standard consumption range, and the number of the standard consumption ranges is at least one. Based on the data analysis terminal, perform data reading and processing on the standard consumption ranges to determine the user's consumption upper limit. If the number of standard consumption ranges is one, set the consumption amount corresponding to the maximum consumption point in the standard consumption range as the user's consumption upper limit value. If the number of standard consumption ranges is greater than one, set the consumption amount corresponding to the maximum consumption point in the standard consumption range with the largest upper limit value as the user's consumption upper limit value.

4. The order automatic generation method based on information analysis according to claim 2, wherein The above-mentioned data analysis terminal classifies the user's historical shopping information based on the number of product purchases as a feature, and determines the frequently purchased product set and the corresponding purchase time set, which specifically includes the following steps: Based on the data analysis terminal, perform product count processing on the user's historical shopping information to obtain the number of purchases of different types of products. Based on the data analysis terminal, compare and judge the number of purchases of different types of products with the set threshold of the number of product purchases. If the number of purchases of different types of products is less than the set threshold of the number of product purchases, the number of purchases of this product does not meet the frequently purchased product standard, and the number of purchases of this type of product is discarded. If the number of purchases of different types of products is greater than or equal to the set threshold of the number of product purchases, the number of purchases of this product meets the frequently purchased product standard, and perform a combined processing on the products that meet the frequently purchased product standard to obtain the frequently purchased product set. Based on the data analysis terminal, calculate the shopping time in the user's historical shopping information with the products in the frequently purchased product set as features, and determine the purchase time set, and the purchase time set is specifically the purchase time interval of each product in the frequently purchased product set.

5. The automatic order generation method based on information analysis according to claim 1, characterized in that The above-mentioned data analysis terminal conducts preferential analysis on the user's shopping cart information to determine the preferential product combination information, which specifically includes the following steps: Based on the data analysis terminal, perform an intersection process on the preferential information of all products in the user's shopping cart information to determine the products with the same preferential information. Based on the data analysis terminal, combine the products with the same preferential information to determine the preferential product combination information, and the number of the preferential product combination information is at least one. Among them, the specific calculation formula for performing an intersection process on the preferential information of all products in the user's shopping cart information is: ； In the formula, the are products with the same preferential information; the is the preferential information of a certain product in the user's shopping cart information; the is the preferential information of the products in the user's shopping cart information that do not include the corresponding products; the i is the specific quantity of the products with the same preferential information; the j is the quantity of all products in the user's shopping cart information; the k = j - 1; the .

6. The automatic order generation method based on information analysis according to claim 1, wherein The above-mentioned data analysis terminal conducts judgment processing on the preferential product combination information and the user's consumption upper limit value to determine the qualified preferential product set, which specifically includes the following steps: Based on the data analysis terminal, perform amount calculation processing on the preferential product combination information to obtain the preferential product combination spending amount, and the number of the preferential product combination spending amount is at least one. Based on the data analysis terminal, perform judgment processing on the amount spent on the preferential product combination and the user's consumption limit value; If the amount spent on the preferential product combination is greater than the user's consumption limit value, the amount spent on the preferential product combination does not meet the user's shopping consumption standard, and discard the preferential product combination information corresponding to the amount spent on the preferential product combination; If the amount spent on the preferential product combination is equal to the user's consumption limit value, the amount spent on the preferential product combination meets the user's shopping consumption standard, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the best preferential product combination and generate order information to be sent to the user's electronic device; If the amount spent on the preferential product combination is less than the user's consumption limit value, set the preferential product combination information corresponding to the amount spent on the preferential product combination as the set of preferential products that meet the standards.

7. A method for automatically generating an order based on information analysis according to claim 1, characterized in that The above-mentioned based on the data analysis terminal, perform product supplementation processing on the set of preferential products that meet the standards, the set of frequently purchased products, and the set of purchase time corresponding to the set of frequently purchased products, and determine the best preferential product combination, which specifically includes the following steps: Based on the data analysis terminal, perform a difference calculation on the amount spent corresponding to the set of preferential products that meet the standards and the user's consumption limit value to obtain the amount to be supplemented; Based on the data analysis terminal, perform a matching process on the amount of each product in the set of frequently purchased products with the amount to be supplemented as a feature to determine the set of frequently purchased products that meet the amount standard; Based on the data analysis terminal, perform product selection processing on the set of frequently purchased products that meet the amount standard with the set of purchase time corresponding to the set of frequently purchased products as a feature to determine the best supplementary products; Based on the data analysis terminal, fill the best supplementary products into the set of preferential products that meet the standards to determine the best preferential product combination, and generate order information for the best preferential product combination to be sent to the user's electronic device.

8. The automatic order generation method based on information analysis according to claim 1, characterized in that The above-mentioned based on the data analysis terminal, perform product selection processing on the set of frequently purchased products that meet the amount standard with the set of purchase time corresponding to the set of frequently purchased products as a feature to determine the best supplementary products, which specifically includes the following steps: Obtain real-time time information; Based on the data analysis terminal, perform data extraction processing on the user's historical shopping information to obtain the user's last shopping time; Based on the data analysis terminal, perform a difference calculation on the real-time time information and the user's last shopping time to obtain the shopping time interval; Based on the data analysis terminal, perform data screening processing on the set of purchase time corresponding to the set of frequently purchased products with each product in the set of frequently purchased products that meet the amount standard as a feature to obtain the product purchase time interval that meets the amount standard; Based on the data analysis terminal, perform judgment processing on the shopping time interval and the product purchase time interval that meets the amount standard; If the shopping time interval is less than the product purchase time interval that meets the amount standard, the products that the user frequently purchases have not been used up, set the set of preferential products that meet the standards as the best preferential product combination, and generate order information for the best preferential product combination to be sent to the user's electronic device; If the shopping time interval is greater than or equal to the product purchase time interval that meets the amount standard, the product corresponding to the largest product purchase time interval in the product purchase time intervals that meet the amount standard is set as the best supplementary product.

9. An order automatic generation system based on information analysis, which is used to implement an order automatic generation method based on information analysis as described in any one of claims 1-8, characterized in that, Including: A data analysis terminal, which is used to perform type analysis, preferential analysis, and product analysis on user shopping-related information to determine the best preferential product combination; A user shopping APP, which is used to store user shopping cart information and user historical shopping information, and the user shopping APP is used to realize the user's online shopping; Among them, the following are integrated inside the data analysis terminal: A central control module, which is used to control data transmission and information interaction between each module; A data reading module, which is used to read data from the user shopping APP; A classification module, which classifies and processes user historical shopping information based on payment information; A consumption upper limit value determination module, which is used to perform dispersion analysis, consumption point screening, and consumption point judgment on several groups of user historical shopping consumption points to determine the user consumption upper limit value; A frequently purchased product determination module, which is used to perform product purchase times counting processing and purchase times judgment processing on user historical shopping information to determine the frequently purchased product set and the purchase time set corresponding to the frequently purchased product set; A preferential analysis module, which is used to perform preferential analysis on user shopping cart information to determine preferential product combination information; A consumption amount comparison module, which is used to judge and process the preferential product combination information and the user consumption upper limit value to determine the set of preferential products that meet the standards; A product selection module, which is used to select products from the set of preferential products that meet the standards, the frequently purchased product set, and the purchase time set corresponding to the frequently purchased product set to determine the best preferential product combination.

10. A storage medium, characterized in that, A computer program is stored thereon, and when the computer program is called and run, it executes a method for automatically generating an order based on information analysis as described in any one of claims 1-8.

Images