Online sales service method based on clothing pattern design

Abstract

The invention relates to the technical field of online sales service, and discloses an online sales service method based on clothing pattern design, which comprises the following steps: a customer inputs body data; obtaining a target garment purchased by the customer and the type thereof; analyzing all historical evaluation records of the customer, and judging whether a good evaluation record the same as the target garment type is included or not; if so, calculating an average value of various data in the favorable comment record according to a first strategy, and recommending the most suitable size; if not, judging whether the customer opens the historical browsing record or not. If not, screening out a target population similar to the customer body data, analyzing a good reputation record of the target population, and recommending a size; and if open, selecting a target size according to a data change trend by analyzing a historical browsing record of the customer. According to the method, accurate size recommendation is realized by comprehensively analyzing customer body data, historical evaluation records and browsing behaviors.

Description

Technical Field

[0001] The present invention relates to the technical field of online sales services, and in particular to an online sales service method based on clothing pattern design. Background Art

[0002] With the development of Internet technology, online shopping has become an indispensable part of people's daily life, especially in the field of clothing purchase. However, due to the lack of actual try-on experience, consumers face many challenges in choosing the right size, which often leads to a high return rate, affecting consumers' shopping experience and merchants' operating efficiency.

[0003] Traditional online clothing size recommendation systems are usually based on simple body data matching methods, but this method has certain limitations. First, the clothing patterns of different brands and styles vary greatly, and it is difficult to accurately recommend the right size based on basic body data alone. Many online platforms have accumulated a large amount of user data, including historical purchase records, evaluation records, and browsing records. However, traditional recommendation methods often fail to make full use of this data, resulting in a waste of data resources and limited recommendation effects.

[0004] In summary, the existing online clothing size recommendation technology has many shortcomings in terms of accuracy, personalization and data utilization. There is an urgent need for an online sales service method based on clothing pattern design to improve consumers' shopping experience and merchants' operational efficiency. Summary of the invention

[0005] The present invention provides an online sales service method based on clothing pattern design, which promotes solving the problems mentioned in the above background technology.

[0006] The present invention provides the following technical solution: an online sales service method based on clothing pattern design, comprising:

[0007] The customer enters physical data;

[0008] The physical data include waist circumference, hip circumference, thigh circumference, leg length, chest circumference, shoulder width, height and weight;

[0009] Get the clothing purchased by the customer this time and record it as the target clothing;

[0010] Get the type of clothing purchased by the customer this time, and record it as the target clothing type;

[0011] Get all historical evaluation records of customers;

[0012] Determine whether all historical evaluation records of the customer contain favorable evaluation records of clothing of the same type as the target clothing;

[0013] If all the historical evaluation records of the customer include favorable reviews of clothing of the same type as the target clothing, then the size recommendation is made to the customer according to the first strategy;

[0014] If all the historical evaluation records of the customer do not contain positive evaluation records of clothing of the same type as the target clothing;

[0015] Send a request to the customer to open browsing history;

[0016] If the customer does not open the browsing history, the size recommendation is made to the customer according to the second strategy;

[0017] If the customer opens the historical browsing history, size recommendations are made to the customer based on the third strategy.

[0018] Optionally, the step of determining whether all historical evaluation records of the customer contain favorable evaluation records of clothing of the same type as the target clothing specifically includes:

[0019] Filter all historical evaluation records of customers, specifically:

[0020] All historical evaluation records of customers constitute the first set;

[0021] For each historical evaluation record of the customer;

[0022] Get the product category corresponding to each historical evaluation record;

[0023] In the first set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a second set;

[0024] Set scoring thresholds;

[0025] For each historical evaluation record in the second set;

[0026] Get the ratings of historical evaluation records;

[0027] The historical evaluation records with a score ≥ the score threshold are considered as good reviews;

[0028] The historical evaluation records with a score lower than the score threshold are considered as negative reviews;

[0029] Get the number of positive reviews in the second set;

[0030] If the number of favorable reviews in the second set is 0, it is determined that all historical evaluation records of the customer do not contain favorable reviews for clothing of the same type as the target clothing;

[0031] If the number of favorable comments in the second set is not 0, it is determined that all historical evaluation records of the customer include favorable comment records of clothing of the same type as the target clothing.

[0032] Optionally, if all the historical evaluation records of the customer include favorable evaluation records of clothing of the same type as the target clothing, size recommendations are made to the customer according to the first strategy, specifically including:

[0033] Obtain favorable comments of clothing of the same type as the target clothing from all historical evaluation records of customers;

[0034] For each favorable review record;

[0035] Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record;

[0036] Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference;

[0037] Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference;

[0038] Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference;

[0039] Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length;

[0040] Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference;

[0041] Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width;

[0042] Get the size chart of the target garment;

[0043] Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width;

[0044] Calculate the sum of the differences;

[0045] Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size;

[0046] The target size is recommended as the customer's purchase size.

[0047] Optionally, if the customer does not open the historical browsing history, recommending sizes to the customer according to the second strategy specifically includes:

[0048] Set the control accuracy;

[0049] The group of people whose physical data deviations from those of customers are less than the control accuracy are recorded as the target group;

[0050] Obtain evaluation records of the target population;

[0051] Screen the evaluation records of the target population, specifically:

[0052] All historical evaluation records of the target population constitute the third set;

[0053] Each historical evaluation record for the target population;

[0054] Get the product category corresponding to each historical evaluation record;

[0055] In the third set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a fourth set;

[0056] Set scoring thresholds;

[0057] For each historical evaluation record in the fourth set;

[0058] Get the ratings of historical evaluation records;

[0059] The historical evaluation records with a score ≥ the score threshold are considered as good reviews;

[0060] Historical evaluation records with a score lower than the score threshold are considered negative reviews.

[0061] Optionally, if the customer does not open the historical browsing history, recommending sizes to the customer according to the second strategy also includes:

[0062] For each favorable review record in the fourth set;

[0063] Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record;

[0064] Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference;

[0065] Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference;

[0066] Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference;

[0067] Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length;

[0068] Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference;

[0069] Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width;

[0070] Get the size chart of the target garment;

[0071] Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width;

[0072] Calculate the sum of the differences;

[0073] Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size;

[0074] The target size is recommended as the customer's purchase size.

[0075] Optionally, if the customer opens the historical browsing record, size recommendation is made to the customer according to the third strategy, specifically including:

[0076] Obtain the customer's browsing history;

[0077] Filter the customer's browsing history, specifically:

[0078] All historical browsing records of customers constitute the fifth set;

[0079] For each historical browsing record of the customer;

[0080] Get the product category corresponding to each historical browsing record;

[0081] In the fifth set, the historical browsing records of the corresponding commodity categories that are the same as the target clothing category are retained to form a sixth set;

[0082] Get the time when the customer last purchased clothing of the target clothing category;

[0083] In the sixth set, historical browsing records whose appearance time is later than the time when the customer last purchased clothing of the target clothing category are retained to form a seventh set.

[0084] Optionally, if the customer opens the historical browsing record, recommending sizes to the customer according to the third strategy also includes:

[0085] Obtain all historical browsing records in the seventh set, and sort them in order of appearance time from earliest to latest, recording them as the first record, the second record, ... the Nth record respectively;

[0086] If the body data of the clothing corresponding to the first record, the second record, ... the Nth record increases in sequence;

[0087] Obtain a size in the target clothing size table whose various body data are greater than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size;

[0088] Recommend target size as the customer's purchase size;

[0089] If the body data of the clothing corresponding to the first record, the second record, ... the Nth record decreases in sequence;

[0090] Obtain a size in the target clothing size table whose various body data are all smaller than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size;

[0091] The target size is recommended as the customer's purchase size.

[0092] Optionally, if the customer opens the historical browsing record, recommending sizes to the customer according to the third strategy also includes:

[0093] If the various body data of the clothing corresponding to the first record, the second record ... the N-1th record increase in sequence, the various body data of the clothing corresponding to the Nth record are less than the various body data of the clothing corresponding to the N-1th record;

[0094] Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the Nth record and less than the body data of the clothing corresponding to the N-1th record, and record it as the target size;

[0095] Recommend target size as the customer's purchase size;

[0096] If the various body data of the clothing corresponding to the first record, the second record, ... the N-1th record decreases in sequence, the various body data of the clothing corresponding to the Nth record is greater than the various body data of the clothing corresponding to the N-1th record;

[0097] Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the N-1th record and less than the body data of the clothing corresponding to the Nth record, and record it as the target size;

[0098] The target size is recommended as the customer's purchase size.

[0099] The present invention has the following beneficial effects:

[0100] 1. An online sales service method based on clothing pattern design, inputting body data enables the online clothing sales service to provide personalized size recommendations for customers. The advantage of this process is that it can accurately reflect the customer's physical characteristics, thereby significantly improving the fit and comfort of clothing. Accurate size recommendations not only reduce the return rate due to inappropriate sizes, but also improve customer satisfaction, enhance brand reputation and customer loyalty. In addition, personalized recommendations can also help merchants optimize inventory management, because customer needs and preferences can be more accurately reflected in sales data.

[0101] 2. This online sales service method based on clothing pattern design can effectively analyze customers' size needs by judging their historical evaluation records. The advantage of this link is that it provides merchants with valuable customer feedback data, allowing merchants to better understand customers' clothing size preferences. If a customer has previously given a positive review of a certain size of clothing, the merchant can make more targeted size recommendations based on this data, thereby improving the purchase conversion rate.

[0102] 3. This online sales service method based on clothing pattern design sends a request to customers to open their browsing history, which is a way to respect customer privacy and also provides more data support for merchants. If customers choose to open these records, merchants can better analyze their shopping behaviors and preferences. The advantage of this link is that it not only increases customers' trust in the platform and improves user experience, but also provides merchants with more accurate recommendation basis.

[0103] 4. This online sales service method based on clothing pattern design recommends sizes according to different strategies, which can maximize the accuracy of recommendations. The advantage of this process is that merchants can flexibly adjust the recommendation method according to the specific circumstances of different customers to ensure that the recommendation results match the actual needs of customers. Through this dynamic recommendation mechanism, merchants can significantly improve customers' shopping experience and reduce returns and exchanges due to inappropriate sizes. In addition, accurate recommendations can also help improve customers' shopping satisfaction, thereby promoting an increase in repurchase rates.

[0104] 5. This online sales service method based on clothing pattern design analyzes and screens data for target groups, which helps merchants build more accurate customer portraits. The advantage of this link is that by analyzing the purchase records of people with similar body data to the customer, and screening out the favorable records of the target clothing types from the purchase records of people with similar body data to the customer, the merchant can better provide size recommendations to customers, improve the accuracy of size recommendations, and thus improve customers' willingness to buy and satisfaction.

[0105] 6. This online sales service method based on clothing pattern design can effectively improve the quality and accuracy of recommendations by screening the historical evaluation records of the target population, especially focusing on the positive reviews. The advantage of this process is that it ensures that the basis for recommendations is based on real customer feedback, thereby avoiding misleading information caused by single or negative reviews. By screening out products with excellent performance, merchants can more confidently recommend suitable sizes to customers and enhance customers' confidence in purchasing decisions.

[0106] 7. This online sales service method based on clothing pattern design uses customers' historical browsing records for analysis, which can help merchants better understand customers' shopping preferences. The advantage of this process is that it not only reveals customers' potential needs, but also optimizes size recommendations based on these needs. This recommendation strategy based on behavioral data helps merchants stand out in the fierce market competition and improve user experience and satisfaction. In addition, customers' browsing behavior reflects their purchasing intentions. Through in-depth analysis of these data, merchants can respond faster and enhance brand flexibility.

[0107] 8. This is an online sales service method based on clothing pattern design. When dynamically comparing the customer's historical browsing records, by comparing the changes in body data of the corresponding clothing in different records, the merchant can recommend a more suitable size for the customer. The advantage of this link is that it provides customers with more personalized and accurate size selection based on the changing trend of data, reducing the customer's trial and error costs. Dynamic comparison can not only improve customer shopping satisfaction, but also effectively reduce the return and exchange rate caused by improper size selection, and optimize the merchant's operating efficiency.

[0108] 9. This is an online sales service method based on clothing pattern design. The control accuracy is set to ensure the accuracy of the recommendation. The advantage of this link is that it can minimize the recommendation error. Through refined data analysis, merchants can target people with smaller body data differences from customers, thereby providing size recommendations that better meet customer needs. This precise recommendation can effectively improve the customer's purchasing experience and increase conversion rate.

[0109] 10. In an online sales service method based on clothing pattern design, if the various body data of the clothing corresponding to the first record to the Nth record increase successively, the merchant can infer the customer's preference for large-size clothing; if the body data of the clothing corresponding to the first record to the Nth record decreases successively, the merchant can also infer the customer's preference for small-size clothing; if the various body data of the clothing corresponding to the first record to the Nth record increases first and then decreases, the merchant recommends by obtaining the size of the target size table whose various body data is greater than the Nth record and less than the N-1th record; if the various body data of the clothing corresponding to the first record to the Nth record decreases first and then increases, the merchant recommends by obtaining the size of the target size table whose various body data is greater than the Nth record and less than the N-1th record; through the analysis and recommendation of the above multiple steps, the merchant can form a set of flexible dynamic recommendation strategies. The advantage of this strategy is that it can continuously optimize the size recommendation process according to the real-time behavior and historical data of the customer. The merchant can not only respond quickly to changes in customer needs, but also continuously adjust the recommendation strategy through data analysis to improve the intelligence level of the service. This flexibility not only enhances customers' shopping experience, but also improves merchants' market competitiveness, enabling them to remain dynamic and attractive in a rapidly changing market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0111] 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.

[0112] Example, see Figure 1 , an online sales service method based on clothing pattern design, comprising:

[0113] The customer enters physical data;

[0114] Entering body data allows online clothing sales services to provide customers with personalized size recommendations. The advantage of this process is that it can accurately reflect the customer's physical characteristics, thereby significantly improving the fit and comfort of clothing. Accurate size recommendations not only reduce the return rate due to inappropriate sizes, but also improve customer satisfaction, enhance brand reputation and customer loyalty. In addition, personalized recommendations can also help merchants optimize inventory management, because customer needs and preferences can be more accurately reflected in sales data;

[0115] The physical data include waist circumference, hip circumference, thigh circumference, leg length, chest circumference, shoulder width, height and weight;

[0116] Get the clothing purchased by the customer this time and record it as the target clothing;

[0117] Get the type of clothing purchased by the customer this time, and record it as the target clothing type;

[0118] Get all historical evaluation records of customers;

[0119] Determine whether all historical evaluation records of the customer contain favorable evaluation records of clothing of the same type as the target clothing;

[0120] If all the historical evaluation records of the customer include favorable reviews of clothing of the same type as the target clothing, then the size recommendation is made to the customer according to the first strategy;

[0121] If all the historical evaluation records of the customer do not contain positive evaluation records of clothing of the same type as the target clothing;

[0122] Send a request to the customer to open browsing history;

[0123] If the customer does not open the browsing history, the size recommendation is made to the customer according to the second strategy;

[0124] If the customer opens the historical browsing history, size recommendations are made to the customer based on the third strategy;

[0125] Sending customers a request to open their browsing history is a way to respect their privacy and also provides more data support for merchants. If customers choose to open these records, merchants can better analyze their shopping behaviors and preferences. The advantage of this link is that it not only increases customers' trust in the platform and improves user experience, but also provides merchants with more accurate recommendation basis;

[0126] By making size recommendations based on different strategies, the accuracy of recommendations can be maximized. The advantage of this process is that merchants can flexibly adjust the recommendation method according to the specific circumstances of different customers to ensure that the recommendation results match the actual needs of customers. Through this dynamic recommendation mechanism, merchants can significantly improve the customer's shopping experience and reduce returns and exchanges due to inappropriate sizes. In addition, accurate recommendations can also help improve customer shopping satisfaction, thereby promoting an increase in repurchase rates.

[0127] The step of judging whether all the historical evaluation records of the customer contain favorable comments on clothing of the same type as the target clothing specifically includes:

[0128] Filter all historical evaluation records of customers, specifically:

[0129] All historical evaluation records of customers constitute the first set;

[0130] For each historical evaluation record of the customer;

[0131] Get the product category corresponding to each historical evaluation record;

[0132] In the first set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a second set;

[0133] Set scoring thresholds;

[0134] For each historical evaluation record in the second set;

[0135] Get the ratings of historical evaluation records;

[0136] The historical evaluation records with a score ≥ the score threshold are considered as good reviews;

[0137] The historical evaluation records with a score lower than the score threshold are considered as negative reviews;

[0138] Get the number of positive reviews in the second set;

[0139] If the number of favorable reviews in the second set is 0, it is determined that all historical evaluation records of the customer do not contain favorable reviews for clothing of the same type as the target clothing;

[0140] If the number of favorable comments in the second set is not 0, it is determined that all historical evaluation records of the customer include favorable comment records of clothing of the same type as the target clothing.

[0141] If all the historical evaluation records of the customer include favorable evaluation records of clothing of the same type as the target clothing, size recommendations are made to the customer according to the first strategy, specifically including:

[0142] Obtain favorable comments of clothing of the same type as the target clothing from all historical evaluation records of customers;

[0143] For each positive review record;

[0144] Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record;

[0145] Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference;

[0146] Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference;

[0147] Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference;

[0148] Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length;

[0149] Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference;

[0150] Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width;

[0151] Get the size chart of the target garment;

[0152] Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width;

[0153] Calculate the sum of the differences;

[0154] Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size;

[0155] Recommend target size as the customer's purchase size;

[0156] By judging the customer's historical evaluation records, the customer's size needs can be effectively analyzed. The advantage of this link is that it provides merchants with valuable customer feedback data, allowing merchants to better understand customers' clothing size preferences. If a customer has previously given a positive review of a certain size of clothing, the merchant can make more targeted size recommendations based on this data, thereby increasing the purchase conversion rate.

[0157] If the customer does not open the historical browsing history, the second strategy is used to recommend a size to the customer, specifically including:

[0158] Set the control accuracy;

[0159] The control accuracy is set to ensure the accuracy of the recommendation. The advantage of this link is that it can minimize the recommendation error. Through refined data analysis, merchants can target people whose body data is less different from that of customers, and thus provide size recommendations that better meet customer needs. This kind of accurate recommendation can effectively improve the customer's shopping experience and increase the conversion rate;

[0160] The group of people whose physical data deviations from those of customers are less than the control accuracy are recorded as the target group;

[0161] Data analysis and screening for target groups can help merchants build more accurate customer portraits. The advantage of this link is that by analyzing the purchase records of people with similar body data to the customer and screening out favorable records of target clothing categories from the purchase records of people with similar body data to the customer, merchants can better provide size recommendations to customers, improve the accuracy of size recommendations, and thus increase customer purchase intention and satisfaction;

[0162] Obtain evaluation records of the target population;

[0163] Screen the evaluation records of the target population, specifically:

[0164] All historical evaluation records of the target population constitute the third set;

[0165] Each historical evaluation record for the target population;

[0166] Get the product category corresponding to each historical evaluation record;

[0167] In the third set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a fourth set;

[0168] Set scoring thresholds;

[0169] For each historical evaluation record in the fourth set;

[0170] Get the ratings of historical evaluation records;

[0171] The historical evaluation records with a score ≥ the score threshold are considered as good reviews;

[0172] Historical evaluation records with a score lower than the score threshold are considered negative reviews.

[0173] If the customer does not open the historical browsing record, recommending the size to the customer according to the second strategy also includes:

[0174] For each favorable review record in the fourth set;

[0175] Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record;

[0176] Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference;

[0177] Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference;

[0178] Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference;

[0179] Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length;

[0180] Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference;

[0181] Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width;

[0182] Get the size chart of the target garment;

[0183] Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width;

[0184] Calculate the sum of the differences;

[0185] Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size;

[0186] Recommend target size as the customer's purchase size;

[0187] Screening the historical evaluation records of the target population, especially focusing on the positive reviews, can effectively improve the quality and accuracy of recommendations. The advantage of this process is that it ensures that the basis for recommendations is based on real customer feedback, thus avoiding misleading information caused by a single or negative review. By screening out products with excellent performance, merchants can more confidently recommend suitable sizes to customers, enhancing customers' confidence in purchasing decisions.

[0188] If the customer opens the historical browsing record, the size recommendation is made to the customer according to the third strategy, which specifically includes:

[0189] Obtain the customer's browsing history;

[0190] Filter the customer's browsing history, specifically:

[0191] All historical browsing records of customers constitute the fifth set;

[0192] For each historical browsing record of the customer;

[0193] Get the product category corresponding to each historical browsing record;

[0194] In the fifth set, the historical browsing records of the corresponding commodity categories that are the same as the target clothing category are retained to form a sixth set;

[0195] Get the time when the customer last purchased clothing of the target clothing category;

[0196] In the sixth set, historical browsing records whose appearance time is later than the time when the customer last purchased clothing of the target clothing category are retained to form a seventh set;

[0197] Analyzing customers' browsing history can help merchants better understand their shopping preferences. The advantage of this process is that it not only reveals customers' potential needs, but also optimizes size recommendations based on these needs. This recommendation strategy based on behavioral data helps merchants stand out in the fierce market competition and improve user experience and satisfaction. In addition, customers' browsing behavior reflects their purchasing intentions. Through in-depth analysis of these data, merchants can respond faster and enhance brand flexibility.

[0198] If the customer opens the historical browsing record, recommending the customer a size according to the third strategy also includes:

[0199] Obtain all historical browsing records in the seventh set, and sort them in order of appearance time from earliest to latest, recording them as the first record, the second record, ... the Nth record respectively;

[0200] When dynamically comparing customers' browsing history, merchants can recommend more suitable sizes to customers by comparing the changes in body data of corresponding clothing in different records. The advantage of this link is that it provides customers with more personalized and accurate size selection based on the changing trend of data, reducing customers' trial and error costs. Dynamic comparison can not only improve customers' shopping satisfaction, but also effectively reduce the return and exchange rate caused by improper size selection, and optimize merchants' operating efficiency;

[0201] If the body data of the clothing corresponding to the first record, the second record, ... the Nth record increases in sequence;

[0202] Obtain a size in the target clothing size table whose various body data are greater than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size;

[0203] Recommend target size as the customer's purchase size;

[0204] If the body data of the clothing corresponding to the first record, the second record, ... the Nth record decreases in sequence;

[0205] Obtain a size in the target clothing size table whose various body data are all smaller than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size;

[0206] The target size is recommended as the customer's purchase size.

[0207] If the customer opens the historical browsing record, recommending the customer a size according to the third strategy also includes:

[0208] If the various body data of the clothing corresponding to the first record, the second record ... the N-1th record increase in sequence, the various body data of the clothing corresponding to the Nth record are less than the various body data of the clothing corresponding to the N-1th record;

[0209] Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the Nth record and less than the body data of the clothing corresponding to the N-1th record, and record it as the target size;

[0210] Recommend target size as the customer's purchase size;

[0211] If the various body data of the clothing corresponding to the first record, the second record, ... the N-1th record decreases in sequence, the various body data of the clothing corresponding to the Nth record is greater than the various body data of the clothing corresponding to the N-1th record;

[0212] Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the N-1th record and less than the body data of the clothing corresponding to the Nth record, and record it as the target size;

[0213] Recommend target size as the customer's purchase size;

[0214] If the body data of the clothing corresponding to the first record to the Nth record increases successively, the merchant can infer the customer's preference for large-size clothing; if the body data of the clothing corresponding to the first record to the Nth record decreases successively, the merchant can also infer the customer's preference for small-size clothing; if the body data of the clothing corresponding to the first record to the Nth record increases first and then decreases, the merchant recommends by obtaining the size of the target size table whose body data is greater than the Nth record and less than the N-1th record; if the body data of the clothing corresponding to the first record to the Nth record decreases first and then increases, the merchant recommends by obtaining the size of the target size table whose body data is greater than the Nth record and less than the N-1th record; through the analysis and recommendation of the above multiple steps, the merchant can form a flexible dynamic recommendation strategy. The advantage of this strategy is that it can continuously optimize the size recommendation process based on the customer's real-time behavior and historical data. Merchants can not only respond quickly to changes in customer needs, but also continuously adjust recommendation strategies through data analysis to improve the intelligence level of services. This flexibility not only enhances the customer's shopping experience, but also improves the market competitiveness of merchants, allowing them to remain vibrant and attractive in a rapidly changing market environment.

[0215] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0216] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An online sales service method based on clothing pattern design, characterized in that: include: The customer enters physical data; The physical data include waist circumference, hip circumference, thigh circumference, leg length, chest circumference, shoulder width, height and weight; Get the clothing purchased by the customer this time and record it as the target clothing; Get the type of clothing purchased by the customer this time, and record it as the target clothing type; Get all historical evaluation records of customers; Determine whether all historical evaluation records of the customer contain favorable evaluation records of clothing of the same type as the target clothing; If all the historical evaluation records of the customer include favorable reviews of clothing of the same type as the target clothing, then the size recommendation is made to the customer according to the first strategy; If all the historical evaluation records of the customer do not contain positive evaluation records of clothing of the same type as the target clothing; Send a request to the customer to open browsing history; If the customer does not open the browsing history, the size recommendation is made to the customer according to the second strategy; If the customer opens the historical browsing history, size recommendations are made to the customer based on the third strategy.

2. The online sales service method based on clothing pattern design according to claim 1, characterized in that: The step of judging whether all the historical evaluation records of the customer contain favorable comments on clothing of the same type as the target clothing specifically includes: Filter all historical evaluation records of customers, specifically: All historical evaluation records of customers constitute the first set; For each historical evaluation record of the customer; Get the product category corresponding to each historical evaluation record; In the first set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a second set; Set scoring thresholds; For each historical evaluation record in the second set; Get the ratings of historical evaluation records; The historical evaluation records with a score ≥ the score threshold are considered as good reviews; The historical evaluation records with a score lower than the score threshold are considered as negative reviews; Get the number of positive reviews in the second set; If the number of favorable reviews in the second set is 0, it is determined that all historical evaluation records of the customer do not contain favorable reviews for clothing of the same type as the target clothing; If the number of favorable comments in the second set is not 0, it is determined that all historical evaluation records of the customer include favorable comment records of clothing of the same type as the target clothing.

3. The online sales service method based on clothing pattern design according to claim 1, characterized in that: If all the historical evaluation records of the customer include favorable evaluation records of clothing of the same type as the target clothing, size recommendations are made to the customer according to the first strategy, specifically including: Obtain favorable comments of clothing of the same type as the target clothing from all historical evaluation records of customers; For each favorable review record; Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record; Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference; Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference; Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference; Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length; Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference; Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width; Get the size chart of the target garment; Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width; Calculate the sum of the differences; Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size; The target size is recommended as the customer's purchase size.

4. The online sales service method based on clothing pattern design according to claim 1, characterized in that: If the customer does not open the historical browsing history, the second strategy is used to recommend a size to the customer, specifically including: Set the control accuracy; The group of people whose physical data deviations from those of customers are less than the control accuracy are recorded as the target group; Obtain historical evaluation records of the target population; Screen the historical evaluation records of the target population, specifically: All historical evaluation records of the target population constitute the third set; Each historical evaluation record for the target population; Get the product category corresponding to each historical evaluation record; In the third set, historical evaluation records of corresponding commodity categories that are the same as the target clothing category are retained to form a fourth set; Set scoring thresholds; For each historical evaluation record in the fourth set; Get the ratings of historical evaluation records; The historical evaluation records with a score ≥ the score threshold are considered as good reviews; Historical evaluation records with a score lower than the score threshold are considered negative reviews.

5. The online sales service method based on clothing pattern design according to claim 4, characterized in that: If the customer does not open the historical browsing record, recommending the size to the customer according to the second strategy also includes: For each favorable review record in the fourth set; Get the values ​​of waist circumference, hip circumference, thigh circumference, leg length, chest circumference and shoulder width of the clothing corresponding to the positive review record; Calculate the average waist circumference of the clothing corresponding to all favorable reviews, and record it as the average waist circumference; Calculate the average hip circumference of the clothing corresponding to all favorable reviews, and record it as the average hip circumference; Calculate the average thigh circumference of the clothing corresponding to all favorable reviews, and record it as the average thigh circumference; Calculate the average leg length of the clothing corresponding to all favorable reviews, and record it as the average leg length; Calculate the average chest circumference of the clothing corresponding to all favorable reviews, and record it as the average chest circumference; Calculate the average shoulder width of all the positive reviews and record it as the average shoulder width; Get the size chart of the target garment; Calculate the difference between the body data of each size in the size chart and the corresponding average waist circumference, average hip circumference, average thigh circumference, average leg length, average chest circumference and average shoulder width; Calculate the sum of the differences; Obtain the size with the smallest sum of the differences in the target clothing size table, and record it as the target size; The target size is recommended as the customer's purchase size.

6. The online sales service method based on clothing pattern design according to claim 1, characterized in that: If the customer opens the historical browsing record, the size recommendation is made to the customer according to the third strategy, which specifically includes: Obtain the customer's browsing history; Filter the customer's browsing history, specifically: All historical browsing records of customers constitute the fifth set; For each historical browsing record of the customer; Get the product category corresponding to each historical browsing record; In the fifth set, the historical browsing records of the corresponding commodity categories that are the same as the target clothing category are retained to form a sixth set; Get the time when the customer last purchased clothing of the target clothing category; In the sixth set, historical browsing records whose appearance time is later than the time when the customer last purchased clothing of the target clothing category are retained to form a seventh set.

7. The online sales service method based on clothing pattern design according to claim 6, characterized in that: If the customer opens the historical browsing record, recommending the customer a size according to the third strategy also includes: Obtain all historical browsing records in the seventh set, and sort them in order of appearance time from earliest to latest, recording them as the first record, the second record, ... the Nth record respectively; If the body data of the clothing corresponding to the first record, the second record, ... the Nth record increases in sequence; Obtain a size in the target clothing size table whose various body data are greater than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size; Recommend target size as the customer's purchase size; If the body data of the clothing corresponding to the first record, the second record, ... the Nth record decreases in sequence; Obtain a size in the target clothing size table whose various body data are all smaller than the various body data of the clothing corresponding to the Nth record and whose difference with the various body data of the clothing corresponding to the Nth record is the smallest, and record it as the target size; The target size is recommended as the customer's purchase size.

8. The online sales service method based on clothing pattern design according to claim 1, characterized in that: If the customer opens the historical browsing record, recommending the customer a size according to the third strategy also includes: If the various body data of the clothing corresponding to the first record, the second record ... the N-1th record increase in sequence, the various body data of the clothing corresponding to the Nth record are less than the various body data of the clothing corresponding to the N-1th record; Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the Nth record and less than the body data of the clothing corresponding to the N-1th record, and record it as the target size; Recommend target size as the customer's purchase size; If the various body data of the clothing corresponding to the first record, the second record ... the N-1th record decreases in sequence, the various body data of the clothing corresponding to the Nth record is greater than the various body data of the clothing corresponding to the N-1th record; Obtain the size in the target clothing size table, in which all body data are greater than the body data of the clothing corresponding to the N-1th record and less than the body data of the clothing corresponding to the Nth record, and record it as the target size; The target size is recommended as the customer's purchase size.

Images