Online order service control method and device, medium and equipment

Abstract

The invention provides an online order service control method and device, a medium and equipment, and the method comprises the steps: responding to a target user to carry out the commodity purchasing operation in at least one target commercial tenant, and determining the total commodity price of all current purchased commodities in real time; determining a current delivery starting price of the target merchant for the target user, and comparing the total commodity price with the current delivery starting price; when the total commodity price is lower than the current delivery starting price, performing price breaking processing on the current delivery starting price based on a user dimension, a merchant dimension, a platform dimension and / or a historical statistical dimension, and determining an updated delivery starting price lower than the current delivery starting price; and performing order service based on the updated delivery starting price. According to the invention, the problem that the order conversion rate is reduced due to too high delivery starting price can be reduced.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to an online order service control method, device, medium and equipment. Background Art

[0002] With the development of Internet technology and the popularization of smart terminals, people are becoming more and more accustomed to online shopping or takeaway services, such as ordering meals online and purchasing daily necessities. Such services rely on takeaway platforms and are provided by merchants in nearby business districts. Since such takeaway services are generally small items or meals, in order to control costs and maximize profits, merchants generally set a minimum delivery price, for example, setting the minimum delivery price to 20 yuan. Only when the total price of goods in the merchant reaches 20 yuan will the user be allowed to place an order.

[0003] It can be seen that when users place an order, due to the high threshold for delivery, some users find it difficult to get the order together. According to the survey, users who only buy food and beverage categories such as milk tea, juice / coffee, snacks, fried chicken, porridge, noodles, steamed buns / dumplings, or daily necessities such as nail clippers and toothbrushes have a high proportion of difficulties in getting the delivery price together, resulting in order loss. Therefore, with respect to the existing method of setting the minimum delivery price, how to improve the order conversion rate is a technical issue that technicians in this field need to consider. Summary of the invention

[0004] In view of this, the present application provides an online order service control method, device, medium and electronic device, the main purpose of which is to improve the existing starting price method to increase the order conversion rate.

[0005] According to one aspect of the present application, there is provided an online order service control method, comprising:

[0006] In response to the target user performing an operation of adding a product to a purchase in at least one target merchant, determining in real time the total price of all the products currently added to the purchase;

[0007] Determine the current starting price of the target merchant for the target user, and compare the total price of the product with the current starting price;

[0008] When the total price of the product is lower than the current starting price, the current starting price is broken based on the user dimension, the merchant dimension, the platform dimension and / or the historical statistical dimension to determine an updated starting price that is lower than the current starting price;

[0009] The order service is performed based on the updated starting price.

[0010] In one implementation, the method further includes:

[0011] Based on the interactive information of the product page, the opportunity for price reduction is detected;

[0012] The price-breaking process for the current starting price is initiated at the price-breaking process timing, and the starting price information prompt is provided based on the latest starting price after the price-breaking process.

[0013] In one implementation,

[0014] The time to detect a price break includes: detecting that the target user does not continue to purchase additional items or place an order for a predetermined period of time after purchasing at least one item, detecting that the target user exits the target merchant page, and detecting that the target user stays on the item purchase page or the order operation page for a period of time exceeding a predetermined time threshold.

[0015] In one implementation, the method further includes:

[0016] Based on at least one of the user dimension data, merchant dimension data, platform dimension data, and historical statistical dimension data, a neural network structure is trained to obtain a starting price and price reduction prediction model; wherein the updated starting price is predicted based on the starting price and price reduction prediction model.

[0017] In one implementation,

[0018] The user dimension data includes one or more of user consumption level data and user average order amount data;

[0019] The merchant dimension data includes one or more of merchant region data, merchant business category data, and merchant type data;

[0020] The platform dimension data includes order amount distribution data of each city and each category;

[0021] The historical statistical dimension data includes one or more of average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, and merchant order price distribution data.

[0022] In one implementation, predicting the updated starting price based on the starting price prediction model includes:

[0023] The target user information, the target merchant information and the current starting price are used as inputs of the starting price prediction model to predict the updated starting price.

[0024] In one implementation, the method further includes:

[0025] Based on at least one of the user dimension data, the merchant dimension data, the platform dimension data, and the historical statistical dimension data, a neural network structure is trained to obtain a minimum delivery amount prediction model; wherein, a minimum delivery amount prediction model is used to predict a minimum delivery amount price, and the updated minimum delivery price is determined based on the minimum delivery amount prediction model and the total price of the product or the current minimum delivery price.

[0026] In one implementation,

[0027] The user dimension data includes one or more of user consumption level data and user average order amount data;

[0028] The merchant dimension data includes one or more of merchant region data, merchant business category data, and merchant type data;

[0029] The platform dimension data includes order amount distribution data of each city and each category;

[0030] The historical statistical dimension data includes one or more of average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, and merchant order price distribution data.

[0031] In one implementation,

[0032] The step of predicting the minimum delivery amount supplement price based on the minimum delivery amount supplement prediction model includes: taking target user information, target merchant information and current minimum delivery amount supplement price as inputs of the minimum delivery amount supplement prediction model to predict the minimum delivery amount supplement price;

[0033] The updated starting price is determined based on the starting price, the total price of the product or the current starting price, including: subtracting the starting price from the current starting price to obtain the updated starting price; or adding the starting price to the total price of the product to obtain the updated starting price.

[0034] According to one aspect of the present application, there is provided an online order service control device, comprising:

[0035] A total price determination unit, configured to determine the total price of all currently added products in real time in response to the target user performing an operation of adding products to the purchase in at least one target merchant;

[0036] A starting price comparison unit, configured to determine a current starting price of the target merchant for the target user, and compare the total price with the current starting price;

[0037] a starting price updating unit, configured to, when the total price is lower than the current starting price, break the current starting price based on a user dimension, a merchant dimension, a platform dimension and / or a historical statistical dimension to determine an updated starting price that is lower than the current starting price;

[0038] An order service unit is used to perform order service based on the updated starting price.

[0039] According to one aspect of the present application, a storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned online order service control method when running.

[0040] According to one aspect of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned online order service control method.

[0041] Through the above technical solution, the present application provides an online order service control method, device, medium and equipment. The present application uses multi-dimensional data such as user dimension, merchant dimension, platform dimension, historical statistical dimension, etc. to break the current starting price, that is, to determine an updated starting price that is lower than the current starting price, so as to benefit users, reduce the situation where users give up orders because the starting price is too high, and improve the order conversion rate.

[0042] In one approach, by detecting the timing of price-breaking processing and performing price-breaking processing only when the timing is right, the price-breaking processing can be performed only when necessary while ensuring the profits of merchants or platforms, so as to improve the order conversion rate of target users in a more targeted manner.

[0043] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 A flow chart of an online order service control method provided by an embodiment of the present application is shown;

[0046] Figure 2 A schematic diagram showing the principle of a price-breaking processing mechanism provided in an embodiment of the present application is shown;

[0047] Figure 3 A flowchart of price-breaking processing based on the starting price-breaking prediction model provided in an embodiment of the present application is shown;

[0048] Figure 4 A flowchart of price-breaking processing based on a starting delivery and replenishment amount prediction model provided in an embodiment of the present application is shown;

[0049] Figure 5 A schematic diagram of the mechanism of an online order service control device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0051] The inventor discovered during the research process that different roles in online order services have different perspectives.

[0052] 1. Merchant (business) perspective:

[0053] Merchants set minimum spending standards to ensure that each order can generate sufficient profits, but this standard may create obstacles for some users to place orders, such as users who only want to order a small amount or have urgent needs.

[0054] 2. Platform perspective

[0055] The core value of the platform is to match supply and demand transactions, but the current mechanism does not give users the ability to exceed the starting price.

[0056] 3. User perspective

[0057] For users who only purchase single-category food and beverage items such as milk tea, juice / coffee, snacks, fried chicken, porridge, noodles, steamed buns / dumplings, or only purchase daily necessities such as nail clippers and toothbrushes, if they cannot afford the gift price, they may give up the purchase.

[0058] In order to solve the existing problem of order loss due to the starting price, in the embodiment of the present application, the platform (such as a food delivery platform) considers providing a service capability that is lower than the starting price to support users to place orders.

[0059] See also Figure 1, is a flow chart of an online order service control method provided in an embodiment of the present application, comprising the following steps S101-S104.

[0060] S101: In response to a target user performing an operation of purchasing additional products in at least one target merchant, determining the total price of all currently purchased additional products in real time.

[0061] Target users refer to users who are currently shopping online. For example, users use food delivery apps on their smartphones to order food or purchase goods. When users are adding goods, the page will calculate and display the total price of the goods, delivery fee information, as well as delivery information or checkout operation buttons in real time.

[0062] Suppose user Zhang San wants to buy a cup of milk tea at merchant A. Zhang San selects milk tea on the merchant A page and adds it to the shopping cart. When adding it to the shopping cart, the page will calculate and display the current product price and delivery fee information in real time. For example, 6 yuan, 2 yuan for delivery fee, 1 yuan for packaging fee, etc. will be displayed in the lower left corner of the page. The minimum delivery price information will also be displayed. For example, 4 yuan is left for the minimum delivery fee in the lower right corner of the page.

[0063] Suppose user Li Si wants to buy a nail clipper and a toothbrush from merchant B. Li Si adds the nail clippers and toothbrush to the shopping cart on the merchant B page. When adding them to the shopping cart, the page will calculate and display the current product price and delivery fee information in real time. For example, 10 yuan (the total price of the toothbrush is 2 yuan and the nail clipper is 8 yuan), 2 yuan for delivery fee, 1 yuan for packaging fee, etc. will be displayed in the lower left corner of the page. The minimum delivery price information will also be displayed. For example, 5 yuan is left for the minimum delivery fee in the lower right corner of the page.

[0064] Assume that user Wang Wu wants to buy a whole box of mineral water from merchant C. Wang Wu selects mineral water on the merchant C page and adds it to the shopping cart. When adding it to the shopping cart, the page will calculate and display the current product price and delivery fee information in real time. For example, 28 yuan, 3 yuan for delivery fee, 1 yuan for packaging fee and other information will be displayed in the lower left corner of the page. At the same time, the settlement operation button will be displayed, for example, the "Go to Checkout" operation button will be displayed in the lower right corner.

[0065] S102: Determine the current starting price of the target merchant for the target user, and compare the total price of the product with the current starting price.

[0066] Merchants may have different starting prices for different users, which is mainly affected by the distance between the merchant and the user, and may also be related to factors such as merchant promotions (for example, new merchants lower the starting price threshold) or user level (for example, high-level users may enjoy merchant services without a starting price threshold). For example, a relatively simple default starting price configuration method is: for users within 2km, the starting price is set to 10 yuan, for users within 2km-5km, the starting price is set to 20 yuan, for users within 5km-10km, the starting price is set to 50 yuan, and so on. Due to the above starting price information configuration of the merchant on the platform, the platform can calculate the merchant's starting price for the current target user in real time based on the merchant information configuration and the distance between the merchant and the user.

[0067] Let’s use the above three examples to illustrate.

[0068] For example, if user Zhang San wants to buy a cup of milk tea for 6 yuan at merchant A, since the lower right corner of the page shows that there is still 4 yuan left for the delivery, it can be determined that merchant A’s current minimum delivery price for user Zhang San is 10 yuan.

[0069] For example, if user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B, since the lower right corner of the page shows that there is still 5 yuan left to deliver the goods, it can be determined that merchant B’s current minimum delivery price for Li Si is 15 yuan.

[0070] For example, if user Wang Wu wants to buy a box of mineral water from merchant C, since the checkout button is displayed in the lower right corner of the page, it can be determined that the current product price has met the current starting price of merchant C for user Wang Wu, for example, the current starting price of merchant C for user Wang Wu is 20 yuan.

[0071] After determining the current starting price of the target merchant for the target user, the total price of the product is compared with the current starting price to determine whether the starting price condition is met. Specifically, it is determined whether the total price of the product is equal to or greater than the current starting price. If so, it is determined that the starting price condition is met, otherwise, it is determined that the starting price condition is not met.

[0072] Let’s use the above three examples to illustrate.

[0073] For example, if user Zhang San wants to buy a cup of 6-yuan milk tea from merchant A, since the lower right corner of the page shows that there is still 4 yuan left for the delivery, it can be determined that the current total price of the product is 6 yuan, which is less than the current delivery price of 10 yuan, and does not meet the delivery price condition.

[0074] For example, user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B. Since the lower right corner of the page shows that there is still 5 yuan left for the delivery start price, it can be determined that the current total price of the goods, 10 yuan, is less than the current delivery start price of 15 yuan, and the delivery start price condition is not met.

[0075] For example, if user Wang Wu wants to buy a box of mineral water from merchant C, since the checkout button is displayed in the lower right corner of the page, it can be determined that the current total price of the product has met the minimum delivery price conditions, and the user can proceed with the checkout and place the order.

[0076] S103: When the total price of the goods is lower than the current starting price, the current starting price is broken based on the user dimension, the merchant dimension, the platform dimension and / or the historical statistical dimension to determine an updated starting price that is lower than the current starting price.

[0077] When the total price of the goods is lower than the current starting price, that is, the starting price condition is not met at present, the embodiment of the present application breaks the starting price, that is, lowers the starting price threshold, benefits the user, reduces the probability of users canceling orders due to too high a starting price threshold, and improves the order conversion rate.

[0078] Among them, one dimension or a combination of multiple dimensions among user dimension, merchant dimension, platform dimension and historical statistical dimension can be used as the basis for price breaking processing, so as to determine an updated starting price that is lower than the current starting price.

[0079] For example, one implementation method is to perform price reduction processing according to the user dimension. For example, determine the user's consumption level data and judge the user's consumer level (for example, advanced user, intermediate user, low-level user, or first-level user, second-level user, third-level user, etc.). If the user is a advanced user of the platform or a advanced user of the merchant, a price reduction processing will be performed. The specific degree of price reduction can be determined by setting a reduction rate, and subtracting the reduction rate from the current starting price to obtain an updated starting price.

[0080] Let’s take the above example to illustrate.

[0081] For example, if user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A, since the current total price of the product is 6 yuan, which is less than the current starting price of 10 yuan, the starting price condition is not met. If user Zhang San is determined to be a senior user of the platform or a senior user of the merchant (or a first-level user of the platform or a first-level user of the merchant) by judging the user's consumption level data, he can enjoy the starting price price reduction service, according to the reduction rate pre-set by the platform or merchant, assuming that the reduction rate is set to different values ​​according to different user levels, assuming that the reduction rate corresponding to the user level of user Zhang San is 2 yuan, then the current starting price of 10 yuan will be reduced to the updated starting price of 8 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as displaying "still 2 yuan short of the starting price (you are a high-quality user, the starting price has been reduced by 2 yuan) and other information and words", so as to increase the user's willingness to place an order, and the user only needs to collect 2 yuan to meet the latest starting price conditions.

[0082] For example, user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B. Since the current total price of the goods is 10 yuan, which is less than the current starting price of 15 yuan, the starting price condition is not met. If the user Zhang San is determined to be a platform intermediate user or a merchant intermediate user (or a platform secondary user or a merchant secondary user) by judging the user's consumption level data, he can enjoy the starting price price reduction service. According to the reduction rate pre-set by the platform or merchant, assuming that the reduction rate is set to different values ​​according to different user levels, assuming that the reduction rate corresponding to the user level of user Zhang San is 1 yuan, the current starting price of 15 yuan will be reduced to the updated starting price of 14 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as displaying "4 yuan is left for the starting price (you are a high-quality user, the starting price has been reduced by 1 yuan) and other information and words", so as to increase the user's willingness to place an order. The user only needs to collect 4 yuan of goods to meet the latest starting price conditions.

[0083] For example, another implementation method is to perform price-breaking processing according to the merchant dimension. For example, the merchant dimension data, including merchant geographical data, business category data, order history data, etc., is determined, and the correlation curve between "time period"-"distance period"-"starting price" is determined, and the price-breaking conditions are set in the correlation curve. According to the correlation curve, it is determined whether the current target user meets the price-breaking conditions of the time period, distance period and starting price. If so, the latest updated starting price is determined according to the correlation between "time period"-"distance period"-"starting price".

[0084] Let’s take the above example to illustrate.

[0085] For example, if user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A, the current total price of 6 yuan is less than the current starting price of 10 yuan, so the starting price condition is not met. If the merchant dimension data is determined to determine that the time period and distance segment of the current add-on behavior meet the price-breaking condition of the association curve, then the updated starting price is determined based on the association curve, for example, the updated starting price is determined to be 9 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "3 yuan left for the starting price (the starting price has been reduced by 1 yuan for you)" and other information and words, so as to increase the user's willingness to place an order. The user only needs to collect 3 yuan of goods to meet the latest starting price condition.

[0086] For example, user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B. Since the current total price of the goods is 10 yuan, which is less than the current starting price of 15 yuan, the starting price condition is not met. If the merchant dimension data is determined to determine that the time period and distance segment of the current purchase behavior meet the price-breaking condition of the association curve, the updated starting price is determined based on the association curve, for example, the updated starting price is determined to be 13 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "still 3 yuan short of the starting price (the starting price has been reduced by 2 yuan for you)" and other information and words, so as to increase the user's willingness to place an order. The user only needs to collect 3 yuan of goods to meet the latest starting price condition.

[0087] For example, another way to implement it is to break the price according to the platform dimension. For example, determine the platform dimension data, including the order amount distribution data of each city / region and each category, establish the correlation curve between "platform revenue"-"merchant revenue"-"starting price", and determine the latest updated starting price under the premise of meeting the minimum threshold of merchant revenue and maximizing the platform revenue as much as possible. Among them, the platform can return part of the commission to the merchant, so as to obtain the maximum profit of both the platform and the merchant in terms of the number of orders.

[0088] For example, user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A. Since the current total price of 6 yuan is less than the current starting price of 10 yuan, the starting price condition is not met. If the platform dimension data is determined, according to the correlation curve between "platform revenue" - "merchant revenue" - "starting price", the latest starting price is determined based on the minimum threshold of merchant revenue and the maximization of platform revenue. For example, the updated starting price is determined to be 8 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "still 2 yuan short of the starting price (the starting price has been reduced by 2 yuan for you)" and other information and words, so as to increase the user's willingness to place an order. The user only needs to collect 2 yuan of goods to meet the latest starting price conditions.

[0089] For example, user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B. Since the current total price of the goods is 10 yuan, which is less than the current starting price of 15 yuan, the starting price condition is not met. If the platform dimension data is determined, according to the correlation curve between "platform revenue" - "merchant revenue" - "starting price", the latest starting price is determined based on the minimum threshold of merchant revenue and the maximization of platform revenue. For example, the updated starting price is determined to be 12 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "still 2 yuan short of the starting price (the starting price has been reduced by 3 yuan for you)" and other information and words, so as to increase the user's willingness to place an order. The user only needs to collect 2 yuan of goods to meet the latest starting price condition.

[0090] For example, another implementation method is to perform price-breaking processing according to historical statistical dimensions. For example, determine historical statistical dimension data, including average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, merchant order price distribution data, etc., establish a correlation curve between "platform revenue"-"merchant revenue"-"starting price", and establish a correlation curve between "time period"-"distance period"-"starting price". Under the premise of meeting the minimum threshold of merchant revenue, the platform revenue is maximized as a condition to determine the latest first starting price. At the same time, according to the correlation curve between "time period"-"distance period"-"starting price", determine whether the current target user meets the price-breaking conditions of time period, distance period and starting price. If satisfied, determine the second starting price according to the correlation between "time period"-"distance period"-"starting price". Weighted processing is performed on the first starting price and the second starting price to obtain the final updated starting price.

[0091] For example, if user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A, the current total price of 6 yuan is less than the current starting price of 10 yuan, so the starting price condition is not met. If the historical dimension data is determined, based on the correlation curve between "platform revenue"-"merchant revenue"-"starting price", the latest first starting price is determined based on the minimum threshold of merchant revenue and the maximization of platform revenue; and the second starting price is determined based on the correlation between "time period"-"distance segment"-"starting price"; finally, the first starting price and the second starting price are weighted to obtain the final updated starting price. For example, the updated starting price is determined to be 9 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "1 yuan is left for the starting price (the starting price has been reduced by 3 yuan for you)" and other information and words, so as to increase the user's willingness to place an order, and the user only needs to collect 1 yuan of goods to meet the latest starting price condition.

[0092] For example, user Li Si wants to buy a nail clipper for 8 yuan and a toothbrush for 2 yuan from merchant B. Since the current total price of the goods is 10 yuan, which is less than the current starting price of 15 yuan, the starting price condition is not met. If the historical dimension data is determined, based on the correlation curve between "platform revenue"-"merchant revenue"-"starting price", the latest first starting price is determined based on the minimum threshold of merchant revenue and the maximization of platform revenue; and, based on the correlation between "time period"-"distance segment"-"starting price", the second starting price is determined; finally, the first starting price and the second starting price are weighted to obtain the final updated starting price. For example, the updated starting price is determined to be 12 yuan. In the actual page display, the starting price information update information can be displayed in real time in the lower right corner of the page, such as "still 2 yuan short of the starting price (the starting price has been reduced by 3 yuan for you)" and other information and words, so as to increase the user's willingness to place an order, the user only needs to collect 2 yuan of goods to meet the latest starting price condition.

[0093] In practice, the user dimension, merchant dimension, platform dimension, and historical dimension can be combined to determine a more reasonable updated starting price. For example, through the consumption level determination of the user dimension, the correlation determination between the "time period"-"distance segment"-"starting price" of the merchant dimension, and the correlation determination between the "platform revenue"-"merchant revenue"-"starting price", multiple dimension determinations are combined to finally determine a more reasonable starting price that is a win-win for all three parties.

[0094] S104: Perform order service based on the updated starting delivery price.

[0095] After the updated starting price is determined, if the user continues to purchase additional items that meet the latest starting price or the current total price of the items already meets the updated starting price, the user can click the "Go to Checkout" button to enter the checkout page. The order total includes the total price of the items, delivery fee (if any), packaging fee (if any), etc. The order amount is finally calculated and the order is completed after the user pays.

[0096] It can be understood that the embodiment of the present application performs a price-cutting process on the starting price, which is essentially to give part of the profit to the user, that is, to lower the threshold of the starting price. In actual operation, as in the above example, the page can be directly displayed with information and words such as "still need 2 yuan to start the delivery (the starting price has been reduced by 3 yuan for you)". In addition, the purpose of lowering the starting price can also be achieved by reducing other costs. For example, the cost can be reduced on other items such as product prices, delivery costs, packaging costs, etc., so as to reduce the cost of the entire order. For example, displaying "add 6 yuan delivery fee to start the delivery" on the page can also achieve the purpose of lowering the starting price.

[0097] It can be seen that the embodiment of the present application uses multi-dimensional data such as user dimension, merchant dimension, platform dimension, historical statistical dimension, etc. to break the current starting price, that is, determine an updated starting price that is lower than the current starting price, so as to benefit users, reduce the situation where users give up orders because the starting price is too high, and improve the order conversion rate. From the perspective of merchants and platforms, the platform can give part of the commission to merchants to protect the profits of merchants. At the same time, due to this method of breaking the starting price, the order conversion rate will be improved. When the profit of a single order decreases but the total number of orders increases, the merchant profit and platform income can still be guaranteed. Based on the above, a win-win situation for all three parties can be achieved, which not only meets the demands of users, but also brings additional orders to merchants, and at the same time, the platform's revenue also increases.

[0098] In one implementation, the timing of price-breaking processing can be set, that is, the conditions for price-breaking processing can be added, and the price-breaking processing operation can be performed only at the timing of price-breaking processing. This can ensure the profits of merchants or platforms, and only perform price-breaking processing at necessary moments, so as to improve the order conversion rate of target users in a more targeted manner.

[0099] Specifically, the opportunity for price reduction processing can be detected through the interactive information of the product page; based on the interactive information of the product page, the opportunity for price reduction processing can be detected; at the opportunity for price reduction processing, the operation of price reduction processing of the current starting price can be initiated.

[0100] During the process of users adding products to their shopping cart, if the user continues to stay on the merchant page to add products to their shopping cart or filter products, it is generally believed that the user will continue to place an order. However, if the user stays on the merchant page for a period of time after adding products without performing other operations, such as not continuing to add products to their shopping cart or not placing an order, it can be determined that the user is likely to have exited the merchant page, that is, the user may not place an order due to the minimum delivery price. Therefore, one opportunity for price-breaking processing is: detecting that the target user has added at least one product and has not continued to purchase products or placed an order for a predetermined period of time.

[0101] For example, user Zhang San wants to buy a cup of 8 yuan milk tea at merchant A. Since the current total price of the product is 6 yuan, which is less than the current starting price of 10 yuan, the starting price condition is not met. If the current page is detected and it is determined that user Zhang San has not made other purchases or other operations for a long time, such as no other operations within 2 minutes, then the price-breaking processing mechanism is activated at this time to calculate and display the latest updated starting price information, such as "The starting price has been lowered for you at merchant A, and you only need 2 yuan to start the delivery" and other information and words to encourage users to place orders as soon as possible.

[0102] In addition, if the user's stay time on the product purchase page or order operation page exceeds the predetermined time threshold, it may be due to the minimum delivery price that the order has not been successfully placed. Therefore, one opportunity for price breaking is: the target user's stay time on the product purchase page or order operation page exceeds the predetermined time threshold.

[0103] For example, user Zhang San wants to buy a cup of milk tea for 8 yuan at merchant A. Since the current total price of the product is 6 yuan, which is less than the current starting price of 10 yuan, the starting price condition is not met. If the current page is detected and it is determined that user Zhang San stays on the page for a long time, such as staying on the page for more than 3 minutes, the price-breaking processing mechanism will be activated at this time to calculate and display the latest updated starting price information, such as "The starting price has been lowered for you, and you only need 2 yuan to start the delivery" and other information and words to encourage users to place orders as soon as possible.

[0104] In addition, if it is detected that the user exits the merchant page, it means that the user may not want to place an order with the merchant due to the starting price. At this time, the price-breaking processing mechanism can be activated, and the latest starting price information can be prompted on the platform page through a prompt box or floating box. Therefore, one time to handle the price-breaking is: the target user exits the target merchant page.

[0105] For example, user Zhang San wants to buy a cup of 8 yuan milk tea at merchant A. Since the current total price of the product is 6 yuan, which is less than the current starting price of 10 yuan, the starting price condition is not met. If it is detected that user Zhang San exits the merchant A page, the price-breaking processing mechanism is activated at this time to calculate and display the latest updated starting price information, such as displaying "The starting price has been lowered for you at merchant A, and you only need 2 yuan to start the delivery" and other information and words to encourage users to place orders as soon as possible.

[0106] This operation of detecting the timing of price-breaking processing and performing price-breaking processing only when the timing is right can ensure the profits of merchants or platforms, and only perform price-breaking processing when necessary, so as to improve the order conversion rate of target users in a more targeted manner.

[0107] The following is an illustrative example of the embodiment of the present application. In the example, a prediction model (a starting price break prediction model or a starting price supplement prediction model) is first trained, and then a price break process is performed based on the prediction results of the prediction model.

[0108] See also Figure 2 , which is a schematic diagram of price-break prediction model training in an online order service control method provided in an embodiment of the present application.

[0109] The model can be obtained by training a neural network structure, and the neural network includes but is not limited to feedforward neural networks, recurrent neural networks, and convolutional neural networks, etc., which are currently or will appear in the future. The user dimension data, merchant dimension data, platform dimension data, and historical statistical dimension data are used as input to train the above neural network structure and obtain a prediction model.

[0110] Among them, examples of data of various dimensions in the offline stage are as follows.

[0111] 1) User dimension data:

[0112] The user's consumption level;

[0113] Average order amount of users;

[0114] 2) Merchant dimension:

[0115] Region: city, district, county, business district;

[0116] Business categories: primary category, secondary category;

[0117] Merchant type: Retail / catering;

[0118] 3) Platform dimension:

[0119] Distribution of order amounts by city / region+category;

[0120] 4) Offline statistical dimension:

[0121] Average actual receipt: average actual receipt amount;

[0122] Actual collection ratio: the actual collection ratio in the most recent period;

[0123] Platform UE: current merchant platform UE;

[0124] The current merchant’s recent order volume;

[0125] The current prices of the merchant’s dishes;

[0126] Current merchant order price distribution.

[0127] Among them, the input features of the online prediction stage include, for example:

[0128] 1) User dimension:

[0129] Current user distance;

[0130] The time when the current user places an order;

[0131] Whether it has timed out;

[0132] 2) Platform dimension strategy:

[0133] Time period strategy;

[0134] Distance strategy;

[0135] City + Category Strategy;

[0136] 3) Merchants:

[0137] Merchant category (primary category, secondary category);

[0138] Merchant city.

[0139] It can be seen that in the offline training stage, the above multi-dimensional data is processed by deduplication and noise reduction, and the processed data is used to train the neural network structure to obtain a prediction model. In the online prediction stage, the real-time data (real-time data of the current add-to-cart operation, including target user information, target merchant information, and current starting price, etc.) is input into the prediction model, and the latest starting price or the starting price is obtained according to the prediction results, so as to perform price-breaking processing.

[0140] In the embodiment of the present application, the prediction model may include a starting price-breaking prediction model and a starting price-addition prediction model. The former directly predicts the latest updated starting price, while the latter predicts the starting price-addition (i.e., the price that gives users a discount). The training principles and prediction methods of the two models are similar. Please refer to the schematic diagram of the price-breaking mechanism principle of the prediction model. Figure 2 , you can estimate the revenue of merchants and platforms under different "time periods" - "distance periods" - "starting prices", and finally recommend the starting price or top-up price with the highest platform revenue within the merchant's revenue acceptance range under each "distance period" - "time period" (for example Figure 2 At point E, the merchant's profit is acceptable and the platform's profit is the largest). Here, the order volume and gross profit can be used as targets to characterize the profit. Among them, it is necessary to first model the merchant's profit in the dimensions of "time period" - "distance period" - "starting price". The modeling features need to include the features of the aforementioned dimensions, and the starting price is used as the treatment feature as the input of the monotonic layer for estimating the order volume period.

[0141] See also Figure 3 , which is a flowchart of price-breaking processing based on the starting price-breaking prediction model.

[0142] S301: Detecting a user's operation of adding a product to purchase;

[0143] S302: Determine whether the total price of the product is lower than the starting price. If so, execute S303; otherwise, execute S306;

[0144] S303: Detecting a price-breaking processing opportunity through page interaction information;

[0145] S304: Determine whether a price-breaking opportunity is detected, if yes, execute S305, otherwise, continue to return to S303 to detect the price-breaking opportunity;

[0146] It is understandable that the steps S303-S304 are not necessary, that is, when it is determined that the total price of the goods is lower than the starting price, S305 can be executed to update the starting price prediction and price break processing.

[0147] S305: Update the starting price through the prediction model of the starting price, and then return to S302;

[0148] S306: When the total price of the goods is equal to or higher than the starting price, that is, when the starting condition is met, the order price is determined based on the current total price of the goods and the delivery fee;

[0149] S307: Generate and complete the order.

[0150] Explain with specific examples.

[0151] For example, if user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A, the current total price of 6 yuan is less than the current starting price of 10 yuan, which does not meet the starting price condition. When detecting page interaction information, it is determined that a price-breaking processing opportunity is detected, such as detecting that user Zhang San exits the current merchant A page. At this time, the price-breaking processing strategy is triggered, that is, the starting price is updated through the pre-trained starting price-breaking prediction model, and the latest updated starting price is predicted. For example, the updated starting price is 8 yuan. At this time, if Zhang San continues to purchase a 2 yuan product, the starting price condition of 8 yuan can be met, and then the order settlement page is entered to complete the order after payment.

[0152] See also Figure 4 , which is a flowchart for price-breaking processing based on the minimum delivery amount prediction model.

[0153] S401: Detecting a user's operation of adding a product to purchase;

[0154] S402: Determine whether the total price of the product is lower than the starting price. If so, execute S403; otherwise, execute S307;

[0155] S403: Detecting a price-breaking processing opportunity through page interaction information;

[0156] S404: Determine whether a price-breaking opportunity is detected, if yes, execute S405, otherwise, continue to return to S403 to detect the price-breaking opportunity;

[0157] It is understandable that the steps S403-S404 are not necessary, that is, when it is determined that the total price of the product is lower than the starting price, S405 can be executed to update the starting price prediction and price break processing.

[0158] S405: Predicting the replenishment price through the initial replenishment prediction model;

[0159] S406: Calculate the updated starting price according to the supplementary price, for example, subtract the supplementary price from the current starting price to obtain the updated starting price; or add the supplementary price to the current total price of the product to obtain the updated starting price; then return to execute S402;

[0160] S407: When the total price of the goods is equal to or higher than the starting price, that is, when the starting condition is met, the order price is determined based on the current total price of the goods and the delivery fee;

[0161] S408: Generate and complete the order.

[0162] Explain with specific examples.

[0163] For example, if user Zhang San wants to buy a cup of 8 yuan milk tea from merchant A, the current total price of 6 yuan is less than the current starting price of 10 yuan, so the starting price condition is not met. When detecting page interaction information, it is determined that a price-breaking processing opportunity is detected. For example, it is detected that user Zhang San stays on the current merchant A page for more than 2 minutes without performing any operation. At this time, the price-breaking processing strategy is triggered, that is, the replenishment price is predicted by the pre-trained starting price replenishment prediction model, for example, the replenishment price is predicted to be 2 yuan. At this time, the updated starting price can be calculated by the replenishment price, for example, the current starting price is subtracted from the replenishment price, that is, 10-2 = 8 yuan, or the current total price of the product is added to the replenishment price to obtain the updated starting price, that is, 6 + 2 = 8 yuan. At this time, if Zhang San continues to purchase a 2 yuan product, the starting price condition of 8 yuan can be met, and the order settlement page is subsequently entered to complete the order after payment.

[0164] Corresponding to the above method, the embodiment of the present application also provides an online order service control device, see Figure 5 ,include:

[0165] A total price determination unit 501 is used to determine the total price of all currently added products in real time in response to the target user performing an operation of adding products to the purchase in at least one target merchant;

[0166] A starting price comparison unit 502 is used to determine the current starting price of the target merchant for the target user, and compare the total price with the current starting price;

[0167] A price-breaking processing unit 503 is configured to, when the total price is lower than the current starting price, perform price-breaking processing on the current starting price based on a user dimension, a merchant dimension, a platform dimension and / or a historical statistical dimension to determine an updated starting price that is lower than the current starting price;

[0168] The order service unit 504 is used to perform order service based on the updated starting price.

[0169] In one implementation, the method further includes:

[0170] The price-breaking timing detection unit 505 is used to detect the price-breaking processing opportunity based on the product page interaction information; wherein the price-breaking processing unit 503 starts the price-breaking processing at the price-breaking processing opportunity, and provides the starting price information prompt based on the latest starting price after the price-breaking processing.

[0171] In one implementation,

[0172] The time to detect a price break includes: detecting that the target user does not continue to purchase additional items or place an order for a predetermined period of time after purchasing at least one item, detecting that the target user exits the target merchant page, and detecting that the target user stays on the item purchase page or the order operation page for a period of time exceeding a predetermined time threshold.

[0173] In one implementation, the price-breaking processing unit 503 is specifically configured to:

[0174] Based on at least one of the user dimension data, merchant dimension data, platform dimension data, and historical statistical dimension data, a neural network structure is trained to obtain a starting price and price reduction prediction model; wherein the updated starting price is predicted based on the starting price and price reduction prediction model.

[0175] In one implementation,

[0176] The user dimension data includes one or more of user consumption level data and user average order amount data;

[0177] The merchant dimension data includes one or more of merchant region data, merchant business category data, and merchant type data;

[0178] The platform dimension data includes order amount distribution data of each city and each category;

[0179] The historical statistical dimension data includes one or more of average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, and merchant order price distribution data.

[0180] In one implementation, the price-breaking processing unit 503 is specifically configured to:

[0181] The target user information, the target merchant information and the current starting price are used as inputs of the starting price prediction model to predict the updated starting price.

[0182] In one implementation, the price-breaking processing unit 503 is specifically configured to:

[0183] Based on at least one of the user dimension data, the merchant dimension data, the platform dimension data, and the historical statistical dimension data, a neural network structure is trained to obtain a minimum delivery amount prediction model; wherein, a minimum delivery amount prediction model is used to predict a minimum delivery amount price, and the updated minimum delivery price is determined based on the minimum delivery amount prediction model and the total price of the product or the current minimum delivery price.

[0184] In one implementation,

[0185] The user dimension data includes one or more of user consumption level data and user average order amount data;

[0186] The merchant dimension data includes one or more of merchant region data, merchant business category data, and merchant type data;

[0187] The platform dimension data includes order amount distribution data of each city and each category;

[0188] The historical statistical dimension data includes one or more of average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, and merchant order price distribution data.

[0189] In one implementation, the price-breaking processing unit 503 is specifically configured to:

[0190] Using target user information, target merchant information and current minimum delivery price as inputs of the minimum delivery amount prediction model to predict the minimum delivery amount prediction price;

[0191] The updated starting price is determined based on the starting price, the total price of the product or the current starting price, including: subtracting the starting price from the current starting price to obtain the updated starting price; or adding the starting price to the total price of the product to obtain the updated starting price.

[0192] An embodiment of the present application further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0193] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0194] In response to the target user performing an operation of adding a product to a purchase in at least one target merchant, determining in real time the total price of all the products currently added to the purchase;

[0195] Determine the current starting price of the target merchant for the target user, and compare the total price of the product with the current starting price;

[0196] When the total price of the product is lower than the current starting price, the current starting price is broken based on the user dimension, the merchant dimension, the platform dimension and / or the historical statistical dimension to determine an updated starting price that is lower than the current starting price;

[0197] The order service is performed based on the updated starting price.

[0198] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0199] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0200] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0201] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0202] In response to the target user performing an operation of adding a product to a purchase in at least one target merchant, determining in real time the total price of all the products currently added to the purchase;

[0203] Determine the current starting price of the target merchant for the target user, and compare the total price of the product with the current starting price;

[0204] When the total price of the product is lower than the current starting price, the current starting price is broken based on the user dimension, the merchant dimension, the platform dimension and / or the historical statistical dimension to determine an updated starting price that is lower than the current starting price;

[0205] The order service is performed based on the updated starting price.

[0206] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0207] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0208] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0209] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0210] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0212] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0213] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An online order service control method, characterized in that: include: In response to the target user performing an operation of adding a product to a purchase in at least one target merchant, determining in real time the total price of all the products currently added to the purchase; Determine the current starting price of the target merchant for the target user, and compare the total price of the product with the current starting price; When the total price of the product is lower than the current starting price, the current starting price is broken based on the user dimension, the merchant dimension, the platform dimension and / or the historical statistical dimension to determine an updated starting price that is lower than the current starting price; The order service is performed based on the updated starting price.

2. The method according to claim 1, characterized in that Also includes: Based on the interactive information of the product page, the opportunity for price reduction is detected; The price-breaking process for the current starting price is initiated at the price-breaking process timing, and the starting price information prompt is provided based on the latest starting price after the price-breaking process.

3. The method according to claim 2, characterized in that The time to detect a price break includes: detecting that the target user does not continue to purchase additional items or place an order for a predetermined period of time after purchasing at least one item, detecting that the target user exits the target merchant page, and detecting that the target user stays on the item purchase page or the order operation page for a period of time exceeding a predetermined time threshold.

4. The method according to claim 1, characterized in that Also includes: Based on at least one of the user dimension data, merchant dimension data, platform dimension data, and historical statistical dimension data, a neural network structure is trained to obtain a starting price and price reduction prediction model; wherein the updated starting price is predicted based on the starting price and price reduction prediction model.

5. The method according to claim 4, characterized in that The user dimension data includes one or more of user consumption level data and user average order amount data; The merchant dimension data includes one or more of merchant region data, merchant business category data, and merchant type data; The platform dimension data includes order amount distribution data of each city and each category; The historical statistical dimension data includes one or more of average actual collection amount data, actual collection ratio data, platform UE information, merchant order volume statistics data, merchant commodity price data, and merchant order price distribution data.

6. The method according to claim 4, characterized in that The step of predicting the updated starting price based on the starting price prediction model includes: The target user information, the target merchant information and the current starting price are used as inputs of the starting price prediction model to predict the updated starting price.

7. The method according to claim 1, characterized in that Also includes: Based on at least one of the user dimension data, the merchant dimension data, the platform dimension data, and the historical statistical dimension data, a neural network structure is trained to obtain a minimum delivery amount prediction model; wherein, a minimum delivery amount prediction model is used to predict a minimum delivery amount price, and the updated minimum delivery price is determined based on the minimum delivery amount prediction model and the total price of the product or the current minimum delivery price.

8. An online order service control device, characterized in that: include: A total price determination unit, configured to determine the total price of all currently added products in real time in response to the target user performing an operation of adding products to the purchase in at least one target merchant; A starting price comparison unit, configured to determine a current starting price of the target merchant for the target user, and compare the total price with the current starting price; a starting price updating unit, configured to, when the total price is lower than the current starting price, break the current starting price based on a user dimension, a merchant dimension, a platform dimension and / or a historical statistical dimension to determine an updated starting price that is lower than the current starting price; An order service unit is used to perform order service based on the updated starting price.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 7.

Images