Item recommendation method and apparatus

Abstract

Embodiments of the present disclosure provide an article recommendation method and device. The method comprises: obtaining a target order of a user in a first network node; determining a to-be-recommended article corresponding to the target order in a second network node according to order information of a preset dimension associated with the target order; determining a target recommended article in the to-be-recommended article according to a promotion cost of the second network node on an order platform, a delivery cost of the target order, and an order commission corresponding to the second network node; and after receiving an ordering operation of the user on a target article in the target recommended article, delivering the target article and order articles corresponding to the target order to the user based on the delivery cost of the target order. Embodiments of the present disclosure can reduce the cost of cross-store shopping and the delivery time of single order distribution.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of item recommendation technology, and more particularly to an item recommendation method and apparatus. Background Technology

[0002] Based on user research and data analysis, it was found that a significant proportion of cross-store purchase demand was not being met. One major reason for this was the ordering cost, which included the delivery costs of multiple consecutive orders, as well as the process costs of repeated purchases and payments when placing orders online. In addition, the separate delivery of multiple orders on the platform resulted in multiple delivery fees, increasing the user's delivery costs, and the delivery time for split orders was also relatively long. Summary of the Invention

[0003] Embodiments of this disclosure provide a method and apparatus for recommending items, thereby reducing various costs and order delivery times for users making cross-store purchases.

[0004] According to a first aspect of the embodiments of this disclosure, an item recommendation method is provided, applied to an order platform, comprising: Obtain the user's target order within the first network node; Based on the order information of the preset dimensions associated with the target order, determine the items to be recommended corresponding to the target order within the second network node; The target recommended item among the items to be recommended is determined based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node; After receiving the user's order for a target item from the recommended items, the system delivers the target item and the corresponding order items to the user based on the delivery fee of the target order.

[0005] Optionally, determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Obtain the type of target item corresponding to the target order; The target combination type is determined based on the number of times the combination types of the target item type co-occur within a preset time period from the current time. Based on the target combination type, determine the items to be recommended corresponding to the target order within the second network node.

[0006] Optionally, determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Obtain the order placement time corresponding to the target order, and the type of target item corresponding to the target order; Based on the target time period in which the order is placed, determine the matching categories corresponding to the target item category; Based on the aforementioned combination type, determine the recommended items corresponding to the target order within the second network node.

[0007] Optionally, determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the user's historical order information, determine the price information of the single order corresponding to the user; Based on the price information of the single order, the item to be recommended corresponding to the target order within the second network node is determined.

[0008] Optionally, determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the user's historical order information, determine the user's preferences; Based on the user preferences, determine the items to be recommended corresponding to the target order within the second network node.

[0009] Optionally, determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the order information of the preset dimensions associated with the target order, determine the main item type corresponding to the target order; Based on the traffic data of each item in the main item category, the target item of the main item category is determined, and the target item is selected as the item to be recommended.

[0010] Optionally, determining the target recommended item among the items to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node includes: The first recommendation score for the item to be recommended is determined based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. Send the item category to which the recommended item belongs to the user; Receive the user's trigger operation for the target item category in the item category; In response to the triggering operation, a first weight corresponding to the target item type and a second weight of other item types besides the target item type are determined. Based on the first weight and the second weight, the first recommendation score is weighted to obtain the second recommendation score corresponding to the item to be recommended; Based on the second recommendation score, the target recommended item is determined from the items to be recommended.

[0011] Optionally, determining the target recommended item among the items to be recommended based on the second recommendation score includes: The items to be recommended are sorted in descending order of the second recommendation score; Based on the sorting results, the top N items to be recommended are selected from the items to be recommended, and the top N items to be recommended are taken as the target recommended items. Where N is a positive integer greater than or equal to 1.

[0012] According to a second aspect of the embodiments of this disclosure, an item recommendation device is provided, applied to an order platform, comprising: The target order acquisition module is used to acquire the user's target orders within the first network node; The module for determining items to be recommended is used to determine the items to be recommended corresponding to the target order within the second network node based on the order information of the target order in a preset dimension. The target recommended item determination module is used to determine the target recommended item among the items to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node; The target item delivery module is used to deliver the target item and the corresponding order items to the user based on the delivery fee of the target order after receiving the user's order for the target item in the target recommended items.

[0013] Optionally, the module for determining the items to be recommended includes: The first target type acquisition unit is used to acquire the target item type corresponding to the target order; The target combination type determination unit is used to determine the target combination type among the combination types based on the number of times the combination types of the target item type co-occur within a preset time period from the current time. The first item determination unit is used to determine the recommended item corresponding to the target order in the second network node based on the target matching type.

[0014] Optionally, the module for determining the items to be recommended includes: The second target type acquisition unit is used to acquire the order time corresponding to the target order and the target item type corresponding to the target order; The matching type determination unit is used to determine the matching type corresponding to the target item type based on the target time period in which the order is placed; The second item determination unit is used to determine the recommended item corresponding to the target order within the second network node based on the combination type.

[0015] Optionally, the module for determining the items to be recommended includes: The order price determination unit is used to determine the price information of a single order corresponding to the user based on the user's historical order information; The third item determination unit is used to determine the item to be recommended corresponding to the target order within the second network node based on the single order price information.

[0016] Optionally, the module for determining the items to be recommended includes: The user preference determination unit is used to determine the user's user preferences based on the user's historical order information; The fourth item determination unit is used to determine the recommended item corresponding to the target order within the second network node based on the user preference.

[0017] Optionally, the module for determining the items to be recommended includes: The main item category determination unit is used to determine the main item category corresponding to the target order based on the order information of a preset dimension associated with the target order; The item to be recommended acquisition unit is used to determine the target item of the main item category based on the traffic data of each item in the main item category, and to use the target item as the item to be recommended.

[0018] Optionally, the target recommended item determination module includes: The first recommendation score determination unit is used to determine the first recommendation score corresponding to the item to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. The item category sending unit is used to send the item category to which the item to be recommended belongs to the user; A trigger operation receiving unit is used to receive the user's trigger operation on the target item category among the item categories; The item weight determination unit is used to determine, in response to the triggering operation, a first weight corresponding to the target item type and a second weight of other item types besides the target item type. The second recommendation score acquisition unit is used to perform weighted processing on the first recommendation score based on the first weight and the second weight to obtain the second recommendation score corresponding to the item to be recommended. The target recommended item determination unit is used to determine the target recommended item among the items to be recommended based on the second recommendation score.

[0019] Optionally, the target recommended item determination unit includes: The item sorting subunit is used to sort the items to be recommended in descending order of the second recommendation score; The target recommended item acquisition subunit is used to filter out the top N recommended items from the items to be recommended based on the sorting results, and to use the top N recommended items as the target recommended items. Where N is a positive integer greater than or equal to 1.

[0020] According to a third aspect of the embodiments of this disclosure, an electronic device is provided, comprising: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the item recommendation method described above.

[0021] According to a fourth aspect of the embodiments of the present disclosure, a readable storage medium is provided that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the item recommendation method described in any of the preceding claims.

[0022] This disclosure provides a method and apparatus for recommending items. By acquiring a user's target order within a first network node, and determining the items to be recommended corresponding to the target order within a second network node based on predefined order information associated with the target order, the method further determines the target recommended items from the list of items to be recommended based on the promotion fees of the second network node on the order platform, the delivery fees of the target order, and the order commission corresponding to the second network node. After receiving an order from a user for the target item from the list of target recommended items, the method delivers the target item and the corresponding order items to the user based on the delivery fees of the target order. This disclosure, by combining the promotion fees of network nodes, the delivery fees of a single order, and the commission of a single order as constraints for item recommendation, enables cross-network node item recommendation, reducing the cost for users to purchase items across network nodes and the time required for order splitting and delivery, thereby improving the user experience. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the steps of an item recommendation method provided for embodiments of this disclosure; Figure 2 A flowchart illustrating the steps of another item recommendation method provided for embodiments of this disclosure; Figure 3 A schematic diagram of the structure of an item recommendation device provided for an embodiment of this disclosure; Figure 4 A schematic diagram of another item recommendation device provided in an embodiment of this disclosure. Detailed Implementation

[0025] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the protection scope of the embodiments of this disclosure.

[0026] Example 1 Reference Figure 1 The diagram illustrates a flowchart of the steps of an item recommendation method provided by an embodiment of this disclosure, such as... Figure 1 As shown, the method for recommending this item may specifically include the following steps: Step 101: Obtain the user's target order within the first network node.

[0027] The embodiments disclosed herein can be applied to scenarios involving cross-store shopping item recommendations.

[0028] This embodiment can be applied to an order platform, that is, the order platform is used as the subject of execution.

[0029] The first network node refers to the network node where a user completes an order within the order platform. In this example, the network node can be a merchant registered within the order platform. When a user places an order for a product with a certain merchant, that merchant can be used as the first network node.

[0030] A target order refers to an order generated when a user places an order for an item within the first network node; this target order is an order that has not yet been delivered.

[0031] When it is necessary to recommend cross-store shopping items to users, the user's target orders within the first network node can be obtained.

[0032] After obtaining the user's target order within the first network node, proceed to step 102.

[0033] Step 102: Based on the order information of the preset dimension associated with the target order, determine the recommended item corresponding to the target order within the second network node.

[0034] Order information refers to information used to obtain the recommended items corresponding to the target order. In this example, order information may include time information associated with the target order, order price information, user preference information, traffic data information, etc. Specifically, the filtering dimensions for order information can be determined according to business needs, and this embodiment does not impose any restrictions on this.

[0035] The second network node refers to the network node where the recommended item is located by the order platform for the user. For example... After obtaining the user's target order in the first network node, the recommended items corresponding to the target order in the second network node can be determined based on the order information of the preset dimensions associated with the target order. This process can be described in detail with specific order information. Specifically, it can be described in detail with the following specific methods.

[0036] In one specific implementation of this disclosure, step 102 may include: Sub-step A1: Obtain the target item type corresponding to the target order.

[0037] In this embodiment, the target item type refers to the item type corresponding to the target order. For example, if the target order is a staple food order, then the target item type is staple food; if the target order is a fruit order, then the target item type is fruit, etc.

[0038] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this disclosure.

[0039] After obtaining the target order, you can obtain the type of target item corresponding to the target order.

[0040] After obtaining the target item type corresponding to the target order, proceed to sub-step A2.

[0041] Sub-step A2: Determine the target combination type among the combination types based on the number of times the combination types of the target item type co-occur within a preset time period from the current time.

[0042] The preset duration refers to the time set by the business personnel in advance to obtain the number of times the target item type and the matching type co-occur. The specific value of the preset duration can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0043] The "combination category" refers to the types of items that other users purchase along with the target item. For example, if the target item is a staple food, and the items that go with a staple food are fruits and drinks, then fruits and drinks can be used as the combination category.

[0044] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation on the embodiments of this disclosure.

[0045] Co-occurrence count refers to the number of times that a combination of the target item type and the corresponding combination type appears together within a preset time interval from the current time.

[0046] After obtaining the target item type corresponding to the target order, the target combination type can be determined based on the number of times the combination types of the target item type co-occur within a preset time period. Specifically, a threshold number of co-occurrences can be preset. From the obtained co-occurrences, the combination types corresponding to co-occurrences greater than the threshold number can be selected as the target combination type.

[0047] After identifying the target combination type, proceed with sub-step A3.

[0048] Sub-step A3: Based on the target combination type, determine the recommended items corresponding to the target order within the second network node.

[0049] After determining the target combination type, the items to be recommended for the target order within the second network node can be determined based on the target combination type. For example, if the target combination type is beverages, then network nodes containing beverages can be selected from the network nodes registered in the order platform as the second network node, and then beverages that the second network node can provide can be selected as the items to be recommended.

[0050] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation on the embodiments of this disclosure.

[0051] In another specific implementation of this disclosure, step 102 may include: Sub-step B1: Obtain the order placement time corresponding to the target order and the target item type corresponding to the target order.

[0052] In this embodiment, the order placement time refers to the order placement time corresponding to the target. For example, when a user purchases an item from the first network node and generates a target order, the generation time of the target order can be obtained and used as the order placement time corresponding to the target order.

[0053] The target item category refers to the type of item corresponding to the target order. For example, if the target order is a staple food order, then the target item category is staple food; if the target order is a fruit order, then the target item category is fruit, and so on.

[0054] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this embodiment.

[0055] After obtaining the target order, you can obtain the order time and the type of target item.

[0056] After obtaining the order time and the type of target item for the target order, proceed to sub-step B2.

[0057] Sub-step B2: Determine the matching category corresponding to the target item type based on the target time period in which the order is placed.

[0058] The target time period refers to the time period in which the order is placed, such as breakfast time or lunch time.

[0059] After obtaining the order time corresponding to the target order, the matching type corresponding to the target item type can be determined based on the target time period in which the order time is located.

[0060] After determining the matching categories corresponding to the target item type based on the target time period in which the order is placed, proceed to sub-step B3.

[0061] Sub-step B3: Based on the matching type, determine the recommended item corresponding to the target order within the second network node.

[0062] After obtaining the matching categories corresponding to the target item type, the recommended items for the target order within the second network node can be determined based on the matching categories.

[0063] In another specific implementation of this disclosure, step 102 may include: Sub-step C1: Determine the price information of a single order corresponding to the user based on the user's historical order information.

[0064] In this embodiment, historical order information refers to the order information of items purchased by the user within the order platform.

[0065] Single order price information refers to the price information of a single order in which a user purchases items.

[0066] After obtaining the user's target order within the first network node, the price information for the user's single order can be determined based on the user's historical order information.

[0067] After determining the price information of a user's single order based on the user's historical order information, proceed to sub-step C2.

[0068] Sub-step C2: Based on the single order price information, determine the item to be recommended corresponding to the target order within the second network node.

[0069] After determining the price information of a user's single order based on the user's historical order information, the recommended items for the target order within the second network node can be determined based on the single order price information. Specifically, the recommended items can be filtered based on the lowest and highest prices of the single order.

[0070] In another specific implementation of this disclosure, step 102 may include: Sub-step D1: Determine the user's user preferences based on the user's historical order information.

[0071] In this embodiment, after obtaining the user's target order within the first network node, the user's preferences can be determined based on the user's historical order information.

[0072] After determining the user's preferences based on the user's historical order information, proceed to sub-step D2.

[0073] Sub-step D2: Based on the user preferences, determine the items to be recommended corresponding to the target order within the second network node.

[0074] After obtaining the user's preferences, the items to be recommended for the target order can be determined from the second network node based on the user preferences.

[0075] In another specific implementation of this disclosure, step 102 may include: Sub-step E1: Determine the main item type corresponding to the target order based on the order information of the preset dimension associated with the target order.

[0076] In this embodiment, the main item category refers to the item category corresponding to the target order in the pre-divided main categories. For example, for food, it can be pre-divided into three main categories: breakfast, lunch, and dinner. If the target order is placed during the noon period, then lunch will be determined as the main item category of the target order.

[0077] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this embodiment.

[0078] After determining the main item type corresponding to the target order based on the order information of the preset dimensions associated with the target order, sub-step E2 is executed.

[0079] Sub-step E2: Based on the traffic data of each item in the main item category, determine the target item of the main item category and use the target item as the item to be recommended.

[0080] After determining the main item category corresponding to the target order based on the order information of the preset dimensions associated with the target order, the target item in the main item category can be determined based on the traffic data of each item in the main item category, and the target item can be used as the item to be recommended.

[0081] The embodiments of this disclosure, through the above-mentioned methods of obtaining items to be recommended, can combine multiple preset dimensions to recommend items, thereby making the recommended items more in line with user needs and improving the user's cross-store purchasing experience.

[0082] After determining the recommended items corresponding to the target order within the second network node based on the order information of the preset dimensions associated with the target order, step 103 is executed.

[0083] Step 103: Determine the target recommended item among the items to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node.

[0084] Promotion costs (also known as advertising costs) refer to the expenses incurred by a second network node in promoting its products on the order platform.

[0085] Delivery costs refer to the expenses incurred by delivery personnel in delivering the target order.

[0086] Order commission refers to the commission that the second network node needs to pay to the order platform when a target order is completed.

[0087] Targeted recommended items refer to the recommended items selected from the items to be recommended and displayed to the user.

[0088] In this example, after determining the recommended items corresponding to the target order within the second network node based on the order information of the preset dimension associated with the target order, the target recommended items among the recommended items can be determined based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. This process will be described in detail in the following embodiment two, and will not be repeated here.

[0089] After identifying the target recommended item among the items to be recommended, proceed to step 104.

[0090] Step 104: After receiving the user's order for the target item in the target recommended items, based on the delivery fee of the target order, deliver the target item and the order items corresponding to the target order to the user.

[0091] After identifying the target recommended items, these items can be sent to the user, who can then select one of them to place an order.

[0092] After receiving a user's order for a target item from the recommended items, the system can deliver the target item and the corresponding order items to the user based on the delivery fee of the target order. This means that the delivery fee of one order can be used to complete the delivery of at least two orders, thereby reducing the delivery fees paid by users while increasing the sales volume of items on the order platform.

[0093] The embodiments of this disclosure combine the promotion fees of network nodes, the delivery fees of a single order, and the commission of a single order as constraints for item recommendation, and perform cross-network node item recommendation. This can reduce the cost for users to purchase items across network nodes and the time for order splitting and delivery, thereby improving the user experience.

[0094] The item recommendation method provided in this disclosure obtains a user's target order within a first network node, determines the recommended items corresponding to the target order within a second network node based on pre-defined order information associated with the target order, and determines the target recommended items among the recommended items based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. After receiving an order from a user for the target item among the recommended items, the method delivers the target item and the corresponding order items to the user based on the delivery fee of the target order. This disclosure, by combining the promotion fee of a network node, the delivery fee of a single order, and the commission of a single order as constraints for item recommendation, performs cross-network node item recommendation, reducing the cost for users to purchase items across network nodes and the time for order splitting and delivery, thus improving the user experience.

[0095] Example 2 Reference Figure 2 The flowchart illustrates the steps of another item recommendation method provided by an embodiment of this disclosure, as shown below. Figure 2 As shown, the method for recommending this item may specifically include the following steps: Step 201: Obtain the user's target order within the first network node.

[0096] The embodiments disclosed herein can be applied to scenarios involving cross-store shopping item recommendations.

[0097] This embodiment can be applied to an order platform, that is, the order platform is used as the subject of execution.

[0098] The first network node refers to the network node where a user completes an order within the order platform. In this example, the network node can be a merchant registered within the order platform. When a user places an order for a product with a certain merchant, that merchant can be used as the first network node.

[0099] A target order refers to an order generated when a user places an order for an item within the first network node; this target order is an order that has not yet been delivered.

[0100] When it is necessary to recommend cross-store shopping items to users, the user's target orders within the first network node can be obtained.

[0101] After obtaining the user's target order within the first network node, proceed to step 202.

[0102] Step 202: Based on the order information of the preset dimension associated with the target order, determine the recommended item corresponding to the target order within the second network node.

[0103] Order information refers to information used to obtain the recommended items corresponding to the target order. In this example, order information may include time information associated with the target order, order price information, user preference information, traffic data information, etc. Specifically, the filtering dimensions for order information can be determined according to business needs, and this embodiment does not impose any restrictions on this.

[0104] The second network node refers to the network node where the recommended item is located by the order platform for the user. For example... After obtaining the user's target order in the first network node, the recommended items corresponding to the target order in the second network node can be determined based on the pre-defined order information associated with the target order. This process can be described in detail with specific order information. Specifically, it can be described in detail with the following specific methods.

[0105] In one specific implementation of this disclosure, step 202 may include: Sub-step F1: Obtain the target item type corresponding to the target order.

[0106] In this embodiment, the target item type refers to the item type corresponding to the target order. For example, if the target order is a staple food order, then the target item type is staple food; if the target order is a fruit order, then the target item type is fruit, etc.

[0107] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this disclosure.

[0108] After obtaining the target order, you can obtain the type of target item corresponding to the target order.

[0109] After obtaining the target item type corresponding to the target order, execute sub-step F2.

[0110] Sub-step F2: Determine the target combination type among the combination types based on the number of times the combination types of the target item type co-occur within a preset time period from the current time.

[0111] The preset duration refers to the time set by the business personnel in advance to obtain the number of times the target item type and the matching type co-occur. The specific value of the preset duration can be determined according to business needs, and this embodiment does not impose any restrictions on it.

[0112] The "combination category" refers to the types of items that other users purchase along with the target item. For example, if the target item is a staple food, and the items that go with a staple food are fruits and drinks, then fruits and drinks can be used as the combination category.

[0113] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation on the embodiments of this disclosure.

[0114] Co-occurrence count refers to the number of times that a combination of the target item type and the corresponding combination type appears together within a preset time interval from the current time.

[0115] After obtaining the target item type corresponding to the target order, the target combination type can be determined based on the number of times the combination types of the target item type co-occur within a preset time period. Specifically, a threshold number of co-occurrences can be preset. From the obtained co-occurrences, the combination types corresponding to co-occurrences greater than the threshold number can be selected as the target combination type.

[0116] After identifying the target combination type, proceed with sub-step F3.

[0117] Sub-step F3: Based on the target combination type, determine the recommended items corresponding to the target order within the second network node.

[0118] After determining the target combination type, the items to be recommended for the target order within the second network node can be determined based on the target combination type. For example, if the target combination type is beverages, then network nodes containing beverages can be selected from the network nodes registered in the order platform as the second network node, and then beverages that the second network node can provide can be selected as the items to be recommended.

[0119] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation on the embodiments of this disclosure.

[0120] In another specific implementation of this disclosure, step 202 may include: Sub-step G1: Obtain the order placement time corresponding to the target order and the target item type corresponding to the target order.

[0121] In this embodiment, the order placement time refers to the order placement time corresponding to the target. For example, when a user purchases an item from the first network node and generates a target order, the generation time of the target order can be obtained and used as the order placement time corresponding to the target order.

[0122] The target item category refers to the type of item corresponding to the target order. For example, if the target order is a staple food order, then the target item category is staple food; if the target order is a fruit order, then the target item category is fruit, and so on.

[0123] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this embodiment.

[0124] After obtaining the target order, you can obtain the order time and the type of target item.

[0125] After obtaining the order time and the type of target item for the target order, execute sub-step G2.

[0126] Sub-step G2: Determine the matching category corresponding to the target item type based on the target time period in which the order is placed.

[0127] The target time period refers to the time period in which the order is placed, such as breakfast time or lunch time.

[0128] After obtaining the order time corresponding to the target order, the matching type corresponding to the target item type can be determined based on the target time period in which the order time is located.

[0129] After determining the matching type corresponding to the target item type based on the target time period in which the order is placed, proceed to sub-step G3.

[0130] Sub-step G3: Based on the matching type, determine the recommended item corresponding to the target order within the second network node.

[0131] After obtaining the matching categories corresponding to the target item type, the recommended items for the target order within the second network node can be determined based on the matching categories.

[0132] In another specific implementation of this disclosure, step 202 may include: Sub-step H1: Determine the price information of a single order corresponding to the user based on the user's historical order information.

[0133] In this embodiment, historical order information refers to the order information of items purchased by the user within the order platform.

[0134] Single order price information refers to the price information of a single order in which a user purchases items.

[0135] After obtaining the user's target order within the first network node, the price information for the user's single order can be determined based on the user's historical order information.

[0136] After determining the price information of a user's single order based on the user's historical order information, proceed to sub-step H2.

[0137] Sub-step H2: Based on the single order price information, determine the item to be recommended corresponding to the target order within the second network node.

[0138] After determining the price information of a user's single order based on the user's historical order information, the recommended items for the target order within the second network node can be determined based on the single order price information. Specifically, the recommended items can be filtered based on the lowest and highest prices of the single order.

[0139] In another specific implementation of this disclosure, step 202 may include: Sub-step I1: Determine the user's user preferences based on the user's historical order information.

[0140] In this embodiment, after obtaining the user's target order within the first network node, the user's preferences can be determined based on the user's historical order information.

[0141] After determining the user's preferences based on the user's historical order information, proceed to sub-step I2.

[0142] Sub-step I2: Based on the user preferences, determine the items to be recommended corresponding to the target order within the second network node.

[0143] After obtaining the user's preferences, the items to be recommended for the target order can be determined from the second network node based on the user preferences.

[0144] In another specific implementation of this disclosure, step 202 may include: Sub-step J1: Determine the main item type corresponding to the target order based on the order information of the preset dimension associated with the target order.

[0145] In this embodiment, the main item category refers to the item category corresponding to the target order in the pre-divided main categories. For example, for food, it can be pre-divided into three main categories: breakfast, lunch, and dinner. If the target order is placed during the noon period, then lunch will be determined as the main item category of the target order.

[0146] It is understood that the above examples are merely examples listed to better understand the technical solutions of the embodiments of this disclosure, and are not intended to be the only limitation of this embodiment.

[0147] After determining the main item type corresponding to the target order based on the order information of the preset dimensions associated with the target order, sub-step J2 is executed.

[0148] Sub-step J2: Based on the traffic data of each item in the main item category, determine the target item of the main item category and use the target item as the item to be recommended.

[0149] After determining the main item category corresponding to the target order based on the order information of the preset dimensions associated with the target order, the target item in the main item category can be determined based on the traffic data of each item in the main item category, and the target item can be used as the item to be recommended.

[0150] The embodiments of this disclosure, through the above-mentioned methods of obtaining items to be recommended, can combine multiple preset dimensions to recommend items, thereby making the recommended items more in line with user needs and improving the user's cross-store purchasing experience.

[0151] After determining the recommended items corresponding to the target order within the second network node based on the order information of the preset dimensions associated with the target order, step 203 is executed.

[0152] Step 203: Determine the first recommendation score corresponding to the item to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node.

[0153] Promotion costs (also known as advertising costs) refer to the expenses incurred by a second network node in promoting its products on the order platform.

[0154] Delivery costs refer to the expenses incurred by delivery personnel in delivering the target order.

[0155] Order commission refers to the commission that the second network node needs to pay to the order platform when a target order is completed.

[0156] The first recommendation score refers to the calculated score of the item to be recommended. The higher the score, the higher the user acceptance, and vice versa.

[0157] After obtaining the items to be recommended, the first recommendation score of the items can be calculated based on the promotion fees of the second network node on the order platform, the delivery fees of the target order, and the order commission corresponding to the second network node.

[0158] Step 204: Send the item category to which the recommended item belongs to the user.

[0159] After obtaining the items to be recommended, the item category to which the items belong can be sent to the user.

[0160] Step 205: Receive the user's trigger operation for the target item category in the item category.

[0161] A trigger operation refers to a user's action on a target item category within an item category.

[0162] After sending the item categories to be recommended to the user, these item categories can be displayed on the user's terminal display screen. Then, the user can perform a trigger operation on the target item category.

[0163] After receiving the user's trigger operation on the target item category, proceed to step 206.

[0164] Step 206: In response to the triggering operation, determine the first weight corresponding to the target item type and the second weight of other item types besides the target item type.

[0165] After receiving a user's trigger operation on a target item category, the system can respond to the trigger operation by determining the first weight of the target item category and the second weight of other item categories besides the target item category.

[0166] Step 207: Based on the first weight and the second weight, the first recommendation score is weighted to obtain the second recommendation score corresponding to the item to be recommended.

[0167] After obtaining the first weight and the second weight, the first recommendation score can be weighted based on the first weight and the second weight to obtain the second recommendation score corresponding to the item to be recommended.

[0168] After obtaining the second recommendation score for the item to be recommended, proceed to step 208.

[0169] Step 208: Determine the target recommended item among the items to be recommended based on the second recommendation score.

[0170] After obtaining the second recommendation score for the item to be recommended, the target recommended item can be determined from among the items to be recommended based on the second recommendation score.

[0171] Step 209: After receiving the user's order for the target item in the target recommended items, based on the delivery fee of the target order, deliver the target item and the order items corresponding to the target order to the user.

[0172] After identifying the target recommended items, these items can be sent to the user, who can then select one of them to place an order.

[0173] After receiving a user's order for a target item from the recommended items, the system can deliver the target item and the corresponding order items to the user based on the delivery fee of the target order. This means that the delivery fee of one order can be used to complete the delivery of at least two orders, thereby reducing the delivery fees paid by users while increasing the sales volume of items on the order platform.

[0174] The embodiments of this disclosure combine the promotion fees of network nodes, the delivery fees of a single order, and the commission of a single order as constraints for item recommendation, and perform cross-network node item recommendation. This can reduce the cost for users to purchase items across network nodes and the time for order splitting and delivery, thereby improving the user experience.

[0175] The item recommendation method provided in this disclosure obtains a user's target order within a first network node, determines the recommended items corresponding to the target order within a second network node based on pre-defined order information associated with the target order, and determines the target recommended items among the recommended items based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. After receiving an order from a user for the target item among the recommended items, the method delivers the target item and the corresponding order items to the user based on the delivery fee of the target order. This disclosure, by combining the promotion fee of a network node, the delivery fee of a single order, and the commission of a single order as constraints for item recommendation, performs cross-network node item recommendation, reducing the cost for users to purchase items across network nodes and the time for order splitting and delivery, thus improving the user experience.

[0176] Example 3 Reference Figure 3 The diagram shows a structural schematic of an item recommendation device provided in an embodiment of this disclosure, such as... Figure 3 As shown, the item recommendation device 300 may specifically include the following modules: The target order acquisition module 310 is used to acquire the user's target orders within the first network node; The item to be recommended module 320 is used to determine the item to be recommended corresponding to the target order in the second network node based on the order information of the preset dimension associated with the target order; The target recommended item determination module 330 is used to determine the target recommended item among the items to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. The target item delivery module 340 is used to deliver the target item and the corresponding order items to the user based on the delivery fee of the target order after receiving the user's order for the target item in the target recommended items.

[0177] The item recommendation device provided in the embodiments of this disclosure obtains a user's target order within a first network node, determines the recommended items corresponding to the target order within a second network node based on the pre-defined order information associated with the target order, and determines the target recommended items among the recommended items based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. After receiving the user's order for the target item among the recommended items, the device delivers the target item and the corresponding order items to the user based on the delivery fee of the target order. The embodiments of this disclosure, by combining the promotion fee of the network node, the delivery fee of a single order, and the commission of a single order as constraints for item recommendation, perform cross-network node item recommendation, which can reduce the cost for users to purchase items across network nodes and the time for order splitting and delivery, thereby improving the user experience.

[0178] Example 4 Reference Figure 4 The diagram illustrates a structural schematic of another item recommendation device provided in an embodiment of this disclosure, such as... Figure 4 As shown, the item recommendation device 400 may specifically include the following modules: The target order acquisition module 410 is used to acquire the user's target orders within the first network node; The item to be recommended module 420 is used to determine the item to be recommended corresponding to the target order in the second network node based on the order information of the preset dimension associated with the target order; The target recommended item determination module 430 is used to determine the target recommended item among the items to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. The target item delivery module 440 is used to deliver the target item and the corresponding order items to the user based on the delivery fee of the target order after receiving the user's order for the target item in the target recommended items.

[0179] Optionally, the item to be recommended determination module 420 includes: The first target type acquisition unit is used to acquire the target item type corresponding to the target order; The target combination type determination unit is used to determine the target combination type among the combination types based on the number of times the combination types of the target item type co-occur within a preset time period from the current time. The first item determination unit is used to determine the recommended item corresponding to the target order in the second network node based on the target matching type.

[0180] Optionally, the item to be recommended determination module 420 includes: The second target type acquisition unit is used to acquire the order time corresponding to the target order and the target item type corresponding to the target order; The matching type determination unit is used to determine the matching type corresponding to the target item type based on the target time period in which the order is placed; The second item determination unit is used to determine the recommended item corresponding to the target order within the second network node based on the combination type.

[0181] Optionally, the item to be recommended determination module 420 includes: The order price determination unit is used to determine the price information of a single order corresponding to the user based on the user's historical order information; The third item determination unit is used to determine the item to be recommended corresponding to the target order within the second network node based on the single order price information.

[0182] Optionally, the item to be recommended determination module 420 includes: The user preference determination unit is used to determine the user's user preferences based on the user's historical order information; The fourth item determination unit is used to determine the recommended item corresponding to the target order within the second network node based on the user preference.

[0183] Optionally, the item to be recommended determination module 420 includes: The main item category determination unit is used to determine the main item category corresponding to the target order based on the order information of a preset dimension associated with the target order; The item to be recommended acquisition unit is used to determine the target item of the main item category based on the traffic data of each item in the main item category, and to use the target item as the item to be recommended.

[0184] Optionally, the target recommended item determination module 430 includes: The first recommendation score determination unit 431 is used to determine the first recommendation score corresponding to the item to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. The item category sending unit 432 is used to send the item category to which the item to be recommended belongs to the user; Trigger operation receiving unit 433 is used to receive the user's trigger operation on the target item type in the item type; The item weight determination unit 434 is used to determine the first weight corresponding to the target item type and the second weight of other item types besides the target item type in response to the triggering operation. The second recommendation score acquisition unit 435 is used to perform weighted processing on the first recommendation score based on the first weight and the second weight to obtain the second recommendation score corresponding to the item to be recommended; The target recommended item determination unit 436 is used to determine the target recommended item among the items to be recommended based on the second recommendation score.

[0185] Optionally, the target recommended item determination unit 436 includes: The item sorting subunit is used to sort the items to be recommended in descending order of the second recommendation score; The target recommended item acquisition subunit is used to filter out the top N recommended items from the items to be recommended based on the sorting results, and to use the top N recommended items as the target recommended items. Where N is a positive integer greater than or equal to 1.

[0186] The item recommendation device provided in the embodiments of this disclosure obtains a user's target order within a first network node, determines the recommended items corresponding to the target order within a second network node based on the pre-defined order information associated with the target order, and determines the target recommended items among the recommended items based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. After receiving the user's order for the target item among the recommended items, the device delivers the target item and the corresponding order items to the user based on the delivery fee of the target order. The embodiments of this disclosure, by combining the promotion fee of the network node, the delivery fee of a single order, and the commission of a single order as constraints for item recommendation, perform cross-network node item recommendation, which can reduce the cost for users to purchase items across network nodes and the time for order splitting and delivery, thereby improving the user experience.

[0187] Embodiments of this disclosure also provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the item recommendation method of the foregoing embodiments.

[0188] Embodiments of this disclosure also provide a readable storage medium that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the item recommendation method of the foregoing embodiments.

[0189] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0190] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of this disclosure are not directed to any particular programming language. It should be understood that the embodiments of this disclosure described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of this disclosure.

[0191] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0192] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various inventive aspects, in the foregoing description of exemplary embodiments of this disclosure, various features of embodiments of this disclosure are sometimes grouped together in a single embodiment, figure, or description thereof. However, this approach to disclosure should not be construed as reflecting an intention that the claimed embodiments of this disclosure require more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the present disclosure.

[0193] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature serving the same, equivalent, or similar purpose.

[0194] The various component embodiments of this disclosure can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the motion picture generation device according to embodiments of this disclosure. Embodiments of this disclosure can also be implemented as device or apparatus programs for performing some or all of the methods described herein. Such programs implementing embodiments of this disclosure can be stored on a computer-readable medium or can take the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0195] It should be noted that the above embodiments are illustrative of embodiments of this disclosure and not restrictive of embodiments of this disclosure, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of this disclosure can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0196] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0197] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the embodiments of the present disclosure. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the embodiments of the present disclosure should be included within the protection scope of the embodiments of the present disclosure.

[0198] The above description is merely a specific implementation of the embodiments of this disclosure, but the protection scope of the embodiments of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this disclosure should be included within the protection scope of the embodiments of this disclosure. Therefore, the protection scope of the embodiments of this disclosure should be determined by the protection scope of the claims.

Claims

1. A product recommendation method applied to an order platform, characterized in that, include: Obtain the user's target order within the first network node; Based on the order information of the preset dimensions associated with the target order, determine the items to be recommended corresponding to the target order within the second network node; The first recommendation score for the item to be recommended is determined based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. Send the item category to which the recommended item belongs to the user; Receive the user's trigger operation for the target item category in the item category; In response to the triggering operation, a first weight corresponding to the target item type and a second weight of other item types besides the target item type are determined. Based on the first weight and the second weight, the first recommendation score is weighted to obtain the second recommendation score corresponding to the item to be recommended; The items to be recommended are sorted in descending order of the second recommendation score; Based on the sorting results, the top N items to be recommended are selected from the list of items to be recommended, and these top N items are used as the target recommended items. Where N is a positive integer greater than or equal to 1; After receiving the user's order for a target item from the recommended items, the system delivers the target item and the corresponding order items to the user based on the delivery fee of the target order.

2. The method according to claim 1, characterized in that, The step of determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Obtain the type of target item corresponding to the target order; The target combination type is determined based on the number of times the combination types of the target item type co-occur within a preset time period from the current time. Based on the target combination type, determine the items to be recommended corresponding to the target order within the second network node.

3. The method according to claim 1, characterized in that, The step of determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Obtain the order placement time corresponding to the target order, and the type of target item corresponding to the target order; Based on the target time period in which the order is placed, determine the matching categories corresponding to the target item category; Based on the aforementioned combination type, determine the recommended items corresponding to the target order within the second network node.

4. The method according to claim 1, characterized in that, The step of determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the user's historical order information, determine the price information of the single order corresponding to the user; Based on the price information of the single order, the item to be recommended corresponding to the target order within the second network node is determined.

5. The method according to claim 1, characterized in that, The step of determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the user's historical order information, determine the user's user preferences; Based on the user preferences, determine the items to be recommended corresponding to the target order within the second network node.

6. The method according to claim 1, characterized in that, The step of determining the recommended item corresponding to the target order within the second network node based on the order information of a preset dimension associated with the target order includes: Based on the order information of the preset dimensions associated with the target order, determine the main item type corresponding to the target order; Based on the traffic data of each item in the main item category, the target item of the main item category is determined, and the target item is selected as the item to be recommended.

7. A product recommendation device applied to an order platform, characterized in that, include: The target order acquisition module is used to acquire the user's target orders within the first network node; The module for determining items to be recommended is used to determine the items to be recommended corresponding to the target order within the second network node based on the order information of the target order in a preset dimension. The first recommendation score determination module is used to determine the first recommendation score corresponding to the item to be recommended based on the promotion fee of the second network node on the order platform, the delivery fee of the target order, and the order commission corresponding to the second network node. The item category sending module is used to send the item category to which the recommended item belongs to the user; A trigger operation receiving module is used to receive the user's trigger operation on the target item category among the item categories; The weight determination module is used to determine, in response to the triggering operation, a first weight corresponding to the target item type and a second weight of other item types besides the target item type. The second recommendation score determination module is used to perform weighted processing on the first recommendation score based on the first weight and the second weight to obtain the second recommendation score corresponding to the item to be recommended; The sorting and filtering module is used to sort the items to be recommended in descending order of the second recommendation score, and to filter out the top N items to be recommended from the items to be recommended based on the sorting result, and to use the top N items to be recommended as the target recommended items, where N is a positive integer greater than or equal to 1. The target item delivery module is used to deliver the target item and the corresponding order items to the user based on the delivery fee of the target order after receiving the user's order for the target item in the target recommended items.

8. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the article recommendation method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the article recommendation method according to any one of claims 1 to 6.

Images