Merchant recommendation method and apparatus, electronic device, and readable storage medium

Abstract

The present disclosure provides a merchant recommendation method and device, electronic equipment and readable storage medium, the method comprises: determining the position of a target user as a target user position; determining at least one candidate merchant whose delivery range covers the target user position; for the candidate merchant, obtaining the target delivery position of the target order of the candidate merchant, the target order is an order in an undelivered state, the undelivered state includes one of a delivery performer rushing state and a delivery performer in-store state; when the distance between at least one target delivery position of the candidate merchant and the target user position is less than or equal to a preset distance threshold, the candidate merchant is recommended to the target user according to the candidate merchant. The present disclosure can reduce the delivery time.

Description

Technical Field

[0001] This disclosure relates to the field of personalized recommendation technology, and in particular to a merchant recommendation method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] In the field of personalized recommendation technology, different objects can be recommended to different users. These objects are typically merchants.

[0003] In existing technologies, a merchant recommendation method mainly includes: First, obtaining user information, merchant information, and platform information. The user information includes age, gender, location, education level, income, and personal interests. The merchant information includes industry, main product category, and geographical location. The platform information includes contextual information, browsing scenario information, and display style information. Then, determining the matching degree between the merchant and the user based on the user information, merchant information, and platform information. Finally, recommending merchants to the user based on the matching degree.

[0004] After studying the above solution, the inventors found that when the solution recommends merchants that provide instant delivery services, the delivery time is relatively long after the user places an order with the recommended merchant. Summary of the Invention

[0005] This disclosure provides a merchant recommendation method, apparatus, electronic device, and readable storage medium that can recommend merchants offering instant delivery services to target users by using undelivered orders as target orders and selecting candidate merchants whose target delivery locations are close to the target user's location, thereby reducing delivery time.

[0006] According to a first aspect of this disclosure, a merchant recommendation method is provided, the method comprising:

[0007] Determine the target user's location as the target user's location;

[0008] Identify at least one candidate merchant whose delivery area covers the target user's location;

[0009] For the candidate merchants, obtain the target delivery location of the target orders of the candidate merchants. The target orders are orders in an undelivered state, which includes one of the following: the delivery executor is on its way or the delivery executor is in the store.

[0010] When it is determined that the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold, merchant recommendations are made to the target user based on the candidate merchants.

[0011] According to a second aspect of this disclosure, a merchant recommendation device is provided, the device comprising:

[0012] The target user location determination module is used to determine the location of the target user as the target user location.

[0013] The candidate merchant determination module is used to determine at least one candidate merchant whose delivery range covers the location of the target user;

[0014] The target delivery location acquisition module is used to acquire the target delivery location of the target order of the candidate merchant. The target order is an order in an undelivered state, which includes one of the following: the delivery execution unit is on its way or the delivery execution unit is in the store.

[0015] The merchant recommendation module is used to recommend merchants to the target user when the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold.

[0016] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0017] 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 aforementioned merchant recommendation method.

[0018] According to a fourth aspect of this 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 aforementioned merchant recommendation method.

[0019] This disclosure provides a merchant recommendation method, apparatus, electronic device, and readable storage medium. It first determines the location of a target user; then determines at least one candidate merchant whose delivery range covers the target user's location; and for each candidate merchant, obtains the target delivery location of a target order, where the target order is an order in an undelivered state, including either a delivery executor's en route state or a delivery executor's in-store state. Finally, when the distance between at least one target delivery location of the candidate merchant and the target user's location is less than or equal to a preset distance threshold, a merchant recommendation is made to the target user based on the candidate merchant. This disclosure, when recommending merchants offering instant delivery services to a target user, uses undelivered orders as target orders and selects candidate merchants whose target delivery locations are close to the target user's location, thus reducing delivery time. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of this disclosure, the accompanying drawings used in the description of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of the merchant recommendation method disclosed herein is shown;

[0022] Figure 2 This illustration shows the multiple states of an order as disclosed herein, from order placement to delivery arrival and after delivery arrival.

[0023] Figure 3 This illustration shows a scenario diagram of merchant recommendation in this disclosure;

[0024] Figure 4 A structural diagram of the merchant recommendation device of this disclosure is shown;

[0025] Figure 5 A structural diagram of the electronic device disclosed herein is shown. Detailed Implementation

[0026] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0027] The embodiments of this disclosure can be applied to a backend server, where the backend server and the corresponding client constitute a complete personalized recommendation platform. Specifically, users can perform operations on the client, which generates data requests based on the user's operations and sends them to the backend server. The backend server then generates business data based on the data requests and returns it to the client for display to the user. In the embodiments of this disclosure, the personalized recommendation platform is an online sales platform, the backend server is the backend server of the online sales platform, the client is the client of the online sales platform, and the recommended items to the user are merchants registered on the online sales platform.

[0028] Reference Figure 1 The flowchart illustrating the merchant recommendation method disclosed herein is as follows:

[0029] Step 101: Determine the location of the target user as the target user location.

[0030] The target users are any users who intend to place an order, including but not limited to: users browsing the online sales platform and users running the client of the online sales platform in the background.

[0031] The target user location mentioned above can be any location related to the target user, including but not limited to: the target user's current location, locations in historical orders, and frequently used locations set by the target user. Specifically, it can be determined based on user actions. If the user selects a location from historical orders or a frequently used location, that location will be used as the target user's location; if the user does not select any location, the current location will be used as the target user's location.

[0032] It is understandable that the above locations can all be represented by latitude and longitude.

[0033] Step 102: Identify at least one candidate merchant whose delivery range covers the target user's location.

[0034] Specifically, candidate merchants can be determined from a target merchant set. This target merchant set can include any merchant used for recommendation. For example, it could include all merchants on an online sales platform or merchants within a designated region. Alternatively, when recommending merchants through a specific advertising space, the target merchant set could also be all merchants who successfully bid for that advertising space.

[0035] The aforementioned target merchant group includes several merchants, each with a pre-defined delivery range. Therefore, the merchant only accepts orders from locations within this delivery range as the target delivery location. It can be understood that the delivery range can be an area marked on a map when the merchant registers on the platform, or it can be a region within a certain distance centered on the merchant's location. The embodiments of this disclosure do not limit the specific form of the delivery range.

[0036] When determining whether the delivery range covers the target user's location, it can be determined based on the longitude and latitude of the target user's location. If both the longitude and latitude are within the delivery range, then the delivery range covers the target user's location; if either the longitude or latitude is not within the delivery range, then the delivery range does not cover the target user's location.

[0037] Step 103: For the candidate merchant, obtain the target delivery location of the target order of the candidate merchant. The target order is an order in an undelivered state. The undelivered state includes one of the following: the delivery execution unit is on its way or the delivery execution unit is in the store.

[0038] The target order is an order that the merchant has accepted but has not yet started delivery. It includes two states: the delivery executor is on its way to the merchant and the delivery executor is waiting at the merchant to prepare the order. In the embodiments of this disclosure, these two states are respectively referred to as the delivery executor on its way state and the delivery executor in store state.

[0039] The delivery execution entity is the entity that delivers the goods or services in the target order from the merchant's location to the target delivery location, including but not limited to: people and equipment. For example, delivery personnel, automated delivery equipment, etc.

[0040] In another embodiment of this disclosure, the delivery executor includes one of a drone and an unmanned vehicle.

[0041] It's understandable that drones and unmanned vehicles are both types of automated delivery equipment that can deliver goods to the target location without human intervention, thus helping to reduce labor costs.

[0042] In the embodiments disclosed herein, an order can be divided into multiple states from the time it is placed until delivery arrives, and after delivery, such as... Figure 2The states are divided as follows: the state between order placement and merchant acceptance is called the "waiting for merchant acceptance state"; the state between merchant acceptance and allocation of the delivery executor is called the "waiting for allocation of the delivery executor state"; the state between allocation of the delivery executor and the delivery executor arriving at the store is called the "delivery executor on its way state"; the state between the delivery executor arriving at the store and the start of delivery is called the "delivery executor in store state"; the state between the start of delivery and delivery arrival is called the "delivery executor delivery state"; and the state after delivery arrival is called the "order completed state". The delivery executor, as understood in this embodiment, can record the current state of each order and the start time of the current state. For example, after an order is placed, its current status is recorded as "Waiting for Merchant to Accept Order," and the start time of this "Waiting for Merchant to Accept Order" status is recorded as the order placement time. After the order is accepted by the merchant, its current status is updated to "Waiting for Delivery Execution Unit Assignment," and the start time of this "Waiting for Delivery Execution Unit Assignment" status is recorded as the merchant acceptance time. After the order is assigned to a delivery execution unit, its current status is updated to "Delivery Execution Unit On its Way," and the start time of this "Delivery Execution Unit On its Way" status is recorded as the delivery execution unit assignment time. After the delivery execution unit arrives at the store, its current status is updated to "Delivery Execution Unit In-Store," and the start time of this "Delivery Execution Unit In-Store" status is recorded as the delivery execution unit arrival time. After the order begins delivery, its current status is updated to "Delivery Execution Unit Delivery Status," and the start time of this "Delivery Execution Unit Delivery Status" is recorded as the delivery start time. After the order is delivered and arrived, its current status is updated to "Order Completed," and the start time of this "Order Completed" status is recorded as the delivery arrival time.

[0043] Based on the current status recorded above, target orders in either the "delivery executor en route" or "delivery executor in store" status can be obtained, and the target delivery location can be extracted from the target order information. The target delivery location is the delivery location specified by the user when placing the order, and can be extracted from the target order information. Of course, in addition to the target delivery location, the order information also includes the order number, user name, user identifier, purchased goods or services, merchant name, merchant number, and merchant location. It can be understood that this target delivery location is also represented by latitude and longitude.

[0044] Step 104: When it is determined that the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold, merchant recommendations are made to the target user based on the candidate merchants.

[0045] Specifically, if the distance between at least one target delivery location of a candidate merchant and the target user's location is less than or equal to a preset distance threshold, the candidate merchant is added to the set of merchants to be recommended. Then, some or all of the merchants in the set of merchants to be recommended are selected and recommended to the target user.

[0046] The preset distance threshold can be set according to the actual application scenario, and the embodiments of this disclosure do not impose any limitations on it. The preset distance threshold is used to limit the distance between the target delivery location and the target user location at which the delivery routes between the two are considered to be relatively convenient. Specifically, if the distance between the target delivery location and the target user location is less than or equal to the preset distance threshold, the delivery routes between the two are considered to be convenient; if the distance between the target delivery location and the target user location is greater than the preset distance threshold, the delivery routes between the two are considered to be inconvenient.

[0047] It's understandable that for each candidate merchant, if there are target orders for that merchant, then if the target delivery location of the target order is along the same route as the target user's location, the candidate merchant can be recommended to the target user. This allows new orders placed by the target user to be delivered together with the target order, helping to reduce the target user's waiting time, for example, saving time such as... Figure 2 The data shows the time between the merchant accepting the order and the allocation of the delivery execution unit, and / or the time between the allocation of the delivery execution unit and the delivery execution unit arriving at the store. Furthermore, this can reduce delivery costs and improve delivery efficiency.

[0048] However, if the candidate merchant does not have any target orders, or if the target delivery locations of all target orders of the candidate merchant are not conveniently located for delivery to the target user, then the candidate merchant will not be recommended to the target user.

[0049] Figure 3 The illustration shows a scenario diagram of merchant recommendation in this disclosure, such as... Figure 3 As shown, user USR1 has placed an order with merchant MCT, and the delivery execution unit RDR is en route to merchant MCT. Therefore, user USR1's order with merchant MCT is the target order for that merchant MCT. Meanwhile, user USR2 is browsing an online sales platform. Since the distance between user USR2 and user USR1 is less than or equal to a preset distance threshold, merchant MCT can be recommended to user USR2, allowing user USR2 to place an order with merchant MCT. Ultimately, the delivery execution unit RDR can deliver both user USR1's and user USR2's orders together. Of course, in... Figure 3 When the delivery execution entity RDR in the system has reached the merchant MCT, it can also recommend the merchant MCT to the user USR2.

[0050] Optionally, in another embodiment of this disclosure, step 104 includes sub-steps A1 to A2:

[0051] Sub-step A1: When the distance between at least one of the target delivery locations of the candidate merchant and the target user location is less than or equal to a preset distance threshold, the time required for the target order of the candidate merchant to be updated from the waiting for delivery execution body status to the undelivered status is obtained, and this time is used as the time saved for the candidate merchant.

[0052] The time required for a target order to change from a status of waiting for a delivery executor to a status of not being delivered includes at least the waiting time required for the delivery executor to be assigned, and may also include the waiting time required for the delivery executor to travel to the merchant.

[0053] Specifically, when the "not yet delivered" status is "delivery executor on its way" status, the saved time is the time consumed while waiting for the delivery executor to be assigned, which is... Figure 2 The time between a merchant accepting an order and the allocation of a delivery execution unit. Based on the start time of each recorded state, the difference between the start time of the delivery execution unit heading to the current state and the start time of the waiting state for allocation to the delivery execution unit can be used as the time saved.

[0054] When the "not delivered" status is "delivery executor in store," the time saved is the total time spent waiting for a delivery executor to be assigned and the time consumed by the delivery executor to arrive at the store. Figure 2 The time from when a merchant receives an order to when the delivery executor arrives at the store. Based on the start time of each recorded state, the difference between the start time of the delivery executor's "in-store" state and the start time of the "waiting for delivery executor allocation" state can be used as the time saved. Alternatively, one can first calculate the first difference between the start time of the delivery executor's "in-store" state and the start time of the delivery executor's "on-the-go" state, then calculate the second difference between the start time of the delivery executor's "on-the-go" state and the start time of the "waiting for delivery executor allocation" state, and finally calculate the sum of the first and second differences as the time saved.

[0055] It should be noted that when a candidate merchant has multiple target orders, and the distance between the target delivery location and the target user's location for these multiple target orders is less than or equal to a preset distance threshold, the candidate merchant will have multiple corresponding time-saving durations. The longest time-saving duration can be selected as the candidate merchant's time-saving duration, and after a user places an order with the candidate merchant, the target order corresponding to that time-saving duration will be delivered together with the new order. For example, for a candidate merchant with two target orders: ORF1, ORF2, and ORF3, whose target delivery locations are 500 meters, 700 meters, and 300 meters from the target user's location, respectively, and whose time-saving durations are 11 minutes, 15 minutes, and 10 minutes, respectively; if the preset distance threshold is 500 meters, then the distances between the target delivery locations and the target user's location for both ORF1 and ORF3 are less than or equal to the preset distance threshold. Since the time-saving duration of ORF1 is greater than that of ORF3, the time-saving duration for this candidate merchant is 11 minutes, and ORF1 will be delivered together with the new order.

[0056] Sub-step A2: Display the candidate merchants and the time-saving duration of the candidate merchants to the target user.

[0057] Specifically, candidate merchants can be recommended to target users in descending order of time saved, allowing target users to prioritize placing orders with merchants offering greater time savings, thus improving the user experience. Alternatively, candidate merchants can be recommended to target users based on other quality scores, which may include, but are not limited to, predicted click-through rate, predicted order rate, and predicted advertising revenue. The embodiments disclosed herein do not impose any limitations on these aspects.

[0058] Click-through rate (CTR) can be predicted using a CTR prediction model, which is trained on training samples including labeled CTR values ​​and merchant features. When using CTR as a quality score, candidate merchants can be sorted in descending order by CTR to improve the overall CTR, which in turn increases advertising revenue.

[0059] The order rate can be predicted using an order rate prediction model, which is trained using a different set of training samples. This training sample includes labeled order rates and sample merchant features. When using the order rate as a quality score, candidate merchants can be ranked in descending order of order rate to improve the overall order rate. A higher order rate leads to increased revenue for both the merchant and the online sales platform.

[0060] It is understandable that click-through rate prediction models and order rate prediction models can be any learnable model, such as deep learning models, logistic regression models, etc.

[0061] After predicting the click-through rate (CTR), the advertising revenue can be calculated by multiplying the CTR by the bids of candidate merchants during the bidding process. When using advertising revenue as a quality score, candidate merchants can be sorted in descending order based on advertising revenue, directly increasing the advertising revenue of the online sales platform.

[0062] After sorting the candidate merchants according to the above methods, the candidate merchants are recommended to the target users, and the time saved is displayed to the target users as a prompt.

[0063] The embodiments of this disclosure can recommend candidate merchants to users while prompting them to save time, which helps to further improve click-through rates, order rates and advertising revenue.

[0064] Optionally, in another embodiment of this disclosure, step 104 includes sub-steps B1 to B2:

[0065] Sub-step B1: When it is determined that the distance between at least one of the target delivery locations of the candidate merchant and the target user's location is less than or equal to a preset distance threshold, the waiting time of the target user is predicted based on the number of unprepared orders of the candidate merchant and the delivery distance of the target user.

[0066] The number of unprepared orders refers to the number of orders that candidate merchants have not yet prepared. If a target user places an order at the current time, these unprepared orders will be ranked before any new orders placed by the target user. The number of unprepared orders includes any new orders placed by the user.

[0067] Specifically, first, the order preparation time is obtained by multiplying the number of unprepared orders by the average preparation time of the orders; then, the delivery time is obtained by calculating the ratio of the delivery distance to the delivery speed between the target user's location and the candidate merchant's location; finally, the order preparation time and the delivery time are added together to obtain the target user's waiting time.

[0068] Sub-step B2: Display the candidate merchants and their waiting times to the target user.

[0069] Specifically, candidate merchants can be sorted in descending order according to waiting time and then displayed to the target user.

[0070] The embodiments of this disclosure can recommend candidate merchants to target users while simultaneously informing them of the waiting time. Since this waiting time saves the time consumed by waiting for the delivery execution unit to be assigned and for the delivery execution unit to arrive, it reduces the target user's waiting time and helps to increase the target user's order rate.

[0071] Optionally, in another embodiment of this disclosure, sub-step A2 includes sub-steps C1 to C2:

[0072] Sub-step C1: Predict the time required for the target order of the candidate merchant to change from the undelivered status to the delivery execution status, and use this as the order deadline for the candidate merchant.

[0073] The order deadline is the time between the current time and the start of delivery for the target order. The order deadline serves as a reminder to users that placing an order within this timeframe can reduce waiting time. When the order deadline becomes 0, it means the target order is already in the delivery execution phase, and new orders placed by the user will not be able to be delivered together with this target order.

[0074] It is understandable that when the "not delivered" status is "delivery executor on its way", the order deadline is the sum of the remaining time required for the delivery executor to reach the candidate merchant and the time the delivery executor has been in the store. The order deadline can be predicted. Specifically, first, the distance between the current location of the delivery vehicle and the merchant's location is obtained, and this distance is divided by the average speed of the delivery vehicle to get the remaining time required for the delivery vehicle to reach the merchant. Then, the number of orders to be prepared (orders waiting for the merchant to prepare before the target order and the target order) is multiplied by the average preparation time of the orders to get the preparation time of the target order. Finally, if the preparation time is less than or equal to the remaining time, the delivery vehicle does not need to wait for the candidate merchant to prepare the goods for the target order after arriving at the store, thus determining that the delivery vehicle's time in the store is 0, and the order deadline is the remaining time. If the preparation time is greater than the remaining time, the delivery vehicle needs to wait in the store for the candidate merchant to prepare the goods for the target order, and the delivery vehicle's time in the store is the difference between the remaining time and the preparation time, and the order deadline is the remaining time.

[0075] When the undelivered status is the delivery executor in-store status, the order deadline is the time required for the delivery executor to wait in-store. This waiting time is the product of the number of orders to be prepared (orders waiting for the merchant to prepare before the target order and the target order) and the average preparation time of the orders.

[0076] Sub-step C2 displays the candidate merchants, the time-saving period of the candidate merchants, and the order deadline of the candidate merchants to the target user.

[0077] After sorting the candidate merchants according to the method of sub-step A2, the candidate merchants are recommended to the target users, and the time saved and the order deadline are displayed to the target users as prompt information.

[0078] The embodiments of this disclosure can remind target users of the order deadline, which helps to reduce waiting time by prompting users to place orders within the deadline.

[0079] Optionally, in another embodiment of this disclosure, sub-step C2 includes sub-steps D1 to D2:

[0080] Sub-step D1: Sort the candidate merchants in descending order according to the time saved to obtain a candidate merchant queue.

[0081] It is understandable that the time saved by the candidate merchants ranked higher is greater, while the time saved by the candidate merchants ranked lower is smaller.

[0082] Sub-step D2: According to the order of the candidate merchants in the candidate merchant queue, display the candidate merchants, the time-saving time of the candidate merchants, and the order deadline of the candidate merchants to the target user.

[0083] The embodiments of this disclosure can recommend merchants to target users based on the time saved, which helps to reduce the waiting time of target users.

[0084] Optionally, in another embodiment of this disclosure, sub-step C2 includes sub-steps E1 to E2:

[0085] Sub-step E1: Sort the candidate merchants in ascending order according to the order deadline to obtain a candidate merchant queue.

[0086] In embodiments of this disclosure, merchants can also be sorted in ascending order by their order deadline, placing candidates with shorter deadlines at the top and those with longer deadlines at the bottom. This allows the user to select a lower-ranked merchant if they are dissatisfied with a higher-ranked one. This avoids a situation where a new order placed by a user with a longer deadline cannot be delivered along with a previously placed order that now has a zero deadline, if the user is dissatisfied with a merchant with a longer deadline.

[0087] Sub-step E2: According to the order of the candidate merchants in the candidate merchant queue, display the candidate merchants, the time-saving time of the candidate merchants, and the order deadline of the candidate merchants to the target user.

[0088] The embodiments disclosed herein can recommend merchants to target users based on the order deadline, which helps to ensure that users have a wide range of merchants to choose from.

[0089] Optionally, in another embodiment of this disclosure, sub-step D2 or sub-step E2 includes sub-steps F1 to F4:

[0090] Sub-step F1: For each candidate merchant in the candidate merchant queue, obtain the feature information of the candidate merchant.

[0091] The merchant's characteristics include: merchant type, merchant name, merchant location, historical sales volume, and historical visit count. Merchant type, merchant name, and merchant location can be obtained from the online sales platform's merchant information database, while historical sales volume and historical visit count can be statistically obtained from the online sales platform's user behavior records.

[0092] Sub-step F2 involves inputting the feature information into the click-through rate prediction model to obtain the click-through rate of the candidate merchant. The click-through rate prediction model is trained using training samples, which include: sample merchant features and sample click-through rates.

[0093] Here, "sample merchant features" refers to the characteristic information of the sample merchants, and "sample click-through rate" refers to the click-through rate of the sample merchants. Click-through rate can be obtained from user behavior records. For example, user behavior records may contain information about several users' visits to the sample merchant, and the merchant's exposure information can also be recorded. Therefore, the number of visits can be counted as the number of visits, and the number of exposures can be counted. Finally, the ratio of exposures to visits is calculated as the click-through rate.

[0094] Sub-step F3 calculates the product of the candidate merchant's advertising bid parameter and the click-through rate as the quality score of the candidate merchant.

[0095] Among them, the advertising bid parameter is the bid made by candidate merchants when bidding for advertising space.

[0096] It's understandable that the quality score equates to advertising revenue.

[0097] Sub-step F4: Based on the order of candidate merchants in the candidate merchant queue and the quality score, display the candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants to the target user.

[0098] Specifically, the candidate merchants in the candidate merchant queue can be sorted in descending order according to their quality scores and then displayed to the target merchant. The system can also simultaneously display the time-saving period and the order deadline for each candidate merchant.

[0099] In addition, candidate merchants whose quality scores are below a certain quality threshold can be removed from the candidate merchant queue. Then, the merchants can be recommended to the target merchant in the order of the candidate merchant queue, and the time-saving period and order deadline of each candidate merchant can be displayed at the same time.

[0100] It is understandable that, in practical applications, candidate merchants can be ranked according to at least one of the following indicators: quality score, time saved, and order deadline. There is no restriction on which indicator to rank them by first, then by next, or finally by last.

[0101] Embodiments of this disclosure can use advertising revenue as a quality score and recommend candidate merchants to target users based on the quality score, which helps to improve advertising revenue.

[0102] In summary, this disclosure provides a merchant recommendation method, comprising: determining the location of a target user as the target user location; determining at least one candidate merchant whose delivery range covers the target user location; for the candidate merchant, obtaining the target delivery location of the target order of the candidate merchant, wherein the target order is an order in an undelivered state, the undelivered state including: a delivery executor on its way state, a delivery executor in-store state; and when the distance between at least one of the target delivery locations of the candidate merchant and the target user location is less than or equal to a preset distance threshold, recommending the merchant to the target user based on the candidate merchant. This disclosure, when recommending merchants providing instant delivery services to the target user, uses undelivered orders as target orders and selects candidate merchants whose target delivery locations are close to the target user's location to recommend to the target user, thereby reducing delivery time.

[0103] Reference Figure 4 The diagram shows a structural representation of the merchant recommendation device disclosed herein, as follows:

[0104] The target user location determination module 201 is used to determine the location of the target user as the target user location.

[0105] The candidate merchant determination module 202 is used to determine at least one candidate merchant whose delivery range covers the location of the target user.

[0106] The target delivery location acquisition module 203 is used to acquire the target delivery location of the target order of the candidate merchant. The target order is an order in an undelivered state, which includes one of the following: the delivery execution unit is on its way or the delivery execution unit is in the store.

[0107] The merchant recommendation module 204 is used to recommend merchants to the target user when the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold.

[0108] Alternatively, in another embodiment of this disclosure, the delivery executor includes either a drone or an unmanned vehicle.

[0109] Optionally, in another embodiment of this disclosure, the merchant recommendation module 204 includes a time-saving acquisition submodule and a first merchant recommendation submodule:

[0110] The time-saving acquisition submodule is used to determine that when the distance between at least one of the target delivery locations of the candidate merchant and the target user location is less than or equal to a preset distance threshold, the time required for the target order of the candidate merchant to be updated from the waiting for delivery execution body status to the undelivered status is used as the time-saving time corresponding to the candidate merchant.

[0111] The first merchant recommendation submodule is used to display the candidate merchants and the time-saving time of the candidate merchants to the target user.

[0112] Optionally, in another embodiment of this disclosure, the merchant recommendation module 204 includes a waiting time determination submodule and a second merchant recommendation submodule:

[0113] The waiting time determination submodule is used to predict the waiting time of the target user based on the number of unprepared orders of the candidate merchant and the delivery distance of the target user when the distance between at least one of the target delivery locations of the candidate merchant and the target user's location is less than or equal to a preset distance threshold.

[0114] The second merchant recommendation submodule is used to display the candidate merchants and their waiting times to the target user.

[0115] Optionally, in another embodiment of this disclosure, the first merchant recommendation submodule includes an order deadline acquisition unit and a merchant recommendation unit:

[0116] The order deadline acquisition unit is used to predict the time required for the target order of the candidate merchant to be updated from the undelivered status to the delivery execution status, and use it as the order deadline for the candidate merchant.

[0117] The merchant recommendation unit is used to display the candidate merchants, the time-saving period of the candidate merchants, and the order deadline of the candidate merchants to the target user.

[0118] Optionally, in another embodiment of this disclosure, the merchant recommendation unit includes a first sorting subunit and a first order recommendation subunit:

[0119] The first sorting subunit is used to sort the candidate merchants in descending order according to the time saved, so as to obtain a candidate merchant queue.

[0120] The first order recommendation subunit is used to display the candidate merchants, their time-saving duration, and their order deadline to the target user according to the order of the candidate merchants in the candidate merchant queue.

[0121] Optionally, in another embodiment of this disclosure, the merchant recommendation unit includes a second sorting subunit and a second order recommendation subunit:

[0122] The second sorting subunit is used to sort the candidate merchants in ascending order according to the order deadline to obtain a candidate merchant queue.

[0123] The second sequential recommendation subunit is used to display the candidate merchants, their time-saving duration, and their order deadline to the target user according to the order of the candidate merchants in the candidate merchant queue.

[0124] Optionally, in another embodiment of this disclosure, the first or second sequential recommendation subunit includes a feature information acquisition subunit, a click-through rate prediction subunit, a quality score calculation subunit, and a third sequential recommendation subunit:

[0125] The feature information acquisition subunit is used to acquire feature information of each candidate merchant in the candidate merchant queue.

[0126] The click-through rate prediction subunit is used to input the feature information into the click-through rate prediction model to obtain the click-through rate of the candidate merchant. The click-through rate prediction model is trained through training samples, which include: sample merchant features and sample click-through rates.

[0127] The quality score calculation subunit is used to calculate the product of the candidate merchant's advertising bid parameters and the click-through rate as the quality score of the candidate merchant.

[0128] The third recommendation subunit is used to display the candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants to the target user based on the quality score.

[0129] In summary, this disclosure provides a merchant recommendation device, comprising: a target user location determination module for determining the location of a target user; a candidate merchant determination module for determining at least one candidate merchant whose delivery range covers the target user's location; a target delivery location acquisition module for acquiring the target delivery location of a target order of the candidate merchant, wherein the target order is an order in an undelivered state, the undelivered state including: a delivery execution unit on its way state, or a delivery execution unit in-store state; and a merchant recommendation module for recommending merchants to the target user when the distance between at least one of the target delivery locations of the candidate merchant and the target user's location is less than or equal to a preset distance threshold. This disclosure, when recommending merchants offering instant delivery services to a target user, uses undelivered orders as target orders and selects candidate merchants whose target delivery locations are close to the target user's location, thus reducing delivery time.

[0130] The apparatus embodiments disclosed herein can be described in detail with reference to the method embodiments, and will not be repeated here.

[0131] This disclosure also provides an electronic device, with reference to Figure 5 The system includes: a processor 301, a memory 302, and a computer program 3021 stored in the memory 302 and executable on the processor. When the processor 301 executes the program, it implements the merchant recommendation method of the foregoing embodiments.

[0132] This disclosure also provides a readable storage medium that, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the merchant recommendation method of the foregoing embodiments.

[0133] 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.

[0134] 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, this disclosure is not directed to any particular programming language. It should be understood that the contents 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 this disclosure.

[0135] Numerous specific details are set forth in the specification provided herein. However, it will be understood that this disclosure can 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.

[0136] 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 above description of exemplary embodiments of this disclosure, various features 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 disclosure requires more features than are 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 this disclosure.

[0137] 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 that serves the same, equivalent, or similar purpose.

[0138] 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 merchant-recommended device according to this disclosure. This disclosure can also be implemented as a device or apparatus program for performing some or all of the methods described herein. Such an implementation 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.

[0139] It should be noted that the above embodiments are illustrative of this disclosure and not restrictive, and that alternative embodiments can be devised by those skilled in the art 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 the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. 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.

[0140] Those skilled in the art will clearly 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.

[0141] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

[0142] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A merchant recommendation method, characterized in that, The method includes: Determine the target user's location as the target user's location; Identify at least one candidate merchant whose delivery area covers the target user's location; For the candidate merchants, obtain the target delivery location of the target orders of the candidate merchants. The target orders are orders in an undelivered state, which includes one of the following: the delivery executor is on its way or the delivery executor is in the store. When it is determined that the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold, merchant recommendations are made to the target user based on the candidate merchants; The step of recommending merchants to the target user based on the candidate merchants when the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold includes: When it is determined that the distance between at least one of the target delivery locations of the candidate merchant and the target user location is less than or equal to a preset distance threshold, the time required for the target order of the candidate merchant to be updated from the waiting to be assigned delivery execution body state to the undelivered state is obtained, and this time is taken as the time saved for the candidate merchant. The candidate merchants and their time savings are displayed to the target users. The step of displaying the candidate merchants and their time-saving durations to the target user includes: The time required for the target order of the candidate merchant to change from the undelivered status to the delivery execution status is predicted and used as the order deadline for the candidate merchant. The candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants are displayed to the target users. The step of displaying the candidate merchants, the time-saving period of the candidate merchants, and the order deadline of the candidate merchants to the target user includes: The candidate merchants are sorted in descending order according to the time saved to obtain a candidate merchant queue. According to the order of the candidate merchants in the candidate merchant queue, the candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants are displayed to the target user. Alternatively, the step of displaying the candidate merchants, the time-saving period of the candidate merchants, and the order deadline of the candidate merchants to the target user includes: The candidate merchants are sorted in ascending order according to the order deadline to obtain a candidate merchant queue. According to the order of the candidate merchants in the candidate merchant queue, the candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants are displayed to the target user. The step of displaying the candidate merchants, their time-saving duration, and their order deadline to the target user according to the order of the candidate merchants in the candidate merchant queue includes: For each candidate merchant in the candidate merchant queue, obtain the characteristic information of the candidate merchant; The feature information is input into the click-through rate prediction model to obtain the click-through rate of the candidate merchant. The click-through rate prediction model is trained using training samples, which include: sample merchant features and sample click-through rates. The product of the candidate merchant's advertising bid parameter and the click-through rate is calculated as the quality score of the candidate merchant. Based on the quality score, the candidate merchants, the time saved by the candidate merchants, and the order deadline of the candidate merchants are displayed to the target user.

2. The method according to claim 1, characterized in that, The delivery execution vehicle includes either a drone or an unmanned vehicle.

3. The method according to claim 1, characterized in that, The step of recommending merchants to the target user based on the candidate merchants when the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold includes: When it is determined that the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold, the waiting time of the target user is predicted based on the number of unprepared orders of the candidate merchants and the delivery distance of the target user. The candidate merchants and their waiting times are displayed to the target user.

4. A merchant recommendation device, characterized in that, The device includes: The target user location determination module is used to determine the location of the target user as the target user location. The candidate merchant determination module is used to determine at least one candidate merchant whose delivery range covers the location of the target user; The target delivery location acquisition module is used to acquire the target delivery location of the target order of the candidate merchant. The target order is an order in an undelivered state, which includes one of the following: the delivery execution unit is on its way or the delivery execution unit is in the store. The merchant recommendation module is used to recommend merchants to the target user when the distance between at least one of the target delivery locations of the candidate merchants and the target user's location is less than or equal to a preset distance threshold.

5. 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 merchant recommendation method as described in any one of claims 1-3.

6. 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 merchant recommendation method as described in any one of claims 1-3.

Images