Advertisement pushing method and device for online fruit shopping mall

Abstract

The invention discloses an advertisement pushing method and device for an online fruit shopping mall, and relates to the technical field of advertisement pushing, and the method comprises the steps: sending an activity advertisement and a first questionnaire about whether to participate in an activity to a target member user, and obtaining a reply result of the first questionnaire; when the target user selects to participate in the activity, calculating the priority index of the store, sending the activity advertisement to the target member user again, and sequentially marking the priority selection sequence of the corresponding store in the newly sent activity advertisement from large to small according to the priority index of the store; and when the target member user selects not to participate in the activity temporarily, sending a second questionnaire and an activity advertisement to the user, and judging whether the activity advertisement needs to be sent to the target member user again according to a reply result of the second questionnaire, so that the user experience is improved, and the user experience is improved. And meanwhile, the advertisement can be flexibly pushed to the user according to the actual condition, so that the user is not disgusted, and the advertisement pushing budget is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of advertisement push, and in particular to an advertisement push method and device for an online fruit mall. Background Art

[0002] A fruit mall generally refers to a retail platform that specializes in selling various fruits. It usually includes two forms: online malls and offline stores. The offline stores of a general fruit mall are usually chain fruit stores. Under this model, the fruit mall opens branches in multiple regions and forms a chain operation network, providing users with more convenient consumption.

[0003] In order to better serve member users, Fruit Mall often organizes various activities to give back, especially offline chain stores. Through a unified activity plan, consumers can enjoy the same discounts and services in different stores. At the same time, it will send activity advertisements to member users and send the specific location of the store at the same time, ensuring that users can receive activity notifications in a timely manner.

[0004] Generally, during the advertising push process, advertisements will be sent to member users before the event starts. However, due to some reasons, some member users may not participate in the event after receiving the advertisements. In order to increase the participation rate of the event, the event advertisements will be sent again to the member users who did not participate in the event. However, the following problems may occur when the event advertisements are sent again:

[0005] 1. When sending advertisements again, the actual status of each store has changed because they have already participated in the event. If the appropriate store selection order cannot be sent to users based on the actual situation, the member user experience may decline;

[0006] 2. Some users may be unable to participate in the event temporarily due to some reasons, while some users choose not to participate in the event. If advertising is not pushed according to the actual situation, it may cause user disgust and affect the brand image. At the same time, it also increases the budget for advertising push and causes unnecessary waste. Summary of the invention

[0007] The purpose of the present invention is to solve the problem and to propose an advertisement pushing method and device for an online fruit mall.

[0008] In a first aspect of the present invention, a method for pushing advertisements in an online fruit mall is first proposed, the method comprising:

[0009] Sending an activity advertisement and a first questionnaire on whether to participate in the activity to target member users, and obtaining the answer results of the first questionnaire within a preset answer time; the target member users are each member user who has not participated in the store activity; the answer results of the first questionnaire are three results: participating in the activity, not participating in the activity, and not participating in the activity temporarily;

[0010] When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index;

[0011] Resend the campaign advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent campaign advertisement according to the store priority index in descending order;

[0012] When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user based on the advertisement browsing time, and it is determined whether the activity advertisement needs to be sent to the target member user again based on the answer result of the second questionnaire; the answer result of the second questionnaire is either participating in the activity or not participating in the activity.

[0013] Optionally, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index, including:

[0014] Obtain the current actual location of the target member user and the actual location of each store, and for each store, obtain a set of drivable routes from the current location of the target member user to the corresponding store; the target member user includes several drivable routes;

[0015] For each driving route in the set of drivable routes, the total number of sections of the corresponding driving route, the average driving speed corresponding to each section, the driving distance corresponding to each section and the maximum travel time of each section are obtained, and the average driving speed, driving distance and maximum travel time corresponding to each section are normalized to obtain the congestion coefficient of each driving route. The calculation formula is:

[0016]

[0017] Wherein, Bcv is the congestion coefficient of each driving route, n is the total number of sections of the corresponding driving route, bm, fv, kh are respectively the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization; a1, a2, a3 are respectively the preset weight coefficients of the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization, and a1, a2, a3 are all greater than 0;

[0018] For each store's drivable route set, select the smallest congestion coefficient in the drivable route set as the congestion coefficient from the store to the target member user;

[0019] According to the congestion coefficient of each store, the store's flow of people, and the store's cargo storage capacity, the corresponding store priority index is obtained.

[0020] Optionally, according to the congestion coefficient of each store, the store's passenger flow, and the store's cargo storage capacity, the corresponding store priority index is obtained, including:

[0021] Obtain the current flow of people, the preset maximum number of people, and the average stay time of each user in each store; calculate the current flow density, the calculation formula is: sd = sf-sx / sx, where sd is the current flow density, sf is the current flow of people, and sx is the preset maximum number of people;

[0022] Calculate the user residence time coefficient, the calculation formula is: cv = cb-ct / ct, where cv is the user residence time coefficient, cb is the average residence time of each user, and ct is the preset benchmark residence time;

[0023] The current crowd density and user residence time coefficient are normalized, and the store customer flow coefficient is obtained based on the normalized current crowd density and user residence time coefficient. The calculation formula is: Where Dxc is the store customer flow coefficient, b1 and b2 are the preset weight coefficients of the current customer flow density and user stay time coefficient after normalization respectively;

[0024] According to the congestion coefficient, passenger flow coefficient and cargo storage capacity of each store, the corresponding store priority index is obtained.

[0025] Optionally, according to the congestion coefficient, the passenger flow coefficient, and the cargo storage capacity of each store, the corresponding store priority index is obtained, including:

[0026] Obtain the consumption records of the target member user in the fruit chain store, and obtain the types of all fruits purchased by the user from the consumption records as the target fruit types;

[0027] For each store, the total number of fruit types including the target fruit type among all the fruit types stored in the current store is obtained as the stored fruit type, and the total number of stored fruit types is divided by the total number of target fruit types to obtain the fruit completeness;

[0028] The average storage time of each type of fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store are obtained to obtain the fruit freshness. The calculation formula is: Where Tkp is the fruit freshness of each stored fruit type, wy, gu, eu, xu are the average storage time of the fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store, gf, ef, xf are the preset optimal storage light intensity, humidity and temperature respectively; the average value of the fruit freshness of all stored fruit types is calculated as the fruit freshness index of the stored fruit type;

[0029] Obtain the fruit storage volume and average consumption rate of each stored fruit type in the store, and divide the fruit storage volume by the average consumption rate to obtain the fruit stability, and calculate the average fruit stability of all stored fruit types as the fruit stability index of the stored fruit type;

[0030] Normalize the fruit completeness, fruit freshness index, and fruit stability index to obtain the fruit storage index of each stored fruit type, and calculate the mean of the fruit storage index of each stored fruit type as the final fruit storage index of each store;

[0031] According to the congestion coefficient, traffic coefficient and final fruit storage index of each store, the corresponding store priority index is obtained.

[0032] Optionally, the fruit completeness, fruit freshness index, and fruit stability index are normalized to obtain a fruit storage index for each stored fruit type, including:

[0033]

[0034] Where Qxd is the fruit storage index, Ta, Tkb, and Box are the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively; c1, c2, and c3 are the preset proportional coefficients of the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively, and c1, c2, and c3 are all greater than 0.

[0035] Optionally, according to the congestion coefficient, the flow coefficient, and the final fruit storage index of each store, the corresponding store priority index is obtained, including:

[0036]

[0037] Where Qxd is the priority index, Bcv, Dxc, and Qxd are the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; f1, f2, and f3 are the preset proportional coefficients of the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; and f1, f2, and f3 are all greater than 0.

[0038] Optionally, sending the second questionnaire and the activity advertisement to the user according to the advertisement browsing time includes:

[0039] Obtain the target member user's ad browsing time, historical store activity participation ratio and preset benchmark sending time interval to obtain the final sending time interval; the specific steps are:

[0040] The ad browsing time and historical store activity participation ratio are normalized, and the adjustment coefficient is obtained based on the normalized ad browsing time and historical store activity participation ratio. The calculation formula is: In the formula, pl and py are respectively the normalized ad browsing time and historical store activity participation ratio, z1 and z2 are respectively the preset proportional coefficients of the normalized ad browsing time and historical store activity participation ratio, and z1 and z2 are both greater than 0;

[0041] Calculate the final sending time interval, the calculation formula is: AD = AQ × (1-GT), where AD is the final sending time interval, and AQ is the preset reference sending time interval;

[0042] The time when the target member user finishes answering the first questionnaire is obtained, and the second questionnaire and the activity advertisement are sent to the target member user again after the final sending time interval after the time.

[0043] Optionally, judging whether it is necessary to send an activity advertisement to the target member user again according to the answer result of the second questionnaire includes:

[0044] The final response time is obtained according to the adjustment coefficient and the preset response time. The calculation formula is: ER = ED × (1 + GT), where ER is the final response time, ED is the preset response time, and GT is the adjustment coefficient;

[0045] After sending the second questionnaire and the activity advertisement to the target member user, the answer result of the second questionnaire of the target member user is obtained; if the target member user does not reply to the second questionnaire within the final reply time or the answer result of the second questionnaire is not to participate in the activity, it is determined that the target member user will no longer participate in the activity of the fruit store, and the activity advertisement will no longer be sent to the user;

[0046] If the target member user's response to the second questionnaire within the final response time is to participate in the activity, the current priority index of the target member user and each store will be calculated in real time, and the priority selection order of the corresponding stores will be marked in descending order according to the store priority index.

[0047] In a second aspect of the present invention, an advertisement push device for an online fruit mall is provided, comprising:

[0048] Initial sending module: sending activity advertisements and a first questionnaire on whether to participate in the activity to target member users, and obtaining the answer results of the first questionnaire within a preset answer time; the target member users are each member user who has not participated in the store activity; the answer results of the first questionnaire are three results: participating in the activity, not participating in the activity, and not participating in the activity temporarily;

[0049] Priority calculation module: When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic flow, and the store's cargo storage volume are obtained to obtain the store priority index;

[0050] Re-sending module: re-send the activity advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent activity advertisement according to the store priority index in descending order;

[0051] Push judgment module: When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user according to the advertisement browsing time, and it is judged whether the activity advertisement needs to be sent to the target member user again according to the reply result of the second questionnaire; the reply result of the second questionnaire is either participating in the activity or not participating in the activity.

[0052] Beneficial effects of the present invention:

[0053] The present invention proposes an advertisement push method and device for an online fruit mall, which can send a suitable store selection order to a user according to the actual situation, thereby increasing the user experience, and can flexibly push advertisements to the user according to the actual situation, without causing user disgust and reducing the impact on the brand image, while also reducing the budget for advertisement push and unnecessary waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] Figure 1 It is a flow chart of an advertisement push method of an online fruit mall;

[0056] Figure 2 The present invention is a framework diagram of an advertisement push device for an online fruit mall. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0059] The embodiment of the present invention provides an advertisement push method for an online fruit mall. Figure 1 , Figure 1 A flowchart of an advertisement push method for an online fruit mall provided by an embodiment of the present invention. The method comprises the following steps:

[0060] Sending the activity advertisement and the first questionnaire on whether to participate in the activity to the target member users, and obtaining the response results of the first questionnaire within the preset response time; the target member users are each member user who has not participated in the store activity; the response results of the first questionnaire are three results: participating in the activity, not participating in the activity, and not participating in the activity temporarily;

[0061] When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index;

[0062] Resend the campaign advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent campaign advertisement according to the store priority index in descending order;

[0063] When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user based on the advertisement browsing time, and it is determined whether the activity advertisement needs to be sent to the target member user again based on the answer results of the second questionnaire; the answer results of the second questionnaire are either participating in the activity or not participating in the activity.

[0064] Based on the advertisement push method of an online fruit mall provided by the embodiment of the present invention, the above method can send a suitable store selection order to the user according to the actual situation, thereby improving the user experience. At the same time, the advertisement can be pushed to the user flexibly according to the actual situation without causing user disgust and reducing the impact on the brand image. At the same time, the budget for advertisement push is reduced, thereby reducing unnecessary waste.

[0065] It should be noted that the preset response time is set by professionals based on actual circumstances and is not limited or elaborated on.

[0066] In one embodiment, when the user's answer to the first questionnaire within the preset response time is not to participate in the activity, or the user does not reply to the first questionnaire, it is assumed that the target member user will no longer participate in the activity of the fruit store. At this time, in order to reduce user disgust and reduce the budget for advertising push, activity advertisements will no longer be sent to such users. While reducing user disgust, it can also reduce the budget for advertising push and reduce unnecessary waste.

[0067] In one embodiment, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index, including:

[0068] Get the current actual location of the target member user and the actual location of each store. For each store, get the set of drivable routes from the current location of the target member user to the corresponding store. The target member user contains several drivable routes.

[0069] For each driving route in the set of drivable routes, the total number of sections of the corresponding driving route, the average driving speed corresponding to each section, the driving distance corresponding to each section and the maximum travel time of each section are obtained, and the average driving speed, driving distance and maximum travel time corresponding to each section are normalized to obtain the congestion coefficient of each driving route. The calculation formula is:

[0070]

[0071] Wherein, Bcv is the congestion coefficient of each driving route, n is the total number of sections of the corresponding driving route, bm, fv, kh are respectively the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization; a1, a2, a3 are respectively the preset weight coefficients of the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization, and a1, a2, a3 are all greater than 0;

[0072] For each store's drivable route set, select the smallest congestion coefficient in the drivable route set as the congestion coefficient from the store to the target member user;

[0073] According to the congestion coefficient of each store, the store's flow of people, and the store's goods storage capacity, the corresponding store priority index is obtained.

[0074] It should be noted that the actual location of the target member user can be obtained through GPS positioning data or location information actively provided by the user; the road condition data of the drivable route (such as average driving speed, distance, driving distance corresponding to each road section, and maximum travel time) can be obtained from the real-time traffic monitoring platform or navigation service; the maximum travel time refers to the time used for the corresponding road section to travel at the fastest speed, that is, the maximum speed limit; of course, the above-mentioned data acquisition method may also be other acquisition methods, which depends on the actual situation and is not limited or elaborated.

[0075] It should be noted that a1, a2, and a3 are set by professionals according to actual conditions. Generally, the sum of a1, a2, and a3 is 1. For example, a1, a2, and a3 can be 0.4, 0.3, and 0.3, respectively, or other numbers, without specific limitation.

[0076] It should be noted that the smaller the congestion coefficient from the offline fruit store to the target member user, the higher the priority of the corresponding fruit store in being selected by the target user. The reason is that the smaller the congestion coefficient from the offline fruit store to the target member user, the more smooth the driving route from the user's current location to the store, the lower the traffic congestion level, the relatively low time cost for the user to go to the store, and the higher the convenience of travel. Giving priority to stores with smoother traffic can effectively reduce the resistance of users to go shopping, making them more willing to choose these stores for consumption, thereby improving the shopping experience of target member users.

[0077] In one embodiment, according to the congestion coefficient of each store, the store's passenger flow, and the store's cargo storage capacity, the corresponding store priority index is obtained, including:

[0078] Obtain the current flow of people, the preset maximum number of people, and the average stay time of each user in each store; calculate the current flow density, the calculation formula is: sd = sf-sx / sx, where sd is the current flow density, sf is the current flow of people, and sx is the preset maximum number of people;

[0079] Calculate the user residence time coefficient, the calculation formula is: cv = cb-ct / ct, where cv is the user residence time coefficient, cb is the average residence time of each user, and ct is the preset benchmark residence time;

[0080] The current crowd density and user residence time coefficient are normalized, and the store customer flow coefficient is obtained based on the normalized current crowd density and user residence time coefficient. The calculation formula is: Where Dxc is the store customer flow coefficient, b1 and b2 are the preset weight coefficients of the current customer flow density and user stay time coefficient after normalization respectively;

[0081] According to the congestion coefficient, passenger flow coefficient and cargo storage capacity of each store, the corresponding store priority index is obtained.

[0082] It should be noted that b1 and b2 are set by professionals according to actual conditions. Generally, the sum of b1 and b2 is 1. For example, b1 and b2 can be 0.5 and 0.5 respectively, or other numbers, which are not specifically limited.

[0083] It should be noted that the current flow of people in each store can be monitored in real time through smart cameras or sensors installed at the entrance and exit of the store, and data can be automatically collected using a people counting system; the preset maximum capacity is determined by the design and operation standards of the store, and is set according to the store area and safety regulations; the average stay time of each user can be calculated by analyzing the time difference between customers entering and leaving the store through tracking devices set up in the store, such as Wi-Fi signal tracking, Bluetooth beacons or positioning systems in the store; at the same time, the preset benchmark stay time is usually derived from statistical analysis of historical data, reflecting the average stay time under normal circumstances in the store.

[0084] It should be noted that the smaller the crowd density of an offline fruit store and the smaller the user residence time coefficient, that is, the smaller the crowd flow coefficient, the higher the priority of the corresponding fruit store in being selected by the target users. The reason is that when the crowd density of a store is small, it means that the store is relatively spacious and the shopping experience will not be affected by crowding. Target users can browse and select products more easily, thereby improving shopping comfort; in addition, a lower user residence time coefficient indicates that the current store has a higher customer mobility, that is, customers will not stay in the store for a long time or queue up to check out, which usually means higher service efficiency; on the whole, stores with a smaller crowd flow coefficient can usually provide users with a faster and more comfortable shopping experience, reduce waiting time and inconvenience during the shopping process, so these stores will be ranked first in the priority selection order, which will improve the shopping experience of target member users.

[0085] In one embodiment, according to the congestion coefficient, the flow coefficient, and the cargo storage capacity of each store, the corresponding store priority index is obtained, including:

[0086] Obtain the consumption records of the target member user in the fruit chain store, and obtain the types of all fruits purchased by the user from the consumption records as the target fruit types;

[0087] For each store, the total number of fruit types including the target fruit type among all the fruit types stored in the current store is obtained as the stored fruit type, and the total number of stored fruit types is divided by the total number of target fruit types to obtain the fruit completeness;

[0088] The average storage time of each type of fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store are obtained to obtain the fruit freshness. The calculation formula is: Where Tkp is the fruit freshness of each stored fruit type, wy, gu, eu, xu are the average storage time of the fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store, gf, ef, xf are the preset optimal storage light intensity, humidity and temperature respectively; the average value of the fruit freshness of all stored fruit types is calculated as the fruit freshness index of the stored fruit type;

[0089] Obtain the fruit storage volume and average consumption rate of each stored fruit type in the store, and divide the fruit storage volume by the average consumption rate to obtain the fruit stability, and calculate the average fruit stability of all stored fruit types as the fruit stability index of the stored fruit type;

[0090] Normalize the fruit completeness, fruit freshness index, and fruit stability index to obtain the fruit storage index of each stored fruit type, and calculate the mean of the fruit storage index of each stored fruit type as the final fruit storage index of each store;

[0091] According to the congestion coefficient, traffic coefficient and final fruit storage index of each store, the corresponding store priority index is obtained.

[0092] It should be noted that the consumption records of target member users in fruit chain stores are extracted through the user's membership system or consumption database, and then the types of fruits purchased by the users are analyzed; secondly, the currently stored fruit types and corresponding storage time, light intensity, humidity and temperature are obtained from the inventory management system of each store. These data are usually recorded in real time through sensors or monitoring systems. In addition, the storage volume and average consumption rate of fruits can be monitored and calculated through the inventory management system to ensure the accuracy and real-time nature of the data; in addition, the preset optimal storage light intensity, humidity and temperature are set by professional personnel according to the actual fruit type, and the specific details are not limited or elaborated.

[0093] In one embodiment, the fruit completeness, fruit freshness index, and fruit stability index are normalized to obtain a fruit storage index for each stored fruit type, including:

[0094]

[0095] Where Qxd is the fruit storage index, Ta, Tkb, and Box are the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively; c1, c2, and c3 are the preset proportional coefficients of the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively, and c1, c2, and c3 are all greater than 0.

[0096] It should be noted that c1, c2, and c3 are set by professionals according to actual conditions. Generally, the sum of c1, c2, and c3 is 1. For example, c1, c2, and c3 can be 0.4, 0.3, and 0.3, respectively, or other numbers, without specific limitation.

[0097] It should be noted that when the offline fruit store has a greater fruit completeness, a greater fruit freshness index, a greater fruit stability index, that is, a greater final fruit storage index, the corresponding fruit store will be selected by the target users with a higher priority. The reason is that this means that the corresponding fruit store can provide more types of fresh fruits, and these fruits maintain good quality and suitable storage conditions during storage, reducing the risk of spoilage; when users choose stores, they tend to prefer those that can meet their specific needs and provide diversified and fresh products. Therefore, the store's fruit completeness and freshness directly affect the user's purchasing experience and satisfaction.

[0098] In one embodiment, according to the congestion coefficient, the flow coefficient, and the final fruit storage index of each store, the corresponding store priority index is obtained, including:

[0099]

[0100] Where Qxd is the priority index, Bcv, Dxc, and Qxd are the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; f1, f2, and f3 are the preset proportional coefficients of the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; and f1, f2, and f3 are all greater than 0.

[0101] It should be noted that f1, f2, and f3 are set by professionals according to actual conditions. Generally, the sum of f1, f2, and f3 is 1. For example, f1, f2, and f3 can be 0.25, 0.35, and 0.4, respectively, or other numbers, without specific limitation.

[0102] It should be noted that the activity advertisement is re-sent to the target member users, and the priority order of the corresponding stores is marked in the newly sent activity advertisement in descending order according to the store priority index; for example, assuming there are offline fruit stores B and C, and the priority index of store B is greater than that of store C, then when the activity-related advertisement is sent to the target member users, the corresponding advertisement will indicate that the priority order of store B is greater than that of store C. This strategy not only ensures that users have priority access to the most attractive and advantageous stores when making consumption decisions, but also improves the efficiency of the activity advertisement delivery, ensuring that the target users can find the fruit store that best meets their needs in the shortest time; in addition, through this sorting method, users can quickly identify the best store, thereby improving their shopping experience and satisfaction, which will improve the shopping experience of the target member users.

[0103] In one embodiment, sending the second questionnaire and the campaign advertisement to the user according to the advertisement browsing time includes:

[0104] Obtain the target member user's ad browsing time, historical store activity participation ratio and preset benchmark sending time interval to obtain the final sending time interval; the specific steps are:

[0105] The ad browsing time and historical store activity participation ratio are normalized, and the adjustment coefficient is obtained based on the normalized ad browsing time and historical store activity participation ratio. The calculation formula is: In the formula, pl and py are respectively the normalized ad browsing time and historical store activity participation ratio, z1 and z2 are respectively the preset proportional coefficients of the normalized ad browsing time and historical store activity participation ratio, and z1 and z2 are both greater than 0;

[0106] Calculate the final sending time interval, the calculation formula is: AD = AQ × (1-GT), where AD is the final sending time interval, and AQ is the preset reference sending time interval;

[0107] The time when the target member user finishes answering the first questionnaire is obtained, and the second questionnaire and the activity advertisement are sent to the target member user again after the final sending time interval after the time.

[0108] It should be noted that z1 and z2 are set by professionals according to actual conditions. Generally, the sum of z1 and z2 is 1. For example, z1 and z2 can be 0.5 and 0.5 respectively, or other numbers, without specific limitation.

[0109] It should be noted that the advertisement browsing time can be recorded in real time through the online questionnaire system or the monitoring tool of the application; the data of the historical store activity participation rate can be extracted through the user's purchase record; the preset benchmark sending time interval is set by professionals based on previous data analysis and marketing experience, and the specific details are not limited or elaborated;

[0110] It should be noted that the longer the target member users browse ads and the longer the proportion of their participation in historical store activities, the time for sending the next event ads and the second questionnaire can be appropriately shortened. This is because the longer the target member users browse ads, the higher their attention and interest in the advertising content, which reflects their potential appeal and willingness to participate in the event. At the same time, the higher the proportion of their participation in historical store activities, the more active their participation in past activities, which further enhances their confidence and expectations for the current event. Therefore, in this case, the time for sending the next event ads and the second questionnaire should be appropriately shortened to increase the participation rate and effectiveness of the event and make advertising push more efficient.

[0111] In one embodiment, judging whether it is necessary to send an activity advertisement to the target member user again according to the answer result of the second questionnaire includes:

[0112] The final response time is obtained according to the adjustment coefficient and the preset response time. The calculation formula is: ER = ED × (1 + GT), where ER is the final response time, ED is the preset response time, and GT is the adjustment coefficient;

[0113] After sending the second questionnaire and the activity advertisement to the target member user, the answer result of the second questionnaire of the target member user is obtained; if the target member user does not reply to the second questionnaire within the final reply time or the answer result of the second questionnaire is not to participate in the activity, it is determined that the target member user will no longer participate in the activity of the fruit store, and the activity advertisement will no longer be sent to the user;

[0114] If the target member user's response to the second questionnaire within the final response time is to participate in the activity, the current priority index of the target member user and each store will be calculated in real time, and the priority selection order of the corresponding stores will be marked in descending order according to the store priority index.

[0115] It should be noted that the preset response time is set by professionals based on actual circumstances and is not limited or elaborated on.

[0116] In one implementation, through the above method, advertisements can be flexibly pushed to users according to actual situations, which will not cause user disgust and reduce the impact on brand image. At the same time, the budget for advertisement push is reduced, reducing unnecessary waste.

[0117] Based on the same inventive concept, the embodiment of the present invention also provides an advertisement push device for an online fruit mall. Figure 2 , Figure 2 A framework diagram of an advertisement push device for an online fruit mall provided by an embodiment of the present invention, the device comprising:

[0118] Initial sending module: Send activity advertisements and the first questionnaire on whether to participate in the activity to target member users, and obtain the response results of the first questionnaire within the preset response time; the target member users are every member user who has not participated in the store activities; the response results of the first questionnaire are three results: participate in the activity, do not participate in the activity, and temporarily do not participate in the activity;

[0119] Priority calculation module: When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index;

[0120] Re-sending module: re-send the activity advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent activity advertisement according to the store priority index in descending order;

[0121] Push judgment module: When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user based on the advertisement browsing time, and based on the reply result of the second questionnaire, it is judged whether it is necessary to send the activity advertisement to the target member user again; the reply result of the second questionnaire is either participating in the activity or not participating in the activity.

[0122] An advertisement push device for an online fruit mall provided by an embodiment of the present invention can send a suitable store selection order to users according to actual circumstances through the above method, thereby increasing the user experience. At the same time, advertisements can be pushed flexibly to users according to actual circumstances without causing user disgust and reducing the impact on the brand image. At the same time, the budget for advertisement push can be reduced, thereby reducing unnecessary waste.

[0123] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An advertisement push method for an online fruit mall, characterized in that: The following steps are involved: Sending an activity advertisement and a first questionnaire on whether to participate in the activity to target member users, and obtaining the answer results of the first questionnaire within a preset answer time; the target member users are each member user who has not participated in the store activity; the answer results of the first questionnaire are three results: participating in the activity, not participating in the activity, and not participating in the activity temporarily; When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index; Resend the campaign advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent campaign advertisement according to the store priority index in descending order; When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user based on the advertisement browsing time, and it is determined whether the activity advertisement needs to be sent to the target member user again based on the answer result of the second questionnaire; the answer result of the second questionnaire is either participating in the activity or not participating in the activity.

2. The method for pushing advertisements for an online fruit mall according to claim 1, characterized in that: Obtain the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume, and obtain the store priority index including: Obtain the current actual location of the target member user and the actual location of each store, and for each store, obtain a set of drivable routes from the current location of the target member user to the corresponding store; the target member user includes several drivable routes; For each driving route in the set of drivable routes, the total number of sections of the corresponding driving route, the average driving speed corresponding to each section, the driving distance corresponding to each section and the maximum travel time of each section are obtained, and the average driving speed, driving distance and maximum travel time corresponding to each section are normalized to obtain the congestion coefficient of each driving route. The calculation formula is: Wherein, Bcv is the congestion coefficient of each driving route, n is the total number of sections of the corresponding driving route, bm, fv, kh are respectively the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization; a1, a2, a3 are respectively the preset weight coefficients of the average driving speed, driving distance and maximum travel time corresponding to each road section after normalization, and a1, a2, a3 are all greater than 0; For each store's drivable route set, select the smallest congestion coefficient in the drivable route set as the congestion coefficient from the store to the target member user; According to the congestion coefficient of each store, the store's flow of people, and the store's cargo storage capacity, the corresponding store priority index is obtained.

3. The method for pushing advertisements for an online fruit mall according to claim 2, wherein: According to the congestion coefficient of each store, the store's traffic flow, and the store's cargo storage capacity, the corresponding store priority index is obtained, including: Obtain the current flow of people, the preset maximum number of people, and the average stay time of each user in each store; calculate the current flow density, the calculation formula is: sd = sf-sx / sx, where sd is the current flow density, sf is the current flow of people, and sx is the preset maximum number of people; Calculate the user residence time coefficient, the calculation formula is: cv = cb-ct / ct, where cv is the user residence time coefficient, cb is the average residence time of each user, and ct is the preset benchmark residence time; The current crowd density and user residence time coefficient are normalized, and the store customer flow coefficient is obtained based on the normalized current crowd density and user residence time coefficient. The calculation formula is: Where Dxc is the store customer flow coefficient, b1 and b2 are the preset weight coefficients of the current customer flow density and user stay time coefficient after normalization respectively; According to the congestion coefficient, passenger flow coefficient and cargo storage capacity of each store, the corresponding store priority index is obtained.

4. The method for pushing advertisements of an online fruit mall according to claim 3, characterized in that: According to the congestion coefficient, passenger flow coefficient, and cargo storage capacity of each store, the corresponding store priority index is obtained, including: Obtain the consumption records of the target member user in the fruit chain store, and obtain the types of all fruits purchased by the user from the consumption records as the target fruit types; For each store, the total number of fruit types including the target fruit type among all the fruit types stored in the current store is obtained as the stored fruit type, and the total number of stored fruit types is divided by the total number of target fruit types to obtain the fruit completeness; The average storage time of each type of fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store are obtained to obtain the fruit freshness. The calculation formula is: Where Tkp is the fruit freshness of each stored fruit type, wy, gu, eu, xu are the average storage time of the fruit in the store, the average light intensity, average humidity and average temperature of the fruit when stored in the store, gf, ef, xf are the preset optimal storage light intensity, humidity and temperature respectively; the average value of the fruit freshness of all stored fruit types is calculated as the fruit freshness index of the stored fruit type; Obtain the fruit storage volume and average consumption rate of each stored fruit type in the store, and divide the fruit storage volume by the average consumption rate to obtain the fruit stability, and calculate the average fruit stability of all stored fruit types as the fruit stability index of the stored fruit type; Normalize the fruit completeness, fruit freshness index, and fruit stability index to obtain the fruit storage index of each stored fruit type, and calculate the mean of the fruit storage index of each stored fruit type as the final fruit storage index of each store; According to the congestion coefficient, traffic coefficient and final fruit storage index of each store, the corresponding store priority index is obtained.

5. The method for pushing advertisements of an online fruit mall according to claim 4, characterized in that: The fruit completeness, fruit freshness index and fruit stability index are normalized to obtain the fruit storage index of each stored fruit type, including: Where Qxd is the fruit storage index, Ta, Tkb, and Box are the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively; c1, c2, and c3 are the preset proportional coefficients of the normalized fruit completeness, fruit freshness index, and fruit stability index, respectively, and c1, c2, and c3 are all greater than 0.

6. The method for pushing advertisements of an online fruit mall according to claim 4, characterized in that: According to the congestion coefficient, traffic coefficient, and final fruit storage index of each store, the corresponding store priority index is obtained, including: Where Qxd is the priority index, Bcv, Dxc, and Qxd are the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; f1, f2, and f3 are the preset proportional coefficients of the congestion coefficient, the flow coefficient, and the final fruit storage index, respectively; and f1, f2, and f3 are all greater than 0.

7. The method for pushing advertisements of an online fruit mall according to claim 1, characterized in that: Sending a second questionnaire and activity ads to users based on ad browsing time includes: Obtain the target member user's ad browsing time, historical store activity participation ratio and preset benchmark sending time interval to obtain the final sending time interval; the specific steps are: The ad browsing time and historical store activity participation ratio are normalized, and the adjustment coefficient is obtained based on the normalized ad browsing time and historical store activity participation ratio. The calculation formula is: In the formula, pl and py are respectively the normalized ad browsing time and historical store activity participation ratio, z1 and z2 are respectively the preset proportional coefficients of the normalized ad browsing time and historical store activity participation ratio, and z1 and z2 are both greater than 0; Calculate the final sending time interval, the calculation formula is: AD = AQ × (1-GT), where AD is the final sending time interval, and AQ is the preset reference sending time interval; The time when the target member user finishes answering the first questionnaire is obtained, and the second questionnaire and the activity advertisement are sent to the target member user again after the final sending time interval after the time.

8. The method for pushing advertisements of an online fruit mall according to claim 7, characterized in that: Based on the results of the second questionnaire, whether it is necessary to send activity advertisements to target member users again includes: The final response time is obtained according to the adjustment coefficient and the preset response time. The calculation formula is: ER = ED × (1 + GT), where ER is the final response time, ED is the preset response time, and GT is the adjustment coefficient; After sending the second questionnaire and the activity advertisement to the target member user, the answer result of the second questionnaire of the target member user is obtained; if the target member user does not reply to the second questionnaire within the final reply time or the answer result of the second questionnaire is not to participate in the activity, it is determined that the target member user will no longer participate in the activity of the fruit store, and the activity advertisement will no longer be sent to the user; If the target member user's response to the second questionnaire within the final response time is to participate in the activity, the current priority index of the target member user and each store will be calculated in real time, and the priority selection order of the corresponding stores will be marked in descending order according to the store priority index.

9. An advertisement push device for an online fruit mall, characterized in that: The device comprises: Initial sending module: sending activity advertisements and a first questionnaire on whether to participate in the activity to target member users, and obtaining the answer results of the first questionnaire within a preset answer time; the target member users are each member user who has not participated in the store activity; the answer results of the first questionnaire are three results: participating in the activity, not participating in the activity, and not participating in the activity temporarily; Priority calculation module: When the target user chooses to participate in the activity, the actual location of the target member user, the store's traffic volume, and the store's cargo storage volume are obtained to obtain the store priority index; Re-sending module: re-send the activity advertisement to the target member users, and indicate the priority selection order of the corresponding stores in the newly sent activity advertisement according to the store priority index in descending order; Push judgment module: When the target member user chooses not to participate in the activity temporarily, the advertisement browsing time of the target member user is obtained, and a second questionnaire and activity advertisement are sent to the user according to the advertisement browsing time, and it is judged whether the activity advertisement needs to be sent to the target member user again according to the reply result of the second questionnaire; the reply result of the second questionnaire is either participating in the activity or not participating in the activity.

Images