User recall method, device and system, electronic equipment and computer storage medium

Abstract

The invention provides a user recall method, device and system, electronic equipment and a computer storage medium, the method is applied to the technical field of computers, and the method comprises the following steps: obtaining consumption data of a plurality of users who have consumed in a target merchant, and determining recall trigger conditions of the plurality of users according to the consumption data; determining a target user meeting the recall triggering condition in a set time period, and determining a corresponding optimal discount coefficient according to consumption data of the target user; obtaining a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; and recalling the target user based on the target discount coupon. Therefore, the recall effect of the user can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a user recall method, device, system, electronic device and computer storage medium. Background Art

[0002] At present, with the development of big data technology, more and more catering businesses have begun to use big data technology for customer marketing and customer recall. Customer recall refers to the use of a formulated recall strategy to recall customers who are about to be lost or have already lost. Among them, issuing discount coupons to customers is the current mainstream customer recall method, but catering businesses do not know when to issue which discount coupons to which customers in order to improve the customer recall effect, resulting in a low customer recall rate. Summary of the invention

[0003] The present application provides a user recall method, device, system, electronic device and computer storage medium.

[0004] The technical solution of this application is implemented as follows:

[0005] The present application provides a user recall method, the method comprising:

[0006] Acquire consumption data of multiple users who have consumed at a target merchant, and determine recall trigger conditions for the multiple users based on the consumption data;

[0007] Determine a target user who meets the recall trigger condition within a set time period, and determine a corresponding optimal discount coefficient according to the consumption data of the target user; the target user is at least one user among the multiple users;

[0008] Acquire a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient;

[0009] The target user is recalled based on the target discount coupon.

[0010] The present application provides a user recall device, the device comprising a first determination module, a second determination module, an acquisition module and a recall module, wherein:

[0011] A first determination module is used to obtain consumption data of multiple users who have consumed at a target merchant, and determine the recall triggering conditions of the multiple users according to the consumption data;

[0012] A second determination module is used to determine a target user who meets the recall trigger condition within a set time period, and determine a corresponding optimal discount coefficient according to the consumption data of the target user; the target user is at least one user among the multiple users;

[0013] An acquisition module, used for acquiring a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient;

[0014] A recall module is used to recall the target user based on the target discount coupon.

[0015] The present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the user recall method provided by one or more of the aforementioned technical solutions when executing the program.

[0016] An embodiment of the present application provides a user recall system, which includes the aforementioned user recall device or the aforementioned electronic device.

[0017] The present application provides a computer storage medium, which stores a computer program; after the computer program is executed, it can implement the user recall method provided by one or more of the above-mentioned technical solutions.

[0018] The embodiments of the present application provide a user recall method, device, system, electronic device and computer storage medium, the method comprising: acquiring consumption data of multiple users who have consumed at a target merchant, and determining recall trigger conditions for the multiple users based on the consumption data; determining a target user who meets the recall trigger condition within a set time period, and determining a corresponding optimal discount coefficient based on the consumption data of the target user; the target user is at least one user among the multiple users; acquiring a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient; and recalling the target user based on the target discount coupon.

[0019] It can be seen that in the embodiment of the present application, for multiple users who have consumed at the target merchant, the recall trigger conditions of these users can be determined first, so that the users who meet the recall trigger conditions within a certain period of time can be recalled, that is, determining the recall trigger conditions of the users can help the target merchant to clarify the users who need to be recalled and the recall time for the user recall; further, after clarifying the users who need to be recalled and the recall time for the user recall, by determining the optimal discount coefficients corresponding to these users, and using the discount coupons closest to the optimal discount coefficients to recall the users, the user recall effect can be improved and the merchant's profits can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of a user recall method provided in an embodiment of the present application;

[0021] Figure 2 A flowchart for determining a recall trigger condition provided in an embodiment of the present application;

[0022] Figure 3 A flow chart for determining an optimal discount coefficient provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of a user recall device provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The technical solution in this application will be clearly and completely described below in conjunction with the drawings in this application.

[0026] The present application will be further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the embodiments provided herein are only used to explain the present application and are not intended to limit the present application. In addition, the embodiments provided below are partial embodiments for implementing the present application, rather than providing all embodiments for implementing the present application. In the absence of conflict, the technical solutions recorded in the present application can be implemented in any combination.

[0027] It should be noted that, in the present application, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a method or device including a series of elements includes not only the elements explicitly recorded, but also includes other elements not explicitly listed, or also includes elements inherent to the implementation of the method or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other related elements (such as steps in the method or units in the device, for example, a unit may be a part of a processor, a part of a program or software, etc.) in the method or device including the element.

[0028] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0029] For example, the user recall method provided in the present application includes a series of steps, but the user recall method provided in the present application is not limited to the recorded steps. Similarly, the user recall device provided in the present application includes a series of modules, but the user recall device provided in the present application is not limited to including the modules explicitly recorded, and may also include modules that need to be set up to obtain relevant information or perform processing based on the information.

[0030] The present application can be implemented based on an electronic device, where the electronic device can be a thin client, a thick client, a handheld or laptop device, a microprocessor-based system, a set-top box, a programmable consumer electronic product, a network personal computer, a small computer system, and the like.

[0031] With the popularity of Software as a Service (SAAS) systems, more and more businesses, such as catering businesses, have begun to choose to use catering SAAS systems for cash register, order management and customer marketing. Catering businesses can use catering SAAS systems to send marketing text messages to customers, such as issuing discount coupons to customers who have consumed in their stores to achieve the purpose of customer recovery. Although catering businesses can easily use catering SAAS systems to recall customers, they are faced with the problem of not knowing when to issue which discount coupons to which customers in order to maximize profits.

[0032] In view of the above problems, the following embodiments are proposed.

[0033] In some embodiments of the present application, the user recall method can be implemented using a processor in a user recall device, and the processor can be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor.

[0034] It should be noted that in the technical solution of this application, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0035] Figure 1 A flowchart of a user recall method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the process may include:

[0036] Step 10: Obtain consumption data of multiple users who have consumed at the target merchant, and determine the recall trigger conditions for the multiple users based on the consumption data.

[0037] In an embodiment of the present application, the user recall method can be applied to a user recall system, which may be a SAAS system. Here, the scenario type of the SAAS system is not specifically limited. For example, it may be a SAAS system in a catering scenario, or a SAAS system in other related scenarios, etc. The catering scenario is used as an example for explanation below.

[0038] For example, in a catering scenario, the target merchant may be a catering merchant that uses a catering SAAS system for cashiering, order management, and customer marketing; here, the type of the corresponding target merchant is not limited, for example, it may be a buffet merchant, a fast food merchant, etc.; wherein the user may be a customer who has consumed at the catering merchant.

[0039] Here, the multiple users who have consumed at the target merchant may include users who have consumed at the target merchant only once so far, and users who have consumed at the target merchant more than once.

[0040] Exemplarily, consumption data may include the number of consumptions and the consumption time of each consumption; that is, the recall trigger condition of the user may be determined based on the number of consumptions of each user and the consumption time of each consumption; wherein the recall trigger condition is related to the recall time, and the recall trigger condition may represent how long the user has not consumed at the target merchant. Here, if days are used as the time unit, the recall trigger condition may represent how many days the user has not consumed at the target merchant; below, an exemplary description is given of the process of determining the recall trigger condition for each user.

[0041] In some embodiments, see Figure 2 , according to the consumption data, determining the recall trigger conditions for multiple users may include the following steps:

[0042] Step 100: for a first user whose consumption times are greater than or equal to a set number, counting the time intervals between two adjacent consumptions, and determining a maximum time interval from the counted time intervals;

[0043] Step 101: determining a recall trigger condition of a first user according to a maximum time interval;

[0044] Step 102: for a second user whose consumption times are less than the set times, counting the time interval between the first two consumptions of the first user;

[0045] Step 103: average the time intervals between the first user's last two consumptions to determine the recall triggering condition for the second user.

[0046] In an embodiment of the present application, multiple users who have consumed at a target merchant may include a first user and a second user, wherein the first user is one or more users whose number of consumption times is greater than or equal to a set number of times, and the second user is one or more users whose number of consumption times is less than a set number of times; here, the value of the set number of times can be set according to actual conditions, and the embodiment of the present application does not make specific limitations on this. For example, the value of the set number of times can be 2.

[0047] For example, when the set number of times is 2, if a user has made 3 purchases at the target merchant, the user is the first user; if a user has made 1 purchase at the target merchant, the user is the second user; the following example is given with the set number of times being 2.

[0048] For example, for each first user j whose consumption times are greater than or equal to 2 (i.e., the user has consumed more than once), the time interval between each two adjacent consumptions is counted. After the time interval between each two adjacent consumptions is counted, the maximum time interval T can be determined from the counted time intervals. j Here, if the time unit is day, the time interval is also called the interval day number. At this time, it can be determined that the recall trigger condition of each first user j is that the first user j has T j The day has not yet arrived at the target merchant for consumption.

[0049] For example, for each second user i whose consumption times are less than 2 (i.e., only consumed once), the time intervals between the last two consumptions of each first user j are counted, which are represented as T1, T2, ..., T n Here, n represents the number of first users j, and the time interval between the first two consumptions represents the time interval between the first consumption and the second consumption of each first user j at the target merchant. Further, after counting the time intervals T1, T2, …, T n Then, the time intervals between the first two consumptions of each first user j are averaged to obtain the average time interval T i ,in, Similarly, if the time unit is day, then the recall trigger condition for each second user i can be determined as follows: i The day has not yet arrived at the target merchant for consumption.

[0050] It can be seen that in the embodiment of the present application, for users who have consumed at the target merchant, by determining the recall trigger conditions corresponding to the users, the recall time for their recall can be clearly determined, thereby helping the merchant to recall users who are about to be lost in a timely manner, and effectively solving the problem of user loss caused by untimely recall.

[0051] Step 11: Determine the target users who meet the recall trigger conditions within the set time period, and determine the corresponding optimal discount coefficient based on the consumption data of the target users.

[0052] Here, the set time period can be every day; illustratively, for multiple users who have consumed at the target merchant, after determining the recall trigger conditions of each user according to the above steps, the target users who meet the recall trigger conditions every day can be determined; wherein the target user can be at least one user among the multiple users, that is, the number of target users can be one or more.

[0053] Exemplarily, taking the setting time period as the current day as an example, assuming that the recall trigger condition for user 1 is that he has not shopped at the target merchant for 3 days, if it is determined on the current day (day D) that user 1 has not shopped at the target merchant in the past 3 days (day D-3, day D-2, and day D-1), then it can be determined that user 1 is one of the target users who meet the recall trigger condition for that day; conversely, if it is determined on the current day (day D) that user 1 has shopped at the target merchant yesterday (day D-1), then it can be determined that user 1 is not a target user who meets the recall trigger condition for that day; and so on, each target user who meets the recall trigger condition for that day can be determined.

[0054] In some embodiments, the above method may further include: determining, based on the consumption data of the multiple users, an average consumption frequency of the multiple users, and an average consumption time interval of the users whose consumption frequency exceeds a set frequency.

[0055] For example, if the time period is set to the current day, after determining the target users who meet the recall triggering conditions on the current day, the average number of consumption times n of the multiple users can be determined based on the consumption data of the multiple users who have consumed at the target merchant before the current day. A , and the average consumption time interval f of users whose consumption frequency exceeds the set number A .

[0056] For example, the average consumption times n can be obtained by averaging the consumption times of multiple users who have consumed at the target merchant before the current day. AAssuming that the users who have consumed at the target merchant before that day include user 1 to user 10, and the number of consumptions of user 1 to user 10 is 1 to 10, the average number of consumptions of these users who have consumed at the target merchant before that day can be determined as n A 5.5 times.

[0057] For example, if the number of times is set to 2, the average consumption time interval f of users who have consumed at the target merchant more than 2 times before the current day can be determined. A Specifically, by averaging the consumption time intervals of each user who has consumed at the target merchant more than twice before the current day, the average consumption time interval f can be obtained. A .

[0058] Further, after obtaining the average consumption times n A and the average consumption time interval f A After that, we can calculate the average consumption times n A , average consumption time interval f A and the consumption data of the target users to determine the optimal discount coefficient for the target users, see Figure 3 , the process may include the following steps:

[0059] Step 110: Determine the time interval from the target user's most recent consumption according to the target user's consumption data;

[0060] Step 111: determining a first ratio of the target user's consumption times to the average consumption times, and a second ratio of the average consumption time interval to the time interval from the target user's most recent consumption;

[0061] Step 112: Determine the optimal discount coefficient for the target user based on the first ratio and the second ratio.

[0062] For example, after determining the time interval from the last consumption of each target user, for each target user who meets the recall trigger condition within a set time period (for example, the same day), the consumption times of each target user and the average consumption times n can be further determined. A The first ratio, and the average consumption time interval f A and a second ratio of the time interval to the most recent consumption of each target user; further, according to the first ratio and the second ratio, determining the optimal discount coefficient for each target user; here, the value range of the optimal discount coefficient is between 0 and 1; the following is an exemplary explanation in conjunction with formula (1).

[0063]

[0064] Here, n trepresents the number of times the target user t spends money at the target merchant A; f t represents the time interval from the last consumption of the target user t. If the time unit is day, then f t represents the number of days that the target user t has not consumed at the target merchant A up to the current day; At represents the optimal discount coefficient of target user t, disn At Corresponding to the first ratio above, it means that the consumption frequency of target user t is proportional to the optimal discount coefficient dis At The contribution value of At Corresponding to the second ratio above, it indicates the time interval from the last consumption of the target user t to the optimal discount coefficient dis At contribution value.

[0065] Understandably, t The larger the value of is, the higher the loyalty of target user t to target merchant A is, and the easier it is to recall. At this time, considering the profit of target merchant A, the discount coefficient of the discount coupon issued to target user t is also larger. On the contrary, n t The smaller the value of is, the lower the target user t's loyalty to the target merchant A is, and the more difficult it is to recall the target user. In this case, it is necessary to issue discount coupons with a smaller discount coefficient to the target user t in order to recall the target user t. Similarly, f t The larger the value of f is, the more difficult it is for the target merchant A to recall the target user t. At this time, it is necessary to issue a discount coupon with a smaller discount coefficient to the target user t in order to recall the target user t. On the contrary, f t The smaller the value of , the easier it is for the target merchant A to recall the target user t. At this time, considering the profit of the target merchant A, the discount coefficient of the discount coupon issued to the target user t is also larger.

[0066] It can be seen that in the embodiment of the present application, for each target user who meets the recall trigger conditions, that is, the user who the merchant needs to recall, the corresponding optimal discount coefficient can be determined. Since the determination of the optimal discount coefficient takes into account the influence of both merchant interests and user recall effects, it can ensure that the merchant's interests are maximized while subsequently recalling users using discount coupons matching the optimal discount coefficient.

[0067] Step 12: Obtain a target discount coupon that is closest to the optimal discount coefficient from the pre-configured multiple discount coupons.

[0068] Exemplarily, the target merchant may pre-configure a variety of discount coupons in the catering SAAS system in use for each target user who meets the recall trigger conditions within a set time period; it should be noted that each discount coupon has a corresponding discount coefficient; for example, a variety of discount coupons with discount coefficients of 0.9, 0.85, 0.75 and 0.7 may be configured, and these discount coupons will be used as discount coupons by the target merchant for subsequent recall of users; it can be understood that since these discount coupons are configured by the target merchant itself, the use of the discount coupons can be in the interests of the target merchant.

[0069] In an embodiment of the present application, after determining the optimal discount coefficient for each target user who meets the recall trigger conditions according to the above steps, a target discount coupon that is closest to the optimal discount coefficient can be obtained from the pre-configured multiple discount coupons, that is, the discount coefficient of the target discount coupon is the closest to the optimal discount coefficient among the multiple discount coupons; subsequently, each target user can be recalled based on the target discount coupon.

[0070] For example, assume that the target merchant has pre-configured discount coupons 1 to 4, and the discount coefficients of these four discount coupons are 0.9, 0.85, 0.75 and 0.7 respectively. If the optimal discount coefficient of a target user is determined to be 0.71 according to the above steps, since discount coupon 4 is closest to the optimal discount coefficient 0.71, discount coupon 4 can be determined as the target discount coupon.

[0071] Understandably, the target discount coupon is also called the optimal discount coupon. Among the various discount coupons pre-configured by the target merchant, the discount coefficient of the target discount coupon is closest to the optimal discount coefficient. Since the determination process of the target discount coupon takes into account both the user recall effect and the merchant cost, it can minimize the cost incurred by the merchant while ensuring the successful recall of the user as much as possible. That is, the target discount coupon is the minimum price that the target merchant needs to pay to recall the target user.

[0072] Step 13: Recall target users based on target discount coupons.

[0073] In the embodiment of the present application, after the target discount coupon of the target user is determined, the corresponding target discount coupon can be issued to the target user to recall him.

[0074] Exemplarily, according to the above step 10, it can be determined when (for example, every day) the target merchant needs to issue discount coupons to which users to recall them; according to the above steps 11 and 12, it can be determined what discount coefficient the target merchant should issue discount coupons to the users it needs to recall; therefore, through the above steps 10 to 12, it can be determined when the target merchant needs to issue discount coupons to which users and what discount coefficients they should issue.

[0075] For example, after determining which users need to be issued target discount coupons with a certain discount coefficient every day, the QR codes of these target discount coupons can be sent to the corresponding target users who need to be recalled in the form of links via text messages every day. In this way, after receiving the recall text messages, the target users can use the QR code of the target discount coupon to make purchases at the target merchant within the validity period of the target discount coupon. In this way, the target users can be effectively recalled.

[0076] An embodiment of the present application provides a user recall method, the method comprising: acquiring consumption data of multiple users who have consumed at a target merchant, and determining recall trigger conditions for the multiple users based on the consumption data; the recall trigger conditions are related to the recall time; determining a target user who meets the recall trigger conditions within a set time period, and determining a corresponding optimal discount coefficient based on the consumption data of the target user; the target user is at least one user among the multiple users; acquiring a target discount coupon that is closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient; and recalling the target user based on the target discount coupon.

[0077] It can be seen that in the embodiment of the present application, for multiple users who have consumed at the target merchant, the recall trigger conditions of these users can be determined first. Since the recall trigger conditions are related to the recall time and within the set time period, for example, users who meet the recall trigger conditions on the same day are the users who need to be recalled on the same day, therefore, determining the user's recall trigger conditions can help the target merchant to clearly identify the users who need to be recalled and the recall time for the user recall; further, after clarifying the users who need to be recalled and the recall time for the user recall, by determining the optimal discount coefficients corresponding to these users and using the discount coupons closest to the optimal discount coefficient to recall the users, the user recall effect can be improved and the merchant's profits can be guaranteed.

[0078] In some embodiments, when there are multiple target users, the above method may further include: determining the value scores of each of the multiple target users; sorting the value scores of the multiple target users in order from large to small, and determining at least one target user ranked in front as a high-value user; judging whether the high-value user has made consumption within the validity period of the target discount voucher; if it is determined not, selecting a discount voucher with the lowest discount rate from a plurality of pre-configured discount vouchers, and recalling the high-value user.

[0079] Understandably, it is very necessary for target merchants to conduct value scoring for target users who need to be recalled. This is because by scoring the value of users, it not only helps target merchants to formulate different marketing strategies according to the size of user value scores, but also helps to identify high-value users from users who need to be recalled, and then conduct a second recall for high-value users who have not been successfully recalled. In this way, the risk of losing high-value customers can be reduced and the success rate of user recall can be improved.

[0080] In the embodiment of the present application, when there are multiple target users, the value score of each target user is determined separately; the process of determining the value score of the target user is described below.

[0081] In some embodiments, determining the value scores of each of the multiple target users may include: determining the direct value score, indirect value score, and potential value score of each of the multiple target users; and performing a weighted combination of the direct value score, indirect value score, and potential value score of each target user to obtain the value scores of each of the multiple target users.

[0082] Exemplarily, the value score of the target user can be comprehensively determined by three aspects: the direct value score, indirect value score and potential value score of the target user; specifically, after determining the direct value score, indirect value score and potential value score of the target user, the corresponding value score can be obtained by weighted combination of the direct value score, indirect value score and potential value score.

[0083] In some embodiments, determining the direct value score of each target user may include: determining the total consumption amount and total consumption times of each target user, and the average consumption amount and average consumption times of users who have consumed at the target merchant; determining a third ratio of the total consumption amount and the average consumption amount of each target user, and a fourth ratio of the total consumption times and the average consumption times of each target user; and performing a weighted combination of the third ratio and the fourth ratio to obtain the direct value score of each target user.

[0084] For example, the direct value of the target user can be understood as the value that the target user can directly bring to the target merchant; wherein, the direct value of the target user to the target merchant can be comprehensively measured by the total consumption amount and total consumption times of the target user at the target merchant.

[0085] For example, taking the target merchant as catering merchant A, the total amount of consumption of each target user at catering merchant A can be determined first. At 、Total consumption times At , and the average amount of money spent by users who have consumed at restaurant AAv and average consumption times Av ; Then, determine the total consumption amount of each target user At and average consumption amount Av The third ratio, and the total consumption times of each target user At and average consumption times Av Then, according to the third ratio and the fourth ratio, determine the direct value score values ​​of each target user AtDf ; The following is an exemplary explanation combining formula (2) and formula (3).

[0086]

[0087] here, Corresponding to the third ratio above, Corresponding to the fourth ratio; further, after obtaining the third ratio and the fourth ratio, the total consumption amount can be determined. At The corresponding score amount Atf , and the total number of consumption times At Corresponding rating times Atf ; Finally, the two scores are weighted and combined to get the direct value score values ​​of each target user AtDf , as shown in formula (3):

[0088] values AtDf =A1*amount Atf +A2*time Atf (3)

[0089] Here, A1 and A2 represent the score amount respectively. Atf and rating times Atf It should be noted that the values ​​of A1 and A2 can be set according to actual conditions, and the embodiment of the present application does not limit this; for example, the values ​​of A1 and A2 can be 0.7 and 0.3 respectively. At this time, values AtDf =0.7*amount Atf +0.3*time Atf .

[0090] In some embodiments, determining the indirect value score of each target user may include: determining the average number of consumers for each consumption by each target user, and the average online score for the target merchant; and determining the indirect value score of each target user based on the average number of consumers and the average online score.

[0091] Exemplarily, the indirect value of the target user can be understood as the value that the target user can indirectly bring to the target merchant; among them, the indirect value of the target user to the target merchant can be comprehensively measured by the average number of consumers each time the target user consumes, and the average online score of the target merchant.

[0092] For example, if the target merchant is catering merchant A, the average number of consumers refers to the average number of diners when the target user dines at the catering merchant A each time, and the average online score refers to the average score of the target user on the online ordering platform for the catering merchant A. It can be understood that the more the average number of diners when the target user dines at the catering merchant A each time, the more popularity and potential orders the target user can bring to the catering merchant A, because these diners brought by the target user may also bring new orders to the catering merchant A. At the same time, the higher the score of the target user on the online ordering platform for the catering merchant A, the more popularity and potential orders the target user will bring to the catering merchant A.

[0093] For example, the target merchant is a restaurant merchant A. When determining the average number of people that each target user eats at the restaurant merchant A each time, Atv , and the average online score of the restaurant A on the online ordering platform Atv After that, the score corresponding to the average number of diners can be determined according to formula (4): people Atvf And the score corresponding to the online average score Atvf .

[0094]

[0095] For example, the online food ordering platform allows users to rate restaurant A from 1 to 5 points. Therefore, the average score of restaurant A given by each target user on the online food ordering platform is 5 points at most and 1 point at the least. If the target user does not rate restaurant A on the online food ordering platform, the overall average score of restaurant A on the online food ordering platform can be used as the online average score of restaurant A given by the target user on the online food ordering platform.

[0096] Further, after obtaining the score corresponding to the average number of people dining, Atvf And the score corresponding to the online average score Atvf , the indirect value score values ​​of each target user can be determined according to formula (5) AtSf .

[0097] values AtSf =B1*people Atvf+B2*score Atvf (5)

[0098] Here, B1 and B2 represent the rating people Atvf and score Atvf It should be noted that the values ​​of B1 and B2 can be set according to actual conditions, and the embodiment of the present application does not limit this; for example, the values ​​of B1 and B2 are 0.5, at this time, values AtSf =0.5*people Atvf +0.5*score Atvf .

[0099] In some embodiments, determining the potential value score of each target user may include: determining the distance between the permanent residence of each target user and the target merchant, and the total amount of expenses spent at other merchants in a historical time period; and determining the potential value score of each target user based on the distance and the total amount of expenses.

[0100] For example, the potential value of the target user to the target merchant can be comprehensively measured by the distance between the target user's permanent residence and the target merchant, and the total amount of consumption of the target user at other merchants in the historical time period before the current moment.

[0101] Exemplarily, the historical time period refers to the time period before the current moment. Here, the length of the historical time period can be set according to actual conditions, and the embodiments of the present application do not limit this. For example, it can be a time period corresponding to the past six months or the past year.

[0102] Here, when the target merchant is a catering merchant, the permanent residence of the target user can be obtained through the online ordering platform, and other merchants are other catering merchants. For example, when determining the distance between the permanent residence of each target user and the target merchant (e.g., catering merchant A), At , and the total amount of money spent at other merchants in the historical period (e.g., the past year) At After that, the distance can be determined according to formula (6) and formula (7) respectively. At Corresponding score distance Atf , and the total amount of money At Corresponding score money Atf .

[0103]

[0104] Among them, distance At The unit is km.

[0105]

[0106] Further, in getting the score distance Atf and score money Atf After that, the potential value score values ​​of each target user can be determined according to formula (8): AtPf .

[0107] values AtPf =C1*distance Atf +C2*money Atf (8)

[0108] Here, C1 and C2 represent the scoring distance Atf and score money Atf It should be noted that the values ​​of C1 and C2 can be set according to actual conditions, and the present application embodiment does not limit this; for example, the values ​​of B1 and B2 can be 0.6 and 0.4 respectively. At this time, values AtPf =0.6*distance Atf +0.4*money Atf .

[0109] In the embodiment of the present application, the direct value score values ​​of each target user are obtained according to the above steps. AtDf , indirect value scores values AtSf and potential value scores AtPf After that, we can give each target user a direct value score. AtDf , indirect value scores values AtSf and potential value scores AtPf Perform weighted combination to obtain the corresponding value score values Atf , as shown in formula (9), the value score values Atf Can represent the value of target users to target merchants.

[0110] values Atf =D1*value AtDf +D2*value AtSf +D3*value AtPf (9)

[0111] Here, D1, D2 and D3 represent direct value scores respectively. AtDf , indirect value scores values AtSf and potential value scoresAtPf It should be noted that the values ​​of D1, D2 and D3 can be set according to actual conditions, and the embodiment of the present application does not limit this; for example, the values ​​of D1, D2 and D3 can be 0.5, 0.3 and 0.2 respectively. At this time, values Atf =0.5*value AtDf +0.3*value AtSf +0.2*value AtPf .

[0112] It can be seen that in the embodiment of the present application, since the value score of the target user is determined based on the three values ​​of direct value, indirect value and potential value to the target merchant, and the industry attributes of the target merchant are taken into consideration when determining each value, the value score result of the target user can more accurately reflect the value of the target user.

[0113] In the embodiment of the present application, for each target user who meets the triggering recall condition within a set time period (for example, every day), the corresponding value score values ​​can be determined according to the above steps. Atf ; That is, the value score of each target user who meets the conditions for triggering recall can be obtained every day; then, the value score of each target user is sorted in order from large to small, that is, the higher the ranking, the higher the value score of the target user; in order to improve the recall effect, at least one target user ranked in the front can be determined as a high-value user; for example, the top 30% of target users can be determined as high-value users of the target merchant.

[0114] Exemplarily, issuing target discount coupons to each target user (including high-value users) according to the above step 13 is equivalent to a recall. If the target user who receives the target discount coupon has not used the discount coupon for consumption within the validity period of the target discount coupon, and the target user is determined to be a high-value user, that is, it is determined that the high-value user has not consumed within the validity period of the target discount coupon, at this time, a discount coupon with the lowest discount rate can be selected from a plurality of pre-configured discount coupons, and then the QR code of the discount coupon can be issued to the high-value user who needs to be recalled in the form of a link to achieve a secondary recall of the high-value user.

[0115] It should be noted that if the number of target users is 1, after determining the value score of the target user according to the above steps, the value score is compared with the set value. If it is determined that the value score of the target user is greater than the set value, the target user is determined to be a high-value user. If it is determined that the high-value user has not made any consumption within the validity period of the target discount coupon, at this time, a discount coupon with the lowest discount rate can be selected from a plurality of pre-configured discount coupons, and then the QR code of the discount coupon is distributed to the high-value user who needs to be recalled in the form of a link, so as to achieve a secondary recall of the high-value user.

[0116] It can be seen that the embodiment of the present application can identify high-value users based on the value scores of target users, and then conduct a second recall of high-value users who have not been successfully recalled, which can solve the problem of reduced profits of target merchants caused by the loss of high-value users.

[0117] Figure 4 Schematic diagram of the structure of the user recall device according to an embodiment of the present application. Figure 4 As shown, the device includes: a first determination module 300, a second determination module 301, an acquisition module 302 and a recall module 303, wherein:

[0118] The first determination module 300 is used to obtain consumption data of multiple users who have consumed at the target merchant, and determine the recall triggering conditions of the multiple users according to the consumption data;

[0119] The second determination module 301 is used to determine a target user who meets the recall trigger condition within a set time period, and determine a corresponding optimal discount coefficient according to the consumption data of the target user; the target user is at least one user among the multiple users;

[0120] An acquisition module 302 is used to acquire a target discount coupon that is closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient;

[0121] The recall module 303 is used to recall the target user based on the target discount coupon.

[0122] In some embodiments, the multiple users include a first user and a second user, the consumption data includes the number of consumptions and the consumption time of each consumption, and the first determination module 300 is further used to:

[0123] For the first user whose consumption times are greater than or equal to the set times, counting the time intervals between two adjacent consumptions, and determining the maximum time interval from the counted time intervals;

[0124] Determining a recall trigger condition for the first user according to the maximum time interval;

[0125] For the second user whose consumption times are less than the set times, counting the time interval between the first user's last two consumptions;

[0126] The time intervals between the first user's last two consumptions are averaged to determine the recall triggering condition for the second user.

[0127] In some embodiments, the second determining module 301 is further configured to:

[0128] Determine, based on the consumption data of the multiple users, an average consumption frequency of the multiple users, and an average consumption time interval of users whose consumption frequency exceeds a set frequency;

[0129] Determine the time interval from the last consumption of the target user according to the consumption data of the target user;

[0130] Determine a first ratio of the target user's consumption times to the average consumption times, and a second ratio of the average consumption time interval to the time interval from the target user's most recent consumption;

[0131] An optimal discount coefficient for the target user is determined according to the first ratio and the second ratio.

[0132] In some embodiments, when there are multiple target users, the recall module 303 is further configured to:

[0133] Determine the value scores of multiple target users;

[0134] Sorting the value scores of the plurality of target users in descending order, and determining at least one of the target users ranked at the top as a high-value user;

[0135] Determining whether the high-value user has made a purchase within the validity period of the target discount coupon;

[0136] In the case of a negative determination, a discount coupon with the lowest discount rate is selected from a plurality of pre-configured discount coupons to recall the high-value user.

[0137] In some embodiments, the recall module 303 is further used to:

[0138] Determine a direct value score, an indirect value score, and a potential value score for each target user among the plurality of target users;

[0139] The direct value score, the indirect value score and the potential value score of each target user are weightedly combined to obtain the value scores of each of the multiple target users.

[0140] In some embodiments, the recall module 303 is further used to:

[0141] Determine the total consumption amount and total consumption times of each target user, and the average consumption amount and average consumption times of the multiple users;

[0142] Determine a third ratio of the total consumption amount of each target user to the average consumption amount, and a fourth ratio of the total consumption times of each target user to the average consumption times;

[0143] A direct value score of each target user is determined according to the third ratio and the fourth ratio.

[0144] In some embodiments, the recall module 303 is further used to:

[0145] Determine the average number of consumers for each target user during each consumption, and the average online score of the target merchant;

[0146] An indirect value score for each target user is determined based on the average number of consumers and the average online score.

[0147] In some embodiments, the recall module 303 is further used to:

[0148] Determine the distance between the permanent residence of each target user and the target merchant, and the total amount of money spent at other merchants in a historical time period;

[0149] A potential value score of each target user is determined according to the distance and the total amount of the fee.

[0150] In actual applications, the above-mentioned first determination module 300, second determination module 301, acquisition module 302 and recall module 303 can all be implemented by a processor located in an electronic device, and the processor can be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.

[0151] In addition, each functional module in this embodiment can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or software functional modules.

[0152] If the integrated unit is implemented in the form of a software function module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment is essentially or the part that contributes to the relevant technology or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method of this embodiment. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0153] Specifically, the computer program instructions corresponding to a user recall method in this embodiment can be stored on a storage medium such as a CD, a hard disk, or a USB flash drive. When the computer program instructions corresponding to a user recall method in the storage medium are read or executed by an electronic device, any user recall method in the aforementioned embodiments is implemented.

[0154] Based on the same technical concept as the above embodiments, see Figure 5 , which shows an electronic device 400 provided in an embodiment of the present application, which may include: a memory 401 and a processor 402; wherein,

[0155] Memory 401, used for storing computer programs and data;

[0156] The processor 402 is configured to execute a computer program stored in the memory to implement any one of the user recall methods in the foregoing embodiments.

[0157] In practical applications, the memory 401 may be a volatile memory, such as RAM; or a non-volatile memory, such as ROM, flash memory, hard disk drive (HDD) or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 402.

[0158] The processor 402 may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. It is understandable that for different user recall systems, the electronic device used to implement the processor function may also be other, which is not specifically limited in the embodiments of the present application.

[0159] An embodiment of the present application further provides a user recall system, which includes the aforementioned user recall device or the aforementioned electronic device.

[0160] In some embodiments, the functions or modules included in the device provided in the embodiments of the present application can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0161] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0162] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0163] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0164] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0168] The above are only preferred embodiments of the present application and are not intended to limit the protection scope of the present application.

Claims

1. A user recall method, characterized in that: The method comprises: Acquire consumption data of multiple users who have consumed at a target merchant, and determine recall trigger conditions for the multiple users based on the consumption data; Determine a target user who meets the recall trigger condition within a set time period, and determine a corresponding optimal discount coefficient according to the consumption data of the target user; the target user is at least one user among the multiple users; Acquire a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient; The target user is recalled based on the target discount coupon.

2. The method according to claim 1, characterized in that The multiple users include a first user and a second user, the consumption data includes the number of consumptions and the consumption time of each consumption, and determining the recall triggering conditions of the multiple users according to the consumption data includes: For the first user whose consumption times are greater than or equal to the set times, counting the time intervals between two adjacent consumptions, and determining the maximum time interval from the counted time intervals; Determining a recall trigger condition for the first user according to the maximum time interval; For the second user whose consumption times are less than the set times, counting the time interval between the first user's last two consumptions; The time intervals between the first user's last two consumptions are averaged to determine the recall triggering condition for the second user.

3. The method according to claim 1, characterized in that The consumption data includes the number of consumptions and the consumption time of each consumption, and the method further includes: Determine, based on the consumption data of the multiple users, an average consumption frequency of the multiple users, and an average consumption time interval of users whose consumption frequency exceeds a set frequency; Determining the corresponding optimal discount coefficient according to the consumption data of the target user includes: Determine the time interval from the last consumption of the target user according to the consumption data of the target user; Determine a first ratio of the target user's consumption times to the average consumption times, and a second ratio of the average consumption time interval to the time interval from the target user's most recent consumption; An optimal discount coefficient for the target user is determined according to the first ratio and the second ratio.

4. The method according to any one of claims 1 to 3, characterized in that: In the case where there are multiple target users, the method further includes: Determine the value scores of multiple target users; Sorting the value scores of the plurality of target users in descending order, and determining at least one of the target users ranked at the top as a high-value user; Determining whether the high-value user has made a purchase within the validity period of the target discount coupon; In the case of a negative determination, a discount coupon with the lowest discount rate is selected from a plurality of pre-configured discount coupons to recall the high-value user.

5. The method according to claim 4, characterized in that Determining the value scores of each of the multiple target users includes: Determine a direct value score, an indirect value score, and a potential value score for each target user among the plurality of target users; The direct value score, the indirect value score and the potential value score of each target user are weightedly combined to obtain the value scores of each of the multiple target users.

6. The method according to claim 5, characterized in that Determine the direct value score of each target user, including: Determine the total consumption amount and total consumption times of each target user, and the average consumption amount and average consumption times of the multiple users; Determine a third ratio of the total consumption amount of each target user to the average consumption amount, and a fourth ratio of the total consumption times of each target user to the average consumption times; A direct value score of each target user is determined according to the third ratio and the fourth ratio.

7. The method according to claim 6, characterized in that Determine the indirect value score of each target user, including: Determine the average number of consumers for each target user during each consumption, and the average online score of the target merchant; An indirect value score for each target user is determined based on the average number of consumers and the average online score.

8. The method according to claim 6, characterized in that Determine the potential value score of each target user, including: Determine the distance between the permanent residence of each target user and the target merchant, and the total amount of money spent at other merchants in a historical time period; A potential value score of each target user is determined according to the distance and the total amount of the fee.

9. A user recall device, characterized in that: The device comprises: A first determination module is used to obtain consumption data of multiple users who have consumed at a target merchant, and determine the recall triggering conditions of the multiple users according to the consumption data; A second determination module is used to determine a target user who meets the recall trigger condition within a set time period, and determine a corresponding optimal discount coefficient according to the consumption data of the target user; the target user is at least one user among the multiple users; An acquisition module, used for acquiring a target discount coupon closest to the optimal discount coefficient from a plurality of pre-configured discount coupons; each of the plurality of discount coupons has a corresponding discount coefficient; A recall module is used to recall the target user based on the target discount coupon.

10. An electronic device, characterized in that: The device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the method according to any one of claims 1 to 8 is implemented when the processor executes the program.

11. A user recall system, comprising the device according to claim 9 or the electronic device according to claim 10.

12. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images