1. A push strategy determination method is characterized by comprising the following steps:

acquiring user data; the user data comprises user information of a plurality of users, and the user information comprises consumption time information and consumption date information corresponding to each consumption time information;

determining users with the consumption times information being larger than or equal to the consumption times threshold value as candidate users, and determining target users from the candidate users;

determining a first consumption interval of the target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user;

determining an optimized individual consumption interval according to the consumption frequency information of the target user, the first consumption interval and the second consumption interval;

determining the life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user;

and determining a first push strategy of the target user from preset strategies according to the life cycle.

2. The push policy determination method according to claim 1, wherein: the determining a first consumption interval of the target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user comprises:

determining the personal average consumption interval of the target user according to the consumption times information and the consumption date information of the candidate user, and determining the overall average consumption interval and the overall consumption interval variance of the candidate user;

wherein the first consumption interval comprises the personal average consumption interval; the second consumption interval comprises the overall average consumption interval and the overall consumption interval variance.

3. The push policy determination method according to claim 2, wherein: determining an optimized individual consumption interval according to the consumption number information of the target user, the first consumption interval and the second consumption interval, including:

determining the total consumption times of the target user according to the consumption time information of the target user;

determining a first parameter according to the ratio of the overall average consumption interval to the overall consumption interval variance, and determining a first numerical value according to the sum of the first parameter and the total consumption times;

determining a second parameter according to the overall average consumption interval and the overall consumption interval variance;

and determining an optimized individual consumption interval according to the total consumption times, the individual average consumption interval, the first parameter and the second parameter.

4. The push policy determination method according to claim 3, wherein: the step of determining an optimized individual consumption interval according to the consumption number information of the target user, the first consumption interval and the second consumption interval further comprises:

determining a first weight corresponding to the personal average consumption interval;

determining a second weight corresponding to the overall average consumption interval;

weighting according to the personal average consumption interval, the first weight, the whole average consumption interval and the second weight to obtain a new personal average consumption interval.

5. The push policy determination method according to claim 1, wherein: determining the life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user, wherein the determining comprises the following steps:

calculating a standard deviation from the individual consumption interval;

taking the individual consumption interval as a mathematical expectation, and determining the life cycle distribution of the target user according to the mathematical expectation, the standard deviation and a semi-normal distribution function;

determining a life cycle interval according to the life cycle distribution; the life cycle interval comprises an existing member interval, a doze member interval, a light-sleep member interval and a deep-sleep member interval;

acquiring current date information;

and calculating a distance value between the current date information and the last consumption date information of the target user, and determining a life cycle interval corresponding to the distance value as the life cycle of the target user.

6. The push policy determination method according to claim 1, wherein: the determining a first push strategy of the target user from preset strategies according to the life cycle includes:

determining a push strategy corresponding to the life cycle from the preset strategies according to the life cycle, and using the push strategy as a first push strategy of the target user;

and the pushing strategy comprises the step of sending preset communication content to the user in a preset communication mode at the preset communication time.

7. The push policy determination method according to claim 1, wherein: the push strategy determination method further comprises the following steps:

and taking the user with the consumption time information smaller than the consumption time threshold value as a new user, and determining a second push strategy of the new user from the preset strategies.

8. An execution method, comprising:

determining a target push strategy; the target push policy is a first push policy or a second push policy determined according to the push policy determination method of any one of claims 1-7;

and executing the target push strategy.

9. A push policy determination device, comprising a processor and a memory;

the memory stores a program;

the processor executes the program to implement the method of any one of claims 1-8.

10. A computer-readable storage medium, characterized in that the storage medium stores a program which, when executed by a processor, implements the method according to any one of claims 1-8.

Background

As the growth of users of the mobile internet tends to saturate, the customer acquisition cost of new users increases, so that the retention of old users is particularly important. Different users have different requirements, so different operation strategies need to be formulated according to different users, and the purpose of reducing user loss is achieved. Nowadays, judgment and analysis are usually performed according to the overall user behaviors of all users, so that logic rules are formulated to divide the users, the influence of the personalized behaviors of the users on the life cycle is ignored, the accuracy is low, the final operation strategy is invalid, and the applicability is poor.

Disclosure of Invention

In view of the above, in order to solve the above technical problems, an object of the present invention is to provide a push policy determining method, an execution method, an apparatus and a storage medium, which improve accuracy and applicability.

The technical scheme adopted by the invention is as follows:

a push policy determination method includes:

acquiring user data; the user data comprises user information of a plurality of users, and the user information comprises consumption time information and consumption date information corresponding to each consumption time information;

determining users with the consumption times information being larger than or equal to the consumption times threshold value as candidate users, and determining target users from the candidate users;

determining a first consumption interval of the target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user;

determining an optimized individual consumption interval according to the consumption frequency information of the target user, the first consumption interval and the second consumption interval;

determining the life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user;

and determining a first push strategy of the target user from preset strategies according to the life cycle.

Further, the determining a first consumption interval of the target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user includes:

determining the personal average consumption interval of the target user according to the consumption times information and the consumption date information of the candidate user, and determining the overall average consumption interval and the overall consumption interval variance of the candidate user;

wherein the first consumption interval comprises the personal average consumption interval; the second consumption interval comprises the overall average consumption interval and the overall consumption interval variance.

Further, the determining an optimized individual consumption interval according to the consumption number information of the target user, the first consumption interval and the second consumption interval includes:

determining the total consumption times of the target user according to the consumption time information of the target user;

determining a first parameter according to the ratio of the overall average consumption interval to the overall consumption interval variance, and determining a first numerical value according to the sum of the first parameter and the total consumption times;

determining a second parameter according to the overall average consumption interval and the overall consumption interval variance;

and determining an optimized individual consumption interval according to the total consumption times, the individual average consumption interval, the first parameter and the second parameter.

Further, the step of determining an optimized individual consumption interval according to the consumption number information of the target user, the first consumption interval and the second consumption interval further comprises:

determining a first weight corresponding to the personal average consumption interval;

determining a second weight corresponding to the overall average consumption interval;

weighting according to the personal average consumption interval, the first weight, the whole average consumption interval and the second weight to obtain a new personal average consumption interval.

Further, the determining the life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user includes:

calculating a standard deviation from the individual consumption interval;

taking the individual consumption interval as a mathematical expectation, and determining the life cycle distribution of the target user according to the mathematical expectation, the standard deviation and a semi-normal distribution function;

determining a life cycle interval according to the life cycle distribution; the life cycle interval comprises an existing member interval, a doze member interval, a light-sleep member interval and a deep-sleep member interval;

acquiring current date information;

and calculating a distance value between the current date information and the last consumption date information of the target user, and determining a life cycle interval corresponding to the distance value as the life cycle of the target user.

Further, the determining a first push policy of the target user from preset policies according to the life cycle includes:

determining a push strategy corresponding to the life cycle from the preset strategies according to the life cycle, and using the push strategy as a first push strategy of the target user;

and the pushing strategy comprises the step of sending preset communication content to the user in a preset communication mode at the preset communication time.

Further, the push policy determining method further includes:

and taking the user with the consumption time information smaller than the consumption time threshold value as a new user, and determining a second push strategy of the new user from the preset strategies.

The invention also provides an execution method, which comprises the following steps:

determining a target push strategy; the target push strategy is a first push strategy or a second push strategy determined according to the push strategy determination method;

and executing the target push strategy.

The invention also provides a push strategy determination device, which comprises a processor and a memory;

the memory stores a program;

the processor executes the program to implement the method.

The present invention also provides a computer-readable storage medium storing a program which, when executed by a processor, implements the method.

The invention has the beneficial effects that: the method comprises the steps of obtaining user data including user information of a plurality of users, wherein the user information includes consumption time information and consumption date information corresponding to each consumption time information, determining the users with the consumption time information being larger than or equal to a consumption time threshold value as candidate users, determining target users from the candidate users, and determining user groups needing to be analyzed; determining a first consumption interval of a target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user, determining an optimized individual consumption interval according to the consumption times information, the first consumption interval and the second consumption interval of the target user, determining a life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user, and determining a first push strategy of the target user from preset strategies according to the life cycle; the life cycle of the target user is determined by combining the second consumption interval of the whole candidate user and the first consumption interval of the single target user, the influence of personalized behaviors on the life cycle is fully considered, and the accuracy of determining the life cycle of the target user is improved, so that the first push strategy of the target user can be determined in a targeted manner, and the applicability and the effectiveness are improved.

Drawings

Fig. 1 is a schematic flowchart illustrating steps of a push policy determination method according to the present invention;

FIG. 2 is a flow chart illustrating steps of a method performed by an embodiment of the present invention;

FIG. 3 is a diagram of a technical architecture according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

As shown in fig. 1, an embodiment of the present invention provides a push policy determining method, including steps S100 to S600:

and S100, acquiring user data.

In the embodiment of the invention, the user data comprises user information of a plurality of users, and the user information comprises consumption time information, consumption date information corresponding to each consumption time information and a user ID. Alternatively, the consumption number information may include the consumption number, the consumption amount per consumption, the consumption number per consumption, and the like, such as the number of purchases for a certain commodity, the amount per purchase, and the specific amount per purchase. In addition, the consumption date information may be a consumption date corresponding to each consumption, for example, the consumption date may be recorded in a year/month/day manner.

Optionally, after acquiring the user data, the data may be subjected to a cleaning process, for example: 1) determining whether the consumption date information is consistent with a preset format, YYYY/MM/DD (year/month/day), and if not, filtering the data; 2) whether the consumption amount is normal or not, if a negative number or 0 exists, whether the consumption amount is abnormal or not needs to be judged, for example: if the sales volume is negative (return goods) or the unit price of the goods is 0, the processing is not carried out; abnormal conditions (if the sales volume is positive (normal sales) or the unit price of the goods is more than 0), the abnormal conditions are defined as dirty data and the data needs to be filtered.

S200, determining the users with the consumption times information larger than or equal to the consumption times threshold value as candidate users, and determining target users from the candidate users.

In the embodiment of the present invention, the consumption number threshold may be set according to a setting, and is not particularly limited. Specifically, taking the consumption number threshold as three as an example, the user with the consumption number information of three or more, specifically, the user with the consumption number of three or more (i.e., the three-shopping user) is determined as a candidate user, and then the target user is determined from the candidate users. For example, when the users who consume the number of times of three or more are user a, user B, user C, user D, and user F, the users a, user B, user C, user D, and user F are determined as candidate users, and then one of the candidate users may be selected as a target user, for example, user a.

S300, determining a first consumption interval of the target user and a second consumption interval of the whole candidate user according to the consumption times information and the consumption date information of the candidate user.

Specifically, step 300 is implemented by step S310:

s310, according to the consumption times information and the consumption date information of the candidate users, determining the personal average consumption interval and the personal consumption interval variance of the target user, and determining the overall average consumption interval and the overall consumption interval variance of the whole candidate users. Wherein the first consumption interval comprises a personal average consumption interval and a personal consumption interval variance; the second consumption interval includes an overall average consumption interval and an overall consumption interval variance.

Specifically, for example, if the consumption times of the target user a is three times and the consumption dates correspond to 2020/01/01, 2020/01/18, and 2020/01/31, and the consumption times of the user B is three times and the consumption dates correspond to 2020/02/01, 2020/02/05, and 2020/02/21, the consumption interval of the target user a may be determined to be 17 and 13, then the average personal consumption interval may be calculated to be 15, and the calculation of the variance of the personal consumption interval uses the existing calculation method, which is not described again. Similarly, it can be determined that the consumption interval of the user B is 4, 16, so that the overall average consumption interval can be calculated to be 12.5 according to the target user a and the user B, and the overall consumption interval variance method also uses the existing calculation method, which is not described again. Note that when there are a plurality of candidate users, calculation may be performed according to the above principle.

S400, determining an optimized individual consumption interval according to the consumption frequency information of the target user, the first consumption interval and the second consumption interval.

Specifically, step S400 includes steps S401-S404:

s401, determining the total consumption times of the target user according to the consumption time information of the target user.

Optionally, the total number of consumption may be the number of consumption, or may also be the number of times of purchasing a certain product repeatedly, which is not limited specifically.

S402, determining a first parameter according to the ratio of the overall average consumption interval to the overall consumption interval variance, and determining a first numerical value according to the sum of the first parameter and the total consumption times.

Specifically, the calculation formula of the first numerical value is as follows:

n_i+α-1

the first parameter α is calculated by the formula:

α＝mu²/sigma+2

wherein mu is the overall average consumption interval, sigma is the variance of the overall consumption interval, n_iThe total number of consumption for the ith user. It should be noted that, the ith user is a target user determined from the candidate users, and the target user a is taken as an example in the embodiment of the present invention.

S403, determining a second parameter according to the overall average consumption interval and the overall consumption interval variance.

Specifically, the calculation formula of the second parameter θ is:

wherein mu is the overall average consumption interval and sigma is the overall consumption interval variance.

S404, determining an optimized individual consumption interval according to the total consumption times, the individual average consumption interval, the first parameter and the second parameter.

Specifically, the calculation formula of the optimized individual consumption interval is as follows:

wherein E is_iOptimized individual consumption intervals for the ith user, final optimization results for individual average consumption intervals,the consumption intervals are averaged for the individual. It is to be understood that, when the ith user is the target user a, the personal average consumption interval is the personal average consumption interval of the target user a, and the optimized individual consumption interval is the optimized individual consumption interval of the target user a.

Optionally, before step S400, the push policy determining method according to the embodiment of the present invention may further include steps S410 to S430:

and S410, determining a first weight corresponding to the average consumption interval of the individuals.

And S420, determining a second weight corresponding to the overall average consumption interval.

And S430, weighting according to the personal average consumption interval, the first weight, the whole average consumption interval and the second weight to obtain a new personal average consumption interval.

Specifically, the optimization formula is as follows:

G＝w₁×(IM)+w₂×(GM)

wherein IM is the average consumption interval of the individual, w₁Is a first weight, GM is an overall average consumption interval, w₂Is the second weight. Wherein the sum of the first weight and the first weight is 1, the personal average consumption interval and the overall average consumption interval may be determined through step S300. Optionally, when the overall average consumption interval is greater than the preset number of times, the first weight may be made greater than the second weight; when the overall average consumption interval is smaller than the preset number of times, the first weight may be smaller than the second weight, for example, when the first weight is 0, the overall average consumption interval is completely dominated; if the overall average consumption interval is equal to the preset number of times, the first weight may be equal to or greater than the second weight, and is not particularly limited. Wherein G is the initial optimization result of the average consumption interval of the individual, and G can be substituted as a new average consumption interval of the individual into step S404 as a new average consumption interval of the individualTo find out optimized individual consumption interval E_i。

And S500, determining the life cycle of the target user according to the individual consumption interval and the last consumption date information of the target user.

Specifically, step S500 includes steps S501-S505:

and S501, calculating the standard deviation according to the individual consumption interval.

Specifically, the calculation formula is:

wherein σ_iRepresents the standard deviation corresponding to the ith user, E_iConsumption intervals for individuals.

S502, taking the individual consumption interval as a mathematical expectation, and determining the life cycle distribution of the target user according to the mathematical expectation, the standard deviation and the semi-normal distribution function.

In the embodiment of the invention, the Half Normal distribution function Half Normal () function refers to taking one Half of the Normal distribution function. Specifically, E is_iAs a mathematical expectation o, thus according to a semi-normal distribution function HalfA lifecycle distribution for the target user is determined. For example, when target user A's individual consumption interval E_i3.744305512, o is 3.744305512, calculate σ_i4.692791032, thus determining a semi-Normal distribution function Half Normal (3.744305512, 4.692791032)²) And obtaining the life cycle distribution of the target user.

And S503, determining a life cycle interval according to the life cycle distribution.

In the embodiment of the present invention, the interval value of the life cycle interval is determined according to a Cumulative Distribution Function (CDF), and it should be noted that a selection rule of the interval value may be adjusted according to actual needs, and is not specifically limited. Specifically, taking 50%, 75%, 80%, and 90% of CDF as an example, the first interval value a (existing) is 50% of CDF, the second interval value S1 is 75% of CDF, the third interval value S2 is 80% of CDF, and the fourth interval value S3 is 90% of CDF, so as to obtain the life cycle interval, for example: existing member intervals: 0 to A (existing), drowsy member interval: a (existing) -S1, light sleep membership interval: S1-S2, sleeping member interval: S2-S3.

And S504, acquiring current date information.

And S505, calculating a distance value between the current date information and the last consumption date information of the target user, and determining a life cycle interval corresponding to the distance value as the life cycle of the target user.

For example, if the current date information is 2021/06/20, and the consumption date in the last consumption date information of the target user is 2021/06/18, the distance value between the current date information and the last consumption date information of the target user is 2, and if a (existing) is 3.165239451, S1 is 5.398349256, S2 is 6.755420378, and S3 is 7.71895435, that is, the existing member section: 0-3.165239451, drowsy member interval: 3.165239451-5.398349256, member interval of light sleep: 5.398349256-6.755420378, sleeping member interval: 6.755420378-7.71895435, the distance value is 2, and the target user is located in the existing member interval, namely the life cycle of the target user is the existing member interval, namely the target user is in the life cycle of the existing member, and the target user is the existing member. It can be understood that if the distance value is in the doze membership interval, the target user is the target user; if the distance value is in the light-sleep member interval, the target user is a light-sleep member; and if the distance value is in the sleeping member interval, the target user is a sleeping member. It should be noted that, if the distance value is greater than S3, the interval corresponds to the sleeping member interval.

S600, determining a first push strategy of the target user from preset strategies according to the life cycle.

Optionally, corresponding preset strategies are set in advance according to users in different life cycles, and a corresponding push strategy is set in each life cycle. For example, when the life cycle of the target user a is determined as the existing member interval, that is, the target user is in the life cycle of the existing member, a push policy corresponding to the life cycle of the existing member is determined from the preset policies at this time, and is used as the first push policy of the target user. It should be noted that, after the life cycle of the target user is determined, the delivery policy is automatically classified according to the life cycle based on artificial intelligence.

Optionally, as shown in table 1, the preset policy is given by way of example, but does not constitute a specific limitation of the preset policy in the embodiment of the present invention. Each push strategy in the preset strategies includes sending preset communication contents, communication frequency, purpose, communication object, planning contents (not shown) and remarks (not shown) to the user in a preset communication time in a preset communication mode. It should be noted that the preset communication time, the preset communication mode and the preset communication content may be determined according to actual requirements. It should be noted that the preset policy may also include a push policy defined for all users, for example, the preset communication content is a daily gift giving or credit using, and the like.

TABLE 1

The contents in table 1 are only part of the contents, and may include other contents, and the contents in table 1 are merely exemplary and not particularly limited. Wherein, the Interval can be a preset Interval, an overall average consumption Interval, an individual average consumption Interval, an optimized individual consumption Interval, etc.; s3-10 can refer to the interval S3-10, and then the preset communication content is sent to the sleeping member twice through SMS/WeChat/EDM within the time of S3-10; or a difference may be made between S3 and S10, where if the difference is not an integer, an integer is taken, and if the difference is a negative number, 0 is taken, and other contents in the table are the same and will not be described again.

The push strategy determining method of the embodiment of the invention further comprises the step S700:

s700, taking the user with the consumption time information smaller than the consumption time threshold value as a new user, and determining a second push strategy of the new user from the preset strategies.

In the embodiment of the present invention, taking the consumption number threshold as three as an example, a user with consumption number information smaller than three, specifically, a user with consumption number smaller than three (i.e., a first-purchase user and a second-purchase user) is determined as a new user, and then a second push policy of the new user is determined from preset policies. It can be understood that, for a user whose consumption number is less than three, i.e. a user whose life cycle is a new user cycle, the second push policy may be determined from the corresponding preset policy in table 1 where the communication object is a new user.

As shown in fig. 2, an embodiment of the present invention further provides an execution method, including steps S801 to S802:

s801, determining a target push strategy.

The target push strategy is a first push strategy or a second push strategy determined according to the push strategy determination method;

s802, executing a target push strategy.

According to the push strategy determining method provided by the embodiment of the invention, the corresponding push strategy is determined by calculating the life cycle of the user, the influence of personalized behaviors on the life cycle is fully considered, and the accuracy of determining the life cycle of the target user is improved, so that the first push strategy of the target user can be determined in a targeted manner, and the applicability and the effectiveness are improved. Meanwhile, the target pushing strategy is executed through the execution method, so that the conversion rate of advertisements put in the promotion activities by the e-commerce platform is improved, the efficiency and the accuracy of screening and marketing users by the e-commerce platform are improved, the conversion rate of marketing activities by the e-commerce platform is improved, the loss probability of the users is reduced, and the repurchase rate is improved by carrying out automatic communication of the full life cycle on the members.

As shown in fig. 3, in the embodiment of the present invention, the adopted technical architecture includes a data storage layer, a data processing layer, and a data application layer. Wherein, the data storage layer is used for executing step S100, the data processing layer is used for executing steps S200-S500, and the data application layer is used for executing step S600 and step S802.

Optionally, the data storage layer adopts a Hadoop as a distributed system infrastructure, the Hadoop is a software framework capable of performing distributed processing on a large amount of data, and can be docked with external systems such as an IT system, an SAP system, a big data platform and other application data related systems to acquire user data, wherein the IT system and the SAP system can be systems for storing original user data, and the acquisition of the user data is a process of extracting the Hadoop from the external systems such as the IT system and the SAP.

Optionally, the data processing layer comprises a data detail layer ODS, a data intermediate layer DWD, a data service layer DWS, a dimension layer DIM, a temporary table TMP and a calculation engine. The data detail layer ODS is a data preparation area, also called a pasting layer, and the data table of the original user data is usually stored as it is, and is a source of the subsequent processing data. The DWD is an isolation layer between a service layer and a data warehouse, and is mainly used for performing data cleaning and normalization operations on the ODS data layer. Based on basic data on the DWB, the data are integrated and summarized to analyze a service data layer of a certain subject domain, generally a broad table, which is used for providing subsequent business query, OLAP analysis, data distribution and the like. Wherein, the data cleaning and processing are summarized, namely ODS- > DWD- > DWS; the compute engines include, but are not limited to, a presto compute engine and a python compute engine for lifecycle computations.

Optionally, the data application layer includes an application service Spring Cloud, which is used for implementing result presentation and related operation policies, specifically result presentation and automatic classification sending policies, and can be connected to an external module to implement a service opening function.

The embodiment of the invention also provides a push strategy determination device, which comprises a processor and a memory;

the memory is used for storing programs;

the processor is used for executing programs to realize the push strategy determination method of the embodiment of the invention. The device of the embodiment of the invention can realize the function of determining the push strategy. The device can be any intelligent terminal such as a mobile phone, a tablet Personal computer, a Personal Digital Assistant (PDA for short), a Point of Sales (POS for short), a vehicle-mounted computer, and the like.

The contents in the above method embodiments are all applicable to the present apparatus embodiment, the functions specifically implemented by the present apparatus embodiment are the same as those in the above method embodiments, and the advantageous effects achieved by the present apparatus embodiment are also the same as those achieved by the above method embodiments.

The embodiment of the present invention further provides a computer-readable storage medium, where a program is stored in the computer-readable storage medium, and the program is executed by a processor to implement the push policy determining method according to the foregoing embodiment of the present invention.

Embodiments of the present invention further provide a computer program product including instructions, which when run on a computer, cause the computer to execute the push policy determination method of the foregoing embodiments of the present invention.

The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.