Push method, device and storage medium of prompt information and electronic equipment

Abstract

The application discloses a kind of prompt information's push method, device and storage medium and electronic equipment.Therein, the method includes: obtaining the first behavior data generated when target application is accessed in first time period, and the second behavior data generated when target application is accessed in second time period, wherein, second time period is located after first time period;First behavior data and second behavior data are integrated and calculated to obtain target calculation result;In the case where target calculation result indicates that target correlation degree reaches target threshold, target prompt information is pushed for target user account accessing target application.The application solves the technical problem that there is no effective means to improve user retention rate.

Description

Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a method, apparatus, storage medium, and electronic device for pushing notification information. Background Technology

[0002] In recent years, applications have grown increasingly powerful, especially those that interact with user accounts, such as shopping apps, reading apps, and short video apps. However, all applications face the challenge of improving user account retention rates.

[0003] In existing technologies, improving user account retention often requires investing significant resources to attract and retain user accounts within the application. However, resources are limited, and the improvement in retention rate cannot be guaranteed. In other words, existing technologies lack effective methods to improve user retention.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, storage medium, and electronic device for pushing notification information, in order to at least solve the technical problem of lacking effective means to improve user retention.

[0006] According to one aspect of the present invention, a method for pushing notification information is provided, comprising: acquiring first behavioral data generated when a target application is accessed during a first time period, and second behavioral data generated when the target application is accessed during a second time period, wherein the second time period is after the first time period; integrating and calculating the first behavioral data and the second behavioral data to obtain a target calculation result, wherein the target calculation result is used to indicate the target relevance between the first behavioral data and the second behavioral data; and pushing target notification information to a target user account accessing the target application when the target calculation result indicates that the target relevance reaches a target threshold, wherein the target notification information is used to prompt the target user account to perform the target access behavior corresponding to the first behavioral data.

[0007] According to another aspect of the present invention, a notification push device is also provided, comprising: a first acquisition unit, configured to acquire first behavioral data generated when a target application is accessed during a first time period, and second behavioral data generated when the target application is accessed during a second time period, wherein the second time period is after the first time period; a first calculation unit, configured to perform integrated calculation on the first behavioral data and the second behavioral data to obtain a target calculation result, wherein the target calculation result is used to indicate the target relevance between the first behavioral data and the second behavioral data; and a first notification unit, configured to push target notification information to a target user account accessing the target application when the target calculation result indicates that the target relevance reaches a target threshold, wherein the target notification information is used to prompt the target user account to perform the target access behavior corresponding to the first behavioral data.

[0008] As an optional solution, it further includes: a third acquisition unit, used to acquire third behavior data generated when the second user account accesses the target application during the first time period, wherein the target user account includes the second user account; a fourth acquisition unit, used to acquire churn data generated when the second user account does not access the target application during the second time period; a third calculation unit, used to integrate and calculate the third behavior data and the churn data to obtain a second calculation result, wherein the second calculation result is used to indicate a second correlation degree between the third behavior data and the churn data; and a reduction unit, used to reduce the frequency / number of times a second prompt message is pushed to the target user account when the second calculation result indicates that the second correlation degree has reached a reference threshold, wherein the second prompt message is used to prompt the target user account to perform the target access behavior corresponding to the third behavior data.

[0009] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-mentioned method for pushing notification information when it is run.

[0010] According to another aspect of the present invention, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-described method for pushing notification information through the computer program.

[0011] In this embodiment of the invention, first behavioral data generated when the target application is accessed during a first time period and second behavioral data generated when the target application is accessed during a second time period are obtained, wherein the second time period is after the first time period; the first behavioral data and the second behavioral data are integrated and calculated to obtain a target calculation result, wherein the target calculation result is used to indicate the target relevance between the first behavioral data and the second behavioral data; when the target calculation result indicates that the target relevance reaches a target threshold, a target prompt message is pushed to the target user account accessing the target application, wherein the target prompt message is used to prompt the target user account to perform the above-mentioned... The target access behavior corresponding to a behavior data point is determined by acquiring the correlation between behavior data generated in different time periods. This determines whether the first behavior data generated in the previous time period will affect the second behavior data generated in the subsequent time period. If so, a push notification is used to prompt the user account to execute the first behavior data. By prompting the user account to execute the first behavior data, the overall execution probability of the first and second behavior data is effectively improved. The amount of behavior data generated by the user account in the target application is often positively correlated with the user retention rate in the target application, thus achieving the technical effect of improving user retention rate and solving the technical problem of lacking effective means to improve user retention rate. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0013] Figure 1 This is a schematic diagram of an application environment for an optional notification information push method according to an embodiment of the present invention;

[0014] Figure 2 This is a schematic diagram of the flow of an optional notification information push method according to an embodiment of the present invention;

[0015] Figure 3 This is a schematic diagram of an optional method for pushing notification information according to an embodiment of the present invention;

[0016] Figure 4 This is a schematic diagram of another optional method for pushing notification information according to an embodiment of the present invention;

[0017] Figure 5 This is a schematic diagram of another optional method for pushing notification information according to an embodiment of the present invention;

[0018] Figure 6 This is a schematic diagram of another optional method for pushing notification information according to an embodiment of the present invention;

[0019] Figure 7 This is a schematic diagram of an optional notification information push device according to an embodiment of the present invention;

[0020] Figure 8 This is a schematic diagram of an optional notification information push device according to an embodiment of the present invention;

[0021] Figure 9 This is a schematic diagram of an optional notification information push device according to an embodiment of the present invention;

[0022] Figure 10 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] First, to facilitate understanding of the embodiments of the present invention, some terms or nouns involved in the present invention will be explained below:

[0026] According to one aspect of the present invention, a method for pushing notification information is provided. Optionally, as an optional implementation, the above-mentioned method for pushing notification information may be applied to, but is not limited to, [examples of other methods]. Figure 1The environment shown may include, but is not limited to, user equipment 102, network 110, and server 112. The user equipment 102 may include, but is not limited to, a display 108, a processor 106, and a memory 104.

[0027] The specific process can be summarized in the following steps:

[0028] Step S102-1: User equipment 102 obtains the first behavior data generated when the target user account accesses the target application 1022 within the first time period;

[0029] Step S102-1: User equipment 102 obtains the second behavior data generated when the target user account accesses the target application 1022 during the second time period;

[0030] In steps S104-S106, user equipment 102 sends the first line of data and the second line of data to server 112 through network 110;

[0031] In step S108, the server 112 processes the first line data and the second line data through the processing engine 116 to determine whether there is a correlation between the first line data and the second line data, and generates target prompt information if there is a correlation.

[0032] In steps S110-S112, server 112 sends the target prompt information to user device 102 via network 110. Processor 106 in user device 102 displays the target prompt information on display 108 and stores the target prompt information in memory 104.

[0033] remove Figure 1 Beyond the illustrated example, the above steps can be performed independently by user equipment 102, i.e., user equipment 102 performs steps such as processing the first line of data and the second line of data, thereby reducing the processing load on the server. User equipment 102 includes, but is not limited to, handheld devices (such as mobile phones), laptops, desktop computers, in-vehicle devices, etc., and this invention does not limit the specific implementation of user equipment 102.

[0034] Alternatively, as an alternative implementation method, such as Figure 2 As shown, the methods for pushing notification messages include:

[0035] S202, Obtain first behavioral data generated when the target application is accessed in a first time period, and second behavioral data generated when the target application is accessed in a second time period, wherein the second time period is after the first time period;

[0036] S204, integrate and calculate the first row of data and the second row of data to obtain the target calculation result, wherein the target calculation result is used to indicate the target correlation between the first row of data and the second row of data;

[0037] S206, when the target calculation result indicates that the target relevance has reached the target threshold, push target prompt information to the target user account that accesses the target application, wherein the target prompt information is used to prompt the target user account to perform the target access behavior corresponding to the first action data.

[0038] Optionally, in this embodiment, the above-mentioned method for pushing notification information can be used, but is not limited to, in scenarios where the push notification method is used to improve the retention data generated when a user account visits the target application. The retention data can be, but is not limited to, indicating that the target user account has become a loyal customer of the target application. Specifically, assuming all behavioral data of the target user account in the first week (first time period) after registration with the target application is taken as first behavioral data, and the retention data of the target user account in the second week (second time period) after registration with the target application is taken as second behavioral data; then, the correlation between the first behavioral data and the second behavioral data is obtained and statistically analyzed. If the correlation reaches a target threshold, it can be understood that the execution of the behavior corresponding to the first behavioral data contributes to the generation of the second behavioral data. Therefore, by using the push notification method, the target user account is prompted or encouraged to perform more of the behavior corresponding to the first behavioral data, thereby increasing the probability of generating the second behavioral data. Since the second behavioral data is retention data, the increase in retention data naturally increases the overall user retention rate of the target application.

[0039] Optionally, in this embodiment, when the second behavioral data is retained data, the second behavioral data may be, but is not limited to, multiple types of behavioral data. Only when the execution information corresponding to these multiple types of behavioral data meets retention conditions is the multiple types of behavioral data determined as retained data or second behavioral data. For example, if the execution information such as the number of times / frequency of a user account performs a target type of behavior within a second time period meets retention conditions (such as target number of times, target frequency, etc.), then the behavioral data generated by the user account when performing the target type of behavior within the second time period is used as second behavioral data. Alternatively, it can be understood that in determining whether a user account is retained or becomes a loyal user account, it is often necessary to comprehensively judge multiple types or multiple operations performed by the user account within a certain period to improve the accuracy of data acquisition.

[0040] Optionally, in this embodiment, the above-mentioned method for pushing notification information can be used, but is not limited to, scenarios where the push notification method is used to increase the amount of behavioral data generated by a user account when accessing a target application. Specifically, it is assumed that one type of behavioral data (such as data generated by liking behavior) of the target user account in a certain week (first time period) of the target application is taken as the first behavioral data, and another type of behavioral data (such as data generated by commenting behavior) of the target user account in another week (second time period) is taken as the second behavioral data. Then, the correlation between the first behavioral data and the second behavioral data is obtained and statistically analyzed. When the correlation reaches a target threshold, it can be understood that the execution of the behavior corresponding to the first behavioral data helps to generate the second behavioral data. Thus, by using the push notification method, the target user account is directly prompted or encouraged to perform more behaviors corresponding to the first behavioral data, while indirectly increasing the probability of generating the second behavioral data. Or, it can be understood that a push notification for prompting the generation of the first behavioral data also takes into account increasing the generation of the second behavioral data. When the target user account performs a large amount of first behavioral data or second behavioral data in the target application, the correlation between the target user account and the target application is naturally increased, thereby making the target user account a loyal user account of the target application.

[0041] Optionally, in this embodiment, the first behavioral data and the second behavioral data may be, but are not limited to, different types of behavioral data. For example, the first behavioral data may be interactive operation data, and the second behavioral data may be resource transfer data. The data type of the second behavioral data may have a first association relationship with the application type of the target application, while the first behavioral data may have a second association relationship with the application type of the target application. The degree of association of the first association relationship is higher than that of the second association relationship. For example, if the target application is a shopping application, the data type corresponding to the shopping application type may be, but is not limited to, a resource transfer type with a first association relationship with the application type of the target application (such as transferring the resources corresponding to the goods to be purchased to the target application). The first behavioral data may be, but is not limited to, a transfer operation type with a second association relationship with the application type of the target application (such as adding virtual goods to the virtual shopping cart in the target application).

[0042] Optionally, in this embodiment, the first line data and the second line data may be, but are not limited to, data obtained by the target application and triggered by all or part of the user accounts accessing the target application (such as big data).

[0043] Optionally, in this embodiment, the first behavioral data and the second behavioral data may also be, but are not limited to, data triggered by the target user account of the target application. The target user account may be, but is not limited to, an account that has accessed the target application, such as a user account whose access time in the target application is less than a first time threshold (e.g., a newly registered user account), or a user account whose access time in the target application reaches a second time threshold but is not marked with a target tag (e.g., an old user account with a long registration time but not a loyal account). In this way, the above-mentioned push notification method can be used to specifically increase the probability of the target user account becoming a loyal account. The target tag may be, but is not limited to, used to mark user accounts whose association with the target application reaches an association threshold (e.g., a loyal account).

[0044] Optionally, in this embodiment, the second time period is located after the first time period, and the second time period may be, but is not limited to, a continuous time period with the first time period. For example, if the first time period is the target week, then the second time period may be, but is not limited to, the next week immediately following the target week.

[0045] It's important to note that when a user account performs a specific action on the application within a certain timeframe (e.g., the action corresponding to the first action data), this action may influence the user account to perform another action on the application in a subsequent timeframe (e.g., the second action data). Therefore, if a prompt message is used to encourage the user account to perform the aforementioned specific action, the probability of the user account performing the other action is increased. After a user account performs a large number of actions on the application, the likelihood of that user account becoming a loyal user account is also greatly increased, thereby improving the application's user retention rate.

[0046] To determine the aforementioned special behavior, we can collect first behavior data generated by the user account performing an undetermined behavior on the application within a certain period of time, and second behavior data generated by the user account performing another behavior on the application in a subsequent period of time. We can further integrate and calculate the first behavior data and the second behavior data to determine the degree of correlation between the first behavior data and the second behavior data. We can then use whether the degree of correlation reaches a target threshold as an indicator to further determine whether the undetermined behavior is the aforementioned special behavior.

[0047] Further examples, such as Figure 3 As shown, assuming the target application 302 is a live streaming application, and user accounts in this application can perform different types of actions by triggering various virtual buttons, such as... Figure 3As shown in (a), the user account triggers the liking action by clicking the virtual "like" button. Further, it is assumed that... Figure 3 Figure (a) shows the generation process of the first row of data in the first time period, and... Figure 3 (b) shows the process of generating the second row of data in the second time period. Specifically, in Figure 3 As shown in (a), a user account triggers the "like" action by clicking the virtual "like" button, thereby generating first-action data (in this scenario, the first-action data can be, but is not limited to, information indicating the number of likes or the time period in which the like action was triggered). Figure 3 As shown in (b), the user account triggers the execution of a tipping action by clicking the virtual button "Gift", thereby generating second action data (in this scenario, the second action data may be used, but is not limited to, to represent the number of tipping actions or the time period in which the tipping action is triggered).

[0048] Furthermore, the first and second lines of data are not limited to data generated when the same user account accesses the target application 302. Figure 3 The content shown is for illustrative purposes only and does not impose any limitations on the generation of the first and second rows of data.

[0049] The embodiments provided in this application obtain first behavioral data generated when the target application is accessed in a first time period and second behavioral data generated when the target application is accessed in a second time period, wherein the second time period is after the first time period. The first and second behavioral data are integrated and calculated to obtain a target calculation result, which indicates the target correlation between the first and second behavioral data. When the target correlation indicated by the target calculation result reaches a target threshold, a target prompt message is pushed to the target user account accessing the target application. The target prompt message prompts the target user account to perform the target access behavior corresponding to the first behavioral data. By obtaining the correlation between behavioral data generated in different time periods, it is determined whether the first behavioral data generated in the previous time period will affect the second behavioral data generated in the subsequent time period. If so, the prompt message is pushed to prompt the user account to perform the first behavioral data. This achieves the technical objective of efficiently increasing the overall execution probability of the first and second behavioral data by prompting the user account to perform the first behavioral data. Furthermore, the amount of behavioral data generated by the user account in the target application is often positively correlated with the user retention rate in the target application, thereby achieving the technical effect of improving user retention rate.

[0050] As an optional approach, the first row of data and the second row of data are integrated and calculated to obtain the target calculation result, including:

[0051] S1, Calculate the first sub-data in the first row of data, where the first sub-data is used to represent the execution information of the target access behavior;

[0052] S2, Statistically analyze the second sub-data associated with the first sub-data in the second behavior data, wherein the second sub-data is used to represent the proportion of the execution time of the target access behavior in the second time period;

[0053] S3 integrates and calculates the first and second sub-data to obtain the target calculation result.

[0054] Optionally, in this embodiment, the second sub-data may be used, but is not limited to, to represent the degree of association between a user account and a target application, such as the percentage of time a user account performs the target access behavior in the second time period reaching a percentage threshold.

[0055] Optionally, in this embodiment, the execution duration may be, but is not limited to, the cumulative execution duration, or it may be, but is not limited to, the duration of the time period in which the execution occurs. For example, if the first action is triggered in the first time period and also in the second time period, the execution duration of the first action can be regarded as the cumulative duration of the first time period and the second time period. Alternatively, the cumulative execution duration of the first action can be calculated specifically without considering the duration of the time period in which it occurs. The specific choice can be based on the scenario and is not limited here.

[0056] It should be noted that, in order to improve the accuracy of the target calculation results, the relationship between the first sub-data and the second sub-data is limited. This can be understood, but is not limited to, that the user account that generates the first sub-data and the user account that generates the second sub-data are of the same type. Based on this, the second sub-data is also limited to representing the proportion of the execution time of the target access behavior in the second time period. This can be understood, but is not limited to, determining the degree of association between the user account and the target application in the second time period through the second sub-data. The degree of association can be, but is not limited to, positively correlated with the proportion value in the above proportion information.

[0057] To further illustrate, optional examples include... Figure 4As shown, the first time period 402 and the second time period 404 each include six equally divided time periods. Each time period is used to represent 1 / 6 of the first time period 402 or the second time period 404. It can be understood that, assuming that the first time period 402 and the second time period 404 are both 6 days, then each time period is used to represent the length of one day. Furthermore, assuming that the first sub-data is the data generated when the first line is executed (406), and the second sub-data is the data generated when the second line is executed (408), and the first line (406) is triggered to execute at the initial moment of the first time period 402, then it can be seen that the first line (406) is only executed once in the first time period 402 (or only executed within one hour), while the second line (408) is triggered to execute in multiple (3) time periods of the second time period 404. Therefore, it can be calculated that the execution time of the second line (408) accounts for 1 / 2 of the second time period 404.

[0058] Through the embodiments provided in this application, the first sub-data in the first row of data is statistically analyzed, wherein the first sub-data is used to represent the execution information of the target access behavior; the second sub-data associated with the first sub-data in the second row of data is statistically analyzed, wherein the second sub-data is used to represent the proportion of the execution time of the target access behavior in the second time period; the first sub-data and the second sub-data are integrated and calculated to obtain the target calculation result, thereby achieving the purpose of improving the granularity of the basis for the integrated calculation and realizing the effect of improving the efficiency of the integrated calculation.

[0059] As an optional approach, the first and second sub-data are integrated and calculated to obtain the target calculation result, including:

[0060] S1, construct the first feature corresponding to the first sub-data;

[0061] S2, construct the second feature corresponding to the second sub-data;

[0062] S3 calculates the first feature and the second feature according to the linear correlation coefficient calculation method to obtain the target calculation result.

[0063] Optionally, in this embodiment, the linear correlation coefficient can be used, but is not limited to, to calculate the correlation relationship, wherein the correlation relationship can be, but is not limited to, a non-deterministic relationship, and the linear correlation coefficient can be used, but is not limited to, to calculate the degree of linear correlation between variables, as shown in the following formula (1):

[0064]

[0065] Where Cov(X,Y) is the covariance of X and Y, Var[X] is the variance of X, and Var[Y] is the variance of Y.

[0066] Optionally, the linear correlation coefficient can be, but is not limited to, the order (SROCC) correlation coefficient. For example, suppose there are two sequences X and Y, with orders R(X) and R(Y), where R(Xi) = k represents that Xi is the kth largest (or kth smallest) in sequence X. Then SROCC(X,Y) = PLCC(R(X),R(Y)), where PLCC is the Pearson linear correlation coefficient.

[0067] Optionally, in this embodiment, the feature construction process may include, but is not limited to, at least one of the following: binning, one-hot encoding, feature hashing, embedding, log transformation, feature scaling, normalization, feature interaction, normalization, etc.

[0068] It should be noted that the linear correlation coefficient is calculated on the constructed features to obtain the linear correlation coefficient of the features corresponding to the first row of data with respect to the second row of data. It is assumed that the larger the linear correlation coefficient, the greater the internal difference between the first row of data and the second row of data, and thus the higher the correlation between the first row of data and the second row of data. This eliminates the need to rely on human experience and automates the process of judging behavioral data.

[0069] As a further example, one could calculate the SROCC order correlation coefficient between the first behavioral feature and the second behavioral feature, using the following formula:

[0070] Suppose there are two sequences X and Y, with orders R(X) and R(Y), where R(Xi) = k represents that Xi is the kth largest (or kth smallest) in sequence X. Then SROCC(X,Y) = PLCC(R(X),R(Y)), where PLCC is the linear correlation coefficient. The formula for calculating linear correlation (2) is as follows:

[0071]

[0072] Where Cov(X,Y) is the covariance of X and Y, Var[X] is the variance of X, and Var[Y] is the variance of Y. Feature selection and segmentation point determination.

[0073] Through the embodiments provided in this application, a first feature corresponding to a first sub-data is constructed; a second feature corresponding to a second sub-data is constructed; the first feature and the second feature are calculated according to the linear correlation coefficient calculation method to obtain the target calculation result, thereby achieving the purpose of automating the behavioral data processing process and improving the data processing efficiency.

[0074] As an optional approach, the execution information includes at least one of the following:

[0075] The number of times the target access behavior is executed;

[0076] The frequency of execution of the target access behavior in the first time period;

[0077] The cumulative execution time of the target access behavior;

[0078] The target access behavior corresponds to the execution location on the target application;

[0079] The time zone in which the target access behavior is executed.

[0080] Optionally, in this embodiment, taking the target access behavior as a click behavior as an example, the number of times the target access behavior is executed can be, but is not limited to, the number of clicks; the execution frequency of the target access behavior in the first time period can be, but is not limited to, the click rate; the cumulative execution time of the target access behavior can be, but is not limited to, the cumulative value of the time consumed by each click operation; the execution position on the target application corresponding to the target access behavior can be, but is not limited to, the position triggered by the click operation; and the time zone where the execution time of the target access behavior is located can be, but is not limited to, the time zone where the click operation is located (such as a certain year, month, and day).

[0081] Optionally, in this embodiment, taking the target access behavior as a resource transfer behavior (such as shopping) as an example, the number of times the target access behavior is executed can be, but is not limited to, the number of resource transfers; the execution frequency of the target access behavior in the first time period can be, but is not limited to, the resource transfer frequency; the cumulative execution time of the target access behavior can be, but is not limited to, the cumulative value of the time consumed by each resource transfer operation; the execution location on the target application corresponding to the target access behavior can be, but is not limited to, the location corresponding to the triggering of the resource transfer operation (such as purchasing goods); and the time zone where the execution time of the target access behavior is located can be, but is not limited to, the time zone where the resource transfer operation is located (such as a certain year, month, and day).

[0082] As an optional approach, after integrating and calculating the first row of data and the second row of data to obtain the target calculation result, the following steps are included:

[0083] S1, Obtain the third line data generated when the target application is accessed within the first time period, wherein the data type of the third line data is different from the data type of the first line data;

[0084] S2, integrate and calculate the third row of data and the second row of data to obtain a first calculation result, wherein the first calculation result is used to indicate the first degree of correlation between the third row of data and the second row of data;

[0085] S3, if the first relevance is greater than the target relevance, push the first prompt information to the target user account, wherein the first prompt information is used to prompt the target user account to perform the access behavior corresponding to the third action data.

[0086] Optionally, in this embodiment, the third row of data may, but is not limited to, representing any kind of data different from the first row of data, and there is no limitation on the quantity or type.

[0087] It should be noted that in scenarios where behavioral data with a high degree of relevance to the second behavioral data is specifically sought, different types of behavioral data within the first time period, such as first behavioral data and second behavioral data, can be obtained separately and calculated according to the integration calculation method to obtain the corresponding calculation results. Based on the calculation results, one or more behavioral data with the highest degree of relevance to the second behavioral data can be obtained to generate corresponding prompt information.

[0088] To further illustrate, optional examples include... Figure 5 As shown, data set 502 includes multiple rows of data, such as the first row, the third row, and so on up to the nth row. Each row of data in data set 502 is further integrated and calculated with the second row of data 504 to obtain the calculation result corresponding to each row of data in data set 502. Based on this calculation result, one or more rows of data with the highest correlation to the second row of data 504 are identified. Furthermore, based on this calculation result, each row of data in data set 502 can be arranged and displayed in ascending or descending order.

[0089] The embodiments provided in this application obtain third behavioral data generated when a target application is accessed within a first time period, wherein the data type of the third behavioral data is different from that of the first behavioral data; the third behavioral data and the second behavioral data are integrated and calculated to obtain a first calculation result, wherein the first calculation result is used to indicate a first correlation degree between the third behavioral data and the second behavioral data; if the first correlation degree is greater than the target correlation degree, a first prompt message is pushed to the target user account, wherein the first prompt message is used to prompt the target user account to perform the access behavior corresponding to the third behavioral data, thereby achieving the purpose of comprehensively comparing the correlation degree between behavioral data and realizing the effect of improving the comprehensiveness of behavioral data processing.

[0090] As an optional approach, the first behavioral data generated when the target application is accessed during a first time period, and the second behavioral data generated when the target application is accessed during a second time period, include:

[0091] S1, Obtain behavioral data generated when the first user account accesses the target application within the first time period, wherein the first user account is the account that first accesses the target application at the target time, and the first time period includes the target time.

[0092] S2, Obtain retention data generated when the first user account accesses the target application during the second time period;

[0093] S3, the retained data is determined as the second row of data.

[0094] It should be noted that, in order to improve the accuracy of behavioral data processing, behavioral data of newly registered user accounts (first user accounts) can be obtained, but is not limited to. For newly registered user accounts, assuming that the first time period is the first week when the newly registered user account starts accessing the target application, and the second time period is the second consecutive week after the first week, the first behavioral data can be understood, but is not limited to, the initial visit behavioral data generated by the first (week) visit of the newly registered user account, and the second behavioral data can be understood, but is not limited to, the return visit behavioral data generated by the second (week) visit of the newly registered user account.

[0095] To further illustrate, an optional assumption is that the behavioral data of the first user account registered with the target application at the target time or within the target time period is determined as the first behavioral data. For example... Figure 6 As shown in (a), after the user account triggers the registration operation, it is registered as the first user account of the target application 602, and further as follows: Figure 6As shown in (b), candidate operation data after registration as the first user account is counted, and if the candidate operation data meets the retention conditions, the candidate operation data is used as the retention data of the first user account.

[0096] The embodiments provided in this application obtain behavioral data generated when a first user account accesses a target application within a first time period, wherein the first user account is the account that first accesses the target application at a target time, and the first time period includes the target time; retention data generated when the first user account accesses the target application within a second time period is obtained; and the retention data is determined as second behavioral data, thereby improving the retention efficiency of user accounts.

[0097] As an optional solution, it also includes:

[0098] S1, Obtain third behavior data generated when the second user account accesses the target application within the first time period, wherein the target user account includes the second user account;

[0099] S2, obtain the churn data resulting from the second user account not accessing the target application during the second time period;

[0100] S3, integrate and calculate the third-line data and the churn data to obtain a second calculation result, wherein the second calculation result is used to indicate the second degree of correlation between the third-line data and the churn data;

[0101] S4, if the second calculation result indicates that the second relevance has reached the reference threshold, reduce the frequency / number of times the second prompt information is pushed to the target user account, wherein the second prompt information is used to prompt the target user account to perform the target access behavior corresponding to the third action data.

[0102] It should be noted that not all user account actions are designed to improve user retention. They may also be negative actions that express negative emotions, such as reporting or complaining. These negative actions may originate from notifications, such as advertisements for a product. If such negative actions lead to an increase in user churn, then the frequency of such advertisements will be reduced.

[0103] The embodiments provided in this application obtain third behavior data generated when a second user account accesses a target application within a first time period, wherein the target user account includes the second user account; obtain churn data generated when the second user account does not access the target application within a second time period; integrate and calculate the third behavior data and the churn data to obtain a second calculation result, wherein the second calculation result is used to indicate a second correlation degree between the third behavior data and the churn data; when the second calculation result indicates that the second correlation degree reaches a reference threshold, reduce the frequency / number of push notifications to the target user account, wherein the second notification is used to prompt the target user account to perform the target access behavior corresponding to the third behavior data, thereby reducing the number / frequency of push notifications that would lead to user account churn and achieving the effect of reducing the user account churn rate.

[0104] As an optional solution, for ease of understanding, let's take a specific scenario of improving user account retention as an example. Specifically, when a user account performs a certain behavior at a certain frequency within a certain period of time, it is more likely to stay and become a loyal user account. Once such behavior is discovered, we can guide the user account to perform it multiple times. Once it reaches a certain number of times, it may bring higher retention to the product account. Therefore, let's assume the above-mentioned behavior that can greatly improve user retention as the target behavior.

[0105] Next, data collection is performed, as follows:

[0106] User account retention tag: Indicates whether a user is retained after a certain time window (such as one week later). If retained, it is marked as 1; if churned, it is marked as 0.

[0107] User account retention rate: The ratio of the number of days a user is retained after a certain time window (such as one week) to the total number of days. For example, if a user is retained for 5 days after one week, the retention rate = 5 / 7. The calculation can be, but is not limited to: retention days n / total number of days in the time window N.

[0108] For example, collecting users' historical behavior within a certain time window (such as within a week). For short video software, behavioral data includes a series of user behaviors such as browsing, liking, collecting, adding friends, and following. Different behavioral matrices exist depending on different business models.

[0109] Furthermore, the collected data is aggregated at the user level to form a wide table with user topics as the dimension. The fields of the wide table are as follows:

[0110] User representation (user_id), retention rate, number of times of behavior 1, number of days of behavior 1, number of times of behavior 2, number of days of behavior 2, number of times of behavior 3, number of days of behavior 3, ... number of times of behavior n, number of days of behavior n, etc.;

[0111] Furthermore, feature construction is performed on the above-summarized data, for example, using standardization and normalization to construct features, in order to obtain multiple corresponding behavioral features;

[0112] Furthermore, the SROCC order correlation coefficient of each behavioral feature (number of times of behavior 1, number of days of behavior 1, number of times of behavior 2, number of days of behavior 2, number of times of behavior 3, number of days of behavior 3, ... number of times of behavior n, number of days of behavior n) with respect to user retention and activity rate is calculated. From this, the order correlation coefficient of all behavioral features with respect to retention can be obtained. The larger the correlation coefficient, the greater the internal difference, and the more likely it is to be the target behavior. The results are sorted from high to low and then displayed so that staff can select the basis for generating prompt information in the display.

[0113] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0114] According to another aspect of the present invention, a notification information push device for implementing the above-described notification information push method is also provided. For example... Figure 7 As shown, the device includes:

[0115] The first acquisition unit 702 is used to acquire first behavioral data generated when the target application is accessed in a first time period, and second behavioral data generated when the target application is accessed in a second time period, wherein the second time period is after the first time period.

[0116] The first calculation unit 704 is used to integrate and calculate the first row of data and the second row of data to obtain a target calculation result, wherein the target calculation result is used to indicate the target correlation between the first row of data and the second row of data;

[0117] The first prompting unit 706 is used to push target prompt information to the target user account accessing the target application when the target calculation result indicates that the target relevance has reached the target threshold. The target prompt information is used to prompt the target user account to perform the target access behavior corresponding to the first action data.

[0118] Optionally, in this embodiment, the aforementioned notification push device can be used, but is not limited to, in scenarios where the push method of notification information is used to improve the retention data generated when a user account visits the target application. The retention data can be, but is not limited to, indicating that the target user account has become a loyal customer of the target application. Specifically, assuming all behavioral data of the target user account in the first week (first time period) after registration with the target application is taken as first behavioral data, and the retention data of the target user account in the second week (second time period) after registration with the target application is taken as second behavioral data; then, the correlation between the first behavioral data and the second behavioral data is obtained and statistically analyzed. If the correlation reaches a target threshold, it can be understood that the execution of the behavior corresponding to the first behavioral data contributes to the generation of the second behavioral data. Therefore, by using the push method of notification information, the target user account is prompted or encouraged to perform more of the behavior corresponding to the first behavioral data, thereby increasing the probability of generating the second behavioral data. Since the second behavioral data is retention data, the increase in retention data naturally increases the overall user retention rate of the target application.

[0119] Optionally, in this embodiment, when the second behavioral data is retained data, the second behavioral data may be, but is not limited to, multiple types of behavioral data. Only when the execution information corresponding to these multiple types of behavioral data meets retention conditions is the multiple types of behavioral data determined as retained data or second behavioral data. For example, if the execution information such as the number of times / frequency of a user account performs a target type of behavior within a second time period meets retention conditions (such as target number of times, target frequency, etc.), then the behavioral data generated by the user account when performing the target type of behavior within the second time period is used as second behavioral data. Alternatively, it can be understood that in determining whether a user account is retained or becomes a loyal user account, it is often necessary to comprehensively judge multiple types or multiple operations performed by the user account within a certain period to improve the accuracy of data acquisition.

[0120] Optionally, in this embodiment, the aforementioned notification push device can be used, but is not limited to, in scenarios where the notification push method is used to increase the amount of behavioral data generated by a user account when accessing a target application. Specifically, assuming that one type of behavioral data (such as data generated by liking behavior) of the target user account in a certain week (first time period) of the target application is taken as first behavioral data, and another type of behavioral data (such as data generated by commenting behavior) of the target user account in another week (second time period) is taken as second behavioral data; then, the correlation between the first behavioral data and the second behavioral data is obtained and statistically analyzed. Wherein, when the correlation reaches a target threshold, it can be understood that the execution of the behavior corresponding to the first behavioral data helps to generate the second behavioral data. Thus, by using the notification push method, the target user account is directly prompted or encouraged to perform more behaviors corresponding to the first behavioral data, while also indirectly increasing the probability of generating the second behavioral data. Or, it can be understood that a notification push for the generation of first behavioral data also takes into account increasing the generation of second behavioral data. When the target user account performs a large amount of first behavioral data or second behavioral data in the target application, the correlation between the target user account and the target application is naturally increased, thereby making the target user account a loyal user account of the target application.

[0121] Optionally, in this embodiment, the first behavioral data and the second behavioral data may be, but are not limited to, different types of behavioral data. For example, the first behavioral data may be interactive operation data, and the second behavioral data may be resource transfer data. The data type of the second behavioral data may have a first association relationship with the application type of the target application, while the first behavioral data may have a second association relationship with the application type of the target application. The degree of association of the first association relationship is higher than that of the second association relationship. For example, if the target application is a shopping application, the data type corresponding to the shopping application type may be, but is not limited to, a resource transfer type with a first association relationship with the application type of the target application (such as transferring the resources corresponding to the goods to be purchased to the target application). The first behavioral data may be, but is not limited to, a transfer operation type with a second association relationship with the application type of the target application (such as adding virtual goods to the virtual shopping cart in the target application).

[0122] Optionally, in this embodiment, the first line data and the second line data may be, but are not limited to, data obtained by the target application and triggered by all or part of the user accounts accessing the target application (such as big data).

[0123] Optionally, in this embodiment, the first behavioral data and the second behavioral data may also be, but are not limited to, data triggered by the target user account of the target application. The target user account may be, but is not limited to, an account that has accessed the target application, such as a user account whose access time in the target application is less than a first time threshold (e.g., a newly registered user account), or a user account whose access time in the target application reaches a second time threshold but is not marked with a target tag (e.g., an old user account with a long registration time but not a loyal account). The push notification device can then be used to specifically increase the probability of the target user account becoming a loyal account. The target tag may be, but is not limited to, used to mark user accounts whose association with the target application reaches an association threshold (e.g., a loyal account).

[0124] Optionally, in this embodiment, the second time period is located after the first time period, and the second time period may be, but is not limited to, a continuous time period with the first time period. For example, if the first time period is the target week, then the second time period may be, but is not limited to, the next week immediately following the target week.

[0125] It's important to note that when a user account performs a specific action on the application within a certain timeframe (e.g., the action corresponding to the first action data), this action may influence the user account to perform another action on the application in a subsequent timeframe (e.g., the second action data). Therefore, if a prompt message is used to encourage the user account to perform the aforementioned specific action, the probability of the user account performing the other action is increased. After a user account performs a large number of actions on the application, the likelihood of that user account becoming a loyal user account is also greatly increased, thereby improving the application's user retention rate.

[0126] To determine the aforementioned special behavior, we can collect first behavior data generated by the user account performing an undetermined behavior on the application within a certain period of time, and second behavior data generated by the user account performing another behavior on the application in a subsequent period of time. We can further integrate and calculate the first behavior data and the second behavior data to determine the degree of correlation between the first behavior data and the second behavior data. We can then use whether the degree of correlation reaches a target threshold as an indicator to further determine whether the undetermined behavior is the aforementioned special behavior.

[0127] The embodiments provided in this application obtain first behavioral data generated when the target application is accessed in a first time period and second behavioral data generated when the target application is accessed in a second time period, wherein the second time period is after the first time period. The first and second behavioral data are integrated and calculated to obtain a target calculation result, which indicates the target correlation between the first and second behavioral data. When the target correlation indicated by the target calculation result reaches a target threshold, a target prompt message is pushed to the target user account accessing the target application. The target prompt message prompts the target user account to perform the target access behavior corresponding to the first behavioral data. By obtaining the correlation between behavioral data generated in different time periods, it is determined whether the first behavioral data generated in the previous time period will affect the second behavioral data generated in the subsequent time period. If so, the prompt message is pushed to prompt the user account to perform the first behavioral data. This achieves the technical objective of efficiently increasing the overall execution probability of the first and second behavioral data by prompting the user account to perform the first behavioral data. Furthermore, the amount of behavioral data generated by the user account in the target application is often positively correlated with the user retention rate in the target application, thereby achieving the technical effect of improving user retention rate.

[0128] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0129] As an alternative solution, such as Figure 8 As shown, the first computing unit 704 includes:

[0130] The first statistics module 802 is used to count the first sub-data in the first row of data, wherein the first sub-data is used to represent the execution information of the target access behavior;

[0131] The second statistics module 804 is used to count the second sub-data associated with the first sub-data in the second behavior data, wherein the second sub-data is used to represent the proportion of the execution time of the target access behavior in the second time period.

[0132] The calculation module 806 is used to integrate and calculate the first sub-data and the second sub-data to obtain the target calculation result.

[0133] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0134] As an optional solution, the computing module 806 includes:

[0135] The first construction submodule is used to construct the first feature corresponding to the first subdata;

[0136] The second construction submodule is used to construct the second feature corresponding to the second subdata.

[0137] The calculation submodule is used to calculate the first feature and the second feature according to the linear correlation coefficient calculation method to obtain the target calculation result.

[0138] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0139] As an optional approach, the execution information includes at least one of the following:

[0140] The number of times the target access behavior is executed;

[0141] The frequency of execution of the target access behavior in the first time period;

[0142] The cumulative execution time of the target access behavior;

[0143] The target access behavior corresponds to the execution location on the target application;

[0144] The time zone in which the target access behavior is executed.

[0145] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0146] As an optional solution, it includes:

[0147] The second acquisition unit is used to acquire the third line data generated when the target application is accessed during the first time period after integrating and calculating the first line data and the second line data to obtain the target calculation result. The data type of the third line data is different from the data type of the first line data.

[0148] The second calculation unit is used to perform integrated calculation on the first row of data and the second row of data to obtain the target calculation result, and then to perform integrated calculation on the third row of data and the second row of data to obtain the first calculation result, wherein the first calculation result is used to indicate the first correlation between the third row of data and the second row of data.

[0149] The second prompting unit is used to push a first prompting message to the target user account after integrating and calculating the first and second line data to obtain the target calculation result, provided that the first relevance is greater than the target relevance. The first prompting message is used to prompt the target user account to perform the access behavior corresponding to the third line data.

[0150] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0151] As an alternative solution, such as Figure 9 As shown, the first acquisition unit 702 includes:

[0152] The first acquisition module 902 is used to acquire behavioral data generated when the first user account accesses the target application within a first time period, wherein the first user account is the account that first accesses the target application at the target time, and the first time period includes the target time.

[0153] The second acquisition module 904 is used to acquire the retention data generated when the first user account accesses the target application during the second time period.

[0154] The determination module 906 is used to determine the retained data as the second row of data.

[0155] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0156] As an optional solution, it also includes:

[0157] The third acquisition unit is used to acquire third behavior data generated when the second user account accesses the target application within the first time period, wherein the target user account includes the second user account.

[0158] The fourth acquisition unit is used to acquire churn data resulting from the second user account not accessing the target application during the second time period;

[0159] The third calculation unit is used to integrate and calculate the third line data and the churn data to obtain a second calculation result, wherein the second calculation result is used to indicate the second correlation between the third line data and the churn data;

[0160] The reduction unit is used to reduce the frequency / number of times a second prompt message is pushed to the target user account when the second calculation result indicates that the second relevance has reached a reference threshold. The second prompt message is used to prompt the target user account to perform the target access behavior corresponding to the third action data.

[0161] For specific implementation examples, please refer to the example shown in the above-mentioned method for pushing notification information; these examples will not be repeated here.

[0162] According to another aspect of the present invention, an electronic device for implementing the above-described method for pushing notification information is also provided, such as... Figure 10As shown, the electronic device includes a memory 1002 and a processor 1004. The memory 1002 stores a computer program, and the processor 1004 is configured to execute the steps of any of the above method embodiments via the computer program.

[0163] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0164] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0165] S1, obtain the first behavior data generated when the target application is accessed in the first time period, and the second behavior data generated when the target application is accessed in the second time period, wherein the second time period is after the first time period.

[0166] S2, integrate and calculate the first row of data and the second row of data to obtain the target calculation result, wherein the target calculation result is used to indicate the target correlation between the first row of data and the second row of data;

[0167] S3, when the target calculation result indicates that the target relevance has reached the target threshold, push target prompt information to the target user account that accesses the target application, wherein the target prompt information is used to prompt the target user account to perform the target access behavior corresponding to the first action data.

[0168] Alternatively, as those skilled in the art will understand, Figure 10 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 10 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 10 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 10 The different configurations shown.

[0169] The memory 1002 can be used to store software programs and modules, such as the program instructions / modules corresponding to the push notification method and device in this embodiment of the invention. The processor 1004 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002, thereby realizing the above-mentioned push notification method. The memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1002 may further include memory remotely located relative to the processor 1004, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 1002 may be used, but is not limited to, to store information such as first line data, second line data, and target notification information. As an example, such as Figure 10 As shown, the memory 1002 may include, but is not limited to, the first acquisition unit 702, the first calculation unit 704, and the first prompting unit 706 in the aforementioned prompting information push device. Furthermore, it may include, but is not limited to, other module units in the aforementioned prompting information push device, which will not be elaborated upon in this example.

[0170] Optionally, the transmission device 1006 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 1006 includes a Network Interface Controller (NIC), which can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 1006 is a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0171] In addition, the aforementioned electronic device also includes: a display 1008 for displaying the first line of data, the second line of data, and target prompt information, etc.; and a connection bus 1010 for connecting the various module components in the aforementioned electronic device.

[0172] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal, or other electronic device, can become a node in the blockchain system by joining this peer-to-peer network.

[0173] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions to cause the computer device to perform the described XX method, wherein the computer program is configured to perform the steps of any of the method embodiments described above when running.

[0174] Optionally, in this embodiment, the computer-readable storage medium described above may be configured to store a computer program for performing the following steps:

[0175] S1, obtain the first behavior data generated when the target application is accessed in the first time period, and the second behavior data generated when the target application is accessed in the second time period, wherein the second time period is after the first time period.

[0176] S2, integrate and calculate the first row of data and the second row of data to obtain the target calculation result, wherein the target calculation result is used to indicate the target correlation between the first row of data and the second row of data;

[0177] S3, when the target calculation result indicates that the target relevance has reached the target threshold, push target prompt information to the target user account that accesses the target application, wherein the target prompt information is used to prompt the target user account to perform the target access behavior corresponding to the first action data.

[0178] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0179] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0180] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0181] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0183] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0184] Furthermore, the functional units in the various embodiments of the present invention 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 integrated unit can be implemented in hardware or as a software functional unit.

[0185] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for pushing notification information, characterized in that, include: Acquire first behavioral data generated when the target application is accessed during a first time period, and second behavioral data generated when the target application is accessed during a second time period, wherein the second time period is after the first time period; The first behavioral data and the second behavioral data are integrated and calculated to obtain a target calculation result, wherein the target calculation result is used to indicate the degree of target correlation between the first behavioral data and the second behavioral data; When the target calculation result indicates that the relevance of the target has reached the target threshold, a target prompt message is pushed to the target user account that accesses the target application, wherein the target prompt message is used to prompt the target user account to perform the target access behavior corresponding to the first behavior data; The step of integrating and calculating the first behavior data and the second behavior data to obtain the target calculation result includes: statistically analyzing the first sub-data in the first behavior data, wherein the first sub-data is used to represent the execution information of the target access behavior; statistically analyzing the second sub-data in the second behavior data that is associated with the first sub-data, wherein the second sub-data is used to represent the proportion of the execution time of the target access behavior in the second time period; and integrating and calculating the first sub-data and the second sub-data to obtain the target calculation result. The step of integrating and calculating the first sub-data and the second sub-data to obtain the target calculation result includes: constructing a first feature corresponding to the first sub-data; constructing a second feature corresponding to the second sub-data; and calculating the first feature and the second feature according to the linear correlation coefficient calculation method to obtain the target calculation result.

2. The method according to claim 1, characterized in that, The execution information includes at least one of the following: The number of times the target access behavior is executed; The execution frequency of the target access behavior in the first time period; The cumulative execution time of the target access behavior; The target access behavior corresponds to the execution location on the target application; The time zone in which the target access behavior is executed.

3. The method according to claim 1, characterized in that, After integrating and calculating the first behavioral data and the second behavioral data to obtain the target calculation result, the process includes: Obtain third behavioral data generated when the target application is accessed within the first time period, wherein the data type of the third behavioral data is different from the data type of the first behavioral data; The third behavioral data and the second behavioral data are integrated and calculated to obtain a first calculation result, wherein the first calculation result is used to indicate a first degree of correlation between the third behavioral data and the second behavioral data; If the first relevance is greater than the target relevance, a first prompt message is pushed to the target user account, wherein the first prompt message is used to prompt the target user account to perform the access behavior corresponding to the third behavior data.

4. The method according to any one of claims 1 to 3, characterized in that, The acquisition of first behavioral data generated when the target application is accessed during a first time period, and second behavioral data generated when the target application is accessed during a second time period, includes: Obtain behavioral data generated when a first user account accesses the target application within the first time period, wherein the first user account is the account that first accesses the target application at the target time, and the first time period includes the target time. Obtain retention data generated when the first user account accesses the target application during the second time period; The retained data is identified as the second type of data.

5. The method according to any one of claims 1 to 3, characterized in that, Also includes: Obtain third behavioral data generated when the second user account accesses the target application within the first time period, wherein the target user account includes the second user account; Obtain churn data resulting from the second user account not accessing the target application during the second time period; The third behavioral data and the churn data are integrated and calculated to obtain a second calculation result, wherein the second calculation result is used to indicate a second degree of correlation between the third behavioral data and the churn data; If the second calculation result indicates that the second relevance has reached a reference threshold, the frequency / number of times the second prompt message is pushed to the target user account is reduced, wherein the second prompt message is used to prompt the target user account to perform the target access behavior corresponding to the third behavior data.

6. A notification push device, characterized in that, include: The first acquisition unit is used to acquire first behavioral data generated when the target application is accessed in a first time period, and second behavioral data generated when the target application is accessed in a second time period, wherein the second time period is after the first time period. The first calculation unit is used to integrate and calculate the first behavioral data and the second behavioral data to obtain a target calculation result, wherein the target calculation result is used to indicate the target correlation between the first behavioral data and the second behavioral data; The first prompting unit is used to push target prompting information to the target user account accessing the target application when the target calculation result indicates that the target relevance has reached the target threshold, wherein the target prompting information is used to prompt the target user account to perform the target access behavior corresponding to the first behavior data; The first computing unit includes: The first statistics module is used to count the first sub-data in the first behavior data, wherein the first sub-data is used to represent the execution information of the target access behavior; The second statistics module is used to count the second sub-data associated with the first sub-data in the second behavior data, wherein the second sub-data is used to represent the percentage of the execution time of the target access behavior in the second time period; A calculation module is used to integrate and calculate the first sub-data and the second sub-data to obtain the target calculation result; The computing module includes: The first construction submodule is used to construct the first feature corresponding to the first subdata; The second construction submodule is used to construct the second feature corresponding to the second subdata; The calculation submodule is used to calculate the first feature and the second feature according to the linear correlation coefficient calculation method to obtain the target calculation result.

7. The apparatus according to claim 6, characterized in that, The execution information includes at least one of the following: The number of times the target access behavior is executed; The execution frequency of the target access behavior in the first time period; The cumulative execution time of the target access behavior; The target access behavior corresponds to the execution location on the target application; The time zone in which the target access behavior is executed.

8. The apparatus according to claim 6, characterized in that, include: The second acquisition unit is used to acquire third behavior data generated when the target application is accessed during the first time period after the first behavior data and the second behavior data are integrated and calculated to obtain the target calculation result. The data type of the third behavior data is different from the data type of the first behavior data. The second calculation unit is configured to perform integrated calculation on the third behavior data and the second behavior data after the first behavior data and the second behavior data are integrated to obtain the target calculation result, so as to obtain the first calculation result, wherein the first calculation result is used to indicate the first correlation degree between the third behavior data and the second behavior data. The second prompting unit is used to push a first prompting message to the target user account after the first behavior data and the second behavior data are integrated and calculated to obtain the target calculation result, when the first relevance is greater than the target relevance. The first prompting message is used to prompt the target user account to perform the access behavior corresponding to the third behavior data.

9. The apparatus according to any one of claims 6 to 8, characterized in that, The first acquisition unit includes: The first acquisition module is used to acquire behavioral data generated when a first user account accesses the target application within the first time period, wherein the first user account is the account that first accesses the target application at the target time, and the first time period includes the target time. The second acquisition module is used to acquire retention data generated when the first user account accesses the target application during the second time period. The determination module is used to determine the retained data as the second line data.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 5.

11. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 5 through the computer program.

Images