User retention analysis methods, devices, storage media, and electronic equipment

Abstract

This specification discloses a user retention analysis method, apparatus, storage medium, and electronic device. By obtaining target data corresponding to the data to be analyzed based on the start and end times, and obtaining at least one corresponding retention analysis indicator based on the window length, the target data is calculated to obtain the retention analysis result corresponding to each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculation, the user retention analysis of the data to be analyzed can be efficiently completed, and at least one user retention analysis result can be obtained.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a user retention analysis method, apparatus, storage medium, and electronic device. Background Technology

[0002] When conducting user analysis for traffic analytics products, data such as retention, mutual visits, and the composition of new and returning customers are key indicators for effectively measuring user stickiness and activation / reactivation. User retention analysis models have emerged to analyze product user retention and are widely used in every measurement that requires user retention analysis. However, given the complex and diverse product examples of traffic operations, and the fact that each product corresponds to multiple user retention metrics, how to quickly build highly adaptable and high-performance user retention analysis models has always been a key research direction in this field. Summary of the Invention

[0003] This specification provides a user retention analysis method, apparatus, storage medium, and electronic device. The technical solution is as follows:

[0004] Firstly, embodiments of this specification provide a user retention analysis method, the method comprising:

[0005] Receive the data to be analyzed, window length, and start and end times;

[0006] Obtain the target data corresponding to the start and end times in the data to be analyzed, and obtain at least one retention analysis indicator corresponding to the window length;

[0007] The target data is calculated based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator.

[0008] Secondly, embodiments of this specification provide a user retention analysis device, the device comprising:

[0009] The parameter receiving module is used to receive the data to be analyzed, the window length, and the start and end times.

[0010] The retention analysis module is used to obtain the target data corresponding to the start and end times in the data to be analyzed, and to obtain at least one retention analysis indicator corresponding to the window length.

[0011] The analysis results module is used to calculate the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator.

[0012] Thirdly, embodiments of this specification provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0013] Fourthly, embodiments of this specification provide a computer program product that stores multiple instructions adapted for loading by a processor and executing the above-described method steps.

[0014] Fifthly, embodiments of this specification provide an electronic device that may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0015] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0016] This manual obtains the target data corresponding to the data to be analyzed based on the start and end times, and obtains at least one corresponding retention analysis indicator based on the window length. It then calculates the target data to obtain the retention analysis result for each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculations, it can efficiently complete the user retention analysis of the data to be analyzed and obtain at least one user retention analysis result. This manual provides a general analysis method for dealing with complex and diverse product-generated data and user retention analysis needs, meeting user requirements and improving analysis efficiency through standardized calculation processes, thus achieving efficient analysis of massive amounts of data. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a user retention analysis method provided in the embodiments of this specification;

[0019] Figure 2 This is a schematic diagram of a page containing data to be analyzed, provided in an embodiment of this specification.

[0020] Figure 3 This is a schematic diagram of a configuration of multiple retention analysis components provided in the embodiments of this specification;

[0021] Figure 4This is a schematic diagram of a reference retention model provided in the embodiments of this specification;

[0022] Figure 5 This is a schematic diagram of a structure for obtaining retention analysis results based on a retention model, provided in the embodiments of this specification.

[0023] Figure 6 This is a flowchart illustrating another user retention analysis method provided in the embodiments of this specification;

[0024] Figure 7 This is a schematic diagram of a page providing a visualization of analysis results, as provided in the embodiments of this specification.

[0025] Figure 8 This is a schematic diagram of a procedure for analyzing reference results provided in an embodiment of this specification;

[0026] Figure 9 This is a schematic diagram of the structure of a user retention analysis device provided in the embodiments of this specification;

[0027] Figure 10 This is a schematic diagram of the structure of an electronic device provided in the embodiments of this specification. Detailed Implementation

[0028] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0029] In the description of this specification, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise expressly specified and limited, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Those skilled in the art can understand the specific meaning of the above terms in this specification based on the specific circumstances. Furthermore, in the description of this specification, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0030] The present specification will now be described in detail with reference to specific embodiments.

[0031] With the rapid development of internet technology, various applications (Apps) are subtly changing people's lifestyles, and user retention rate is a crucial indicator guiding App developers in adjusting or optimizing their Apps. Analyzing user retention first requires identifying retention behaviors, that is, defining target events occurring on the target product as retention behaviors. For example, clicking on a target page can be set as a retention behavior, as can staying on a target page for a preset time. The settings for retention behaviors can be designed by relevant personnel as needed, and this manual does not impose any restrictions on this.

[0032] In one embodiment, such as Figure 1 The diagram shown is a flowchart of a user retention analysis method proposed in this specification. This method can be implemented using a computer program and can run on a user retention analysis device based on the von Neumann architecture. This computer program can be integrated into applications or run as a standalone utility application.

[0033] Specifically, the user retention analysis method includes:

[0034] S102, Receive the data to be analyzed, window length, and start and end times.

[0035] The data to be analyzed can be understood as data representing the occurrence of target events on the target product. This data requires user retention analysis, including the frequency and timing of the target events. For example... Figure 2The diagram illustrates a page for obtaining data to be analyzed, as provided in this application embodiment. It includes an app page 101 representing the target product and data to be analyzed 102. Retention behavior is defined as user clicks on page 101. The data to be analyzed includes user identification numbers (UIDs) of users who clicked on page 101 at each time point from November 1, 2019 to December 1, 2020. For example, at 00:01 on November 1, 2019, users with UIDs 12313, 25633, 35948, 88458, and 83543 clicked on page 101; at 00:02, users with UIDs 25633, 52189, and 56825 clicked on page 101. It is understood that... Figure 2 This is only one possible implementation provided in this specification. This specification also includes any other form of representation or statistical method of the data to be analyzed.

[0036] The window length can be understood as the time window corresponding to the retention analysis of the data to be analyzed. For example, the window length can be any length such as 1 day, 7 days, 30 days, 180 days, etc. When the window length is 30 days, the retention results of multiple users corresponding to the data to be analyzed are calculated with 30 days as a time window.

[0037] The start and end times, including the start and end times, can be understood as the target time period within the total time length corresponding to the data to be analyzed. For example, the data to be analyzed is all data collected between January 1, 2018 and December 31, 2019, with start and end times of January 1, 2019 and December 31, 2019, respectively. The start and end times can be specified to any time granularity and include multiple time periods, as needed by relevant personnel.

[0038] In another embodiment, an output table name is also received, which is used to name the output retention analysis results. For example, the received output table names are "Table 1-2021.3.1" and "Table 2-2021.3.1". When the retention analysis results are output, the above output table names are configured for the retention analysis results and saved. When no input output table name is received, the retention analysis results are named based on a preset output table name. In this embodiment, users are allowed to name the output retention analysis results to meet their customization needs.

[0039] S104. Obtain the target data corresponding to the start and end times in the data to be analyzed, and obtain at least one retention analysis indicator corresponding to the window length.

[0040] The target data corresponding to the target time in the data to be analyzed is obtained based on the start and end times. For example, the data to be analyzed is all data collected between January 1, 2018 and December 31, 2019, with start and end times of January 1, 2019 and December 31, 2019, respectively. The target data is the data between January 1, 2019 and December 31, 2019 in the data to be analyzed.

[0041] Based on the window length, obtain at least one corresponding retention analysis metric. For example, if the window length is 30 days, the corresponding retention analysis metric would include: new user retention within 30 days, existing user retention within 30 days, and the ratio of new users in the 30-day period to new users in the previous period.

[0042] S106. Calculate the target data based on at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator.

[0043] Based on the corresponding calculation formula for each retention analysis metric, the target data is calculated to obtain the retention analysis results for each metric. For example, the retention analysis metric is 30-day new user retention. The calculation formula is defined as the proportion of all new users whose time interval between two retention actions is less than or equal to 30 days, or the ratio of new users on the new day to the daily new users in the previous period, or the proportion of new users who are still retained after 30 days among all new users on the new day.

[0044] In one embodiment, at least one retention analysis component is encapsulated, and a target retention analysis component corresponding to each retention analysis metric is obtained based on at least one retention analysis metric. The target retention analysis component is then used to calculate the target data to obtain the retention analysis result corresponding to each retention analysis metric. Figure 3 The diagram shown is a schematic diagram of a retention analysis component provided in an embodiment of this application. It includes a processor 201 and multiple retention analysis components, wherein the retention analysis components include: a periodic retention analysis component 202, a cumulative retention analysis component 203 and a tag analysis component 204.

[0045] The periodic retention analysis component 202 includes multiple periodic retention analysis components, each corresponding to a different period. For example, the periodic retention analysis component 202 includes a T1 periodic retention analysis component, a T2 periodic retention analysis component, and a T3 periodic retention analysis component, where the T1 period is 1 day, the T2 period is 7 days, and the T3 period is 30 days. It is understood that the number of periodic retention analysis components provided in this embodiment is merely illustrative, and the preset period corresponding to each periodic retention analysis component is set according to the needs of relevant personnel.

[0046] The target retention analysis component corresponding to each retention analysis metric is obtained based on at least one retention analysis metric. In other words, the corresponding parameters are configured for the retention analysis component based on the content of the retention analysis metric. For example, multiple corresponding retention analysis metrics are obtained based on a window length of 30 days, including a 30-day cumulative retention analysis metric, a tag analysis metric, and a 30-day periodic retention analysis metric. Parameters are then configured for the periodic retention analysis component 202, the cumulative retention analysis component 203, and the tag analysis component 204 based on these metrics.

[0047] The method for obtaining the target periodic retention analysis component in the periodic retention analysis component 202 is to obtain periodic retention analysis components with a period length less than or equal to the window length. For example, if the T1 period is 1 day, the T2 period is 7 days, and the T3 period is 30 days, and the window length is 30 days, then the T1 periodic retention analysis component, the T2 periodic retention analysis component, and the T3 periodic retention analysis component are obtained as the target periodic retention analysis components; if the window length is 7 days, then the T1 periodic retention analysis component and the T2 periodic retention analysis component are obtained as the target periodic retention analysis components.

[0048] After obtaining the target retention analysis component, it is used to calculate the target data, yielding the retention analysis results corresponding to each retention analysis metric. For example... Figure 4 The diagram shown is a schematic of a program that references a retention model according to an embodiment of this specification. In this embodiment, multiple retention analysis components are encapsulated into a retention model JAR file using Structured Query Language (SQL), such as... Figure 4 As shown, the user configures the table name of the data to be analyzed, the table name of the output table, the start and end times (bizdate), and the window length (window 180). The user also references the retention model that encapsulates multiple retention analysis components. Based on the window length and start and end times, the user performs retention analysis on the data to be analyzed and obtains the retention analysis results. The results are named according to the table name of the output table.

[0049] In this embodiment, multiple retention analysis components are pre-encapsulated using SQL statements. When performing user retention analysis on the data to be analyzed, the encapsulated components are referenced to perform calculations on the data. This method has good portability, and users can obtain user retention analysis results for most products without having to build calculation formulas or model generics.

[0050] In one embodiment, an update instruction is obtained; wherein the update instruction is used to update at least one retention analysis metric corresponding to the window length. Users update the retention analysis metrics corresponding to the window length by adding instructions, that is, adding richer retention analysis formulas to enrich the types of user retention analysis results for the data to be analyzed and refine the user retention analysis results. The update instruction can be any type of numerical or electrical instruction, and can be added via any method such as a wide area network, a local area network, or an input device; for example, by encapsulating more retention analysis components in the retention model.

[0051] In one embodiment, as shown in Figure 5, it is a schematic diagram of a structure for obtaining retention analysis results based on a retention model according to an embodiment of this specification. The intelligent modeling process of the retention model includes model abstraction, computational design, component encapsulation, and optimization updates. Model abstraction involves initializing the retention analysis model. Computational design involves setting corresponding calculation formulas for each retention analysis metric and setting each calculation formula as a corresponding computational analysis component, for example, such as... Figure 5 As shown, the retention model includes multiple calculation and analysis components: aggregation processing component 501, periodic retention analysis component 202, cumulative retention analysis component 203, and tag analysis component 204. The structure and working principle of aggregation processing component 501, periodic retention analysis component 202, and cumulative retention analysis component 203 are described above. Figure 3 The structure and working principle of the polymerization processing component 501 are described below. Figure 5 The component encapsulation involves encapsulating the aforementioned multiple computational and analytical components. The encapsulation process is described above. Figure 3 This will not be elaborated further here. The optimization update involves updating at least one retention analysis metric corresponding to the window length based on the update command, and updating the calculation formula corresponding to each calculation analysis component.

[0052] like Figure 5 The steps shown involve receiving user input of the input table name (i.e., the storage address or identifier of the data to be analyzed), window length, start and end dates, or output table name. This output table name is used to name the output retention analysis results. If no output table name is received, the retention analysis results are named based on a preset output table name. Further, a retention model is used to perform one-stop calculation and visualization processing of the input data through multiple computational analysis components. For instructions on using the retention model, please refer to [link to relevant documentation]. Figure 4 The diagram shown is a schematic of a reference retention model, which will not be described in detail here.

[0053] In this embodiment, the one-stop calculation includes multiple retention analysis calculations, such as the calculation of the periodic retention analysis component 202, the calculation of the cumulative retention analysis component 203, and the calculation of the tag analysis component 204, as described above. Figure 3As shown. The visualization process includes calculations corresponding to the aggregation processing components. Specifically, at least one aggregation analysis result is obtained based on at least one aggregation dimension. These aggregation analysis results and retention analysis results are then visualized to obtain retention views corresponding to each aggregation analysis result and retention analysis result. For example, aggregation dimensions include merchant identifier (PID) and application identifier (app-id) dimensions, as well as cross-retention dimensions, etc. The process of obtaining at least one aggregation analysis result based on at least one aggregation dimension and visualizing these results is described below. Figure 6 .

[0054] This manual obtains the target data corresponding to the data to be analyzed based on the start and end times, and obtains at least one corresponding retention analysis indicator based on the window length. It then calculates the target data to obtain the retention analysis result for each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculations, it can efficiently complete the user retention analysis of the data to be analyzed and obtain at least one user retention analysis result. This manual provides a general analysis method for dealing with complex and diverse product-generated data and user retention analysis needs, meeting user requirements and improving analysis efficiency through standardized calculation processes, thus achieving efficient analysis of massive amounts of data.

[0055] In one embodiment, such as Figure 6 The diagram shown is a flowchart of a user retention analysis method proposed in this specification. This method can be implemented using a computer program and can run on a user retention analysis device based on the von Neumann architecture. This computer program can be integrated into applications or run as a standalone utility application.

[0056] Specifically, the user retention analysis method includes:

[0057] S202, Receive the data to be analyzed, window length, and start and end times.

[0058] See S102 above, which will not be repeated here.

[0059] S204. Obtain the target data corresponding to the start and end times in the data to be analyzed, and obtain at least one retention analysis indicator corresponding to the window length.

[0060] Obtain at least one retention analysis metric corresponding to the window length, including at least one of the following: maximum period retention metric, cumulative retention metric, and tag analysis metric, based on the window length value. For example, if the window length is 30 days, at least one retention analysis metric would include: new user retention within 30 days, existing user retention within 30 days, and the ratio of new users in the 30-day period to new users in the previous period.

[0061] In one embodiment, at least one retention analysis metric further includes at least one preset period retention metric; wherein the period length corresponding to each preset period retention metric is less than the period length corresponding to the maximum period retention metric. For example, at least one preset period retention metric includes a T1 period retention metric, a T2 period retention metric, and a T3 period retention metric, wherein the T1 period is 1 day, the T2 period is 7 days, and the T3 period is 30 days. When the window length is 30 days, the T1 period retention metric, the T2 period retention metric, and the T3 period retention metric are obtained; when the window length is 7 days, the T1 period retention metric and the T2 period retention metric are obtained. In this embodiment, multiple preset period retention metrics are set. After obtaining the maximum period retention metric according to the window length, multiple preset period retention metrics are also obtained to enrich the retention analysis results obtained from the retention analysis metrics and meet the user's retention analysis needs for complex user data.

[0062] S206. Obtain the bitmap information of the target data.

[0063] The bitmap information of the target data in the data to be analyzed is obtained, that is, the target data is mapped using bits to obtain the bitmap information of the target data. Before obtaining the bitmap information of the target data, there are also data processing steps such as data cleaning. This embodiment does not impose any restrictions on the method of obtaining the bitmap information of the target data.

[0064] S208. Using a sliding time window method, the bitmap information of the target data is calculated based on at least one retention analysis indicator to obtain the retention analysis results corresponding to at least one retention analysis indicator.

[0065] The sliding time window method for calculating retention analysis results can be understood as using a specified window length to frame the target data displayed based on time series, and then calculating the user retention analysis result for each window using the formula corresponding to the retention analysis indicators. In other words, it's like a slider of a specified length sliding on a ruler, and each unit of sliding provides feedback on the data within the slider.

[0066] In this embodiment, a sliding time window method is used to obtain retention analysis results. Compared with calculation methods such as historical databases and model pre-aggregation, this method effectively reduces computational and R&D costs and avoids downstream multi-cycle scanning and repetitive calculations.

[0067] In one embodiment, the bitmap information of the target data is converted into the array format of Open Data Processing Service (ODPS). A sliding time window method is then used to calculate the bitmap information of the array-formatted target data based on at least one retention analysis metric, yielding retention analysis results corresponding to each metric. ODPS, also known as MaxCompute, is a fast, fully managed GB / TB / PB-level data warehouse solution provided by Alibaba's general computing platform. The array format is a data format developed in conjunction with ODPS. Compared to the int format (maximum 4 bytes) or long format (maximum 16 bytes), the bitmap information of the target data stored in the array format can be extended to 64 bytes. Therefore, when using the sliding time window method for calculation, it supports a larger window length compared to other formats, resulting in richer user retention results to meet the user retention analysis needs of the data to be analyzed.

[0068] S210. Aggregate the target data according to at least one aggregation dimension to obtain the aggregation analysis results corresponding to each aggregation dimension.

[0069] Aggregation dimensions can be understood as the dimensions used when processing target data, specifically the content corresponding to the horizontal and vertical axes when aggregating the target data. For example, aggregation dimensions can be any user-defined dimension such as daily new customer visits, daily returning customer visits, total daily visits, weekly daily active users, etc. In one embodiment, the target data is aggregated based on cross-retention dimensions to obtain the cross-retention analysis results corresponding to those dimensions. For example, the cross-retention dimension could be the increase in new customer visits on the day after the start time compared to the daily data on the previous day, or the difference between the number of new customers on the day after the start time and the number of new customers on the previous day.

[0070] S212. Visualize the aggregation analysis results for each dimension to obtain the retention view for each aggregation analysis result.

[0071] Visualization can be understood as the process of transforming aggregate analysis results into visually appealing charts. For example, using the DeepinSight standard component to visualize aggregate analysis results to obtain a retention view, and then displaying that retention view on a display device. Figure 7 The image shown is a schematic diagram of a page for visualizing analysis results provided in an embodiment of this specification. Figure 7The following figure is a retention view of the cross-retention analysis results under a cross-aggregation dimension. It shows the new customer growth on January 6th compared to January 1st to January 5th, January 5th compared to January 1st to January 5th, January 4th compared to January 1st to January 3rd, January 3rd compared to January 1st to January 2nd, and January 2nd compared to January 1st. It is understood that this embodiment is only an example of a retention view, and this specification also includes other forms of retention views, such as bar charts, line charts, pie charts, etc.

[0072] S214. Visualize each retention analysis result to obtain the retention view corresponding to each retention analysis result.

[0073] In this embodiment, after visualizing the aggregation analysis results, the method further includes visualizing the retention analysis results to obtain a retention view corresponding to each retention analysis result. For example... Figure 7 The image shown is a schematic diagram of a page for visualizing analysis results provided in an embodiment of this specification. Figure 7 The above figure is a retention view of the results of a periodic retention analysis under a certain periodic retention analysis indicator, with a period of 30 days and a start time of 1 month, showing the increase in new customers in each period compared to the previous period. It should be understood that this embodiment is only an example of a retention view, and this specification also includes other forms of retention views, such as bar charts, line charts, pie charts, etc.

[0074] After obtaining the aggregation analysis results under the aggregation dimension and the retention analysis results under the retention analysis metrics, users can reference these results and input them into other calculation or display models for calculation or processing. For example... Figure 8 The diagram shown is a schematic representation of a procedure for displaying reference analysis results, as provided in an embodiment of this specification. Figure 8 The report references shown in lines 1-9 are references to the aggregated analysis results obtained from the retention model. The retention view of the aggregated analysis results is configured as "Retention Matrix - Interface Table". The calculation applications shown in lines 10-15 of the table are to configure the retention view of the retention analysis results as "Retention Overview - Interface Table". The retention model is the model used to analyze and process the data to be analyzed. The "Retention Matrix - Interface Table" and / or "Retention Overview - Interface Table" are further configured into other calculation models or processing models for further processing, such as comprehensive calculation, bar chart to pie chart conversion, chart splitting, etc.

[0075] This manual obtains the target data corresponding to the data to be analyzed based on the start and end times, and obtains at least one corresponding retention analysis indicator based on the window length. It then calculates the target data to obtain the retention analysis result for each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculations, it can efficiently complete the user retention analysis of the data to be analyzed and obtain at least one user retention analysis result. This manual provides a general analysis method for dealing with complex and diverse product-generated data and user retention analysis needs, meeting user requirements and improving analysis efficiency through standardized calculation processes, thus achieving efficient analysis of massive amounts of data.

[0076] The following are embodiments of the apparatus described in this specification, which can be used to execute the embodiments of the methods described in this specification. For details not disclosed in the apparatus embodiments of this specification, please refer to the embodiments of the methods described in this specification.

[0077] Please see Figure 9 This diagram illustrates the structure of a user retention analysis device provided in an exemplary embodiment of this specification. The user retention analysis device can be implemented as all or part of a device through software, hardware, or a combination of both. The device includes a parameter receiving module 901, a retention analysis module 902, and an analysis result module 903.

[0078] The parameter receiving module 901 is used to receive the data to be analyzed, the window length, and the start and end times.

[0079] The retention analysis module 902 is used to obtain the target data corresponding to the start and end times in the data to be analyzed, and to obtain at least one retention analysis indicator corresponding to the window length.

[0080] The analysis results module 903 is used to calculate the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator.

[0081] In one embodiment, the analysis results module 903 includes:

[0082] A bitmap acquisition unit is used to acquire bitmap information of the target data;

[0083] The sliding calculation unit is used to calculate the bitmap information of the target data based on the at least one retention analysis indicator using a sliding time window method, so as to obtain the retention analysis results corresponding to the at least one retention analysis indicator.

[0084] In one embodiment, the user retention analysis device includes:

[0085] The format conversion module is used to convert the bitmap information of the target data into the array format of Open Data Processing Service;

[0086] The analysis results module 903 is specifically used to calculate the bitmap information of the target data in array format based on the at least one retention analysis indicator using the sliding time window method, and obtain the retention analysis results corresponding to the at least one retention analysis indicator respectively.

[0087] In one embodiment, the user retention analysis device further includes:

[0088] The aggregation processing module is used to aggregate the target data according to at least one aggregation dimension to obtain the aggregation analysis result corresponding to each aggregation dimension.

[0089] In one embodiment, the aggregation dimension includes a cross-retention dimension. The aggregation processing module is specifically used to aggregate the target data according to the cross-retention dimension to obtain the cross-retention analysis result corresponding to the cross-retention dimension.

[0090] In one embodiment, the user retention analysis device further includes:

[0091] The first visualization module is used to visualize the aggregation analysis results corresponding to each dimension, and obtain the retention view corresponding to each aggregation analysis result.

[0092] In one embodiment, the at least one retention analysis metric includes:

[0093] The window length value corresponds to at least one of the maximum periodic retention metric, cumulative retention metric, and tag analysis metric.

[0094] In one embodiment, the at least one retention analysis indicator further includes: at least one preset period retention indicator; wherein the period length corresponding to each preset period retention indicator is less than the period length corresponding to the maximum period retention indicator.

[0095] In one embodiment, user retention analytics metrics include:

[0096] The component encapsulation module is used to encapsulate at least one retention analysis component;

[0097] The analysis results module 903 is specifically used to obtain the target retention analysis component corresponding to each retention analysis indicator based on at least one retention analysis indicator, and to use the target retention analysis component to calculate the target data to obtain the retention analysis result corresponding to each retention analysis indicator.

[0098] In one embodiment, the at least one retention analysis component includes:

[0099] At least one of the following: periodic retention analysis component, cumulative retention analysis component, and tag analysis component.

[0100] In one embodiment, the user retention analysis device includes:

[0101] The indicator update module is used to obtain update instructions; wherein the update instructions are used to update at least one retention analysis indicator corresponding to the window length.

[0102] In one embodiment, the user retention analysis device further includes:

[0103] The second visualization module is used to visualize each retention analysis result to obtain a retention view corresponding to each retention analysis result.

[0104] This manual obtains the target data corresponding to the data to be analyzed based on the start and end times, and obtains at least one corresponding retention analysis indicator based on the window length. It then calculates the target data to obtain the retention analysis result for each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculations, it can efficiently complete the user retention analysis of the data to be analyzed and obtain at least one user retention analysis result. This manual provides a general analysis method for dealing with complex and diverse product-generated data and user retention analysis needs, meeting user requirements and improving analysis efficiency through standardized calculation processes, thus achieving efficient analysis of massive amounts of data.

[0105] It should be noted that the user retention analysis device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the user retention analysis method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the user retention analysis device and the user retention analysis method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0106] The example numbers in this specification are for descriptive purposes only and do not represent the superiority or inferiority of the examples.

[0107] This specification also provides a computer storage medium that can store multiple instructions adapted to be loaded and executed by a processor as described above. Figures 1-8 The user retention analysis method described in the illustrated embodiment can be found in the following documentation for its specific execution process. Figures 1-8 The specific details of the illustrated embodiments will not be elaborated here.

[0108] This specification also provides a computer program product that stores at least one instruction, said at least one instruction being loaded and executed by the processor as described above. Figures 1-8 The user retention analysis method described in the illustrated embodiment can be found in the following documentation for its specific execution process. Figures 1-8 The specific details of the illustrated embodiments will not be elaborated here.

[0109] Please see Figure 10 This document provides a schematic diagram of the structure of an electronic device as an embodiment of the present specification. Figure 10 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0110] The communication bus 1002 is used to realize the connection and communication between these components.

[0111] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0112] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0113] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts of the server 1000 via various interfaces and lines, and performs various functions and processes data of the server 1000 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0114] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 10 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for user retention analysis.

[0115] exist Figure 10In the illustrated electronic device 1000, the user interface 1003 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 1001 can be used to call the user retention analysis application stored in the memory 1005 and specifically perform the following operations:

[0116] Receive the data to be analyzed, window length, and start and end times;

[0117] Obtain the target data corresponding to the start and end times in the data to be analyzed, and obtain at least one retention analysis indicator corresponding to the window length;

[0118] The target data is calculated based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator.

[0119] In one embodiment, the processor 1001 performs the calculation of the target data based on the at least one retention analysis metric to obtain the retention analysis result corresponding to each retention analysis metric, specifically:

[0120] Obtain the bitmap information of the target data;

[0121] The bitmap information of the target data is calculated based on the at least one retention analysis indicator using a sliding time window method to obtain the retention analysis results corresponding to the at least one retention analysis indicator.

[0122] In one embodiment, before the processor 1001 executes the method of calculating the bitmap information of the target data based on the at least one retention analysis metric and the sliding time window to obtain the retention analysis results corresponding to the at least one retention analysis metric, it further executes:

[0123] Convert the bitmap information of the target data into the array format of Open Data Processing Service;

[0124] The method employing a sliding time window calculates the bitmap information of the target data based on at least one retention analysis metric to obtain retention analysis results corresponding to each of the at least one retention analysis metric, including:

[0125] The method using a sliding time window calculates the bitmap information of the target data in array format based on at least one retention analysis metric to obtain the retention analysis results corresponding to each of the at least one retention analysis metric.

[0126] In one embodiment, after the processor 1001 performs the calculation on the target data based on the at least one retention analysis metric to obtain the retention analysis result corresponding to each retention analysis metric, it further performs:

[0127] The target data is aggregated based on at least one aggregation dimension to obtain the aggregation analysis results corresponding to each aggregation dimension.

[0128] In one embodiment, the aggregation dimension includes a cross-retention dimension. The processor 1001 performs aggregation processing on the target data based on at least one aggregation dimension to obtain the aggregation analysis result corresponding to each aggregation dimension. Specifically, the following steps are performed:

[0129] The target data is aggregated based on the cross-retention dimension to obtain the cross-retention analysis results corresponding to the cross-retention dimension.

[0130] In one embodiment, after the processor 1001 performs the aggregation processing on the target data according to at least one dimension to obtain the analysis results corresponding to each dimension, it further performs:

[0131] The aggregation analysis results corresponding to each dimension are visualized to obtain the retention view corresponding to each aggregation analysis result.

[0132] In one embodiment, the at least one retention analysis metric includes:

[0133] The window length value corresponds to at least one of the maximum periodic retention metric, cumulative retention metric, and tag analysis metric.

[0134] In one embodiment, at least one retention analysis metric further includes: at least one preset period retention metric; wherein the period length corresponding to each preset period retention metric is less than the period length corresponding to the maximum period retention metric.

[0135] In one embodiment, before the processor 1001 executes the process of receiving the data to be analyzed, the window length, and the start and end times, it also executes:

[0136] Encapsulate at least one retention analysis component;

[0137] The step of calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator includes:

[0138] Based on at least one retention analysis metric, obtain the target retention analysis component corresponding to each retention analysis metric, and use the target retention analysis component to calculate the target data to obtain the retention analysis result corresponding to each retention analysis metric.

[0139] In one embodiment, the at least one retention analysis component includes:

[0140] At least one of the following: periodic retention analysis component, cumulative retention analysis component, and tag analysis component.

[0141] In one embodiment, after the processor 1001 performs the calculation on the target data based on the at least one retention analysis metric to obtain the retention analysis result corresponding to each retention analysis metric, it further performs:

[0142] Obtain an update instruction; wherein the update instruction is used to update at least one retention analysis metric corresponding to the window length.

[0143] In one embodiment, after the processor 1001 performs the calculation on the target data based on the at least one retention analysis metric to obtain the retention analysis result corresponding to each retention analysis metric, it further performs:

[0144] Each retention analysis result is visualized to obtain a retention view corresponding to each retention analysis result.

[0145] This manual obtains the target data corresponding to the data to be analyzed based on the start and end times, and obtains at least one corresponding retention analysis indicator based on the window length. It then calculates the target data to obtain the retention analysis result for each retention analysis indicator. In other words, by only receiving the data to be analyzed, the window length, and the start and end times, and through standardized calculations, it can efficiently complete the user retention analysis of the data to be analyzed and obtain at least one user retention analysis result. This manual provides a general analysis method for dealing with complex and diverse product-generated data and user retention analysis needs, meeting user requirements and improving analysis efficiency through standardized calculation processes, thus achieving efficient analysis of massive amounts of data.

[0146] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0147] The above-disclosed embodiments are merely preferred embodiments of this specification and should not be construed as limiting the scope of this specification. Therefore, any equivalent variations made in accordance with the claims of this specification shall still fall within the scope of this specification.

Claims

1. A user retention analysis method, comprising: Receive the data to be analyzed, the user-configured window length, and the start and end times; Obtain the target data corresponding to the start and end times in the data to be analyzed, and obtain at least one retention analysis indicator corresponding to the window length; wherein, the at least one retention analysis indicator includes: the maximum period retention indicator, the cumulative retention indicator, and the tag analysis indicator corresponding to the value of the window length, and the at least one retention analysis indicator further includes: at least one preset period retention indicator, wherein the period length corresponding to each preset period retention indicator is less than the period length corresponding to the maximum period retention indicator; The target data is calculated based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator; The step of calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator includes: The target data bitmap information is obtained by mapping the target data using bitmaps. The bitmap information of the target data is calculated based on the at least one retention analysis indicator using a sliding time window method to obtain the retention analysis results corresponding to the at least one retention analysis indicator.

2. The method according to claim 1, before calculating the bitmap information of the target data based on the at least one retention analysis indicator and the sliding time window method to obtain the retention analysis results corresponding to the at least one retention analysis indicator, further includes: Convert the bitmap information of the target data into the array format of Open Data Processing Service; The method employing a sliding time window calculates the bitmap information of the target data based on at least one retention analysis metric to obtain retention analysis results corresponding to each of the at least one retention analysis metric, including: The method using a sliding time window calculates the bitmap information of the target data in array format based on at least one retention analysis metric to obtain the retention analysis results corresponding to each of the at least one retention analysis metric.

3. The method according to claim 1, further comprising, after calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator, the method includes: The target data is aggregated based on at least one aggregation dimension to obtain the aggregation analysis results corresponding to each aggregation dimension.

4. The method according to claim 3, wherein the aggregation dimension includes a cross-retention dimension, and the step of aggregating the target data according to at least one aggregation dimension to obtain the aggregation analysis result corresponding to each aggregation dimension includes: The target data is aggregated based on the cross-retention dimension to obtain the cross-retention analysis results corresponding to the cross-retention dimension.

5. The method according to claim 3, after aggregating the target data according to at least one dimension to obtain the analysis results corresponding to each dimension, further comprising: The aggregation analysis results corresponding to each dimension are visualized to obtain the retention view corresponding to each aggregation analysis result.

6. The method according to claim 1, wherein before receiving the data to be analyzed, the user-configured window length, and the start and end times, the following steps are taken: Encapsulate at least one retention analysis component; The step of calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator includes: Based on at least one retention analysis metric, obtain the target retention analysis component corresponding to each retention analysis metric, and use the target retention analysis component to calculate the target data to obtain the retention analysis result corresponding to each retention analysis metric.

7. The method of claim 6, wherein the at least one retention analysis component comprises: Periodic retention analysis component, cumulative retention analysis component, and tag analysis component.

8. The method according to any one of claims 1-7, wherein after calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator, the method further comprises: Obtain an update instruction; wherein the update instruction is used to update at least one retention analysis metric corresponding to the window length.

9. The method according to any one of claims 1-7, wherein after calculating the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator, the method further comprises: Each retention analysis result is visualized to obtain a retention view corresponding to each retention analysis result.

10. A user retention analysis device, the device comprising: The parameter receiving module is used to receive the data to be analyzed, the user-configured window length, and the start and end times. The retention analysis module is used to obtain target data corresponding to the start and end times in the data to be analyzed, and to obtain at least one retention analysis indicator corresponding to the window length; wherein, the at least one retention analysis indicator includes: the maximum period retention indicator, the cumulative retention indicator, and the tag analysis indicator corresponding to the value of the window length, and the at least one retention analysis indicator further includes: at least one preset period retention indicator, wherein the period length corresponding to each preset period retention indicator is less than the period length corresponding to the maximum period retention indicator; The analysis results module is used to calculate the target data based on the at least one retention analysis indicator to obtain the retention analysis result corresponding to each retention analysis indicator; The analysis results module includes: A bitmap acquisition unit is used to acquire the target data bitmap information by mapping the target data through bit bits; The sliding calculation unit is used to calculate the bitmap information of the target data based on the at least one retention analysis indicator using a sliding time window method, so as to obtain the retention analysis results corresponding to the at least one retention analysis indicator.

11. A computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the method steps of any one of claims 1 to 9.

12. A computer program product storing a plurality of instructions adapted for loading by a processor and executing the method steps of any one of claims 1 to 9.

13. An electronic device, comprising: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed the method steps as claimed in any one of claims 1 to 9.

Images