CN113656275A - User activity prediction method and device, electronic equipment and storage medium - Google Patents
User activity prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113656275A CN113656275A CN202110973589.3A CN202110973589A CN113656275A CN 113656275 A CN113656275 A CN 113656275A CN 202110973589 A CN202110973589 A CN 202110973589A CN 113656275 A CN113656275 A CN 113656275A
- Authority
- CN
- China
- Prior art keywords
- user
- preset
- active
- activity
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000694 effects Effects 0.000 title claims abstract description 144
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000000977 initiatory effect Effects 0.000 claims abstract description 58
- 238000012360 testing method Methods 0.000 claims description 137
- 230000006399 behavior Effects 0.000 claims description 42
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009499 grossing Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis, and provides a user activity prediction method and device, electronic equipment and a storage medium. Obtaining an initial activity value of a user to be detected according to the behavior characteristics of the user to be detected in a preset time; then according to the initial activity value of the user to be detected, determining the initial activity level of the user to be detected from a plurality of preset activity levels; and predicting the probability value of the user to be detected converted from the initial activity level to each preset activity level according to the initial activity level of the user to be detected and a preset estimation model. The possibility prediction of the user in various activity levels is realized, and the efficiency and the accuracy of the user activity prediction are improved.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a user activity prediction method and device, electronic equipment and a storage medium.
Background
With the popularization of smart devices, users are increasingly accustomed to using smart devices for activities such as learning, entertainment, social interaction, and the like. According to the using habit of the user, the activity of the user can be obtained. In the prior art, the prediction mode of the user activity is single, and the situation of inaccurate prediction exists.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, an electronic device and a storage medium for predicting user activity.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, the present invention provides a method for predicting user activity, the method comprising:
obtaining an initial activity value of a user to be detected according to the behavior characteristics of the user to be detected in a preset time;
determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
and predicting the probability value of the user to be tested converted from the initial active level to each preset active level according to the initial active level of the user to be tested and a preset estimation model.
In an optional embodiment, each of the preset active levels has a corresponding preset range;
the step of determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected comprises the following steps:
determining a target preset range to which the initial active value belongs from a plurality of preset ranges according to the initial active value of the user to be detected;
and taking the target preset active level corresponding to the target preset range as the initial active level of the user to be detected.
In an alternative embodiment, the preset estimation model is obtained as follows:
obtaining a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period; the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
and constructing the preset estimation model according to the first active level of each test user and all the second active levels of each test user.
In an optional embodiment, the step of constructing the preset estimation model according to the first activity level of each test user and all the second activity levels of each test user includes:
aiming at each target time sequence, obtaining a sub-estimation model corresponding to the target time sequence according to the first active level of each test user and the target second active level of each test user; the target time sequence is any one of the plurality of time sequences, and the target second active level corresponds to the target time sequence;
traversing each time sequence to obtain a plurality of sub-estimation models; the preset estimation model comprises all sub-estimation models.
In an optional embodiment, the step of obtaining the first activity level of each test user according to the behavior feature of each test user in the first preset period includes:
obtaining a first active value of each test user according to the behavior characteristics of each test user in a first preset period;
dividing a plurality of initial intervals according to the first activity values of all test users;
smoothing each initial interval to obtain a plurality of active ranges;
and obtaining a first active level of each test user according to the first active value and the plurality of active ranges of each test user.
In a second aspect, the present invention provides a user activity prediction apparatus, the apparatus comprising:
the computing module is used for obtaining an initial activity value of a user to be tested according to the behavior characteristics of the user to be tested in a preset time;
the determining module is used for determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
and the prediction module is used for predicting the probability value of the user to be tested converted from the initial activity level to each preset activity level according to the initial activity level of the user to be tested and a preset estimation model.
In an optional embodiment, each of the preset active levels has a corresponding preset range; the determining module is specifically configured to:
determining a target preset range to which the initial active value belongs from a plurality of preset ranges according to the initial active value of the user to be detected;
and taking the target preset active level corresponding to the target preset range as the initial active level of the user to be detected.
In an alternative embodiment, the prediction module is further configured to:
obtaining a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period; the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
and constructing the preset estimation model according to the first active level of each test user and all the second active levels of each test user.
In a third aspect, the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor implements the method of any one of the preceding embodiments when executing the computer program.
In a fourth aspect, the present invention provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of the preceding embodiments.
The embodiment of the invention provides a user activity prediction method and device, electronic equipment and a storage medium. Obtaining an initial activity value of a user to be detected according to the behavior characteristics of the user to be detected in a preset time; then according to the initial activity value of the user to be detected, determining the initial activity level of the user to be detected from a plurality of preset activity levels; and predicting the probability value of the user to be detected converted from the initial activity level to each preset activity level according to the initial activity level of the user to be detected and a preset estimation model. The possibility prediction of the user in various activity levels is realized, and the efficiency and the accuracy of the user activity prediction are improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic diagram of a scenario provided by an embodiment of the present invention;
FIG. 2 is a block diagram of an electronic device provided by an embodiment of the invention;
FIG. 3 is a flowchart illustrating a method for predicting user activity according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating a user activity prediction method according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating a user activity prediction method according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart illustrating a user activity prediction method according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart illustrating a user activity prediction method according to an embodiment of the present invention;
fig. 8 is a functional block diagram of a user activity prediction apparatus according to an embodiment of the present invention.
Icon: 100-a server; 102-a terminal device; 120-a processor; 130-a memory; 170 — a communication interface; 300-user activity prediction means; 310-a calculation module; 330-a determination module; 350-prediction module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Fig. 1 is a schematic view of a scene according to an embodiment of the present invention. The server 100 and the plurality of terminal devices 102 are included, and the server 100 is in communication connection with the plurality of terminal devices 102 to realize data interaction.
The server 100 may be a stand-alone server or a server cluster composed of a plurality of servers.
The terminal device 102 may be a smart phone, a personal computer, a tablet computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), or the like. The embodiments of the present invention do not limit this.
Optionally, the scenario diagram may be used to provide a variety of possible services, including but not limited to: multimedia streaming services, cloud gaming, distributed storage, and the like. Taking live video as an example, the server 100 may be a server providing live video stream, and the terminal device 102 may install a live video related Application (APP).
The server 100 may collect and analyze data related to the live video application in the terminal device 102 for different analysis purposes. The terminal device 102 may obtain relevant data of the user when using the live video application, and report the data to the server 100.
Fig. 2 is a block diagram of an electronic device according to an embodiment of the present invention. The structure of the server can be used for implementing the server 100 or the terminal device 102 in fig. 1. The electronic device includes a processor 120, a memory 130, and a communication interface 170.
The processor 120, memory 130, and communication interface 170 are in direct or indirect electrical communication with each other to facilitate the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The user activity prediction apparatus 300 includes at least one software function module that may be stored in the memory 130 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the server 100. Processor 120 is configured to execute executable modules stored in memory 130, such as software functional modules or computer programs included in user activity prediction apparatus 300.
The processor 120 may be an integrated circuit chip having signal processing capability. The Processor 120 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The Memory 130 may be, but is not limited to, a Random Access Memory 130 (RAM), a Read Only Memory 130 (ROM), a Programmable Read Only Memory 130 (PROM), an Erasable Read Only Memory 130 (EPROM), an electrically Erasable Read Only Memory 130 (EEPROM), and the like. The memory 130 is used for storing a program, and the processor 120 executes the program after receiving an execution instruction, and the method executed by the server 100 defined by the flow process disclosed in any embodiment of the present invention may be applied to the processor 120, or implemented by the processor 120.
The communication interface 170 may be used for communicating signaling or data with other node devices.
It should be noted that the structure shown in fig. 2 is only a schematic structural diagram of the electronic device, and the electronic device may further include more or less components than those shown in fig. 2, or have a different configuration from that shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
It is to be understood that the electronic device may also comprise other modules, for example: radio frequency circuits, I/O interfaces, batteries, touch screens, microphones/speakers, etc. And are not limiting herein.
The server 100 is used as an execution subject to execute each step in each method provided by the embodiment of the present invention, and achieve the corresponding technical effect.
Referring to fig. 3, fig. 3 is a flowchart illustrating a user activity prediction method according to an embodiment of the present invention.
Step S202, obtaining an initial activity value of a user to be detected according to the behavior characteristics of the user to be detected in a preset time;
it can be understood that, in the process of using the application program by the user, the terminal device may obtain that the use condition of the user is the behavior characteristic. The behavior characteristics can be used for data representing the activity of the user, such as any one or combination of the data of the number of active days, the number of active times, the active duration and the like.
The preset duration may be the length of time of the past week of the node on the current date. It can be understood that the preset time period may be set according to actual requirements, and the embodiment of the present invention is not limited.
Optionally, the activity value of the user may be calculated according to the behavior characteristics of the user in a preset time and a preset formula. For example, the initial activity value of the user to be tested is calculated according to the past behavior characteristics of the user to be tested, namely the number of active days, the number of active times and the active duration, and a preset formula.
The preset formula is H-w 1 active days + w2 active times + w3 active duration, wherein H represents an initial active value of the user to be tested; w1, w2 and w3 are preset parameters, alternatively, w1 is 0.5, w2 is 0.3 and w3 is 0.2. The preset parameter may be understood as a weighted value of different behavior characteristic data, the number of active days may more obviously reflect the activity of the user than the number of active times and the active duration, and the weighted value corresponding to the number of active days, that is, the preset parameter w1, may be set to be the maximum. It can be understood that the preset parameters can be set according to actual requirements, and the embodiment of the present invention is not limited.
Step S204, determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
the preset active levels may be multiple active levels set based on data collected by the terminal device and used by a large number of test users for using the application program.
For example, three active levels, i.e., a high active level, a medium active level, and a low active level, may be set. It can be understood that the preset activity level may be set according to actual requirements, and the embodiment of the present invention is not limited.
The active value of the user has a corresponding relationship with a preset active level.
Optionally, according to the initial active value of the user to be tested and the corresponding relationship between the active value and the preset active level, the preset active level corresponding to the initial active value, that is, the initial active level of the user to be tested, may be determined from a plurality of preset active levels.
Step S206, predicting the probability value of the user to be detected converted from the initial activity level to each preset activity level according to the initial activity level of the user to be detected and a preset estimation model;
the preset estimation model may be a model constructed based on data of a large number of test users using the application program, and the preset estimation model may predict the probability that the activity level of the user changes. The input of the preset estimation model is the current activity level of the user, and the output is the probability value of the user changing from the current activity level to each preset activity level.
Optionally, after the initial activity level of the user to be detected is obtained, the initial activity level is used as the input of a preset estimation model, and the obtained output is a plurality of probability values. A probability value represents the probability that the user to be tested changes from the initial active level to a preset active level.
For convenience of understanding, the user a to be measured is taken as an example, and the foregoing steps are described with reference to the scene diagram shown in fig. 1.
As shown in fig. 1, the terminal device 102 acquires behavior characteristics of the user a to be tested in a predicted time period, such as the number of active days, the number of active times, and the active time period of the application program used by the user a to be tested, specifically, data such as the number of times of logging in the application program, the online time period, and the number of times of sending the interaction information. The terminal device 102 sends the collected behavior characteristics of the user a to be tested to the server 100.
After receiving the behavior characteristics of the user A to be tested, the server 100 calculates an initial activity value H1 of the user A to be tested according to the behavior characteristics and a preset formula; then, according to the initial active value H1, the initial active level of the user a to be tested is determined to be a medium active level from a plurality of preset active levels, for example, three preset active levels (a high active level, a medium active level, and a low active level).
The server 100 then obtains a plurality of probability values such as G1, G2, G3 according to the initial activity level of the user a to be tested and a preset estimation model, where one probability value represents the probability that the user a to be tested is converted from the initial activity level, i.e., the middle level, to a preset activity level. If the probability value G1 represents the probability that the user A to be tested is changed from the medium active level to the high active level; the probability value G1 represents the probability that the user A to be tested is converted from the medium active level to the medium active level; the probability value G1 represents the probability that the user a under test transitions from a medium activity level to a low activity level. Based on a plurality of probability values, the possibility prediction of the user for various liveness is realized.
Based on the steps, the initial activity value of the user to be detected is obtained according to the behavior characteristics of the user to be detected in the preset time; then according to the initial activity value of the user to be detected, determining the initial activity level of the user to be detected from a plurality of preset activity levels; and predicting the probability value of the user to be detected converted from the initial activity level to each preset activity level according to the initial activity level of the user to be detected and a preset estimation model. Compared with a single prediction mode in the prior art, the method and the device realize the possibility prediction of the user for multiple activity levels, thereby improving the efficiency and the accuracy of the activity prediction of the user, and being beneficial to providing a targeted strategy for the user according to the predicted activity so as to adjust the activity of the user.
Optionally, to further improve the accuracy of predicting user liveness. With respect to the step S204, the embodiment of the present invention provides a possible implementation manner. Please refer to fig. 4. Wherein, step S204 may further include the following steps:
step S204-1, determining a target preset range to which the initial activity value belongs from a plurality of preset ranges according to the initial activity value of the user to be detected;
it will be appreciated that each preset activity level has a corresponding preset range.
The preset ranges are ranges divided based on a large number of active values obtained by using the application programs by a large number of test users.
Optionally, after the initial activity value of the user to be detected is obtained, a target preset range may be determined from the plurality of preset ranges according to the preset range to which the initial activity value belongs.
Step S204-3, taking a target preset active level corresponding to the target preset range as an initial active level of the user to be detected;
optionally, the preset active level has a corresponding relationship with the preset range. The target preset active level can be determined from the multiple preset active levels based on the preset active levels corresponding to the target preset range, and the initial active level of the user to be detected is obtained.
Through the steps, based on the initial activity value of the user to be detected, the target preset range to which the initial activity value belongs is determined from the multiple preset ranges, and the target preset activity level corresponding to the target preset range is used as the initial activity level of the user to be detected. Therefore, the active value is converted into the active level, the change of the active level of the user can be conveniently predicted subsequently, and the prediction accuracy is improved.
Optionally, the preset estimation model has an important influence on the prediction of the user activity, which is a key factor of the prediction accuracy, and further, the embodiment of the present invention provides a possible implementation manner for obtaining the preset estimation model, please refer to fig. 5, which is another schematic flow diagram provided by the embodiment of the present invention.
Step S212, obtaining a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
optionally, a set number of test users may be obtained, and for each test user, behavior characteristics of the test user in a first set period, such as the number of active days, the number of active times, and the active duration of the past week, are collected to obtain a first active level of each test user.
Step S214, obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period;
the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
alternatively, the second preset period may be set to 24 weeks, and the second preset period may include 24 time series, for example, the 1 st time series is the first week, the 2 nd time series is the first two weeks, and the 3 rd time series is the first three weeks, so as to sequentially obtain the 24 time series.
Optionally, according to the behavior characteristics of the test user in a time series, a second activity level corresponding to the time series may be obtained. Based on the plurality of time series, a plurality of second activity levels of the test user may be obtained.
It can be understood that the first preset period and the second preset period may be set according to actual requirements based on a plurality of time sequences, and the embodiment of the present invention is not limited.
Step S216, constructing a preset estimation model according to the first activity level of each test user and all second activity levels of each test user;
optionally, after the first activity level of each test user and all the second activity levels of each test user are obtained, the change condition of the activity level of each test user based on the time dimension can be obtained. Based on the change condition of the activity levels of a plurality of test users, a preset estimation model can be constructed.
With respect to the step S212, the embodiment of the present invention provides a possible implementation manner. Referring to fig. 6, step S212 may further include the following steps:
step S212-1, obtaining a first activity value of each test user according to the behavior characteristics of each test user in a first preset period;
optionally, the first preset period is one week in the past, and the first activity value of each test user may be calculated according to the behavior characteristics of each test user in the past one week, such as the number of active days, the number of active times, the active duration, and the preset formula H-w 1 + w2 + w3 + the active duration.
Step S212-3, dividing a plurality of initial intervals according to the first activity values of all test users;
optionally, all the first active values for testing are arranged according to a preset sequence, and then a plurality of initial intervals are divided based on a plurality of preset percentages and quantiles, where the quantile may be the largest first active value.
For example, the first activity values of all the test users are arranged in a descending order, based on a plurality of preset percentages such as 25%, 75% and quantiles, 25% of the quantiles are used as a first initial interval, 25% to 75% of the quantiles are used as a second initial interval, and 75% to 100% of the quantiles are used as a third initial interval.
Taking the example that all the primary activity values are 1,2,3,4,5,6 … 100, and the quantile is the largest primary activity value, i.e. 100, the first initial interval is [0,25 ], the second initial interval is [25,75 ], and the third initial interval is [75,100 ].
Step S212-5, smoothing each initial interval to obtain a plurality of active ranges;
alternatively, the average of all the first activity values belonging to the first initial interval is calculated, which can be denoted by E (H low activity); calculating the average value of all the first activity values belonging to the second interval, which can be represented by E (H activity); the average of all the first activity values belonging to the third difference is calculated and can be represented by E (H high activity).
Each initial interval may be smoothed based on the plurality of average values to obtain a plurality of active ranges. Less than E (H low activity) is the low activity range; the range between E (H low activity) and E (H medium activity) is the medium activity range; greater than E (H high activity) is the high activity range.
It is to be understood that the preset ranges in step S204 may also be set in this manner, and the plurality of preset ranges and the plurality of active ranges may coincide.
Step S212-7, obtaining a first active level of each test user according to the first active value and the plurality of active ranges of each test user;
optionally, if the first activity value of the test user belongs to the low activity range, the first activity level of the test user is a low activity level.
And if the first activity value of the test user belongs to the medium activity range, the first activity level of the test user is the medium activity level.
And if the first activity value of the test user belongs to the high activity range, the first activity level of the test user is a high activity level.
It is understood that, for the step S214, a plurality of second activity values may also be calculated through the behavior characteristics of each test user in the second preset period and the preset formula, where each second activity value corresponds to a time sequence. And obtaining a plurality of second activity levels of each test user based on the plurality of second activity values. I.e. a time sequence corresponding to one second activity value and one second activity value corresponding to one second activity level.
Through the steps, the activity levels in different preset periods are obtained based on the behavior characteristics of the test users in different preset periods, so that the change conditions of the activity levels of the test users are obtained, and the preset estimation model is constructed based on the change conditions of the activity levels of a large number of test users, so that the prediction accuracy is improved.
With respect to step S216, the embodiment of the present invention provides a possible implementation manner. Referring to fig. 7, step S216 may further include the following steps:
step S216-1, aiming at each target time sequence, obtaining a sub-estimation model corresponding to the target time sequence according to the first active level of each test user and the target second active level of each test user;
the target time sequence is any one of the plurality of time sequences, and the target second activity level corresponds to the target time sequence.
It can be understood that the first active level is an active level corresponding to a first preset period, and the second active level is an active level corresponding to a time sequence in a second preset period, where the first preset period and the second preset period are consecutive in time.
The first activity level of the test user may be represented by Ei and the second activity level of the test user may be represented by Ej. The activity level change of the test user in the time dimension can be obtained according to the first activity level and the second activity level, and can be represented by P (Ej/Ei).
Optionally, for each target time sequence, a sub-estimation model corresponding to the target time sequence is obtained according to the first active levels of all the test users and the second active levels, namely the target second active levels, corresponding to the target time sequence of all the test users.
For example, the first week, which is the 1 st time series, is taken as the target time series. And setting the number of S test users, and acquiring the behavior characteristics of the S test users in the past week for the node on the current date to obtain the first activity level of each test user. And then acquiring the behavior characteristics of the S test users in the first week after the current date to obtain a second activity level of each test user.
And respectively calculating the change conditions of the active levels of the test user groups with the first active levels of a low active level, a medium active level and a high active level.
For a test user population with a first active level being a low active level, it may be represented by E1:
calculating the proportional probability that the second active level in the test user group is a low active level, which can be represented by P (E11/E1), and can be understood as the probability that the test user with the low active level is changed into the low active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the medium active level, which can be represented by P (E12/E1), and can be understood as the probability that the test user with the low active level is changed into the medium active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the high active level, which can be represented by P (E13/E1), and can be understood as the probability that the test user with the low active level is changed into the high active level in the first preset period and the first time sequence.
For a test user population with a first active level being a medium active level, it can be represented by E2:
calculating the proportional probability that the second active level in the test user group is the low active level, which can be represented by P (E21/E2), and can be understood as the probability that the test user with the medium active level is changed into the low active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the medium active level, which can be represented by P (E22/E2), and can be understood as the probability that the test user with the medium active level is changed into the medium active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the high active level, which can be represented by P (E23/E2), and can be understood as the probability that the test user with the medium active level is changed into the high active level in the first preset period and the first time sequence.
For a test user population with a first active level being a high active level, it can be represented by E3:
calculating the proportional probability that the second active level in the test user group is the low active level, which can be represented by P (E31/E3), and can be understood as the probability that the test user with the high active level is changed into the low active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the medium active level, which can be represented by P (E32/E3), and can be understood as the probability that the test user with a high active level is changed into the medium active level in the first preset period and the first time sequence;
calculating the proportional probability that the second active level in the test user group is the high active level, which can be represented by P (E33/E3), and can be understood as the probability that the test user with the high active level is changed into the high active level in the first preset period and the first time sequence.
By calculating the variation conditions of the active levels of all the test users in the first preset period and the first time sequence, the sub-estimation model corresponding to the first time sequence can be obtained, namely:
step S216-2, traversing each time sequence to obtain a plurality of sub-estimation models;
optionally, for each time sequence, a second activity level corresponding to each test user in the time sequence may be calculated, so as to obtain a sub-estimation model corresponding to each time sequence. And obtaining a preset estimation model according to a plurality of sub estimation models corresponding to the plurality of time sequences, wherein the preset estimation model comprises all the sub estimation models.
Through the steps, based on the first active levels and the second active levels of a large number of test users, the change conditions of the active levels of test user groups with different active levels can be obtained, and the probability of the users changing into different active levels is obtained, so that multiple possibility predictions of the user activity are realized, a targeted service strategy is provided for the users conveniently, and the user activity can be regulated.
In order to execute the corresponding steps in the above embodiments and various possible manners, an implementation manner of the user activity prediction apparatus is given below. Referring to fig. 8, fig. 8 is a functional block diagram of a user activity prediction apparatus 300 according to an embodiment of the present invention. It should be noted that the basic principle and the generated technical effects of the user activity prediction apparatus 300 provided in the present embodiment are the same as those of the above embodiments, and for the sake of brief description, no part of the present embodiment is mentioned, and reference may be made to the corresponding contents in the above embodiments. The user activity prediction apparatus 300 includes:
the calculating module 310 is configured to obtain an initial activity value of the user to be tested according to the behavior characteristics of the user to be tested in the preset duration;
the determining module 330 is configured to determine an initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
the predicting module 350 is configured to predict, according to the initial activity level of the user to be tested and a preset estimation model, a probability value of converting the initial activity level of the user to be tested into each preset activity level.
Optionally, each preset active level has a corresponding preset range, and the determining module 330 is specifically configured to: determining a target preset range to which the initial active value belongs from a plurality of preset ranges according to the initial active value of the user to be detected; and taking the target preset active level corresponding to the target preset range as the initial active level of the user to be detected.
Optionally, the prediction module 350 is further configured to: acquiring a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period; the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
and constructing a preset estimation model according to the first active level of each test user and all the second active levels of each test user.
Optionally, the prediction module 350 is further configured to: aiming at each target time sequence, obtaining a sub-estimation model corresponding to the target time sequence according to the first active level of each test user and the target second active level of each test user; the target time sequence is any one of a plurality of time sequences, and the target second active level corresponds to the target time sequence;
traversing each time sequence to obtain a plurality of sub-estimation models; the preset estimation model includes all the sub-estimation models.
Optionally, the prediction module 350 is further configured to: acquiring a first active value of each test user according to the behavior characteristics of each test user in a first preset period;
dividing a plurality of initial intervals according to the first activity values of all test users;
smoothing each initial interval to obtain a plurality of active ranges;
and obtaining the first activity level of each test user according to the first activity value and the plurality of activity ranges of each test user.
The embodiment of the present invention further provides an electronic device, which includes a processor 120 and a memory 130, where the memory 130 stores a computer program, and when the processor executes the computer program, the method for predicting user activity disclosed in the foregoing embodiment is implemented.
An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program, when executed by the processor 120, implements the method for predicting user activity disclosed in the embodiment of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for predicting user activity, the method comprising:
obtaining an initial activity value of a user to be detected according to the behavior characteristics of the user to be detected in a preset time;
determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
and predicting the probability value of the user to be tested converted from the initial active level to each preset active level according to the initial active level of the user to be tested and a preset estimation model.
2. The method of claim 1, wherein each of said predetermined active levels has a corresponding predetermined range;
the step of determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected comprises the following steps:
determining a target preset range to which the initial active value belongs from a plurality of preset ranges according to the initial active value of the user to be detected;
and taking the target preset active level corresponding to the target preset range as the initial active level of the user to be detected.
3. The method according to claim 1 or 2, characterized in that the preset estimation model is obtained in the following way:
obtaining a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period; the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
and constructing the preset estimation model according to the first active level of each test user and all the second active levels of each test user.
4. The method of claim 3, wherein the step of constructing the pre-set estimation model according to the first activity level of each of the test users and the total second activity levels of each of the test users comprises:
aiming at each target time sequence, obtaining a sub-estimation model corresponding to the target time sequence according to the first active level of each test user and the target second active level of each test user; the target time sequence is any one of the plurality of time sequences, and the target second active level corresponds to the target time sequence;
traversing each time sequence to obtain a plurality of sub-estimation models; the preset estimation model comprises all sub-estimation models.
5. The method according to claim 3, wherein the step of obtaining the first activity level of each test user according to the behavior characteristics of each test user in the first preset period comprises:
obtaining a first active value of each test user according to the behavior characteristics of each test user in a first preset period;
dividing a plurality of initial intervals according to the first activity values of all test users;
smoothing each initial interval to obtain a plurality of active ranges;
and obtaining a first active level of each test user according to the first active value and the plurality of active ranges of each test user.
6. An apparatus for predicting user activity, the apparatus comprising:
the computing module is used for obtaining an initial activity value of a user to be tested according to the behavior characteristics of the user to be tested in a preset time;
the determining module is used for determining the initial activity level of the user to be detected from a plurality of preset activity levels according to the initial activity value of the user to be detected;
and the prediction module is used for predicting the probability value of the user to be tested converted from the initial activity level to each preset activity level according to the initial activity level of the user to be tested and a preset estimation model.
7. The apparatus of claim 6, wherein each of said preset activity levels has a corresponding preset range; the determining module is specifically configured to:
determining a target preset range to which the initial active value belongs from a plurality of preset ranges according to the initial active value of the user to be detected;
and taking the target preset active level corresponding to the target preset range as the initial active level of the user to be detected.
8. The apparatus of claim 6 or 7, wherein the prediction module is further configured to:
obtaining a first active level of each test user according to the behavior characteristics of each test user in a first preset period;
obtaining a plurality of second active levels of each test user according to the behavior characteristics of each test user in a second preset period; the second preset period comprises a plurality of time sequences, and one time sequence corresponds to one second active level;
and constructing the preset estimation model according to the first active level of each test user and all the second active levels of each test user.
9. An electronic device, comprising a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method of any of claims 1 to 5.
10. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when executed by a processor, implements the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973589.3A CN113656275B (en) | 2021-08-24 | 2021-08-24 | User activity prediction method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973589.3A CN113656275B (en) | 2021-08-24 | 2021-08-24 | User activity prediction method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113656275A true CN113656275A (en) | 2021-11-16 |
| CN113656275B CN113656275B (en) | 2024-03-26 |
Family
ID=78492640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110973589.3A Active CN113656275B (en) | 2021-08-24 | 2021-08-24 | User activity prediction method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113656275B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
| CN110796484A (en) * | 2019-10-11 | 2020-02-14 | 上海上湖信息技术有限公司 | Method and device for constructing customer activity degree prediction model and application method thereof |
| CN111047338A (en) * | 2018-10-12 | 2020-04-21 | 北大方正集团有限公司 | User activity prediction method, prediction system and medium |
-
2021
- 2021-08-24 CN CN202110973589.3A patent/CN113656275B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
| CN111047338A (en) * | 2018-10-12 | 2020-04-21 | 北大方正集团有限公司 | User activity prediction method, prediction system and medium |
| CN110796484A (en) * | 2019-10-11 | 2020-02-14 | 上海上湖信息技术有限公司 | Method and device for constructing customer activity degree prediction model and application method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113656275B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113194306B (en) | Frame rate fluctuation evaluation method and device, mobile terminal, system and storage medium | |
| CN107305611B (en) | Method and device for establishing model corresponding to malicious account and method and device for identifying malicious account | |
| CN111459783B (en) | Application program optimization method and device, electronic equipment and storage medium | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN109543940B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN109213965B (en) | System capacity prediction method, computer readable storage medium and terminal device | |
| CN111311014B (en) | Service data processing method, device, computer equipment and storage medium | |
| Rafsanjani et al. | QARIMA: A new approach to prediction in queue theory | |
| CN112001563B (en) | Method and device for managing ticket quantity, electronic equipment and storage medium | |
| CN113569965A (en) | User behavior analysis method and system based on Internet of things | |
| CN116756522A (en) | Probability forecasting method and device, storage medium and electronic equipment | |
| CN113656275B (en) | User activity prediction method, device, electronic equipment and storage medium | |
| CN116662904A (en) | Method, device, computer equipment and medium for detecting variation of data type | |
| CN111160614A (en) | Training method and device of resource transfer prediction model and computing equipment | |
| CN110717653A (en) | Risk identification method and device and electronic equipment | |
| CN111882349B (en) | Data processing method, device and storage medium | |
| CN114143571B (en) | User processing method, device, equipment and storage medium | |
| CN112669091A (en) | Data processing method, device and storage medium | |
| CN111598390B (en) | Method, device, equipment and readable storage medium for evaluating high availability of server | |
| CN113641909A (en) | Information pushing method and device, electronic equipment and computer readable medium | |
| CN113626705B (en) | User retention analysis method, device, electronic equipment and storage medium | |
| CN112131468A (en) | Data processing method and device in recommendation system | |
| JP2020150524A (en) | Communication band calculation device, communication band calculation method and program | |
| CN114867046B (en) | Wireless network equipment firmware updating method and wireless network equipment | |
| CN110048890B (en) | Industrial Internet of things service device based on QoS (quality of service) drive |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |