CN105005909A - Method and device for predicting lost users - Google Patents
Method and device for predicting lost users Download PDFInfo
- Publication number
- CN105005909A CN105005909A CN201510337449.1A CN201510337449A CN105005909A CN 105005909 A CN105005909 A CN 105005909A CN 201510337449 A CN201510337449 A CN 201510337449A CN 105005909 A CN105005909 A CN 105005909A
- Authority
- CN
- China
- Prior art keywords
- targeted customer
- time interval
- parameter
- training
- login
- 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.)
- Pending
Links
Abstract
The invention discloses a method and device for predicting lost users and belongs to the field of network technology. The method comprises: acquiring the number of days and the number of times that a target user logs in an application program within an assigned time segment, and acquiring the time interval between the time when the target user logs in the application program at the last time and the current time to obtain a first time interval; determining the severe parameter of the target user according to the account registration time of the target user; determining the losing probability of the target user by means of an assigned logistic regression model according to the number of login days, the number of login times, the severe parameter, and the first time interval; considering the target user as a user to be lost when the losing probability of the target user is more than or equal to an assigned probability threshold. The method and device are wide in application range, easy to operate, good in robustness, and high in efficiency of predicting lost users.
Description
Technical field
The present invention relates to networking technology area, particularly a kind of method of predicted flows appraxia family and device.
Background technology
Along with the fast development of technology, there is various application program, such as, game application, body-building application program, communication application program etc.In order to ensure the utilization rate of these application programs, need to take appropriate measures to keep the user being about to run off, therefore, need for these application programs, the user being about to run off is predicted.
At present, be substantially all the method by manually runing, the user being about to run off is predicted.And when coming predicted flows appraxia family by the method for manually runing, operation more complicated, workload is large, therefore, reduces the efficiency at predicted flows appraxia family, and it is poor to carry out the robustness at predicted flows appraxia family by the method for manually runing.
Summary of the invention
In order to solve the problem of prior art, embodiments provide a kind of method and device of predicted flows appraxia family.Described technical scheme is as follows:
On the one hand, provide a kind of method of predicted flows appraxia family, described method comprises:
Obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain described targeted customer and log in time interval between the time of described application program and current time for the last time, obtain very first time interval;
The hour of log-on of based target user account, determines the severe parameter of described targeted customer;
Based on described login number of days, described login times, described severe parameter and described very first time interval, by specifying Logic Regression Models, determine the loss probability of described targeted customer;
When the loss probability of described targeted customer is more than or equal to appointment probability threshold value, then determine that described targeted customer is the user being about to run off.
On the other hand, provide a kind of device of predicted flows appraxia family, described device comprises:
First acquisition module, for obtaining the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain described targeted customer and log in time interval between the time of described application program and current time for the last time, obtain very first time interval;
First determination module, for the hour of log-on of based target user account, determines the severe parameter of described targeted customer;
Second determination module, for based on described login number of days, described login times, described severe parameter and described very first time interval, by specifying Logic Regression Models, determines the loss probability of described targeted customer;
3rd determination module, when specifying probability threshold value for being more than or equal to when the loss probability of described targeted customer, then determines that described targeted customer is the user being about to run off.
The beneficial effect that the technical scheme that the embodiment of the present invention provides is brought is: in embodiments of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the method flow diagram at a kind of predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 2 is the method flow diagram at the another kind of predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 3 is the apparatus structure schematic diagram at the first predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 4 is the one first determination module structural representation that the embodiment of the present invention provides;
Fig. 5 is the apparatus structure schematic diagram at the second predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 6 is the apparatus structure schematic diagram at the third predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 7 is one the 6th determination module structural representation that the embodiment of the present invention provides;
Fig. 8 is the apparatus structure schematic diagram at the 4th kind of predicted flows appraxia family that the embodiment of the present invention provides;
Fig. 9 is the apparatus structure schematic diagram at the 5th kind of predicted flows appraxia family that the embodiment of the present invention provides.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Fig. 1 is the method flow diagram at a kind of predicted flows appraxia family that the embodiment of the present invention provides.See Fig. 1, the method comprises:
Step 101: obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain this targeted customer and log in time interval between the time of this application program and current time for the last time, obtain very first time interval.
Step 102: the hour of log-on of based target user account, determines the severe parameter of this targeted customer.
Step 103: based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, determines the loss probability of this targeted customer.
Step 104: when the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then determine that this targeted customer is the user being about to run off.
In embodiments of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
Optionally, the hour of log-on of based target user account, determine the severe parameter of this targeted customer, comprising:
Determine the time interval between the hour of log-on of this targeted customer's account and this current time, obtained for second time interval;
When this second time interval is less than or equal to the first fixed time interval, determine that the severe parameter of this targeted customer is the first numerical value;
When this second interval greater than this second fixed time interval time, determine that the severe parameter of this targeted customer is second value.
Optionally, based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, before determining the loss probability of this targeted customer, also comprise:
Obtain and wait to train Logic Regression Models;
Based on the training sample stored, determine this parameters of waiting to train Logic Regression Models, in this training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
Wait to train Logic Regression Models and this to wait to train the parameters of Logic Regression Models based on this, determine this appointment Logic Regression Models.
Optionally, when the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then, after determining that this targeted customer is the user being about to run off, also comprise:
Determine the loss parameter of this targeted customer;
By this login number of days, this login times, this very first time interval, this severe parameter and this loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
Optionally, determine the loss parameter of this targeted customer, comprising:
When this targeted customer is the user being about to run off, determine that the loss parameter of this targeted customer is third value;
When this targeted customer is non-streaming appraxia family, determine that the loss parameter of this targeted customer is the 4th numerical value.
Above-mentioned all alternatives, all can form optional embodiment of the present invention according to combining arbitrarily, the embodiment of the present invention repeats no longer one by one to this.
Fig. 2 is the method flow diagram at the another kind of predicted flows appraxia family that the embodiment of the present invention provides.See Fig. 2, the method comprises:
Step 201: obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain targeted customer and log in time interval between the time of this application program and current time for the last time, obtain very first time interval.
In order to predicted flows appraxia family, that is to say, judge whether targeted customer is the user being about to run off, the device at predicted flows appraxia family can obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and targeted customer logs in the time of this application program for the last time before acquisition current time, and determine that targeted customer logs in the time interval between the time of this application program and current time for the last time, obtain very first time interval.
Wherein, before fixed time section is current time and from the nearest fixed time section of current time, such as, before fixed time section can be current time and from nearest two weeks of current time.Targeted customer at the appointed time in section the login number of days of login application program be less than or equal to fixed time section.
It should be noted that, in embodiments of the present invention, the device at predicted flows appraxia family can be server corresponding to this application program, certainly, the device at predicted flows appraxia family can also be independent of server corresponding to this application program outside device, this device can be terminal, also can be server.The embodiment of the present invention is not specifically limited this.
When the device at predicted flows appraxia family is server corresponding to this application program, when logging in this application program in targeted customer at the appointed time section, the device at this predicted flows appraxia family can be added up the login number of days of this targeted customer and login times, thus obtains the targeted customer's at the appointed time login number of days of login application program and login times in section.In addition, the device at this predicted flows appraxia family can also record current time before targeted customer log in time of this application program for the last time, and determine that targeted customer logs in the time interval between the time of this application program and current time for the last time, obtain very first time interval.
And during device outside the server that the device at predicted flows appraxia family is corresponding independent of this application program, the device at this predicted flows appraxia family can also from server corresponding to this application program, obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and before obtaining current time, targeted customer logs in the time of this application program for the last time.Thus determine that targeted customer logs in the time interval between the time of this application program and current time for the last time, obtain very first time interval.
Such as, the targeted customer at the appointed time interior login number of days logging in this application program of section is 8 days, login times is 20 times, and the time that targeted customer logs in this application program is for the last time 10:00 on May 20th, 2015, if current time is 10:00 on May 23rd, 2015, therefore, obtain targeted customer and log in time interval between the time of this application program and current time for the last time, obtaining the very first time is spaced apart 3 days.
Step 202: the hour of log-on of based target user account, determines the severe parameter of this targeted customer.
It is new user or old user that the severe parameter of this targeted customer is used to indicate this targeted customer, and targeted customer's account user account that to be targeted customer corresponding.Therefore, the device at predicted flows appraxia family can determine the hour of log-on of targeted customer's account, and determines the time interval between the hour of log-on of targeted customer's account and current time, obtains for second time interval; When second time interval was less than or equal to the first fixed time interval, determine that the severe parameter of targeted customer is the first numerical value; When second interval greater than the second fixed time interval, determine that the severe parameter of targeted customer is second value.
Wherein, when second time interval was less than or equal to the first fixed time interval, determine that targeted customer is new user, when second interval greater than the second fixed time interval, determine that targeted customer is old user.
It should be noted that, first fixed time interval and the second fixed time interval arrange in advance, and the first fixed time interval is less than the second fixed time interval, such as, first fixed time interval can be 2 days, second fixed time interval can be 30 days, and the embodiment of the present invention is not specifically limited this.
In addition, the first numerical value and second value also can be arrange in advance, and such as, the first numerical value is 0, and second value is 1, and the embodiment of the present invention is not specifically limited this.
Such as, the hour of log-on of targeted customer's account is 15:00 on May 22nd, 2015, determine the time interval between the hour of log-on of targeted customer's account and current time, obtaining for second time interval is 19 hours, if the first fixed time was spaced apart 2 days, first numerical value is 0, then determine that second time interval was less than the first fixed time interval, and determines that the severe parameter of targeted customer is 0.
Step 203: based on this login number of days, login times, severe parameter and very first time interval, by specifying Logic Regression Models, determines the loss probability of targeted customer.
All application programs are applicable in order to make the method at predicted flows appraxia family, therefore, can by the login number of days of login application program in targeted customer at the appointed time section and login times, and the severe parameter of very first time interval and targeted customer is defined as the user characteristics of targeted customer, thus based on this login number of days, login times, severe parameter and very first time interval, by specifying Logic Regression Models, determine the loss probability of targeted customer.And based on this login number of days, login times, severe parameter and very first time interval, by specifying Logic Regression Models, determine that the process of the loss probability of targeted customer can be: based on this login number of days, login times, severe parameter and very first time interval, determine the loss parameter of targeted customer; And the loss parameter of based target user, by specifying Logic Regression Models, determine the loss probability of targeted customer.
Wherein, the device at predicted flows appraxia family based on this login number of days, login times, severe parameter and very first time interval, according to following formula (1), can determine the loss parameter of targeted customer; And the loss parameter of based target user, by the appointment Logic Regression Models shown in following formula (2), determine the loss probability of targeted customer;
f(θ,x)＝θ
0+θ
1×x
1+θ
2×x
2+θ
3×x
3+θ
4×x
4(1)
h(x)＝e
f(θ,x)/(1+e
f(θ,x)) (2)
Wherein, the loss parameter that the f (θ, x) in above-mentioned formula (1) is targeted customer, θ
0to θ
4for specifying the parameters of Logic Regression Models, and be known parameters, x
1for logging in number of days, x
2for login times, x
3for very first time interval, x
4for severe parameter.The loss probability that h (x) in above-mentioned formula (2) is targeted customer.
Such as, the device at predicted flows appraxia family based on this login number of days 8 days, login times 20 times, severe parameter 0 and very first time interval 3 days, according to above-mentioned formula (1), can determine that the loss parameter of targeted customer is 2.4; And the loss parameter 2.4 of based target user, by the appointment Logic Regression Models shown in above-mentioned formula (2), determine that the loss probability of targeted customer is 0.92.
Further, the device at predicted flows appraxia family, based on login number of days, login times, severe parameter and very first time interval, by specifying Logic Regression Models, before determining the loss probability of targeted customer, also comprises: obtain and wait to train Logic Regression Models; Based on the training sample stored, determine the parameters of waiting to train Logic Regression Models, in training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter; Based on the parameters waiting to train Logic Regression Models and wait to train Logic Regression Models, determine to specify Logic Regression Models.
It should be noted that, based on the training sample stored, determine that the method for the parameters treating training Logic Regression Models can with reference to correlation technique, the embodiment of the present invention is not specifically limited this.In addition, training sample is based on using the historic user behavioral data of all users of this application program to obtain, and this historic user behavioral data is that the behavior logging in this application program based on user produces.
Step 204: when the loss probability of targeted customer is more than or equal to appointment probability threshold value, then determine that targeted customer is the user being about to run off.
The loss probability of targeted customer compares with specifying probability threshold value by the device at predicted flows appraxia family, when the loss probability of targeted customer is more than or equal to appointment probability threshold value, then determines that targeted customer is the user being about to run off.Further, when the loss probability of targeted customer is less than appointment probability threshold value, then determine that targeted customer is the non-user being about to run off, that is to say, targeted customer is non-streaming appraxia family.
It should be noted that, specify probability threshold value to be arrange in advance, such as, specify probability threshold value can be 0.9, the embodiment of the present invention be not specifically limited this.
Further, when the loss probability of targeted customer is more than or equal to appointment probability threshold value, then, after determining that targeted customer is the user being about to run off, also comprise: the loss parameter determining targeted customer; The loss parameter of number of days, login times, very first time interval, severe parameter and targeted customer will be logged in, be stored in training to log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter, thus training sample is upgraded, improve the accuracy at predicted flows appraxia family.
Wherein, determine the loss parameter of targeted customer, comprising: when targeted customer is the user being about to run off, determine that the loss parameter of targeted customer is third value; When targeted customer is non-streaming appraxia family, determine that the loss parameter of targeted customer is the 4th numerical value.
It should be noted that, third value and the 4th numerical value are also arrange in advance, and third value can be equal with second value, 4th numerical value can be equal with the first numerical value, that is to say, third value can be 1,4th numerical value can be 0, and the embodiment of the present invention is not specifically limited this.
In embodiments of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
See Fig. 3, embodiments provide a kind of device 300 of predicted flows appraxia family, this device 300 comprises:
First acquisition module 301, for obtaining the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain this targeted customer and log in time interval between the time of this application program and current time for the last time, obtain very first time interval;
First determination module 302, for the hour of log-on of based target user account, determines the severe parameter of this targeted customer;
Second determination module 303, for based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, determines the loss probability of this targeted customer;
3rd determination module 304, when specifying probability threshold value for being more than or equal to when the loss probability of this targeted customer, then determines that this targeted customer is the user being about to run off.
Optionally, see Fig. 4, this first determination module 302 comprises:
First determining unit 3021, for determining the time interval between the hour of log-on of this targeted customer's account and this current time, obtained for second time interval;
Second determining unit 3022, for when this second time interval is less than or equal to the first fixed time interval, determines that the severe parameter of this targeted customer is the first numerical value;
3rd determining unit 3023, for when this second interval greater than this second fixed time interval time, determine that the severe parameter of this targeted customer is second value.
Optionally, see Fig. 5, this device also comprises:
Second acquisition module 305, waits to train Logic Regression Models for obtaining;
4th determination module 306, for the training sample based on storage, determine this parameters of waiting to train Logic Regression Models, in this training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
5th determination module 307, for waiting to train Logic Regression Models and this to wait to train the parameters of Logic Regression Models based on this, determines this appointment Logic Regression Models.
Optionally, see Fig. 6, this device also comprises:
6th determination module 308, for determining the loss parameter of this targeted customer;
Memory module 309, for by this login number of days, this login times, this very first time interval, this severe parameter and this loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
Optionally, see Fig. 7, the 6th determination module 308 comprises:
4th determining unit 3081, during for being the user being about to run off as this targeted customer, determines that the loss parameter of this targeted customer is third value;
5th determining unit 3082, during for being non-streaming appraxia family as this targeted customer, determines that the loss parameter of this targeted customer is the 4th numerical value.
In sum, in the embodiment of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
It should be noted that: the predicted flows that above-described embodiment provides loses user's set when predicted flows appraxia family, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by device is divided into different functional modules, to complete all or part of function described above.In addition, the device at the predicted flows appraxia family that above-described embodiment provides and the embodiment of the method at predicted flows appraxia family belong to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
Please refer to Fig. 8, it illustrates the block diagram that one embodiment of the invention provides the device at predicted flows appraxia family, the device at this predicted flows appraxia family can be terminal 800, terminal 800 can comprise communication unit 810, includes the storer 820 of one or more computer-readable recording mediums, input block 830, display unit 840, sensor 850, voicefrequency circuit 860, WIFI (Wireless Fidelity, Wireless Fidelity) module 870, include the parts such as processor 880 and power supply 890 that more than or processes core.It will be understood by those skilled in the art that the restriction of the not structure paired terminal of the terminal structure shown in Fig. 8, the parts more more or less than diagram can be comprised, or combine some parts, or different parts are arranged.Wherein:
Communication unit 810 can be used for receiving and sending messages or in communication process, the reception of signal and transmission, this communication unit 810 can be RF (Radio Frequency, radio frequency) circuit, router, modulator-demodular unit, etc. network communication equipment.Especially, when communication unit 810 is RF circuit, after being received by the downlink information of base station, more than one or one processor 880 is transferred to process; In addition, base station is sent to by relating to up data.Usually, RF circuit as communication unit includes but not limited to antenna, at least one amplifier, tuner, one or more oscillator, subscriber identity module (SIM) card, transceiver, coupling mechanism, LNA (Low Noise Amplifier, low noise amplifier), diplexer etc.In addition, communication unit 810 can also by radio communication and network and other devices communicatings.Described radio communication can use arbitrary communication standard or agreement, include but not limited to GSM (Global System of Mobile communication, global system for mobile communications), GPRS (General Packet Radio Service, general packet radio service), CDMA (Code Division Multiple Access, CDMA), WCDMA (Wideband Code DivisionMultiple Access, Wideband Code Division Multiple Access (WCDMA)), LTE (Long TermEvolution, Long Term Evolution), Email, SMS (Short Messaging Service, Short Message Service) etc.Storer 820 can be used for storing software program and module, and processor 880 is stored in software program and the module of storer 820 by running, thus performs the application of various function and data processing.Storer 820 mainly can comprise storage program district and store data field, and wherein, storage program district can store operating system, application program (such as sound-playing function, image player function etc.) etc. needed at least one function; Store data field and can store the data (such as voice data, phone directory etc.) etc. created according to the use of terminal 800.In addition, storer 820 can comprise high-speed random access memory, can also comprise nonvolatile memory, such as at least one disk memory, flush memory device or other volatile solid-state parts.Correspondingly, storer 820 can also comprise Memory Controller, to provide the access of processor 880 and input block 830 pairs of storeies 820.
Input block 830 can be used for the numeral or the character information that receive input, and produces and to arrange with user and function controls relevant keyboard, mouse, control lever, optics or trace ball signal and inputs.Preferably, input block 830 can comprise Touch sensitive surface 831 and other input equipments 832.Touch sensitive surface 831, also referred to as touch display screen or Trackpad, user can be collected or neighbouring touch operation (such as user uses any applicable object or the operations of annex on Touch sensitive surface 831 or near Touch sensitive surface 831 such as finger, stylus) thereon, and drive corresponding coupling arrangement according to the formula preset.Optionally, Touch sensitive surface 831 can comprise touch detecting apparatus and touch controller two parts.Wherein, touch detecting apparatus detects the touch orientation of user, and detects the signal that touch operation brings, and sends signal to touch controller; Touch controller receives touch information from touch detecting apparatus, and converts it to contact coordinate, then gives processor 880, and the order that energy receiving processor 880 is sent also is performed.In addition, the polytypes such as resistance-type, condenser type, infrared ray and surface acoustic wave can be adopted to realize Touch sensitive surface 831.Except Touch sensitive surface 831, input block 830 can also comprise other input equipments 832.Preferably, other input equipments 832 can include but not limited to one or more in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, control lever etc.
Display unit 840 can be used for the various graphical user interface showing information or the information being supplied to user and the terminal 800 inputted by user, and these graphical user interface can be made up of figure, text, icon, video and its combination in any.Display unit 840 can comprise display panel 841, optionally, the form such as LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) can be adopted to configure display panel 841.Further, Touch sensitive surface 831 can cover display panel 841, when Touch sensitive surface 831 detects thereon or after neighbouring touch operation, send processor 880 to determine the type of touch event, on display panel 841, provide corresponding vision to export with preprocessor 880 according to the type of touch event.Although in fig. 8, Touch sensitive surface 831 and display panel 841 be as two independently parts realize input and input function, in certain embodiments, can by Touch sensitive surface 831 and display panel 841 integrated and realize input and output function.
Terminal 800 also can comprise at least one sensor 850, such as optical sensor, motion sensor and other sensors.Optical sensor can comprise ambient light sensor and proximity transducer, wherein, ambient light sensor the light and shade of environmentally light can regulate the brightness of display panel 841, and proximity transducer when terminal 800 moves in one's ear, can cut out display panel 841 and/or backlight.As the one of motion sensor, Gravity accelerometer can detect the size of all directions (are generally three axles) acceleration, size and the direction of gravity can be detected time static, can be used for identifying the application (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating) of mobile phone attitude, Vibration identification correlation function (such as passometer, knock) etc.; As for terminal 800 also other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor, do not repeat them here.
Voicefrequency circuit 860, loudspeaker 861, microphone 862 can provide the audio interface between user and terminal 800.Voicefrequency circuit 860 can by receive voice data conversion after electric signal, be transferred to loudspeaker 861, by loudspeaker 861 be converted to voice signal export; On the other hand, the voice signal of collection is converted to electric signal by microphone 862, voice data is converted to after being received by voicefrequency circuit 860, after again voice data output processor 880 being processed, through communication unit 810 to send to such as another terminal, or export voice data to storer 820 to process further.Voicefrequency circuit 860 also may comprise earphone jack, to provide the communication of peripheral hardware earphone and terminal 800.
In order to realize radio communication, this terminal can be configured with wireless communication unit 870, this wireless communication unit 870 can be WIFI module.WIFI belongs to short range wireless transmission technology, and terminal 800 can help user to send and receive e-mail by wireless communication unit 870, browse webpage and access streaming video etc., and its broadband internet wireless for user provides is accessed.Although there is shown wireless communication unit 870, be understandable that, it does not belong to must forming of terminal 800, can omit in the scope of essence not changing invention as required completely.
Processor 880 is control centers of terminal 800, utilize the various piece of various interface and the whole mobile phone of connection, software program in storer 820 and/or module is stored in by running or performing, and call the data be stored in storer 820, perform various function and the process data of terminal 800, thus integral monitoring is carried out to mobile phone.Optionally, processor 880 can comprise one or more process core; Preferably, processor 880 accessible site application processor and modem processor, wherein, application processor mainly processes operating system, user interface and application program etc., and modem processor mainly processes radio communication.Be understandable that, above-mentioned modem processor also can not be integrated in processor 880.
Terminal 800 also comprises the power supply 890 (such as battery) of powering to all parts, preferably, power supply can be connected with processor 880 logic by power-supply management system, thus realizes the functions such as management charging, electric discharge and power managed by power-supply management system.Power supply 860 can also comprise one or more direct current or AC power, recharging system, power failure detection circuit, power supply changeover device or the random component such as inverter, power supply status indicator.
Although not shown, terminal 800 can also comprise camera, bluetooth module etc., does not repeat them here.
In the present embodiment, terminal also includes one or more than one program, this or more than one program are stored in storer, and be configured to be performed by more than one or one processor, described more than one or one routine package loses the instruction of user method containing the predicted flows provided for carrying out the embodiment of the present invention, comprising:
Obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain this targeted customer and log in time interval between the time of this application program and current time for the last time, obtain very first time interval;
The hour of log-on of based target user account, determines the severe parameter of this targeted customer;
Based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, determine the loss probability of this targeted customer;
When the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then determine that this targeted customer is the user being about to run off.
Optionally, the hour of log-on of based target user account, determine the severe parameter of this targeted customer, comprising:
Determine the time interval between the hour of log-on of this targeted customer's account and this current time, obtained for second time interval;
When this second time interval is less than or equal to the first fixed time interval, determine that the severe parameter of this targeted customer is the first numerical value;
When this second interval greater than this second fixed time interval time, determine that the severe parameter of this targeted customer is second value.
Optionally, based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, before determining the loss probability of this targeted customer, also comprise:
Obtain and wait to train Logic Regression Models;
Based on the training sample stored, determine this parameters of waiting to train Logic Regression Models, in this training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
Wait to train Logic Regression Models and this to wait to train the parameters of Logic Regression Models based on this, determine this appointment Logic Regression Models.
Optionally, when the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then, after determining that this targeted customer is the user being about to run off, also comprise:
Determine the loss parameter of this targeted customer;
By this login number of days, this login times, this very first time interval, this severe parameter and this loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
Optionally, determine the loss parameter of this targeted customer, comprising:
When this targeted customer is the user being about to run off, determine that the loss parameter of this targeted customer is third value;
When this targeted customer is non-streaming appraxia family, determine that the loss parameter of this targeted customer is the 4th numerical value.
In embodiments of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
Please refer to Fig. 9, a kind of predicted flows that it illustrates one embodiment of the invention provides loses the structural representation of user's set.This predicted flows appraxia family can be server 900, this server 900 comprises CPU (central processing unit) (CPU) 901, comprises the system storage 904 of random access memory (RAM) 902 and ROM (read-only memory) (ROM) 903, and the system bus 905 of connected system storer 904 and CPU (central processing unit) 901.Server 900 also comprises the basic input/output (I/O system) 906 of transmission information between each device in help computing machine, and for storing the mass-memory unit 907 of operating system 913, application program 910 and other program modules 915.
Described basic input/output 906 includes the input equipment 909 of the display 908 for showing information and the such as mouse, keyboard and so on for user's input information.Wherein said display 908 and input equipment 909 are all connected to CPU (central processing unit) 901 by the input/output control unit 910 being connected to system bus 905.Described basic input/output 906 can also comprise input/output control unit 910 for receiving and processing the input from other equipment multiple such as keyboard, mouse or electronic touch pens.Similarly, input/output control unit 910 also provides the output device outputting to display screen, printer or other types.
Described mass-memory unit 907 is connected to CPU (central processing unit) 901 by the bulk memory controller (not shown) being connected to system bus 905.Described mass-memory unit 907 and the computer-readable medium that is associated thereof provide non-volatile memories for server 900.That is, described mass-memory unit 907 can comprise the computer-readable medium (not shown) of such as hard disk or CD-ROM drive and so on.
Without loss of generality, described computer-readable medium can comprise computer-readable storage medium and communication media.Computer-readable storage medium comprises the volatibility and non-volatile, removable and irremovable medium that realize for any method or technology that store the information such as such as computer-readable instruction, data structure, program module or other data.Computer-readable storage medium comprises RAM, ROM, EPROM, EEPROM, flash memory or its technology of other solid-state storage, CD-ROM, DVD or other optical memory, tape cassete, tape, disk storage or other magnetic storage apparatus.Certainly, the known described computer-readable storage medium of those skilled in the art is not limited to above-mentioned several.Above-mentioned system storage 904 and mass-memory unit 907 can be referred to as storer.
According to various embodiments of the present invention, the remote computer that server 900 can also be connected on network by networks such as such as the Internets runs.Also namely server 900 can be connected to network 912 by the network interface unit 911 be connected on described system bus 905, in other words, network interface unit 911 also can be used to be connected to network or the remote computer system (not shown) of other types.
Described storer also comprises one or more than one program, described more than one or one program is stored in storer, described more than one or one routine package loses the instruction of user method containing the predicted flows provided for carrying out the embodiment of the present invention, comprising:
Obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain this targeted customer and log in time interval between the time of this application program and current time for the last time, obtain very first time interval;
The hour of log-on of based target user account, determines the severe parameter of this targeted customer;
Based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, determine the loss probability of this targeted customer;
When the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then determine that this targeted customer is the user being about to run off.
Optionally, the hour of log-on of based target user account, determine the severe parameter of this targeted customer, comprising:
Determine the time interval between the hour of log-on of this targeted customer's account and this current time, obtained for second time interval;
When this second time interval is less than or equal to the first fixed time interval, determine that the severe parameter of this targeted customer is the first numerical value;
When this second interval greater than this second fixed time interval time, determine that the severe parameter of this targeted customer is second value.
Optionally, based on this login number of days, this login times, this severe parameter and this very first time interval, by specifying Logic Regression Models, before determining the loss probability of this targeted customer, also comprise:
Obtain and wait to train Logic Regression Models;
Based on the training sample stored, determine this parameters of waiting to train Logic Regression Models, in this training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
Wait to train Logic Regression Models and this to wait to train the parameters of Logic Regression Models based on this, determine this appointment Logic Regression Models.
Optionally, when the loss probability of this targeted customer is more than or equal to appointment probability threshold value, then, after determining that this targeted customer is the user being about to run off, also comprise:
Determine the loss parameter of this targeted customer;
By this login number of days, this login times, this very first time interval, this severe parameter and this loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
Optionally, determine the loss parameter of this targeted customer, comprising:
When this targeted customer is the user being about to run off, determine that the loss parameter of this targeted customer is third value;
When this targeted customer is non-streaming appraxia family, determine that the loss parameter of this targeted customer is the 4th numerical value.
In embodiments of the present invention, based target user is the login number of days of login application program and login times in section at the appointed time, and the very first time interval of targeted customer and severe parameter, by specifying Logic Regression Models, the loss probability of targeted customer can be determined, thus determine whether targeted customer is the user being about to run off.And be that each application program is suitable for owing to logging in number of days, login times, very first time interval and severe parameter, that is to say, each application program comprises the feature logging in number of days, login times, very first time interval and severe parameter, therefore, the method at this predicted flows appraxia family goes for all application programs, and range of application is wider.Moreover the method at this predicted flows appraxia family is that the device at predicted flows appraxia family automatically performs completely, and operate simpler answering, workload is little, thus improves the efficiency at predicted flows appraxia family, and the robustness of the method at this predicted flows appraxia family is better.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the method at predicted flows appraxia family, is characterized in that, described method comprises:
Obtain the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain described targeted customer and log in time interval between the time of described application program and current time for the last time, obtain very first time interval;
The hour of log-on of based target user account, determines the severe parameter of described targeted customer;
Based on described login number of days, described login times, described severe parameter and described very first time interval, by specifying Logic Regression Models, determine the loss probability of described targeted customer;
When the loss probability of described targeted customer is more than or equal to appointment probability threshold value, then determine that described targeted customer is the user being about to run off.
2. the method for claim 1, is characterized in that, the hour of log-on of described based target user account, determines the severe parameter of described targeted customer, comprising:
Determine the time interval between the hour of log-on of described targeted customer's account and described current time, obtained for second time interval;
When described second time interval is less than or equal to the first fixed time interval, determine that the severe parameter of described targeted customer is the first numerical value;
When described second interval greater than described second fixed time interval, determine that the severe parameter of described targeted customer is second value.
3. the method for claim 1, it is characterized in that, described based on described login number of days, described login times, described severe parameter and described very first time interval, by specifying Logic Regression Models, before determining the loss probability of described targeted customer, also comprise:
Obtain and wait to train Logic Regression Models;
Based on the training sample stored, wait the parameters of training Logic Regression Models described in determining, in described training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
Train Logic Regression Models and described parameters of waiting to train Logic Regression Models based on described waiting, determine described appointment Logic Regression Models.
4. the method as described in claim 1 or 3, is characterized in that, when the described loss probability as described targeted customer is more than or equal to appointment probability threshold value, then, after determining that described targeted customer is the user being about to run off, also comprises:
Determine the loss parameter of described targeted customer;
By described login number of days, described login times, described very first time interval, described severe parameter and described loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
5. method as claimed in claim 4, it is characterized in that, the described loss parameter determining described targeted customer, comprising:
When described targeted customer is the user being about to run off, determine that the loss parameter of described targeted customer is third value;
When described targeted customer is non-streaming appraxia family, determine that the loss parameter of described targeted customer is the 4th numerical value.
6. the device at predicted flows appraxia family, is characterized in that, described device comprises:
First acquisition module, for obtaining the targeted customer's at the appointed time login number of days of login application program and login times in section, and obtain described targeted customer and log in time interval between the time of described application program and current time for the last time, obtain very first time interval;
First determination module, for the hour of log-on of based target user account, determines the severe parameter of described targeted customer;
Second determination module, for based on described login number of days, described login times, described severe parameter and described very first time interval, by specifying Logic Regression Models, determines the loss probability of described targeted customer;
3rd determination module, when specifying probability threshold value for being more than or equal to when the loss probability of described targeted customer, then determines that described targeted customer is the user being about to run off.
7. device as claimed in claim 6, it is characterized in that, described first determination module comprises:
First determining unit, for determining the time interval between the hour of log-on of described targeted customer's account and described current time, obtained for second time interval;
Second determining unit, for when described second time interval is less than or equal to the first fixed time interval, determines that the severe parameter of described targeted customer is the first numerical value;
3rd determining unit, for when described second interval greater than described second fixed time interval, determines that the severe parameter of described targeted customer is second value.
8. device as claimed in claim 6, it is characterized in that, described device also comprises:
Second acquisition module, waits to train Logic Regression Models for obtaining;
4th determination module, for the training sample based on storage, wait the parameters of training Logic Regression Models described in determining, in described training sample, storage training logs in number of days, training login times, training time interval, training severe parameter and trains the corresponding relation between loss parameter;
5th determination module, for training Logic Regression Models and described parameters of waiting to train Logic Regression Models based on described waiting, determines described appointment Logic Regression Models.
9. the device as described in claim 6 or 8, is characterized in that, described device also comprises:
6th determination module, for determining the loss parameter of described targeted customer;
Memory module, for by described login number of days, described login times, described very first time interval, described severe parameter and described loss parameter, be stored in training and log in number of days, training login times, training time interval, training severe parameter and train in the corresponding relation between loss parameter.
10. device as claimed in claim 9, it is characterized in that, the 6th determination module comprises:
4th determining unit, during for being the user being about to run off as described targeted customer, determines that the loss parameter of described targeted customer is third value;
5th determining unit, during for being non-streaming appraxia family as described targeted customer, determines that the loss parameter of described targeted customer is the 4th numerical value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510337449.1A CN105005909A (en) | 2015-06-17 | 2015-06-17 | Method and device for predicting lost users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510337449.1A CN105005909A (en) | 2015-06-17 | 2015-06-17 | Method and device for predicting lost users |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105005909A true CN105005909A (en) | 2015-10-28 |
Family
ID=54378571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510337449.1A Pending CN105005909A (en) | 2015-06-17 | 2015-06-17 | Method and device for predicting lost users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105005909A (en) |
Cited By (29)
| 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 |
| CN105760957A (en) * | 2016-02-23 | 2016-07-13 | 国元证券股份有限公司 | Securities soft lost customer prediction method |
| CN106204127A (en) * | 2016-07-06 | 2016-12-07 | 乐视控股（北京）有限公司 | User's evaluation methodology and device for application |
| CN106658394A (en) * | 2015-11-04 | 2017-05-10 | 中国移动通信集团公司 | High-speed rail user separation method and apparatus thereof |
| CN106875225A (en) * | 2017-02-24 | 2017-06-20 | 泰康保险集团股份有限公司 | For the method and device of customer service |
| CN107203822A (en) * | 2016-03-16 | 2017-09-26 | 上海吉贝克信息技术有限公司 | Method and system based on the Logistic security customers attrition predictions returned |
| CN107358247A (en) * | 2017-04-18 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of method and device for determining to be lost in user |
| CN107370614A (en) * | 2016-05-13 | 2017-11-21 | 北京京东尚科信息技术有限公司 | Network user active degree appraisal procedure and Forecasting Methodology |
| CN107507036A (en) * | 2017-08-28 | 2017-12-22 | 深圳市诚壹科技有限公司 | The method and terminal of a kind of data prediction |
| CN107633419A (en) * | 2017-08-10 | 2018-01-26 | 无锡雅座在线科技股份有限公司 | Member is lost in treating method and apparatus |
| CN107634850A (en) * | 2017-08-10 | 2018-01-26 | 腾讯科技（深圳）有限公司 | A kind of application state acquisition methods and its equipment, storage medium, server |
| CN108009855A (en) * | 2017-12-13 | 2018-05-08 | 北京小度信息科技有限公司 | Data processing method, equipment and storage medium |
| WO2018090531A1 (en) * | 2016-11-17 | 2018-05-24 | 深圳市行远科技发展有限公司 | Early warning analysis method and apparatus for height data of user |
| CN108549594A (en) * | 2018-03-30 | 2018-09-18 | 武汉斗鱼网络科技有限公司 | Determine the method and device of customer loss reason |
| CN108683949A (en) * | 2018-05-18 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of live streaming platform potential user |
| CN108876394A (en) * | 2017-05-16 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Identify the potential method and apparatus for being lost user of e-commerce platform |
| CN108932625A (en) * | 2017-05-23 | 2018-12-04 | 北京京东尚科信息技术有限公司 | Analysis method, device, medium and the electronic equipment of user behavior data |
| WO2019033677A1 (en) * | 2017-08-17 | 2019-02-21 | 北京小度信息科技有限公司 | Method and apparatus for determining whether user behavior indicates disengagement, and electronic device |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN109903100A (en) * | 2018-12-25 | 2019-06-18 | 深圳市梦域科技有限公司 | A kind of customer churn prediction technique, device and readable storage medium storing program for executing |
| CN109993560A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system and computer-readable medium |
| CN110298508A (en) * | 2019-06-28 | 2019-10-01 | 京东数字科技控股有限公司 | Behavior prediction method, device and equipment |
| CN111461188A (en) * | 2020-03-20 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Target service control method, device, computing equipment and storage medium |
| CN111813920A (en) * | 2020-07-06 | 2020-10-23 | 龙马智芯（珠海横琴）科技有限公司 | Learning strategy generation method, device, generation equipment and readable storage medium |
| CN112465544A (en) * | 2020-11-25 | 2021-03-09 | 北京深演智能科技股份有限公司 | User loss early warning method and device |
| CN113240451A (en) * | 2021-04-12 | 2021-08-10 | 西南财经大学 | User loss prediction method and device |
| CN113657635A (en) * | 2020-05-12 | 2021-11-16 | 中国移动通信集团湖南有限公司 | Method for predicting communication user loss and electronic equipment |
| CN113827980A (en) * | 2021-08-17 | 2021-12-24 | 杭州电魂网络科技股份有限公司 | Loss user prediction method and device and computer readable storage medium |
| CN113827978A (en) * | 2021-08-17 | 2021-12-24 | 杭州电魂网络科技股份有限公司 | Loss user prediction method and device and computer readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679969A (en) * | 2013-11-29 | 2015-06-03 | 腾讯科技（深圳）有限公司 | Method and device for avoiding user churn |
-
2015
- 2015-06-17 CN CN201510337449.1A patent/CN105005909A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679969A (en) * | 2013-11-29 | 2015-06-03 | 腾讯科技（深圳）有限公司 | Method and device for avoiding user churn |
Non-Patent Citations (4)
| Title |
|---|
| 于彩娴: "关于银行客户流失预测的数学建模分析", 《武汉生物工程学院学报》 * |
| 庞一非: "数据挖掘在客户流失预警模型中的应用—基于山东联通3G用户的研究", 《中国优秀硕士学位论文全文数据库》 * |
| 腾讯大数据: "基于腾讯信鸽平台的手游流失用户预测模型概览", 《HTTP://WWW.CSDN.NET/ARTICLE/2015-06-12/2824948》 * |
| 蒙肖莲等: "商业银行客户流失预测模型研究", 《系统工程》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106658394A (en) * | 2015-11-04 | 2017-05-10 | 中国移动通信集团公司 | High-speed rail user separation method and apparatus thereof |
| 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 |
| CN105760957A (en) * | 2016-02-23 | 2016-07-13 | 国元证券股份有限公司 | Securities soft lost customer prediction method |
| CN107203822A (en) * | 2016-03-16 | 2017-09-26 | 上海吉贝克信息技术有限公司 | Method and system based on the Logistic security customers attrition predictions returned |
| CN107370614A (en) * | 2016-05-13 | 2017-11-21 | 北京京东尚科信息技术有限公司 | Network user active degree appraisal procedure and Forecasting Methodology |
| CN106204127A (en) * | 2016-07-06 | 2016-12-07 | 乐视控股（北京）有限公司 | User's evaluation methodology and device for application |
| WO2018090531A1 (en) * | 2016-11-17 | 2018-05-24 | 深圳市行远科技发展有限公司 | Early warning analysis method and apparatus for height data of user |
| CN106875225A (en) * | 2017-02-24 | 2017-06-20 | 泰康保险集团股份有限公司 | For the method and device of customer service |
| CN107358247A (en) * | 2017-04-18 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of method and device for determining to be lost in user |
| CN107358247B (en) * | 2017-04-18 | 2020-08-04 | 阿里巴巴集团控股有限公司 | Method and device for determining lost user |
| CN108876394A (en) * | 2017-05-16 | 2018-11-23 | 北京京东尚科信息技术有限公司 | Identify the potential method and apparatus for being lost user of e-commerce platform |
| CN108932625B (en) * | 2017-05-23 | 2022-04-26 | 北京京东尚科信息技术有限公司 | User behavior data analysis method, device, medium and electronic equipment |
| CN108932625A (en) * | 2017-05-23 | 2018-12-04 | 北京京东尚科信息技术有限公司 | Analysis method, device, medium and the electronic equipment of user behavior data |
| CN107633419A (en) * | 2017-08-10 | 2018-01-26 | 无锡雅座在线科技股份有限公司 | Member is lost in treating method and apparatus |
| CN107634850A (en) * | 2017-08-10 | 2018-01-26 | 腾讯科技（深圳）有限公司 | A kind of application state acquisition methods and its equipment, storage medium, server |
| WO2019033677A1 (en) * | 2017-08-17 | 2019-02-21 | 北京小度信息科技有限公司 | Method and apparatus for determining whether user behavior indicates disengagement, and electronic device |
| CN107507036A (en) * | 2017-08-28 | 2017-12-22 | 深圳市诚壹科技有限公司 | The method and terminal of a kind of data prediction |
| CN108009855A (en) * | 2017-12-13 | 2018-05-08 | 北京小度信息科技有限公司 | Data processing method, equipment and storage medium |
| CN109993560A (en) * | 2017-12-29 | 2019-07-09 | 北京京东尚科信息技术有限公司 | Data processing method, system and computer-readable medium |
| CN108549594A (en) * | 2018-03-30 | 2018-09-18 | 武汉斗鱼网络科技有限公司 | Determine the method and device of customer loss reason |
| CN108549594B (en) * | 2018-03-30 | 2021-07-23 | 武汉斗鱼网络科技有限公司 | Method and device for determining user loss reason |
| CN108683949A (en) * | 2018-05-18 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of live streaming platform potential user |
| CN109461023A (en) * | 2018-10-12 | 2019-03-12 | 中国平安人寿保险股份有限公司 | It is lost user and retrieves method and device, electronic equipment, storage medium |
| CN109461023B (en) * | 2018-10-12 | 2023-10-24 | 中国平安人寿保险股份有限公司 | Loss user retrieval method and device, electronic equipment and storage medium |
| CN109903100A (en) * | 2018-12-25 | 2019-06-18 | 深圳市梦域科技有限公司 | A kind of customer churn prediction technique, device and readable storage medium storing program for executing |
| CN110298508A (en) * | 2019-06-28 | 2019-10-01 | 京东数字科技控股有限公司 | Behavior prediction method, device and equipment |
| CN111461188A (en) * | 2020-03-20 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Target service control method, device, computing equipment and storage medium |
| CN111461188B (en) * | 2020-03-20 | 2023-09-12 | 腾讯科技（深圳）有限公司 | Target service control method, device, computing equipment and storage medium |
| CN113657635B (en) * | 2020-05-12 | 2023-10-27 | 中国移动通信集团湖南有限公司 | Method for predicting loss of communication user and electronic equipment |
| CN113657635A (en) * | 2020-05-12 | 2021-11-16 | 中国移动通信集团湖南有限公司 | Method for predicting communication user loss and electronic equipment |
| CN111813920A (en) * | 2020-07-06 | 2020-10-23 | 龙马智芯（珠海横琴）科技有限公司 | Learning strategy generation method, device, generation equipment and readable storage medium |
| CN112465544A (en) * | 2020-11-25 | 2021-03-09 | 北京深演智能科技股份有限公司 | User loss early warning method and device |
| CN113240451A (en) * | 2021-04-12 | 2021-08-10 | 西南财经大学 | User loss prediction method and device |
| CN113827978A (en) * | 2021-08-17 | 2021-12-24 | 杭州电魂网络科技股份有限公司 | Loss user prediction method and device and computer readable storage medium |
| CN113827980A (en) * | 2021-08-17 | 2021-12-24 | 杭州电魂网络科技股份有限公司 | Loss user prediction method and device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105005909A (en) | Method and device for predicting lost users | |
| CN104869468A (en) | Method and apparatus for displaying screen information | |
| CN104967896A (en) | Method for displaying bulletscreen comment information, and apparatus thereof | |
| CN104780164A (en) | Method and device for operating game client | |
| CN104954402A (en) | Application recommending method, system and apparatus | |
| CN105119806A (en) | Message updating method and device | |
| CN105278937A (en) | Method and device for displaying pop-up box messages | |
| CN104135728B (en) | Method for connecting network and device | |
| CN104427083A (en) | Volume adjusting method and device | |
| CN104142868A (en) | Connection establishment method and device | |
| CN104636047A (en) | Method and device for operating objects in list and touch screen terminal | |
| CN104252341A (en) | Method and device for resurfacing application program and client side device of application program | |
| CN103475914A (en) | Video playing method, video playing device, terminal equipment and server | |
| CN104618223A (en) | Information recommendation management method, device and system | |
| CN105049470A (en) | Event confirming method, apparatus and system | |
| CN104519262A (en) | Method, device for acquiring video data, and terminal | |
| CN104423822A (en) | Automated test script recording method and device | |
| CN105207880A (en) | Group recommendation method and apparatus | |
| CN104602135A (en) | Method and device for controlling full screen play | |
| CN103945241A (en) | Streaming data statistical method, system and related device | |
| CN104363590A (en) | Access point connection method and device | |
| CN104253870A (en) | Method and device for controlling data access period | |
| CN104660769A (en) | Method, device and system for adding contact person information | |
| CN103561155B (en) | Send the method for note, device and terminal | |
| CN104243394A (en) | Multimedia file playing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151028 |