CN113822435A - User conversion rate prediction method and related equipment - Google Patents
User conversion rate prediction method and related equipment Download PDFInfo
- Publication number
- CN113822435A CN113822435A CN202010565072.6A CN202010565072A CN113822435A CN 113822435 A CN113822435 A CN 113822435A CN 202010565072 A CN202010565072 A CN 202010565072A CN 113822435 A CN113822435 A CN 113822435A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- target
- delay parameter
- target service
- 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
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 161
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000003860 storage Methods 0.000 claims description 29
- 238000009826 distribution Methods 0.000 claims description 21
- 238000010801 machine learning Methods 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 15
- 238000012545 processing Methods 0.000 description 15
- 238000013473 artificial intelligence Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 238000003058 natural language processing Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 230000001413 cellular effect Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 230000003203 everyday effect Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a user conversion rate prediction method and related equipment, wherein random delay parameters constructed at the moment that a user is not converted in a business and characteristics of the user are trained in a machine learning mode to obtain a prediction model, and when the conversion rate of the user is predicted through the prediction model, more accurate conversion rate is obtained. The method comprises the following steps: determining characteristics of a target user; determining the exposure time of the target service; determining an actual delay parameter of a target user according to the exposure time and the current time of the target service; the method comprises the steps of determining the conversion rate of a target user in a target service based on an actual delay parameter of the target user, the characteristics of the target user and a prediction model, wherein the prediction model is obtained by training a training sample, the training sample comprises the characteristics of M users and random delay parameters corresponding to the M users, the random delay parameters corresponding to the M users are determined according to the conversion duration of the M users, and M is a positive integer greater than or equal to 1.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method and a related device for predicting user conversion rate.
Background
Delayed feedback modeling means that conversion of a user may be delayed after advertisement exposure is frequently encountered in business, and when dynamic modeling needs to pull all tag data of the exposed user, the delayed feedback tag needs to be modeled because the user may not be converted in the calculation process and may have conversion later, so that the user cannot simply act as a negative sample. The conversion has different specific meanings in different services, which means the indexes of final attention of the services, such as that the card is finally checked and sold for the user in the card advertisement, and the game is finally downloaded and registered for the user in the game recommendation service.
The classical delay feedback modeling method needs to adopt a double-gradient finer calculation method to optimize the model, but the double-gradient updating calculation method has constraint on the realization of the model, so that the application range of the model obtained by the classical delay feedback modeling method is not wide enough. The inverse gradient method is mainly suitable for online learning modeling of continuous model updating, and cannot be used if the business needs to take current historical data to model and calculate again every day.
Therefore, when the user conversion rate is predicted through the model, the obtained user conversion rate is not accurate enough.
Disclosure of Invention
The application provides a user conversion rate prediction method and related equipment, and accuracy of user conversion rate prediction is improved.
The first aspect of the present application provides a method for predicting user conversion rate, including:
determining the characteristics of a target user, wherein the target user is an object to be predicted and is associated with a target service;
determining the exposure time of the target service;
determining an actual delay parameter of the target user according to the exposure time and the current time of the target service;
determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and a prediction model, wherein the prediction model corresponds to the target service and is obtained by training a training sample, the training sample comprises the characteristics of M users and random delay parameters corresponding to the M users, the random delay parameters corresponding to the M users are determined according to the conversion duration of the M users, and M is a positive integer greater than or equal to 1.
Optionally, the method further comprises:
acquiring target data of the M users;
determining the range of the delay parameter of each user in the M users according to the target data;
determining a random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users;
acquiring the characteristics of each user in the M users;
and carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain the prediction model.
Optionally, the determining the random delay parameter of each of the M users according to the range of the delay parameter of each of the M users includes:
calculating the range of the delay parameter of each of the M users based on a preset rule to obtain a random delay parameter of each of the M users, wherein the preset rule at least includes one of the following rules: exponential, power-law, normal, and bernoulli distributions.
Optionally, the determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and a prediction model includes:
determining the conversion end time of the target service;
and determining the conversion rate of the target user in the target service based on the conversion finishing time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model.
Optionally, the method further comprises:
displaying the conversion rate of the target service in the target service;
when the conversion period of the target service is finished, obtaining label data of an object corresponding to the target service, wherein the label data comprises the exposure time of the target service, the conversion time of the object corresponding to the target service, the conversion finishing time of the target service and the characteristics of the object corresponding to the target service;
and optimizing the prediction model by using the label data as a training sample.
A second aspect of the embodiments of the present application provides an apparatus for predicting a user conversion rate, including:
the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining the characteristics of a target user, the target user is an object to be predicted, and the target user is associated with a target service;
a second determining unit, configured to determine an exposure time of the target service;
a third determining unit, configured to determine an actual delay parameter of the target user according to the exposure time of the target service and the current time;
the prediction unit is configured to determine a conversion rate of the target user in the target service based on an actual delay parameter of the target user, a feature of the target user, and a prediction model, where the prediction model corresponds to the target service and is obtained by training a training sample, and the training sample includes features of M users and random delay parameters corresponding to the M users, where the random delay parameters corresponding to the M users are determined according to conversion durations of the M users, and M is a positive integer greater than or equal to 1.
Optionally, the device for predicting user conversion rate further includes:
a training unit to:
acquiring target data of the M users;
determining the range of the delay parameter of each user in the M users according to the target data;
determining a random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users;
acquiring the characteristics of each user in the M users;
and carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain the prediction model.
Optionally, the determining, by the training unit, the random delay parameter of each of the M users according to the range of the delay parameter of each of the M users includes:
calculating the range of the delay parameter of each of the M users based on a preset rule to obtain a random delay parameter of each of the M users, wherein the preset rule at least includes one of the following rules: exponential, power-law, normal, and bernoulli distributions.
Optionally, the prediction unit is specifically configured to:
determining the conversion end time of the target service;
and determining the conversion rate of the target user in the target service based on the conversion finishing time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model.
Optionally, the apparatus further comprises:
a processing unit to:
displaying the conversion rate of the target user in the target service;
when the conversion period of the target service is finished, obtaining label data of an object corresponding to the target service, wherein the label data comprises the exposure time of the target service, the conversion time of the object corresponding to the target service, the conversion finishing time of the target service and the characteristics of the object corresponding to the target service;
and optimizing the prediction model by using the label data as a training sample.
A third aspect of the present application provides a computer apparatus comprising at least one connected processor, a memory and a transceiver, wherein the memory is configured to store program code, which is loaded and executed by the processor to implement the steps of the user conversion rate prediction method described above.
A fourth aspect of the present application provides a computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the steps of the method for predicting user conversion rate as described above.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method provided in the various alternative implementations of the first aspect described above.
In summary, it can be seen that, in the embodiment provided by the application, the random delay parameters obtained by the instant construction of M users that have not been transformed are added into the model for training, and because the sample size of this part is huge, a more excellent prediction model can be obtained by training, so that when the transformation rate of the user is predicted by the model, the accuracy of predicting the transformation rate of the user can be improved.
Drawings
Fig. 1 is a schematic flowchart of a method for predicting user conversion rate according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a training process of a prediction model according to an embodiment of the present disclosure;
fig. 3 is a schematic virtual structure diagram of a device for predicting user conversion rate according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present application;
fig. 5 is a schematic hardware structure diagram of a server according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments.
The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprise," "include," and "have," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules expressly listed, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus, the division of modules presented herein is merely a logical division that may be implemented in a practical application in a further manner, such that a plurality of modules may be combined or integrated into another system, or some feature vectors may be omitted, or not implemented, and such that couplings or direct couplings or communicative coupling between each other as shown or discussed may be through some interfaces, indirect couplings or communicative coupling between modules may be electrical or other similar, this application is not intended to be limiting. The modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in a plurality of circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present disclosure.
The embodiment of the application relates to the field of artificial intelligence and the field of machine learning, and the following description is made on relevant contents of artificial intelligence and machine learning:
with the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like.
Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.
The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Key technologies for Speech Technology (Speech Technology) are automatic Speech recognition Technology (ASR) and Speech synthesis Technology (TTS), as well as voiceprint recognition Technology. The computer can listen, see, speak and feel, and the development direction of the future human-computer interaction is provided, wherein the voice becomes one of the best viewed human-computer interaction modes in the future.
Natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.
Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.
The current delay feedback model is generally constructed by a classical delay feedback modeling method and an inverse gradient method, and two models are simultaneously established for the delay feedback model constructed by the classical delay feedback modeling method:
transformation model: p (C ═ 1) ═ sigmod (-w)cX) for predicting whether the user will eventually convert, wcConverting model parameters, wherein X is user characteristics, y is whether conversion is performed at present, C is whether conversion is performed at last, D is time required for conversion, and e is elapsed time from the click moment to the current moment;
delay model: p (D | C ═ 1) ═ λ (x) exp (- λ (x) D), and the probability that the user will have a delay time of D if the user finally switches is predicted by an exponential distribution. Where λ is a random delay parameter, to ensure that it is greater than 0, λ (x) ═ exp (w) can be useddX) where w is calculateddI.e. the parameters of the delay model.
According to the formula whether the user converts currently, the Loss function Loss which needs to be optimized finally can be deduced as follows:
wherein x isiFeatures representing user i, yiIndicating whether the user i is converted or not finally, and if so, yi1, if not converted, yi＝0，eiIndicating the time elapsed from the click time of the user i to the current time.
During training, every time one sample comes, the model parameters of the conversion model and the delay model are updated according to Loss. During prediction, the trained transformation model is only required to be taken out for use. Because the classical delay feedback modeling method adopts a double-gradient finer calculation method to optimize the model, and the double-gradient updating calculation method has constraint on the realization of the model, the application range of the model obtained by the classical delay feedback modeling method is not wide enough, and the prediction precision is not high easily when the model is used.
For the delay feedback model constructed by the reverse gradient method, when an exposure sample comes, the exposure sample is firstly used as a negative sample to update the Loss of the existing model, and then when the conversion data comes, the gradient for updating the Loss is further stepped in the reverse direction, the reverse gradient method is mainly suitable for the online learning modeling of the continuous updating of the model, if the business needs to be subjected to modeling calculation again by taking current historical data every day, the model cannot be used, and if the business is not updated every day, the phenomenon that the prediction precision is not high when the model is used online can also occur.
In view of this, the present application provides a method for predicting user conversion rate, where a target user is an object to be predicted and is associated with a target service by determining characteristics of the target user and an exposure time of the target service; determining an actual delay parameter of a target user according to the exposure time of the target service and the current time; the method comprises the steps of determining the conversion rate of a target user in a target service based on an actual delay parameter of the target user, the characteristics of the target user and a prediction model, wherein the prediction model corresponds to the target service, the prediction model is obtained by training a training sample, the training sample comprises the characteristics of M users and random delay parameters corresponding to the M users, and M is a positive integer greater than or equal to 1. When prediction is performed through a prediction model obtained by training a training sample in advance, random delay parameters and the characteristics of an object are used as the training sample to perform model training in the model training, and the random delay parameters corresponding to M users are determined according to the conversion duration of the M users. Therefore, in the application, random delay parameters obtained by instantaneous construction of M users which are not converted are added into the model for training, and due to the fact that the sample size of the random delay parameters is large, a more excellent prediction model can be obtained through training, and therefore when the conversion rate of the users is predicted through the model, the accuracy of predicting the conversion rate of the users can be improved.
The method for predicting the user conversion rate provided by the present application is described below in terms of a device for predicting the user conversion rate, which may be a terminal device, a server, or a service unit in the server, and is not particularly limited.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for predicting user conversion rate according to an embodiment of the present application, including:
101. characteristics of the target user are determined.
In this embodiment, the prediction apparatus of the user conversion rate may first determine the characteristics of a target user, where the target user is an object to be predicted, and the target user is associated with a target service, and the target service may pay a lookelike diffusion item for a face-to-face card ticket of the WeChat, or may download an advertisement for a certain game, and the target user is a user who receives the face-to-face card volume of the WeChat and pays a card volume in the lookelike diffusion item, or clicks the advertisement downloaded by the certain game.
It should be noted that the characteristics of the target users corresponding to different services are different, and the user conversion rate prediction apparatus may obtain the characteristics corresponding to the target users according to the actual content of the target services.
102. The exposure time of the target service is determined.
In this embodiment, the prediction apparatus for user conversion rate may determine the exposure time of the target service, that is, determine the time when the upper line of the target service faces the user, and the time when the user can see the target service.
103. And determining the actual delay parameter of the target user according to the exposure time and the current time of the target service.
In this embodiment, after obtaining the exposure time of the target service, the prediction apparatus of the user conversion rate may determine the actual delay parameter of the target user according to the exposure time of the target service and the current time, for example, if the exposure time of the target service is 5/1/2020 and the current time is 5/10/2020, the actual delay parameter of the target user may be determined to be 9 days, that is, the actual delay parameter may be obtained by subtracting 1 from the duration from the exposure time to the current time. It is understood that the actual delay parameter is illustrated herein in units of days, but may also be in other time units, such as hours, weeks, months, etc., without limitation.
It should be noted that, the characteristics of the target user may be determined through step 101, and the actual delay parameter of the target user may be determined through steps 102 to 103, however, there is no restriction on the execution sequence between step 101 and steps 102 to 103, and step 101 may be executed first, or steps 102 to 103 may be executed first, or executed simultaneously, which is not limited specifically.
104. And determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and the prediction model.
In this embodiment, after obtaining the actual delay parameter of the target user and the characteristics of the target user, the actual delay parameters of the target user and the characteristics of the target user may be input into a pre-trained predictive model to determine the conversion rate of the target user in the target business, such as click downloading of the target business for "royal glory" game, the conversion rate is the probability of the target user downloading the game, namely, whether the target user finally downloads the 'Royal of King' is predicted through a prediction model, and the probability of the user downloading the 'Royal of King', namely, the conversion rate is finally obtained, of course, the target service may be other services, such as a coupon issued by a WeChat, which may be used by a user after the user picks up the coupon, the probability of whether the user will use the coupon, that is, the conversion rate of the coupon by the user, may be determined in the above manner, which is not specifically limited. The prediction model corresponds to a target service, the prediction model is obtained by training a training sample, the training sample comprises characteristics of M users and random delay parameters corresponding to the M users, the random delay parameters corresponding to the M users are determined according to conversion duration of the M users, M is a positive integer greater than or equal to 1, namely, data with an unknown label can be extracted by using data with a historical conversion period completed (if the conversion period is completed in two steps of exposure-conversion, all exposed users are obtained, and if the conversion is exposure-click-conversion, all clicked users are obtained, it can be understood that exposure refers to service facing users, such as a card ticket service, and a certain item of card ticket is on-line, and click refers to card ticket service, which is obtained by users, but not used; the conversion refers to whether the user finally downloads or uses the service, such as a card ticket service, and the user finally uses the taken card tickets) as a training sample for model training.
In one embodiment, determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and the prediction model comprises:
determining the conversion end time of the target service;
and determining the conversion rate of the target user in the target service based on the conversion finishing time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model.
In this embodiment, the prediction apparatus for user conversion rate may further determine the conversion end time of the target service, that is, determine the end time of the target service, for example, the end time of the ticket activity, and then determine the conversion rate of the target user in the target service based on the conversion end time of the target service, the actual delay parameter of the target user, the characteristic of the target user, and the prediction model, that is, pre-predict the conversion rate of the target user in the target serviceDuring measurement, the characteristics of the target service distance conversion end time can be taken into account according to the service requirements, that is, after the random delay parameter d is constructed, the current distance conversion end time information T can be taken into accountl-TeD, exposure time distance conversion end time information Tl-TeInputting the characteristics of the target user and the actual delay parameter of the target user into a prediction model to obtain the conversion rate of the target user in the target service, wherein TlIs the conversion end time of the target service, TeIs the exposure time of the target service. Therefore, all time nodes are comprehensively considered, and the conversion rate of the user obtained through prediction is more accurate. Correspondingly, when the model is trained, the current distance conversion end time information T also needs to be comprehensively consideredl-TeD, exposure time distance conversion end time information Tl-TeCharacteristics of the target user, and a random delay parameter of the target user.
In one embodiment, the user conversion rate predicting device further performs the following operations after determining the conversion rate of the target user in the target service:
displaying the conversion rate of the target user in the target service;
when the conversion period of the target service is finished, obtaining label data of an object corresponding to the target service, wherein the label data comprises the exposure time of the target service, the conversion time of the object corresponding to the target service, the conversion finishing time of the target service and the characteristics of the object corresponding to the target service;
and (5) optimizing the prediction model by taking the label data as a training sample.
In this embodiment, after the user conversion rate prediction apparatus obtains the conversion rate of the target user on the target service, the conversion rate may be displayed, and when the conversion cycle of the target service is completed, the label data of the user corresponding to the target service is used as a training sample, so as to optimize the prediction model, enrich the training sample of the prediction model, and make the prediction result more accurate.
In summary, it can be seen that, in the embodiment provided by the application, random delay parameters obtained by instantaneous construction of M users without conversion are added to the model for training, and because the sample size of the part is huge, a more excellent prediction model can be obtained by training, so that when the model is used for predicting the conversion rate of the user, a more accurate conversion rate of the user can be obtained.
The following describes a training process of a prediction model, and the training method of the prediction model is to establish the prediction model through data of which a conversion period has ended historically, and perform delay feedback modeling specifically for users with unknown labels. The established prediction model is f (x, d, theta), wherein x is the user characteristic, d is the delay between the exposure time and the current time, and theta is a model parameter. When the prediction model is used, whether f (x, d, theta) is larger than a specified threshold value is judged, if so, the sample label is 1, otherwise, the sample label is 0.
It can be understood that if the business form is just to observe whether the user is converted after exposure, there are two types of label data, the label of the converted user is 1, and the label of the non-converted user is unknown. If the business form has intermediate states besides exposure and conversion, such as exposure-click-conversion, and the previous step is necessary to have the next action, the label of the exposed and un-clicked user is 0, the label of the exposed and converted user is 1, and the label of the exposed and un-converted user is unknown.
Referring to fig. 2, fig. 2 is a schematic diagram of a training process of a prediction model according to an embodiment of the present application, including:
201. and acquiring target data of M users.
In this embodiment, the user conversion rate prediction apparatus may obtain target data of M users, where the target data is data corresponding to the M users and indicating that a historical conversion cycle has ended, and extract data that may have unknown labels (all exposed users if there are two steps of exposure-conversion, and all clicked users if there are two steps of exposure-conversion) as a training sample; the target data includes at least an exposure time, a conversion time for each of the M users, and an end time.
202. And determining the range of the delay parameter of each user in the M users according to the target data.
In this embodiment, the target data may obtain a label of whether the object is finally transformed because of the data of which the transformation period is already finished, and the prediction model needs to construct an untransformed moment according to whether the known data is finally transformed, that is, a delay parameter d needs to be constructed, so that the object is not transformed after the exposure time d; this range should be d e 0, Tmax) Whereas for samples of different labels, TmaxThe values are different, that is, the conversion time is different for different objects.
It should be noted that, assuming that the conversion is finally possible, the label of the user is 1, and the exposure time is TeConversion time of TcThen the constructed delay parameter d range should be 0, Tc-Te) (ii) a If there is eventually no conversion, then the user tag is 0, assuming that the latest time allowed for conversion is TlThen the range of d constructed should be [0, Tl-Te)。
203. And determining the random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users.
In this embodiment, after obtaining the range of the delay parameter of each of the M users, the user conversion rate predicting apparatus may determine the random delay parameter of each of the M users according to the range of the delay parameter of each of the M users. Specifically, the range of the delay parameter of each of the M users may be calculated based on a preset rule to obtain a random delay parameter of each of the M users, where the preset rule at least includes one of the following rules: exponential distribution, power-law distribution, normal distribution, bernoulli distribution, and numerical models. The following description will take a preset rule as an example of exponential distribution to generate random delay parameters:
after obtaining the range of the delay parameter d, the randomly generated d in this range should also conform to the true distribution, so that the problem of inconsistent distribution of the training and prediction samples does not occur. The delay parameters of the conventional delay feedback can be represented by an exponential distribution P (d ═ k ═ λ e)-λkE is a constant, k is a variable, for example, the conversion time of the user is conversion within 10 days after exposure, the range of the delay parameter of the user is [0,9 ], that is, the value of k is [0,9), wherein the parameter λ can pass through
To calculate ciIndicates the number of samples whose sample transition time occurs at the post-exposure time i, and since d ranges from 0, Tmax) The probability function generated in this range is therefore a normalized exponential distribution:
thereby ensuring
Has a value of 1.
When the range of the delay parameter is known, the random delay parameter d is generated from a certain distribution, which is not necessarily an exponential distribution, but may be generated from a distribution corresponding to the actual traffic, such as a power-law distribution, a normal distribution, a bernoulli distribution, or the like, or may be generated by directly counting the ratio of the real delay without generating a numerical model:
the method is not particularly limited as long as the random delay parameter of each of the M users can be obtained.
204. The characteristics of each of the M users are obtained.
In this embodiment, the user conversion rate prediction device may obtain the characteristics of each of the M users, and the characteristics of the users corresponding to different services are different, where the user conversion rate prediction device may obtain the corresponding characteristics according to the prediction model to be trained.
It should be noted that, the random delay parameter of each user in the M users may be determined through steps 201 to 203, and the characteristics of each user in the M users may be obtained through step 204, however, there is no limitation on the execution sequence between steps 201 to 203 and step 204, and step 201 to step 203 may be executed first, step 204 may be executed first, or step 204 may be executed simultaneously, which is not limited specifically.
205. And carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain a prediction model.
In this embodiment, after obtaining the random delay parameter of each of the M users and the feature of each of the M users, the user conversion rate prediction apparatus may perform model training on the random delay parameter of each of the M users and the feature of each of the M users to obtain a prediction model.
It should be noted that, during model training, the characteristics of distance conversion end can be taken into account according to the service requirement, that is, after the random delay parameter d is constructed, the current distance conversion end time information T can be taken into accountl-TeD, exposure time distance conversion end time information Tl-TeAnd adding the features of the user and the random delay parameters of the user into the model for training.
In summary, it can be seen that in the embodiment provided by the application, in the process of model training, random delay model parameters are constructed at the moment that each user in M users is not transformed yet, and because the sample size of the part is huge, a more excellent prediction model can be trained, so that the prediction is more accurate when the prediction model is used on line.
The present application is described above from the viewpoint of a method for predicting user conversion rate, and the present application is described below from the viewpoint of a device for predicting user conversion rate.
Referring to fig. 3, fig. 3 is a schematic view of a virtual structure of a device for predicting user conversion rate according to an embodiment of the present application, including:
a first determining unit 301, configured to determine a feature of a target user, where the target user is an object to be predicted and is associated with a target service;
a second determining unit 302, configured to determine an exposure time of the target service;
a third determining unit 303, configured to determine an actual delay parameter of the target user according to the exposure time of the target service and the current time;
a predicting unit 304, configured to determine a conversion rate of the target user in the target service based on an actual delay parameter of the target user, a feature of the target user, and a prediction model, where the prediction model corresponds to the target service, and the prediction model is obtained by training a training sample, and the training sample includes features of M users and random delay parameters corresponding to the M users, where the random delay parameters corresponding to the M users are determined according to conversion durations of the M users, and M is a positive integer greater than or equal to 1.
Optionally, the device for predicting user conversion rate further includes:
a training unit 305, the training unit 305 to:
acquiring target data of the M users;
determining the range of the delay parameter of each user in the M users according to the target data;
determining a random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users;
acquiring the characteristics of each user in the M users;
and carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain the prediction model.
Optionally, the determining, by the training unit, the random delay parameter of each of the M users according to the range of the delay parameter of each of the M users includes:
calculating the range of the delay parameter of each of the M users based on a preset rule to obtain a random delay parameter of each of the M users, wherein the preset rule at least includes one of the following rules: exponential, power-law, normal, and bernoulli distributions.
Optionally, the prediction unit 304 is specifically configured to:
determining the conversion end time of the target service;
and predicting the target user based on the conversion finishing time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model to obtain the prediction result.
Optionally, the apparatus further comprises:
a processing unit 306, the processing unit 306 being configured to:
displaying the conversion rate of the target user in the target service;
when the conversion period of the target service is finished, obtaining label data of an object corresponding to the target service, wherein the label data comprises the exposure time of the target service, the conversion time of the object corresponding to the target service, the conversion finishing time of the target service and the characteristics of the object corresponding to the target service;
and optimizing the prediction model by using the label data as a training sample.
In summary, it can be seen that, in the embodiment provided by the application, random delay parameters obtained by instant construction of M users which are not transformed are added into a model for training, and because the sample size of the random delay parameters is huge, a more excellent prediction model can be obtained by training, so that the prediction accuracy can be improved when the random delay parameters are applied on line.
The embodiment of the present application further provides another device for predicting user conversion rate, as shown in fig. 4, for convenience of description, only the relevant portions of the embodiment of the present application are shown, and details of the specific technology are not disclosed, please refer to the method portion of the embodiment of the present application. The device for predicting the user conversion rate may be a terminal, and the terminal may be any terminal device including a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a vehicle-mounted computer, and the like, taking the terminal as the mobile phone as an example:
fig. 4 is a block diagram illustrating a partial structure of a mobile phone related to a terminal provided in an embodiment of the present application. Referring to fig. 4, the handset includes: radio Frequency (RF) circuit 410, memory 420, input unit 430, display unit 440, sensor 450, audio circuit 460, wireless fidelity (WiFi) module 470, processor 480, and power supply 490. Those skilled in the art will appreciate that the handset configuration shown in fig. 4 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The following describes each component of the mobile phone in detail with reference to fig. 4:
the RF circuit 410 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 480; in addition, the data for designing uplink is transmitted to the base station. In general, the RF circuit 410 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuitry 410 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.
The memory 420 may be used to store software programs and modules, and the processor 480 executes various functional applications and data processing of the mobile phone by operating the software programs and modules stored in the memory 420. The memory 420 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The input unit 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone. Specifically, the input unit 430 may include a touch panel 431 and other input devices 432. The touch panel 431, also called a touch screen, may collect touch operations of a user on or near the touch panel 431 (e.g., operations of the user on or near the touch panel 431 using any suitable object or accessory such as a finger or a stylus) and drive the corresponding connection device according to a preset program. Alternatively, the touch panel 431 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 480, and receives and executes commands sent from the processor 480. In addition, the touch panel 431 may be implemented in various types, such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. The input unit 430 may include other input devices 432 in addition to the touch panel 431. In particular, other input devices 432 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.
The display unit 440 may be used to display information input by the user or information provided to the user and various menus of the cellular phone. The Display unit 440 may include a Display panel 441, and optionally, the Display panel 441 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 431 may cover the display panel 441, and when the touch panel 431 detects a touch operation on or near the touch panel 431, the touch panel is transmitted to the processor 480 to determine the type of the touch event, and then the processor 480 provides a corresponding visual output on the display panel 441 according to the type of the touch event. Although the touch panel 431 and the display panel 441 are shown in fig. 4 as two separate components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 431 and the display panel 441 may be integrated to implement the input and output functions of the mobile phone.
The handset may also include at least one sensor 450, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display panel 441 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 441 and/or the backlight when the mobile phone is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured on the mobile phone, further description is omitted here.
WiFi belongs to short-distance wireless transmission technology, and the mobile phone can help a user to receive and send e-mails, browse webpages, access streaming media and the like through the WiFi module 470, and provides wireless broadband Internet access for the user. Although fig. 4 shows the WiFi module 470, it is understood that it does not belong to the essential constitution of the handset, and can be omitted entirely as needed within the scope not changing the essence of the invention.
The processor 480 is a control center of the mobile phone, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone and processes data by operating or executing software programs and/or modules stored in the memory 420 and calling data stored in the memory 420, thereby integrally monitoring the mobile phone. Optionally, processor 480 may include one or more processing units; preferably, the processor 480 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 480.
The handset also includes a power supply 490 (e.g., a battery) for powering the various components, which may preferably be logically connected to the processor 480 via a power management system, so that the power management system may perform functions such as managing charging, discharging, and power consumption.
Although not shown, the mobile phone may further include a camera, a bluetooth module, etc., which are not described herein.
In the embodiment of the present application, the steps performed by the user conversion rate predicting device may be performed by the processor 480 included in the terminal.
Fig. 5 is a schematic diagram of a server structure provided by an embodiment of the present application, where the server 500 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 522 (e.g., one or more processors) and a memory 532, and one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 542 or data 544. Memory 532 and storage media 530 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 522 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the server 500.
The server 500 may also include one or more power supplies 526, one or more wired or wireless network interfaces 550, one or more input-output interfaces 558, and/or one or more operating systems 541, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
The steps performed by the prediction means of the user conversion rate in the above embodiment may be based on the server configuration shown in fig. 5.
The embodiment of the present application further provides a computer-readable storage medium, on which a program is stored, and the program, when executed by a processor, implements the steps of the method for predicting user conversion rate.
The embodiment of the application further provides a processor, wherein the processor is used for executing a program, and the program executes the steps of the user conversion rate prediction method when running.
The embodiment of the application further provides a terminal device, which includes a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the program code is loaded and executed by the processor to implement the steps of the user conversion rate prediction method.
The present application also provides a computer program product adapted to perform the steps of the user conversion rate prediction method described above when executed on a data processing device.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
It should also be noted that 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 the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for predicting user conversion rate, comprising:
determining the characteristics of a target user, wherein the target user is an object to be predicted and is associated with a target service;
determining the exposure time of the target service;
determining an actual delay parameter of the target user according to the exposure time and the current time of the target service;
determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and a prediction model, wherein the prediction model corresponds to the target service and is obtained by training a training sample, the training sample comprises the characteristics of M users and random delay parameters corresponding to the M users, the random delay parameters corresponding to the M users are determined according to the conversion duration of the M users, and M is a positive integer greater than or equal to 1.
2. The method of claim 1, further comprising:
acquiring target data of the M users;
determining the range of the delay parameter of each user in the M users according to the target data;
determining a random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users;
acquiring the characteristics of each user in the M users;
and carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain the prediction model.
3. The method of claim 2, wherein the determining the random delay parameter for each of the M users according to the range of the delay parameter for each of the M users comprises:
calculating the range of the delay parameter of each of the M users based on a preset rule to obtain a random delay parameter of each of the M users, wherein the preset rule at least includes one of the following rules: exponential, power-law, normal, and bernoulli distributions.
4. The method according to any one of claims 1 to 3, wherein the determining the conversion rate of the target user in the target service based on the actual delay parameter of the target user, the characteristics of the target user and a prediction model comprises:
determining the conversion end time of the target service;
and determining the conversion rate of the target user in the target service based on the conversion finishing time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model.
5. The method according to any one of claims 1 to 3, further comprising:
displaying the conversion rate of the target user in the target service;
when the conversion period of the target service is finished, obtaining label data of an object corresponding to the target service, wherein the label data comprises the exposure time of the target service, the conversion time of the object corresponding to the target service, the conversion finishing time of the target service and the characteristics of the object corresponding to the target service;
and optimizing the prediction model by using the label data as a training sample.
6. An apparatus for predicting user conversion rate, comprising:
the system comprises a first determining unit, a second determining unit and a third determining unit, wherein the first determining unit is used for determining the characteristics of a target user, the target user is an object to be predicted, and the target user is associated with a target service;
a second determining unit, configured to determine an exposure time of the target service;
a third determining unit, configured to determine an actual delay parameter of the target user according to the exposure time of the target service and the current time;
the prediction unit is configured to determine a conversion rate of the target user in the target service based on an actual delay parameter of the target user, a feature of the target user, and a prediction model, where the prediction model corresponds to the target service, the prediction model is obtained by training a training sample, and the training sample includes features of M users and random delay parameters corresponding to the M users, where the random delay parameters corresponding to the M users are determined according to conversion durations of the M users, and M is a positive integer greater than or equal to 1.
7. The apparatus for predicting user conversion rate of claim 6, further comprising:
a training unit to:
acquiring target data of the M users;
determining the range of the delay parameter of each user in the M users according to the target data;
determining a random delay parameter of each user in the M users according to the range of the delay parameter of each user in the M users;
acquiring the characteristics of each user in the M users;
and carrying out model training on the random delay parameter of each user in the M users and the characteristics of each user in the M users to obtain the prediction model.
8. The apparatus of claim 7, wherein the training unit determines the random delay parameter for each of the M users according to the range of the delay parameter for each of the M users comprises:
calculating the range of the delay parameter of each of the M users based on a preset rule to obtain a random delay parameter of each of the M users, wherein the preset rule at least includes one of the following rules: exponential, power-law, normal, and bernoulli distributions.
9. The apparatus according to any one of claims 6 to 8, wherein the prediction unit is specifically configured to:
determining the conversion end time of the target service;
determining the conversion rate of the target user in the target service based on the conversion end time of the target service, the actual delay parameter of the target user, the characteristics of the target user and the prediction model。
10. A computer-readable storage medium, comprising instructions which, when executed on a computer, cause the computer to perform the steps of the method of predicting user conversion rate of any of the preceding claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010565072.6A CN113822435B (en) | 2020-06-19 | 2020-06-19 | Prediction method of user conversion rate and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010565072.6A CN113822435B (en) | 2020-06-19 | 2020-06-19 | Prediction method of user conversion rate and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113822435A true CN113822435A (en) | 2021-12-21 |
| CN113822435B CN113822435B (en) | 2023-11-03 |
Family
ID=78924583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010565072.6A Active CN113822435B (en) | 2020-06-19 | 2020-06-19 | Prediction method of user conversion rate and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822435B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350351A (en) * | 2023-12-04 | 2024-01-05 | 支付宝(杭州)信息技术有限公司 | Training method of user response prediction system, user response prediction method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150339570A1 (en) * | 2014-05-22 | 2015-11-26 | Lee J. Scheffler | Methods and systems for neural and cognitive processing |
| US20160191336A1 (en) * | 2013-09-06 | 2016-06-30 | Huawei Technologies Co., Ltd. | Network performance prediction method and apparatus |
| US20170140433A1 (en) * | 2015-11-17 | 2017-05-18 | At&T Intellectual Property I, Lp | Dynamic Predictive Analytics For Targeted Advertising |
| US20170286997A1 (en) * | 2016-04-05 | 2017-10-05 | Facebook, Inc. | Advertisement conversion prediction based on unlabeled data |
| US20180150874A1 (en) * | 2016-11-30 | 2018-05-31 | Facebook, Inc. | Conversion optimization with long attribution window |
| CN110415032A (en) * | 2019-07-24 | 2019-11-05 | 深圳乐信软件技术有限公司 | A kind of exposure conversion ratio predictor method, device, equipment and storage medium |
| WO2019218751A1 (en) * | 2018-05-16 | 2019-11-21 | 阿里巴巴集团控股有限公司 | Processing method, apparatus and device for risk prediction of insurance service |
| CN110490334A (en) * | 2019-08-27 | 2019-11-22 | 上海丙晟科技有限公司 | A kind of machine learning of low latency is the generation method of service |
| CN110570232A (en) * | 2019-08-05 | 2019-12-13 | 科大讯飞股份有限公司 | Internet advertisement putting method, device, server and storage medium |
| CN111159241A (en) * | 2019-12-20 | 2020-05-15 | 深圳前海微众银行股份有限公司 | Click conversion estimation method and device |
-
2020
- 2020-06-19 CN CN202010565072.6A patent/CN113822435B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160191336A1 (en) * | 2013-09-06 | 2016-06-30 | Huawei Technologies Co., Ltd. | Network performance prediction method and apparatus |
| US20150339570A1 (en) * | 2014-05-22 | 2015-11-26 | Lee J. Scheffler | Methods and systems for neural and cognitive processing |
| US20170140433A1 (en) * | 2015-11-17 | 2017-05-18 | At&T Intellectual Property I, Lp | Dynamic Predictive Analytics For Targeted Advertising |
| US20170286997A1 (en) * | 2016-04-05 | 2017-10-05 | Facebook, Inc. | Advertisement conversion prediction based on unlabeled data |
| US20180150874A1 (en) * | 2016-11-30 | 2018-05-31 | Facebook, Inc. | Conversion optimization with long attribution window |
| WO2019218751A1 (en) * | 2018-05-16 | 2019-11-21 | 阿里巴巴集团控股有限公司 | Processing method, apparatus and device for risk prediction of insurance service |
| CN110415032A (en) * | 2019-07-24 | 2019-11-05 | 深圳乐信软件技术有限公司 | A kind of exposure conversion ratio predictor method, device, equipment and storage medium |
| CN110570232A (en) * | 2019-08-05 | 2019-12-13 | 科大讯飞股份有限公司 | Internet advertisement putting method, device, server and storage medium |
| CN110490334A (en) * | 2019-08-27 | 2019-11-22 | 上海丙晟科技有限公司 | A kind of machine learning of low latency is the generation method of service |
| CN111159241A (en) * | 2019-12-20 | 2020-05-15 | 深圳前海微众银行股份有限公司 | Click conversion estimation method and device |
Non-Patent Citations (2)
| Title |
|---|
| 赵杨;袁析妮;陈亚文;武立强;: "基于机器学习混合算法的APP广告转化率预测研究", 数据分析与知识发现, no. 11 * |
| 颜金尧 等: "计算广告中的点击率和转化率预测研究", 《中国传媒大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350351A (en) * | 2023-12-04 | 2024-01-05 | 支付宝(杭州)信息技术有限公司 | Training method of user response prediction system, user response prediction method and device |
| CN117350351B (en) * | 2023-12-04 | 2024-03-05 | 支付宝(杭州)信息技术有限公司 | Training method of user response prediction system, user response prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113822435B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110364144B (en) | Speech recognition model training method and device | |
| CN110634474B (en) | Speech recognition method and device based on artificial intelligence | |
| CN109033156B (en) | Information processing method and device and terminal | |
| CN110069715A (en) | A kind of method of information recommendation model training, the method and device of information recommendation | |
| CN111432347B (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN111353299B (en) | Dialog scene determining method based on artificial intelligence and related device | |
| CN112735418B (en) | Voice interaction processing method, device, terminal and storage medium | |
| CN110209778A (en) | A kind of method and relevant apparatus of dialogue generation | |
| CN114357278B (en) | Topic recommendation method, device and equipment | |
| CN113821720A (en) | Behavior prediction method and device and related product | |
| CN110910964A (en) | Intermolecular binding activity prediction method and device | |
| CN111612178A (en) | Model diagnosis method and related equipment | |
| CN111522592A (en) | Intelligent terminal awakening method and device based on artificial intelligence | |
| CN113822460A (en) | Traffic flow prediction method and device, electronic equipment and storage medium | |
| CN108053826A (en) | For the method, apparatus of human-computer interaction, electronic equipment and storage medium | |
| CN113220848A (en) | Automatic question answering method and device for man-machine interaction and intelligent equipment | |
| CN112907255A (en) | User analysis method and related device | |
| CN113822435B (en) | Prediction method of user conversion rate and related equipment | |
| CN113569572A (en) | Text entity generation method, model training method and device | |
| CN111553163A (en) | Text relevance determining method and device, storage medium and electronic equipment | |
| CN111709789B (en) | Method for determining user conversion rate and related equipment | |
| CN114430504B (en) | Recommendation method and related device for media content | |
| CN115392405A (en) | Model training method, related device and storage medium | |
| CN116933149A (en) | Object intention prediction method and device, electronic equipment and storage medium | |
| CN115080840A (en) | Content pushing method and device and storage medium |
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 |