CN113743636B - Target operation prediction method and device, electronic equipment and storage medium - Google Patents
Target operation prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113743636B CN113743636B CN202010469618.8A CN202010469618A CN113743636B CN 113743636 B CN113743636 B CN 113743636B CN 202010469618 A CN202010469618 A CN 202010469618A CN 113743636 B CN113743636 B CN 113743636B
- Authority
- CN
- China
- Prior art keywords
- account
- target operation
- historical
- data
- browsing
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims description 162
- 238000010801 machine learning Methods 0.000 claims description 32
- 238000013507 mapping Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 description 20
- 238000006243 chemical reaction Methods 0.000 description 15
- 238000005457 optimization Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000003213 activating effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The disclosure provides a target operation prediction method, a target operation prediction device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring operation intention characteristic data of an account to be predicted, wherein the operation intention characteristic data comprises characteristic data representing the preference degree of the account to a target operation, and the target operation comprises an operation performed after the account browses a push object; estimating a second association degree of the operation intention feature of the account to be predicted and a target operation result through the operation intention feature of each historical account and the first association degree of the target operation result determined by the time length data of the push object browsed by each historical account; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not. The method provides a new way of predicting the target operation.
Description
Technical Field
The disclosure relates to the field of computer technology, and in particular, to a target operation prediction method, a target operation prediction device, electronic equipment and a storage medium.
Background
In the related art, when a user is predicted to perform a specified operation after aiming at a push object, for example, the user is predicted to purchase a push commodity in an internet electronic commerce and the like, the user is often predicted to perform the specified operation aiming at the push object by acquiring historical data comprising operation characteristic data of the user and operation results of whether the user performs the specified operation or not, and analyzing a data association relationship between the operation characteristic data of the user and the operation results of whether the user performs the specified operation or not based on the acquired historical data, so that whether an account to be predicted performs the specified operation aiming at the push object or not is estimated based on the data association relationship and the user operation characteristic data of the user to be predicted; if the pushing object is a commodity and the designated operation is to purchase the commodity, the historical data containing the commodity purchase result is required to be obtained, and whether the user can purchase the pushed commodity is further predicted based on the commodity purchase result and the user operation characteristic data in the obtained historical data; if the pushing object is an application and the designated operation is a downloaded application, historical data containing an application downloading result needs to be acquired, and whether the user downloads the pushed application or not is estimated based on application downloading information and user operation characteristic data in the acquired historical data.
However, in the above prediction process, it is required to obtain the history data including the operation result of whether the user performs the specified operation, and these history data are usually stored in the server of the specific platform, for example, the history data including the purchase result of the commodity is stored in the server of the e-commerce platform, the history data including the download result of the application is stored in the server of the application operation platform, and authorization of the specific platform is required to obtain these history data, so the above method for predicting whether the user performs the specified operation has a great limitation, and how to predict whether the user performs the specified operation is a problem to be considered if the history data including the operation result of whether the user performs the specified operation is not obtained.
Disclosure of Invention
The embodiment of the disclosure provides a target operation prediction method, a target operation prediction device, electronic equipment and a storage medium, and provides a new target operation prediction method.
In a first aspect of the present disclosure, a target operation prediction method is provided, including:
acquiring operation intention characteristic data of an account to be predicted, wherein the operation intention characteristic data comprises characteristic data representing the preference degree of the account to a target operation, and the target operation comprises an operation performed after the account browses a push object;
Estimating a second association degree of the operation intention characteristic data of the account to be predicted and a target operation result through the first association degree of the operation intention characteristic data of each historical account and the target operation result determined by the time length data of the push object browsed by each historical account; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not.
In a possible implementation manner, the first association degree of the target operation result determined by the operation intention characteristic data of each historical account and the time length data of the push object browsed by each historical account is used for estimating the second association degree of the operation intention characteristic data of the account to be predicted and the target operation result; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the step comprises the following steps:
The operation intention prediction model is used for inputting the operation intention characteristic data of the accounts to be predicted, and obtaining the operation intention probability value of the target operation performed by the accounts to be predicted, which is output by the operation intention prediction model, wherein the operation intention prediction model is obtained by training a training sample by adopting the operation intention characteristic data of each historical account and the time length data of each historical account for browsing a pushing object based on a machine learning method.
In one possible implementation, the trained operational intent prediction model is obtained by:
extracting operation intention characteristic data of a historical account in each training sample and duration data of a browsing push object of the historical account;
according to the time length data of the historical account browsing pushing object in each training sample, determining a target operation result corresponding to each training sample;
and obtaining the trained operation intention prediction model by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result and adjusting the operation intention prediction model obtained by the historical training or the operation intention prediction model which is initially created through machine learning.
In one possible implementation manner, the step of determining the target operation result of the history object in each training sample according to the time length data of the history account browsing push object in each training sample includes:
According to the time length data of the historical account browsing push object in each training sample, determining a target operation result corresponding to the training sample with the time length of the historical account browsing push object not smaller than a set time length threshold value as a first result of the target operation, and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold value as a second result without performing the target operation.
In one possible implementation, the method further includes: and determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
In one possible implementation manner, the set duration threshold is determined according to duration data of a first set number of historical objects browsing push objects and corresponding real target operation results.
In one possible implementation, the method further includes:
Determining historical browsing object data in a set time before the current time as the training sample; or (b)
And determining the second set number of historical browsing object data before the current time as the training sample.
In a second aspect of the present disclosure, there is provided a target operation prediction apparatus including:
The device comprises an intention feature acquisition unit, a push object pushing unit and a push object pushing unit, wherein the intention feature acquisition unit is configured to execute operation intention feature data of an account to be predicted, the operation intention feature data comprises feature data representing preference degree of the account on target operation, and the target operation comprises operation performed after the account browses the push object;
A target operation prediction unit configured to perform a first degree of association of target operation results determined by operation intention feature data of each history account and duration data of a push object browsed by each history account, and estimate a second degree of association of the operation intention feature data of the account to be predicted with the target operation results; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not.
In one possible implementation, the target operation prediction unit is specifically configured to perform:
The operation intention prediction model is used for inputting the operation intention characteristic data of the accounts to be predicted, and obtaining the operation intention probability value of the target operation performed by the accounts to be predicted, which is output by the operation intention prediction model, wherein the operation intention prediction model is obtained by training a training sample by adopting the operation intention characteristic data of each historical account and the time length data of each historical account for browsing a pushing object based on a machine learning method.
In one possible implementation, the target operation prediction unit is further configured to perform:
The trained operational intent estimation model is obtained by:
extracting operation intention characteristic data of a historical account in each training sample and duration data of a browsing push object of the historical account;
according to the time length data of the historical account browsing pushing object in each training sample, determining a target operation result corresponding to each training sample;
and obtaining the trained operation intention prediction model by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result and adjusting the operation intention prediction model obtained by the historical training or the operation intention prediction model which is initially created through machine learning.
In one possible implementation, the target operation prediction unit is specifically configured to perform:
According to the time length data of the historical account browsing push object in each training sample, determining a target operation result corresponding to the training sample with the time length of the historical account browsing push object not smaller than a set time length threshold value as a first result of the target operation, and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold value as a second result without performing the target operation.
In one possible implementation, the target operation prediction unit is further configured to perform:
and determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
In one possible implementation manner, the set duration threshold is determined according to duration data of a first set number of historical objects browsing push objects and corresponding real target operation results.
In one possible implementation, the target operation prediction unit is further configured to perform:
Determining historical browsing object data in a set time before the current time as the training sample; or (b)
And determining the second set number of historical browsing object data before the current time as the training sample.
In a third aspect of the disclosure, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of the first aspect and one of the possible implementations when executing the program.
In a fourth aspect of the disclosure, there is provided a computer readable storage medium storing computer instructions that, when run on a computer, cause the computer to perform a method as described in any one of the first aspect and one of the possible implementations.
The scheme of the present disclosure brings at least the following beneficial effects:
In the method, the label of the operation result of the target operation of the training sample is determined according to the duration of the browse object, and then the first association degree of the operation intention characteristic data of the historical account in the training sample and the target operation result determined by the duration data of the browse push object of the historical account are utilized to estimate the second association degree of the operation intention characteristic data of the account to be predicted and the target operation result, and the second association degree is converted into the operation intention probability value of the target operation after the browse push object of the account to be predicted, so that the actual target operation result data of whether the target operation is performed by the historical account is not required to be acquired from a specific platform in the process, and a new mode for predicting the target operation is provided.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
Fig. 1 is a schematic diagram of an application scenario provided in an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a target operation prediction method according to an exemplary embodiment of the present disclosure;
FIG. 3 is a schematic diagram of an acquisition flow of a currently used machine learning model provided by an exemplary embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an acquisition flow of another currently used machine learning model provided by an exemplary embodiment of the present disclosure;
fig. 5 is a flowchart of obtaining a set duration threshold according to an exemplary embodiment of the present disclosure;
fig. 6 is a schematic structural view of a target operation prediction apparatus according to an exemplary embodiment of the present disclosure;
Fig. 7 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
In order to facilitate a better understanding of the technical solutions of the present disclosure by those skilled in the art, the technical terms related to the present disclosure are described below.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein.
Pushing an object: including objects pushed to an account over a network. The pushing object in the embodiment of the disclosure may include, but is not limited to, website links, that is, the pushing object may be an advertisement object detail webpage of an internet electronic commerce platform, such as an article detail page corresponding to the article links or an application detail page corresponding to the application links, where the application may be, but is not limited to, one or more of a game application, an information application, and an instant messaging application; the account includes an identification of the user at a particular platform, and in the embodiment of the present disclosure, the account is sometimes expressed synonymously with the user.
Target operation: the method comprises the operation performed after the account browses the push object. If the pushing object is an item detail page, the target operation may be an operation of adding an item corresponding to the item detail page into the electronic shopping cart, or the target operation may be an operation of transferring electronic resources to an item corresponding to the item detail page; when the pushing object is an application detail page, the target operation may be an operation of activating an application corresponding to the application detail page, or an operation of downloading the application corresponding to the application detail page, or an operation of transferring an electronic resource to obtain a use permission of the application corresponding to the application detail page; the above-mentioned electronic resources include funds such as legal notes, electronic money, etc. for purchasing the use authority of goods or applications, etc.; the above-mentioned electronic money refers to money stored in electronic form in an electronic wallet (such as QQ wallet, letter wallet, etc.) held by an account, and the electronic money may include, but is not limited to, electronic bill, digital money (an unregulated, digitized money), and the like.
And (3) a terminal: may be a mobile terminal, a fixed terminal, or a portable terminal, such as a mobile handset, a site, a unit, a device, a multimedia computer, a multimedia tablet, an internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a Personal Communications System (PCS) device, a personal navigation device, a Personal Digital Assistant (PDA), an audio/video player, a digital camera/camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including the accessories and peripherals of these devices, or any combination thereof.
The following is a description of the design concept of the present disclosure.
In the related art, in the process of predicting whether a user performs a specified operation on a push object, generally, historical data including operation feature data of the user and operation results of whether the user performs the specified operation are obtained, and a data association relationship between the user operation feature data and the operation results in the obtained historical data is analyzed, so that whether the user to be predicted performs the specified operation on the push object is estimated based on the analysis results and the user operation feature data of the user to be predicted.
In the internet e-commerce, e-commerce advertisements are an important category, and the purpose of the e-commerce advertisements is to guide users to enter commodity detail pages linked with commodities of an advertiser, complete appointed operation of purchasing the corresponding commodities and promote sales of the corresponding commodities of the advertiser; the electronic commerce advertisement generally comprises a flow party, an advertisement platform and an advertiser, wherein the flow party provides flow service required by the whole process, the advertisement platform provides a platform of the electronic commerce advertisement, the advertiser can push own commodity to a user in a commodity link mode through the advertisement platform, and the user can click the commodity link to enter a commodity detail page so as to purchase the corresponding commodity; the electronic commerce advertisement is generally realized through a mechanism of information flow bidding advertisement CPA (Cost Per Action) or OCPC (Optimized Cost Per Click) at present, in the mode, an advertiser sets up an optimization target (namely the specified operation) and a bid (selling price) for the optimization target of the electronic commerce advertisement as the basis of bidding of an advertisement platform, namely the core logic of the electronic commerce advertisement is to calculate expected income ecpm of the advertiser based on the following formula 1, and the higher the ecpm is, the more likely the advertisement platform wins from bidding, so that the traffic of the advertisement is obtained; under this scenario, the advertisement platform estimates the click rate ctr and conversion rate cvr of clicking a certain advertisement (i.e. the commodity link) by the user through machine learning and deep learning technologies, and the more accurate the estimation is, the larger the income brought to the advertiser and the advertisement platform is.
Equation 1: ecpm = cpabid x cvr x ctr;
Ecpm in the formula 1 is expected income, and represents income brought by pushing commodity links for advertisers for a set number of times on an advertising platform; ctr is the click rate, and represents the probability of clicking the pushed commodity link by the user; cvr is a conversion rate, which represents the ratio of the number of times the user purchases the corresponding commodity of the commodity link to the pushing number of times of the commodity link; the cpa_bid is a bid (selling price) of an optimization target, the optimization target is that the cpa_bid can be 100 yuan when selling goods, namely, the bid of an advertiser for one of the goods is 100 yuan, the optimization target is that the cpa_bid can be 40 yuan when activating an application, namely, the bid of the advertiser for one operation of activating the application is 40 yuan, and the like.
When the click rate ctr and the conversion rate cvr are estimated by using a machine learning technology, historical click data and conversion data related to the pushing object are needed to complete training and online service of a machine learning model in machine learning; at present, some flow parties and advertisement platforms are integrated, namely, some flow parties build the advertisement platform by themselves, if an advertiser performs an electronic commerce advertisement on the advertisement platform, the corresponding clicking data (such as clicking the data of commodity links into commodity detail pages) and conversion data (such as clicking the data of commodities corresponding to commodity links and shopping list and purchasing the data of commodities corresponding to commodity links) are smooth, the advertisement platform can directly acquire historical clicking data and conversion data, a machine learning model is trained based on the historical clicking data and conversion data to complete estimation of commodity conversion rate cvr (namely, the probability that a user purchases the commodity corresponding to the pushed commodity links), and then the advertisement platform can provide the estimated conversion rate as an optimization target for the advertiser to select.
However, if the flow party and the advertisement platform are not one platform, the data acquisition link of the conversion data of the electronic commercial advertisement is limited, the advertisement platform cannot acquire the historical conversion data, and further the machine learning model cannot be trained based on the historical conversion data to complete estimation of the commodity conversion rate cvr; similarly, if the optimization objective of the advertiser is to activate the application, the advertisement platform cannot obtain the conversion rate of the application activated by the user (i.e. the ratio of the number of times the application is activated by the user to the number of times the application is pushed by the advertisement platform), and further cannot predict the conversion rate of the application activation based on machine learning, so how to predict the specified operation of the account is a problem to be considered under the condition that the historical data including the actual operation result of the specified operation is not obtained.
In view of this, the present disclosure designs a target operation prediction method, apparatus, electronic device, and storage medium for optimizing a prediction process of a target operation; considering whether the account performs the target operation on the push object (i.e. the above-mentioned designated operation on the push object), the higher the interest level of the account in the push object, the more likely the account performs the target operation on the push object, and the information of browsing the push object by the account can reflect the interest level of the account in the push object to a great extent. Therefore, under the condition that the historical browsing object data containing the operation result of the historical account on the pushing object is not obtained, the embodiment of the application considers the information of browsing the pushing object according to the historical account to determine the interested degree of the historical account on the pushing object, and further determines whether the historical account is subjected to the approximate target operation result of the target operation or not based on the interested degree of the historical account on the pushing object; and further, estimating a second association degree of the operation intention characteristic data of the account to be predicted and the target operation result by using a first association degree of the operation intention characteristic data of the historical account (namely the user operation characteristic data) and the approximate target operation result of the historical account, and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation.
The browsing duration can reflect the preference degree of the account to the push object to a large extent in the information of the account browsing push object, so that when the approximate target operation result of the historical account is determined according to the information of the historical account browsing push object, the approximate target operation result of the historical account can be determined according to the duration information of the historical account browsing push object.
The following describes the aspects of the present disclosure in detail with reference to the accompanying drawings:
as shown in fig. 1, an embodiment of the present disclosure provides an application scenario, where the application scenario includes at least one terminal 101 and a server 102, where:
The server 102 is configured to send a push object to an account logged in by the user terminal, obtain operation intention feature data of an account to be predicted, and estimate a second association degree of the operation intention feature data of the account to be predicted and a target operation result by using the first association degree of the operation intention feature data of each history account and the target operation result determined by the time length data of each history account browsing the push object; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for carrying out the target operation.
The terminal 101 is configured to log in an account according to an instruction of a user, browse a push object sent by the server 102 according to an instruction of the user, and perform a target operation after browsing the push object according to an instruction of the user.
As shown in fig. 2, an embodiment of the present disclosure provides a target operation prediction method, which specifically includes the following steps:
Step S201, obtaining operation intention feature data of an account to be predicted, where the operation intention feature data includes feature data representing a preference degree of the account for a target operation, and the target operation includes an operation performed after the account browses a push object.
As an embodiment, the operation intention may include at least one feature data of an account feature of the account to be predicted, a feature of the push object, and a scene feature of the account to be predicted browsing the push object.
The account features may include, but are not limited to, one or more of information in a user profile feature corresponding to the account, a time of account creation, a history of target operations performed on the pushing object by the account, and the like, where the user profile feature may include an age, a gender, a height, a weight, a native place, a national place, a current geographical area, a favorite object type, a occupation, a hobbies, and the like of the user.
When the push object is an advertisement object of an internet e-commerce platform, the feature of the push object may include, but is not limited to, advertisement categories of the push object in the internet advertisement platform, a time period of pushing of the push object in the internet advertisement platform, one or more information among advertiser features of an advertiser to which the push object belongs, where the advertiser features may be identification information of the advertiser, historical sales information of the advertiser, and the like.
The scene feature may include, but is not limited to, one or more of a network connection mode including a terminal logging in an account to be predicted, a type of the terminal, a geographical area where the terminal is currently located, and a current time when the account to be predicted browses the push object, where the network connection mode may include, but is not limited to, a wired network connection or a wireless network connection, such as wifi connection, and the type of the terminal may be a mobile terminal, such as a smart phone, a notebook computer, a multimedia tablet, and the like; or may be a fixed terminal such as a site, desktop computer, internet node, etc.
Step S202, estimating a second association degree of operation intention characteristic data of an account to be predicted and a target operation result through the first association degree of the operation intention characteristic data of each historical account and the target operation result determined by the time length data of each historical account browsing push object; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not.
As an embodiment, in the embodiment of the disclosure, a first association degree of operation intention feature data of each historical account and a target operation result determined by time length data of browsing push objects by each historical account may be learned through machine learning, and based on the learned first association degree, a second association degree of the operation intention feature data of the account to be predicted and the target operation result is calculated, and the estimated second association degree is converted into an operation intention probability value for performing the target operation; the first degree of association may be learned by, but not limited to, a machine learning method such as supervised classification learning, unsupervised classification learning, reinforcement learning, or deep reinforcement learning.
The operation intention probability value in the embodiment of the disclosure may be a value between 0 and 1, where the magnitude of the value represents a probability value of performing a target operation after the account to be tested browses the push object.
The following description of the embodiments of the present disclosure provides a process for estimating an operation intention probability value of a target operation of an account to be predicted by a machine learning method in the above step S202, which is specifically as follows:
Firstly, before estimating an operation intention probability value of target operation of an account to be predicted, using operation intention characteristic data of each historical account and duration data of a push object browsed by the historical account as training samples based on a machine learning method to train to obtain an operation intention prediction model.
When the operation intention probability value of the account to be predicted for target operation is estimated, a trained operation intention prediction model is adopted, the extracted operation intention characteristic data of the account to be predicted is input, and the operation intention probability value of the account to be predicted for target operation, which is output by the operation intention prediction model, is obtained.
The following disclosure provides a training process of an operational intent estimation model, where the training process specifically includes:
firstly, historical browsing object data is obtained as training samples, wherein the historical browsing object data comprises time length data of a historical account browsing pushing object and operation intention characteristic data of a historical account for carrying out target operation.
Further, the historical browsing object data within a set period of time before the current time may be determined as training samples, or the historical browsing object data of a second set number before the current time may be determined as training samples.
As an example, the acquired history browsing object data may have a problem of data missing, such as missing a certain item or items of data in the operation intention feature data, in which case the missing data in the history browsing object data may be processed by setting a character string.
Further training an operation intention prediction model by using the obtained training sample; specifically, an initially created operational intent prediction model may be trained based on an initially obtained training sample; and after the trained operation intention prediction model is obtained in the history training, the operation intention prediction model obtained in the history training is updated according to the newly generated history object browsing data, for example, a training sample is updated according to the newly generated history object browsing data, and the operation intention prediction model obtained in the history training is adjusted by utilizing the operation intention characteristic data of the history account in the updated training sample and a target operation result determined by the time length data of the history account browsing push object, so that the new trained operation prediction model is obtained.
The process of obtaining the trained operational intent prediction model is described in detail below.
First mode of model acquisition: an operational intent prediction model initially created by machine learning is adjusted.
As shown in fig. 3, the training process of the operation intention prediction model in this manner mainly includes the following steps:
step S301, a training sample and an operation intention pre-estimation model which is initially created are obtained.
The initially created operational intent prediction model may be a supervised machine learning model, such as, but not limited to, xgboost models, deep learning models, logistic regression models, and the like.
In this step, each training sample includes operation intention feature data of the historical account and duration data of the historical account browsing push object, and the training sample may be historical browsing object data obtained from a designated platform, such as an internet e-commerce platform, or may be obtained from the historical browsing object data according to other manners, and those skilled in the art may obtain the training sample in this step according to actual requirements.
The training sample in the step can be historical browsing data in a set time period before the current time, such as historical browsing data in a month before the current time; the training samples may also be a set number of historical browsing data before the current time, such as 100 ten thousand historical browsing data before the current time, where the current time may be understood as the time of creating the initial operation intention prediction model or the time of triggering the training operation intention prediction model.
Step S302, extracting operation intention characteristic data of a historical account and duration data of a historical account browsing push object in each training sample.
Because the operation intention feature data in the embodiment of the present disclosure may include a plurality of feature data, in this step, the training sample may be processed by setting a processing manner, so that the operation intention feature data of the history account and the duration data of the history account browsing push object are extracted.
Step S303, according to the time length data of the historical account browsing push objects in each training sample, determining the target operation result of the historical account in each training sample.
In general, the longer the account browses the push object, the greater the possibility that the account performs the target operation after browsing the push object, for example, the longer the account browses the commodity detail page corresponding to the commodity link, the greater the possibility that the account purchases the commodity corresponding to the commodity detail page; and the shorter the time that the account browses the push object, the less the possibility that the account performs the target operation after browsing the push object, so that the target operation result of the target operation performed by the historical account in the training sample can be determined based on the time length data of browsing the push object in the training sample, wherein the target operation result comprises that the target operation is performed or not performed.
Further, in order to facilitate learning of the first association degree between the operation intention feature data of the historical account in the training samples and the target operation result of the historical account, the target operation result of the historical account in each training sample may be marked by a label, for example, the label of the training sample with the target operation result being the target operation is marked as 1, the label of the training sample with the target operation result not being the target operation is marked as 0, and the like, that is, the label of each training sample may be determined by browsing the duration data of the push object through the historical account in each training sample.
Step S304, the operation intention prediction model which is initially created is adjusted through machine learning by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result, and the trained operation intention prediction model is obtained.
The method comprises the steps of inputting operation intention feature data of a historical account in a training sample and a target operation result into an initial created operation intention prediction model, learning a first association degree of the operation intention feature data of the historical account in the training sample and the target operation result by the initial created operation intention prediction model, and adjusting parameters in the initial created operation intention prediction model to obtain a trained operation intention prediction model.
When the operation intention feature data and the target operation result of the historical account in the training sample are input into the initially created intention operation prediction model, the operation intention feature data and the target operation result of the historical account in the training sample can be input into the initially created operation intention prediction model in batches, for example, the operation intention feature data and the target operation result of the historical account in a set number of training samples are input at one time, or the operation intention feature data and the target operation result of the historical account in the training sample in a period of time are input at one time, and the like.
If the target operation result corresponding to the training sample is embodied in the form of a label, the operation intention characteristic data of the historical account in the training sample and the label input operation intention pre-estimated model which is initially created can be trained, and the trained operation intention pre-estimated model is obtained.
After the initial created operation intention prediction model is adjusted to the trained operation intention prediction model, the trained operation intention prediction model can be used for predicting target operation of the account to be predicted, and in the process of predicting target operation of the account to be predicted by using the trained machine learning model, the trained operation intention prediction model can be used as an operation intention prediction model obtained through historical training, and a new trained operation intention prediction model is obtained through retraining, such as a set time period, and the operation intention prediction model obtained through historical training can be adjusted periodically.
The second mode of model acquisition: training the operation intention pre-estimation model obtained through historical training to obtain a new trained operation intention pre-estimation model.
As shown in fig. 4, the training process of the operation intention prediction model in this manner mainly includes the following steps:
Step S401, updating a training sample based on historical browsing object data before the current moment;
it should be noted that, the current time herein may be understood as a time for triggering the update of the operation intention prediction model, such as a time interval between the current time and a time for obtaining the last trained machine learning model reaching the above-mentioned set time period, or a time interval between the current time and a time for triggering the training operation intention prediction model last reaching the above-mentioned set time period, or a time for triggering the update of the operation intention prediction model for some reason, such as service upgrade, etc.
Specifically, the historical browsing object data within a set time period before the current time can be determined as the training sample, for example, the historical browsing object data generated between the current time and the time when the training operation intention estimation model is triggered last time is determined as the training sample; the historical browsing object data of a second set number before the current time can be determined to be training samples; the historical browsing object data in a set time period before the current time and the training sample used for obtaining the predicted model of the previous training operation can be determined as the training sample of the step, for example, the training sample used for obtaining the predicted model of the previous training operation and the historical browsing object data generated between the current time and the time for obtaining the predicted model of the previous training operation are determined as the training sample.
Step S402, determining a target operation result of the historical account in each training sample according to the updated time length data of the historical account browsing object in each training sample.
This step is described with reference to step S303, and will not be repeated here.
Step S403, obtaining an operation intention prediction model after the training by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result through machine learning adjustment history training.
The operation intention feature data of the historical account in the training sample and the corresponding target operation result can be input into a machine learning model for historical training, the machine learning model for historical training learns the mapping relation between the operation intention feature data of the historical account in the training sample and the target operation result, and parameters in an operation intention estimation model obtained through historical training are adjusted to obtain the operation intention estimation model after the current training.
The process of inputting the operation intention feature data and the target operation result in the training sample into the operation intention prediction model obtained by historical training may be referred to the description in step S304, and the description is not repeated here.
As an embodiment, in step S303 and step S402, the target operation result of the history object in each training sample may be determined according to the duration data of the history account browsing push object in each training sample in the following manners.
First operation result determination method:
the method comprises the steps that a target operation result corresponding to a training sample, in which the time length of a historical account browsing push object is not smaller than a set time length threshold, is determined to be a first result of the target operation; and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold as a second result without performing the target operation.
If the target operation result is represented in the form of a label, the first result may be set as a positive sample label and the second result may be set as a negative sample label.
In this way, for the training sample without the duration data of the push object browsed by the history account, the duration of the browse object of the history account can be regarded as zero, and then the target operation result of such training sample is the second result, that is, when the push object is the commodity detail page corresponding to the commodity link, the target operation result of the training sample without the browse commodity detail page by the history account is regarded as the second result.
The second operation result determining mode:
the method comprises the steps that a target operation result corresponding to a training sample, in which the time length of a historical account browsing push object is not smaller than a set time length threshold, is determined to be a first result of the target operation; and
Determining a target operation result corresponding to a training sample with the time length of browsing the push object of the historical account being smaller than the set time length threshold value as a second result without performing the target operation; and
And determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
If the target operation result is represented in the form of a label, the first result may be set as a positive sample label and the second result may be set as a negative sample label.
The positive sample label may be set to 1, the negative sample label may be set to 0, and the person skilled in the art may also use other identifiers as the positive sample label or the negative sample label.
As an embodiment, in the first operation result determining manner and the second operation result determining manner, the set duration threshold is determined according to duration data of a first set number of historical objects browsing push objects and real target operation results of the historical objects, or the set duration threshold is obtained through an AB test.
Specifically, a first set number of historical browsing object data may be obtained in advance, where the first set number of historical browsing object data includes duration data of a historical account browsing push object and a real target operation result of the historical account.
Referring to fig. 5, a specific example of acquiring the set duration threshold is provided below, which specifically includes the following steps:
it should be noted that each history browsing object data in this example is among the above-described first set number of history browsing data.
In step S501, an initial time period threshold T0 is set.
Specifically, the above-described time period threshold T0 may be set by a technician based on experimental tests or empirical predictions.
Step S502, according to the time length threshold T0 and the time length data of the historical account browsing push object in the historical browsing object data, determining the approximate target operation result of the historical account in the historical browsing object data.
Specifically, the approximate target operation result comprises that target operation is performed or not performed, if the duration of the historical account browsing push object in the historical browsing object data is not less than a duration threshold T0, determining that the approximate target operation result in the historical browsing object data is that the target operation is performed; if the time length of the history account browsing push object in the history browsing object data is smaller than the time length threshold T0, determining that the approximate target operation result of the history object in the history browsing object data is not the target operation.
Step S503, determining a prediction error rate of the target operation result based on the actual target operation result and the approximate target operation result of each history browsing object data.
Specifically, the number of historical browsing object data, of which the approximate target operation result and the actual target operation result are inconsistent, is determined, and the ratio of the determined number to the first set number is used as the prediction error rate of the target operation result.
Step S504, it is determined whether the prediction error rate is greater than the error rate threshold, if so, the process proceeds to step S505, and if not, the process proceeds to step S506.
In step S505, the duration threshold T0 is adjusted to obtain a new duration threshold T0, and the process proceeds to step S502.
In this step, the product of the current duration threshold T0 and the set weight may be determined as the new duration threshold T0; the sum of the current duration threshold T0 and the set duration may also be determined as the new duration threshold T0, or the current duration threshold T0 may be transformed in other manners to obtain the new duration threshold T0.
In step S506, the duration threshold T0 is determined as the set duration threshold.
A specific example of target operation prediction is provided below.
In this example, the pushing object is an item detail page of an item link, the target operation is an operation of transferring electronic money for an item corresponding to the item detail page (i.e. an operation of purchasing an item corresponding to the item detail page), the duration information of the account browsing pushing object is a duration of the account browsing the item detail page, and in this example, an operation intention prediction model using training is adopted to estimate an operation intention probability value of the target operation after the account to be predicted browses the pushing object.
The example mainly includes the following two processes:
the first process comprises the following steps: and obtaining a trained operation intention prediction model.
Firstly, acquiring training samples containing operation intention characteristic data of a historical account and duration information of a browsing push object of the historical account; according to the time length data of the historical account browsing push object, a label of a training sample, the time length of which is not less than a set time length threshold, of the historical account browsing push object is set as a positive sample label, a label of a training sample, the time length of which is less than the set time length threshold, of which is set as a negative sample label, wherein the positive sample label is used for representing that the historical account performs electronic money transferring operation on commodities corresponding to the browsing commodity detail page (namely, the historical account browses the commodity corresponding to the commodity detail page and purchases the commodity detail page), and the negative sample label is used for representing that the historical account does not perform electronic money transferring operation on the commodities corresponding to the commodity detail page (namely, the historical account browses the commodity corresponding to the commodity detail page and does not purchase the commodity detail page).
Based on machine learning, the operation intention pre-estimation model which is initially created or the operation intention pre-estimation model which is obtained through historical training is adjusted through learning the mapping relation between the operation intention characteristic data of the historical account in the training sample and the label, so that the trained operation intention pre-estimation model is obtained.
The second process is as follows: and estimating an operation intention probability value of the account to be predicted for performing the target operation.
Acquiring operation intention feature data of an account to be tested, inputting the acquired operation intention feature data into a trained operation intention prediction model, and acquiring an operation intention probability value of target operation after browsing a pushing object of the account to be tested.
In the embodiment of the disclosure, the operation intention characteristic data of the historical accounts and the first association degree of the target operation result determined by the time length data of the pushing objects browsed by each historical account are utilized to estimate the operation intention predicted value of the target operation of the account to be predicted after the pushing objects are browsed; in the process, a real target operation result of target operation performed by a historical account is not required to be acquired, and a new mode for predicting the target operation is provided.
As shown in fig. 6, based on the same inventive concept, the disclosed embodiment further provides a target operation prediction apparatus 600, which includes:
An intention feature obtaining unit 601 configured to perform obtaining operation intention feature data of an account to be predicted, where the operation intention feature data includes feature data that characterizes a preference degree of the account for a target operation, and the target operation includes an operation performed after the account browses a push object;
A target operation prediction unit 602 configured to perform a first association degree of a target operation result determined by operation intention feature data of each history account and duration data of a push object browsed by each history account, and estimate a second association degree of the operation intention feature data of the account to be predicted and the target operation result; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not.
As one embodiment, the target operation prediction unit 602 is specifically configured to perform:
The operation intention prediction model is used for inputting the operation intention characteristic data of the account to be predicted, and obtaining the operation intention probability value of the target operation performed by the account to be predicted, which is output by the operation intention prediction model, wherein the operation intention prediction model is obtained by training a training sample by adopting the operation intention characteristic data of each historical account and the time length data of each historical account for browsing a pushing object based on a machine learning method.
As an embodiment, the target operation prediction unit 602 is further configured to perform:
the trained operation intention estimation model is obtained by the following steps:
extracting operation intention characteristic data of a historical account in each training sample and duration data of a browsing push object of the historical account;
according to the time length data of the historical account browsing pushing object in each training sample, determining a target operation result corresponding to each training sample;
And obtaining the trained operation intention prediction model by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result and adjusting the operation intention prediction model obtained by the historical training or the operation intention prediction model which is initially created through machine learning.
As one embodiment, the target operation prediction unit 602 is specifically configured to perform:
According to the time length data of the historical account browsing push object in each training sample, determining a target operation result corresponding to the training sample with the time length of the historical account browsing push object not smaller than the set time length threshold value as a first result of the target operation, and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold as a second result without performing the target operation.
As an embodiment, the target operation prediction unit 602 is further configured to perform:
And determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
As an embodiment, the set duration threshold is determined according to duration data of a first set number of historical objects browsing push objects and corresponding real target operation results.
As an embodiment, the target operation prediction unit 602 is further configured to perform:
Determining historical browsing object data in a set time before the current time as the training sample; or (b)
And determining the second set number of historical browsing object data before the current time as the training sample.
As shown in fig. 7, the present disclosure provides an electronic device 700 comprising a processor 701, a memory 702 for storing the above-described processor executable instructions;
Wherein the processor is configured to execute executable instructions to implement any of the target operation prediction methods described above.
In an exemplary embodiment, a storage medium is also provided, e.g., a memory, comprising instructions executable by a processor of the electronic device to perform the above-described method. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, the above-described non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (12)
1. A target operation prediction method, comprising:
acquiring operation intention characteristic data of an account to be predicted, wherein the operation intention characteristic data comprises characteristic data representing the preference degree of the account to a target operation, and the target operation comprises an operation performed after the account browses a push object;
Estimating a second association degree of the operation intention characteristic data of the account to be predicted and a target operation result through the first association degree of the operation intention characteristic data of each historical account and the target operation result determined by the time length data of the push object browsed by each historical account; and converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not, and the method comprises the following steps: the method comprises the steps of adopting a trained operation intention prediction model, inputting operation intention characteristic data of an account to be predicted, and obtaining an operation intention probability value of the account to be predicted, which is output by the operation intention prediction model, for performing target operation, wherein the operation intention prediction model is obtained by training a training sample by adopting the operation intention characteristic data of each historical account and the time length data of each historical account for browsing a pushing object based on a machine learning method;
The trained operational intent estimation model is obtained by:
extracting operation intention characteristic data of a historical account in each training sample and duration data of a browsing push object of the historical account;
according to the time length data of the historical account browsing pushing object in each training sample, determining a target operation result corresponding to each training sample;
and obtaining the trained operation intention prediction model by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result and adjusting the operation intention prediction model obtained by the historical training or the operation intention prediction model which is initially created through machine learning.
2. The method of claim 1, wherein the step of determining the target operation result of the history object in each training sample according to the time length data of the history account browsing push object in each training sample comprises:
According to the time length data of the historical account browsing push object in each training sample, determining a target operation result corresponding to the training sample with the time length of the historical account browsing push object not smaller than a set time length threshold value as a first result of the target operation, and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold value as a second result without performing the target operation.
3. The method as recited in claim 2, further comprising:
and determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
4. The method of claim 2, wherein the set duration threshold is determined based on duration data of a first set number of historical objects browsing push objects and corresponding actual target operation results.
5. The method as recited in claim 1, further comprising:
Determining historical browsing object data in a set time before the current time as the training sample; or (b)
And determining the second set number of historical browsing object data before the current time as the training sample.
6. A target operation prediction apparatus, comprising:
The device comprises an intention feature acquisition unit, a push object pushing unit and a push object pushing unit, wherein the intention feature acquisition unit is configured to execute operation intention feature data of an account to be predicted, the operation intention feature data comprises feature data representing preference degree of the account on target operation, and the target operation comprises operation performed after the account browses the push object;
A target operation prediction unit configured to perform a first degree of association of target operation results determined by operation intention feature data of each history account and duration data of a push object browsed by each history account, and estimate a second degree of association of the operation intention feature data of the account to be predicted with the target operation results; converting the estimated second association degree into an operation intention probability value of the account to be predicted for performing the target operation, wherein the target operation result comprises a result of whether the target operation is performed or not; the target operation prediction unit is specifically configured to perform:
The method comprises the steps of adopting a trained operation intention prediction model, inputting operation intention characteristic data of an account to be predicted, and obtaining an operation intention probability value of the account to be predicted, which is output by the operation intention prediction model, for performing target operation, wherein the operation intention prediction model is obtained by training a training sample by adopting the operation intention characteristic data of each historical account and the time length data of each historical account for browsing a pushing object based on a machine learning method; the target operation prediction unit is further configured to perform:
The trained operational intent estimation model is obtained by:
extracting operation intention characteristic data of a historical account in each training sample and duration data of a browsing push object of the historical account;
according to the time length data of the historical account browsing pushing object in each training sample, determining a target operation result corresponding to each training sample;
and obtaining the trained operation intention prediction model by utilizing the mapping relation between the operation intention characteristic data of the historical account in each training sample and the corresponding target operation result and adjusting the operation intention prediction model obtained by the historical training or the operation intention prediction model which is initially created through machine learning.
7. The apparatus of claim 6, wherein the target operation prediction unit is specifically configured to perform:
According to the time length data of the historical account browsing push object in each training sample, determining a target operation result corresponding to the training sample with the time length of the historical account browsing push object not smaller than a set time length threshold value as a first result of the target operation, and
And determining a target operation result corresponding to the training sample with the time length of browsing the push object by the historical account being smaller than the set time length threshold value as a second result without performing the target operation.
8. The apparatus of claim 7, wherein the target operation prediction unit is further configured to perform:
and determining a target operation result corresponding to the training sample without the historical account browsing the duration data of the push object as a second result without the target operation.
9. The apparatus of claim 7, wherein the set duration threshold is determined based on duration data of a first set number of historical objects browsing push objects and corresponding actual target operation results.
10. The apparatus of claim 6, wherein the target operation prediction unit is further configured to perform:
Determining historical browsing object data in a set time before the current time as the training sample; or (b)
And determining the second set number of historical browsing object data before the current time as the training sample.
11. An electronic device comprising a processor, a memory for storing instructions executable by the processor;
wherein the processor is configured to perform the method of any one of claims 1 to 5.
12. A computer readable storage medium storing computer instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010469618.8A CN113743636B (en) | 2020-05-28 | 2020-05-28 | Target operation prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010469618.8A CN113743636B (en) | 2020-05-28 | 2020-05-28 | Target operation prediction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743636A CN113743636A (en) | 2021-12-03 |
| CN113743636B true CN113743636B (en) | 2024-05-14 |
Family
ID=78724227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010469618.8A Active CN113743636B (en) | 2020-05-28 | 2020-05-28 | Target operation prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743636B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Commodity information push method, device, storage medium and server |
| CN107742250A (en) * | 2017-12-04 | 2018-02-27 | 深圳春沐源控股有限公司 | The display methods and display system of goods browse record |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN110020176A (en) * | 2017-12-29 | 2019-07-16 | 中国移动通信集团公司 | A kind of resource recommendation method, electronic equipment and computer readable storage medium |
| CN110716979A (en) * | 2019-10-18 | 2020-01-21 | 重庆锐云科技有限公司 | House buying intention client mining method, device and server |
| CN110929206A (en) * | 2019-11-20 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Click rate estimation method and device, computer readable storage medium and equipment |
| CN111177575A (en) * | 2020-04-07 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, electronic equipment and storage medium |
-
2020
- 2020-05-28 CN CN202010469618.8A patent/CN113743636B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Commodity information push method, device, storage medium and server |
| CN107742250A (en) * | 2017-12-04 | 2018-02-27 | 深圳春沐源控股有限公司 | The display methods and display system of goods browse record |
| CN110020176A (en) * | 2017-12-29 | 2019-07-16 | 中国移动通信集团公司 | A kind of resource recommendation method, electronic equipment and computer readable storage medium |
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN110716979A (en) * | 2019-10-18 | 2020-01-21 | 重庆锐云科技有限公司 | House buying intention client mining method, device and server |
| CN110929206A (en) * | 2019-11-20 | 2020-03-27 | 腾讯科技（深圳）有限公司 | Click rate estimation method and device, computer readable storage medium and equipment |
| CN111177575A (en) * | 2020-04-07 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743636A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102191486B1 (en) | Automatic advertisement execution device, method for automatically generating campaign information for an advertisement medium to execute an advertisement and computer program for executing the method | |
| CN107105031A (en) | Information-pushing method and device | |
| US20220012768A1 (en) | Iteratively improving an advertisement response model | |
| CN105160545B (en) | Method and device for determining release information style | |
| US10552863B1 (en) | Machine learning approach for causal effect estimation | |
| CN111125574A (en) | Method and apparatus for generating information | |
| CN110598120A (en) | Behavior data based financing recommendation method, device and equipment | |
| CN108074003B (en) | Prediction information pushing method and device | |
| CN107517251B (en) | Information pushing method and device | |
| CN111667024B (en) | Content pushing method, device, computer equipment and storage medium | |
| CN110348947B (en) | Object recommendation method and device | |
| US20230316106A1 (en) | Method and apparatus for training content recommendation model, device, and storage medium | |
| CN114971716A (en) | Service interface quality evaluation method and device, equipment, medium and product thereof | |
| CN111738766B (en) | Data processing method and device for multimedia information and server | |
| CN109978594B (en) | Order processing method, device and medium | |
| CN113034168B (en) | Content item delivery method, device, computer equipment and storage medium | |
| CN111651679A (en) | Recommendation method and device based on reinforcement learning | |
| CN113822734B (en) | Method and device for generating information | |
| CN113159877B (en) | Data processing method, device, system and computer readable storage medium | |
| US12062060B2 (en) | Method and device for processing user interaction information | |
| CN113743636B (en) | Target operation prediction method and device, electronic equipment and storage medium | |
| CN111767290B (en) | Method and apparatus for updating user portraits | |
| CN111506643B (en) | Method, device and system for generating information | |
| CN111125502B (en) | Methods and apparatus for generating information | |
| CN117573973A (en) | Resource recommendation method, device, electronic equipment 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 |