CN111126649A - Method and apparatus for generating information - Google Patents
Method and apparatus for generating information Download PDFInfo
- Publication number
- CN111126649A CN111126649A CN201811290050.2A CN201811290050A CN111126649A CN 111126649 A CN111126649 A CN 111126649A CN 201811290050 A CN201811290050 A CN 201811290050A CN 111126649 A CN111126649 A CN 111126649A
- Authority
- CN
- China
- Prior art keywords
- information
- displayed
- sample
- display
- cost value
- 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
Images
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"
Abstract
The embodiment of the application discloses a method and a device for generating information. One embodiment of the method comprises: acquiring at least one piece of information to be displayed and user information of a target user, wherein the information to be displayed is to be pushed to a terminal of the target user; acquiring a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed. The embodiment can improve the accuracy of information generation and is beneficial to improving the pertinence of information pushing.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for generating information.
Background
With the development of internet technology, users browse information more and more frequently through terminals, in the prior art, a ratio of an expected display amount of the information in a certain time period to a total display amount of the information displayed in the time period is generally calculated for the certain information, the calculated ratio is used as a frequency for pushing the information, and the information is pushed to the users according to the frequency, so that the actual display amount of the information reaches the expected display amount.
Disclosure of Invention
The embodiment of the application provides a method and a device for generating information.
In a first aspect, an embodiment of the present application provides a method for generating information, where the method includes: acquiring at least one piece of information to be displayed and user information of a target user, wherein the information to be displayed is to be pushed to a terminal of the target user; acquiring a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
In some embodiments, the method further comprises: extracting the information to be displayed, of which the corresponding predicted click rate is greater than or equal to the corresponding click rate threshold value and the corresponding single display cost value meets the preset condition, from the at least one information to be displayed; and pushing the extracted information to be displayed to the terminal.
In some embodiments, the preset condition includes at least one of: the single-show cost value is the maximum value of the obtained single-show cost values; the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
In some embodiments, the first predictive model is trained by: acquiring a first training sample set, wherein the first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of a sample, and a corresponding marking click rate threshold value and a marking single display cost value; and training to obtain a first prediction model by using a machine learning method and taking the total sample display cost value and the sample expected display amount in the first training sample set as input, and taking the input total sample display cost value, the marking click rate threshold value corresponding to the sample expected display amount and the marking single display cost value as expected output.
In some embodiments, the first predictive model is a model trained based on a linear regression model.
In some embodiments, the second predictive model is trained by: acquiring a second training sample set, wherein the second training sample comprises pre-acquired characteristic information of sample display information, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information; and training to obtain a second prediction model by using a machine learning method and taking the feature information and the sample user information in the second training sample set as input and taking the input feature information and the marking information corresponding to the sample user information as expected output.
In a second aspect, an embodiment of the present application provides an apparatus for generating information, where the apparatus includes: the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire at least one piece of information to be displayed and user information of a target user to be pushed to a terminal of the target user; the generating unit is configured to acquire a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
In some embodiments, the apparatus further comprises: the extraction unit is configured to extract the information to be displayed, of which the corresponding predicted click rate is greater than or equal to the corresponding click rate threshold value and the corresponding single display cost value meets the preset condition, from the at least one information to be displayed; and the pushing unit is configured to push the extracted information to be displayed to the terminal.
In some embodiments, the preset condition includes at least one of: the single-show cost value is the maximum value of the obtained single-show cost values; the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
In some embodiments, the first predictive model is trained by: acquiring a first training sample set, wherein the first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of a sample, and a corresponding marking click rate threshold value and a marking single display cost value; and training to obtain a first prediction model by using a machine learning method and taking the total sample display cost value and the sample expected display amount in the first training sample set as input, and taking the input total sample display cost value, the marking click rate threshold value corresponding to the sample expected display amount and the marking single display cost value as expected output.
In some embodiments, the first predictive model is a model trained based on a linear regression model.
In some embodiments, the second predictive model is trained by: acquiring a second training sample set, wherein the second training sample comprises pre-acquired characteristic information of sample display information, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information; and training to obtain a second prediction model by using a machine learning method and taking the feature information and the sample user information in the second training sample set as input and taking the input feature information and the marking information corresponding to the sample user information as expected output.
In a third aspect, an embodiment of the present application provides a server, where the server includes: one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.
According to the method and the device for generating the information, at least one piece of information to be displayed and user information of a target user are obtained, then the total display cost value and the expected display amount corresponding to the information to be displayed are obtained, and the click rate threshold value, the single display cost value and the predicted click rate corresponding to the information to be displayed are obtained by using the first prediction model and the second prediction model, so that the accuracy of information generation can be improved, and the pertinence of information push is improved by using data output by the models.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for generating information, according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for generating information according to an embodiment of the present application;
FIG. 4 is a flow diagram of yet another embodiment of a method for generating information according to an embodiment of the present application;
FIG. 5 is a block diagram of one embodiment of an apparatus for generating information according to an embodiment of the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing a server according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary system architecture 100 to which a method for generating information or an apparatus for generating information of embodiments of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., software or software modules used to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background information processing server that provides support for information presented on the terminal devices 101, 102, 103. The background information processing server can process the acquired information such as the information to be displayed and the user information and generate a processing result (such as a click rate threshold value, a single display cost value and a predicted click rate).
It should be noted that the method for generating information provided in the embodiment of the present application is generally performed by the server 105, and accordingly, the apparatus for generating information is generally disposed in the server 105.
The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating information in accordance with the present application is shown. The method for generating information comprises the following steps:
In this embodiment, an execution subject (for example, a server shown in fig. 1) of the method for generating information may obtain at least one piece of information to be presented and user information of the target user to be pushed to a terminal of the target user from a remote place or a local place through a wired connection manner or a wireless connection manner. Wherein, the information to be presented may include but is not limited to at least one of the following: pictures, text, audio, video, link addresses, etc. The target user may be a user who is to browse information to be presented using a terminal (e.g., a terminal device shown in fig. 1) used by the user. The user information of the target user may be used to characterize characteristics of the target user, including but not limited to at least one of: gender, age, interests, etc. of the target user.
In this embodiment, for the information to be displayed in the at least one information to be displayed acquired in step 201, the executing entity may execute the following steps for the information to be displayed:
Wherein the total display cost value is used for representing the total cost (such as price, integral value and the like) paid by the provider of the information to be displayed for displaying the information to be displayed to the user. The expected display amount is the number of preset users who expect to browse the information to be displayed, or the number of times that the execution main body pushes the information to be displayed.
The single-time display cost value is used for representing the cost paid by a provider (such as an owner of an article indicated by the information to be displayed provided to the user) of the information to be displayed once displayed on the terminal used by the user. The first prediction model is used for representing the corresponding relation between the total display cost value, the expected display amount, the click rate threshold value and the single display cost value. Specifically, as an example, the first prediction model may be a correspondence table in which a plurality of total presentation cost values, expected presentation amounts, corresponding click rate thresholds, and single presentation cost values are stored, which is pre-made by a technician based on statistics of a large number of total presentation cost values, expected presentation amounts, and click rate thresholds, and single presentation cost values; the model may also be a model obtained by training an initial model (for example, a generalized linear regression model, a locally weighted linear regression model, a neural network, or the like) by using a machine learning method based on a preset training sample. By using the first prediction model, different click rate thresholds and single display cost values can be obtained according to different total display cost values and expected display amounts of the information to be displayed, and reference is provided for determining whether to push the information to be displayed to a target user.
In some optional implementations of this embodiment, the executing entity or other electronic device may train to obtain the first prediction model according to the following steps:
first, a first set of training samples is obtained. The first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of the sample, and a corresponding marking click rate threshold value and a marking single display cost value.
Then, by using a machine learning method, the total sample presentation cost value and the sample expected presentation amount in the first training sample set are used as input, the input total sample presentation cost value, the marking click rate threshold value corresponding to the sample expected presentation amount and the marking single presentation cost value are used as expected output, and a first prediction model is obtained through training.
Specifically, the first prediction model may be a model obtained by training an initial model. The initial model may be a linear regression model, a neural network model, or the like. The initial model may be provided with initial parameters, which may be continuously adjusted during the training process. The execution subject training the first prediction model may calculate a loss value based on a preset loss function, and determine whether the initial model is trained according to the loss value. Here, it should be noted that the loss value can be used to characterize the difference between the actual output and the expected output. In practice, various loss functions preset can be used to calculate the loss value of the actual output relative to the labeled output. For example, a loss value may be calculated using a squared loss function.
In some optional implementations of the present embodiment, the first prediction model may be a model trained based on a linear regression model. Linear regression is a statistical analysis method that uses regression analysis in mathematical statistics to determine the interdependent quantitative relationships between two or more variables, and is simple and widely applicable.
In practice, the first prediction model may include two linear regression models, namely a first linear regression model and a second linear regression model. The first linear regression model can be used for representing the corresponding relation between the total display cost value, the expected display amount and the click rate threshold value. The second linear regression model may be used to characterize the correspondence between total presentation cost value, expected presentation amount, and single presentation cost value.
As an example, assume that the first linear regression model and the second linear regression model are respectively as shown in equation (1) and equation (2):
f1(S,C)＝CTR_th (1)
f2(S,C)＝bid (2)，
wherein S is the expected display amount, C is the total display cost value, CTR _ th is the click rate threshold, and bid is the single display cost value. When the first prediction model is trained, the expected sample display amount and the total sample display cost value can be used as the input of the initial first linear regression model, the marking click rate threshold value is used as the expected output of the initial first linear regression model, and the first linear regression model is obtained through training. And taking the expected sample display amount and the total sample display cost value as the input of the initial second linear regression model, taking the marked single display cost value as the expected output of the initial second linear regression model, and training to obtain the second linear regression model.
In the present example, it is assumed that the above-described initial first linear regression model and initial second linear regression model are as shown in the following equations (3) and (4):
α1×S+α2×C＝CTR_th (3)
α3×S+α4×C＝bid (4)，
when the executive body inputs the total display cost value C and the expected display amount S into the first prediction model, the click rate threshold value CTR _ th and the single display cost value bid are respectively calculated by the trained first linear regression model and the trained second linear regression model.
Alternatively, the independent variables and dependent variables of the first linear regression model and the second linear regression model may be interchanged. That is, the first linear regression model and the second linear regression model may be represented by equations (5) and (6), respectively:
f1(CTR_th,bid)＝C (5)
f2(CTR_th,bid)＝S (6)，
when the first prediction model is trained, the marking click rate threshold value and the marking single display cost value can be used as the input of the initial first linear regression model, the total sample display cost value is used as the expected output of the initial first linear regression model, and the first linear regression model is obtained through training. And taking the marked click rate threshold value and the marked single display cost value as the input of the initial second linear regression model, taking the sample expected display amount as the expected output of the initial second linear regression model, and training to obtain the second linear regression model.
In the present example, it is assumed that the above-described initial first linear regression model and initial second linear regression model are as shown in the following equations (7) and (8):
β1×CTR_th+β2×bid＝C (7)
β3×CTR_th+β4×bid＝S (8)，
after the initial first linear regression model and the initial second linear regression model are trained, parameter values of the parameters β 1, β, β and β can be determined, so that the trained first linear regression model and the trained second linear regression model are obtained.
When the executing agent inputs the total presentation cost value C and the expected presentation amount S to the first prediction model, the system of equations consisting of the above equations (7) and (8) may be solved, thereby obtaining the click rate threshold CTR _ th and the single presentation cost value bid.
The characteristic information is used for representing the characteristics of the information to be displayed. The characteristics of the information to be presented may include, but are not limited to, at least one of: title, type, link address, etc. of the information to be presented.
The Click Rate is also called Click Through Rate (CTR), i.e. the actual number of clicks of a certain display information is divided by the display amount of the display information (e.g. the number of times the display information is pushed, the number of terminals receiving the display information, etc.). The predicted click rate can be used for representing the probability that the information to be shown is clicked by the target user, namely, the larger the predicted click rate is, the higher the probability that the information to be shown is clicked by the target user is.
And the second prediction model is used for representing the corresponding relation between the characteristic information and the user information and the predicted click rate. Specifically, as an example, the second prediction model may be a correspondence table in which a plurality of pieces of feature information, user information, and corresponding predicted click rates are stored, the correspondence table being pre-made by a technician in advance based on statistics of the feature information, the user information, and the predicted click rates of a large amount of information to be displayed; the model may be obtained by training an initial model (e.g., an FM (Factorization Machine) model, an FFM (Field-aware Factorization Machine) model, a neural network model, etc.) by using a Machine learning method based on a preset training sample. By using the second prediction model, the possibility that the target user clicks the information to be displayed can be accurately predicted, so that the pertinence of pushing the information to be displayed to the target user is improved.
In some optional implementations of this embodiment, the executing entity or other electronic device may train to obtain the second prediction model according to the following steps:
first, a second set of training samples is obtained. The second training sample comprises characteristic information of sample display information acquired in advance, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information. By way of example, the annotation information can be a number, such as "0" indicating that the sample user did not click on the sample presentation information and "1" indicating that the sample user clicked on the sample presentation information.
And then, by using a machine learning method, taking the feature information and the sample user information in the second training sample set as input, taking the input feature information and the marking information corresponding to the sample user information as expected output, and training to obtain a second prediction model. As an example, the output data of the second prediction model may be a value between 0 and 1, the closer the value is to 1, the more likely the characterization feature information indicates that the information to be presented is clicked on by the user.
Specifically, the second prediction model may be a model obtained by training an initial model. The initial model may include an FM model, a neural network model, and the like. The initial model may be provided with initial parameters, which may be continuously adjusted during the training process. The execution subject training the first prediction model may calculate a loss value based on a preset loss function, and determine whether the initial model is trained according to the loss value. Here, it should be noted that the loss value can be used to characterize the difference between the actual output and the expected output. In practice, various loss functions preset can be used to calculate the loss value of the actual output relative to the labeled output. For example, the loss value may be calculated using a logarithmic loss function, a cross-entropy loss function, or the like.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for generating information according to the present embodiment. In the application scenario of fig. 3, the server 301 first obtains locally three pieces of information to be presented 3021, 3022, and 3023 to be pushed to the terminal of the target user, and the user information 304 of the target user 303. The user information 304 includes information such as sex and age of the target user 303. Then, the server 301 obtains a preset total display cost value 3051 (e.g., "1000"), 3052 (e.g., "2000"), 3053 (e.g., "2500"), and a desired display amount 3061 (e.g., "10000"), 3062 (e.g., "20000"), 3063 (e.g., "10000") for each piece of information to be displayed. Then, the server 301 inputs the obtained total exhibition cost value and the expected exhibition amount into the pre-trained first prediction model 307 respectively, and obtains a click rate threshold value 3071 (e.g., "10%"), 3072 (e.g., "5.9%"), 3073 (e.g., "16%") and a single exhibition cost value 3081 (e.g., "1.2"), 3082 (e.g., "0.9"), 3083 (e.g., "1.5") corresponding to each piece of information to be exhibited. Then, the server 301 acquires feature information (for example, 3091, 3092, 3093 in the drawing) of each piece of information to be shown, inputs the acquired feature information and the user information 304 into the second prediction model 310 trained in advance, and obtains predicted click rates 3101 (for example, "11%"), 3102 (for example, "5%"), and 3103 (for example, "13%") for predicting the click rate of each piece of information to be shown.
According to the method provided by the embodiment of the application, the click rate threshold value, the single-display cost value and the predicted click rate corresponding to the information to be displayed are obtained by using the first prediction model and the second prediction model, so that the accuracy of information generation can be improved, and the pertinence of information pushing is improved.
With further reference to fig. 4, a flow 400 of yet another embodiment of a method for generating information is shown. The flow 400 of the method for generating information comprises the steps of:
In this embodiment, step 401 is substantially the same as step 201 in the corresponding embodiment of fig. 2, and is not described here again.
In this embodiment, step 402 is substantially the same as step 202 in the corresponding embodiment of fig. 2, and is not described herein again.
In this embodiment, an executing entity (for example, the server shown in fig. 1) of the method for generating information may determine, from the at least one piece of information to be shown, where a corresponding predicted click rate is greater than or equal to a corresponding click rate threshold and a corresponding single-showing cost value meets a preset condition. The click rate threshold may be used for comparing with the predicted click rate, and when the predicted click rate corresponding to a certain to-be-displayed information is greater than or equal to the click rate threshold, it indicates that the probability that the to-be-displayed information is clicked by the target user is higher. The preset condition may be a condition preset by a technician for selecting information to be presented from at least one piece of information to be presented.
In some optional implementations of this embodiment, the preset condition may include, but is not limited to, at least one of the following:
the single-show cost value is the maximum value of the obtained single-show cost values;
the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
The preset position may be a single position or a plurality of positions. For example, the preset position may be a single showing cost value of the top N (N is a preset positive integer) bits after sorting the obtained single cost values from large to small.
And step 404, pushing the extracted information to be displayed to the terminal.
In this embodiment, the executing entity may push the information to be displayed determined in step 403 to the terminal. So that the information to be presented is displayed on the terminal.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the method for generating information in the present embodiment highlights the steps of extracting information to be presented from at least one piece of information to be presented and pushing the information to be presented. Therefore, the scheme described in this embodiment can more specifically push information to the terminal of the target user based on the output results of the first prediction model and the second prediction model.
With further reference to fig. 5, as an implementation of the method shown in the above figures, the present application provides an embodiment of an apparatus for generating information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 5, the apparatus 500 for generating information of the present embodiment includes: an obtaining unit 501, configured to obtain at least one piece of information to be presented to be pushed to a terminal of a target user and user information of the target user; a generating unit 502 configured to acquire a preset total display cost value and an expected display amount corresponding to information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
In this embodiment, the obtaining unit 501 may obtain at least one piece of information to be presented and user information of the target user to be pushed to the terminal of the target user from a remote location or a local location through a wired connection manner or a wireless connection manner. Wherein, the information to be presented may include but is not limited to at least one of the following: pictures, text, audio, video, link addresses, etc. The target user may be a user who is to browse information to be presented using a terminal (e.g., a terminal device shown in fig. 1) used by the user. The user information of the target user may be used to characterize characteristics of the target user, including but not limited to at least one of: gender, age, interests, etc. of the target user.
In this embodiment, for the information to be shown in the at least one piece of information to be shown acquired by the acquiring unit 501, the generating unit 502 may perform the following steps for the information to be shown:
step 5021, acquiring a preset total display cost value and an expected display amount corresponding to the information to be displayed.
The total display cost value is used for representing the cost of a provider of the information to be displayed for displaying the information to be displayed to a user. The expected display amount is the number of preset users who expect to browse the information to be displayed, or the number of times that the execution main body pushes the information to be displayed.
Step 5022, inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model, and obtaining a click rate threshold value and a single display cost value corresponding to the information to be displayed.
The first prediction model is used for representing the corresponding relation between the total display cost value, the expected display amount, the click rate threshold value and the single display cost value. Specifically, as an example, the first prediction model may be a correspondence table in which a plurality of total presentation cost values, expected presentation amounts, corresponding click rate thresholds, and single presentation cost values are stored, which is pre-made by a technician based on statistics of a large number of total presentation cost values, expected presentation amounts, and click rate thresholds, and single presentation cost values; the model may also be a model obtained by training an initial model (for example, a generalized linear regression model, a locally weighted linear regression model, a neural network, or the like) by using a machine learning method based on a preset training sample. By using the first prediction model, different click rate thresholds and single display cost values can be obtained according to different total display cost values and expected display amounts of the information to be displayed, and reference is provided for determining whether to push the information to be displayed to a target user.
Step 5023, obtaining the characteristic information of the information to be displayed.
The characteristic information is used for representing the characteristics of the information to be displayed. The characteristics of the information to be presented may include, but are not limited to, at least one of: title, type, link address, etc. of the information to be presented.
Step 5024, inputting the acquired feature information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
The Click Rate is also called Click Through Rate (CTR), i.e. the actual number of clicks of a certain display information is divided by the display amount of the display information (e.g. the number of times the display information is pushed, the number of terminals receiving the display information, etc.). The predicted click rate can be used for representing the probability that the information to be shown is clicked by the target user, namely, the larger the predicted click rate is, the higher the probability that the information to be shown is clicked by the target user is.
And the second prediction model is used for representing the corresponding relation between the characteristic information and the user information and the predicted click rate. Specifically, as an example, the second prediction model may be a correspondence table in which a plurality of pieces of feature information, user information, and corresponding predicted click rates are stored, the correspondence table being pre-made by a technician in advance based on statistics of the feature information, the user information, and the predicted click rates of a large amount of information to be displayed; the model may be obtained by training an initial model (e.g., an FM (Factorization Machine) model, an FFM (Field-aware Factorization Machine) model, a neural network model, etc.) by using a Machine learning method based on a preset training sample. By using the second prediction model, the possibility that the target user clicks the information to be displayed can be accurately predicted, so that the pertinence of pushing the information to be displayed to the target user is improved.
In some optional implementations of this embodiment, the apparatus 500 may further include: an extracting unit (not shown in the figure) configured to extract, from at least one piece of information to be displayed, of which a corresponding predicted click rate is greater than or equal to a corresponding click rate threshold and a corresponding single display cost value meets a preset condition; a pushing unit (not shown in the figure) configured to push the extracted information to be shown to the terminal.
In some optional implementations of this embodiment, the preset condition may include at least one of: the single-show cost value is the maximum value of the obtained single-show cost values; the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
In some optional implementations of this embodiment, the first prediction model is trained by: acquiring a first training sample set, wherein the first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of a sample, and a corresponding marking click rate threshold value and a marking single display cost value; and training to obtain a first prediction model by using a machine learning method and taking the total sample display cost value and the sample expected display amount in the first training sample set as input, and taking the input total sample display cost value, the marking click rate threshold value corresponding to the sample expected display amount and the marking single display cost value as expected output.
In some embodiments, the first predictive model is a model trained based on a linear regression model.
In some embodiments, the second predictive model is trained by: acquiring a second training sample set, wherein the second training sample comprises pre-acquired characteristic information of sample display information, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information; and training to obtain a second prediction model by using a machine learning method and taking the feature information and the sample user information in the second training sample set as input and taking the input feature information and the marking information corresponding to the sample user information as expected output.
According to the device provided by the embodiment of the application, the click rate threshold value, the single-time display cost value and the predicted click rate corresponding to the information to be displayed are obtained by using the first prediction model and the second prediction model, so that the accuracy of information generation can be improved, and the information push pertinence is improved.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a server according to embodiments of the present application. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Liquid Crystal Display (LCD) and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable medium or any combination of the two. A computer readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit and a generation unit. The names of the units do not form a limitation on the units themselves in some cases, for example, the acquiring unit may also be described as a "unit for acquiring at least one of information to be presented to be pushed to a terminal of a target user and user information of the target user".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the server described in the above embodiments; or may exist separately and not be assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: acquiring at least one piece of information to be displayed and user information of a target user, wherein the information to be displayed is to be pushed to a terminal of the target user; acquiring a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (14)
1. A method for generating information, comprising:
acquiring at least one piece of information to be displayed and user information of a target user, wherein the information to be displayed is pushed to a terminal of the target user;
acquiring a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
2. The method of claim 1, wherein the method further comprises:
extracting the information to be displayed, of which the corresponding predicted click rate is greater than or equal to the corresponding click rate threshold value and the corresponding single display cost value meets the preset condition, from the at least one information to be displayed;
and pushing the extracted information to be displayed to the terminal.
3. The method of claim 2, wherein the preset condition comprises at least one of:
the single-show cost value is the maximum value of the obtained single-show cost values;
the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
4. The method of claim 1, wherein the first predictive model is trained by:
acquiring a first training sample set, wherein the first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of a sample, and a corresponding marking click rate threshold value and a marking single display cost value;
and training to obtain a first prediction model by using a machine learning method and taking the total sample display cost value and the sample expected display amount in the first training sample set as input, and taking the input total sample display cost value, the marking click rate threshold value corresponding to the sample expected display amount and the marking single display cost value as expected output.
5. The method according to one of claims 1 to 4, wherein the first prediction model is a model trained on a linear regression model.
6. The method according to one of claims 1 to 4, wherein the second predictive model is trained by:
acquiring a second training sample set, wherein the second training sample comprises pre-acquired characteristic information of sample display information, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information;
and training to obtain a second prediction model by using a machine learning method and taking the feature information and the sample user information in the second training sample set as input and taking the input feature information and the marking information corresponding to the sample user information as expected output.
7. An apparatus for generating information, comprising:
the information display device comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire at least one piece of information to be displayed and user information of a target user to be pushed to a terminal of the target user;
the generating unit is configured to acquire a preset total display cost value and an expected display amount corresponding to the information to be displayed for the information to be displayed in the acquired at least one piece of information to be displayed; inputting the obtained total display cost value and the expected display amount into a pre-trained first prediction model to obtain a click rate threshold value and a single display cost value corresponding to the information to be displayed; acquiring characteristic information of the information to be displayed; and inputting the acquired characteristic information and the user information into a pre-trained second prediction model to obtain a predicted click rate for predicting the click rate of the information to be displayed.
8. The apparatus of claim 7, wherein the apparatus further comprises:
the extraction unit is configured to extract the information to be displayed, of which the corresponding predicted click rate is greater than or equal to the corresponding click rate threshold value and the corresponding single display cost value meets a preset condition, from the at least one information to be displayed;
the pushing unit is configured to push the extracted information to be displayed to the terminal.
9. The apparatus of claim 8, wherein the preset condition comprises at least one of:
the single-show cost value is the maximum value of the obtained single-show cost values;
the single showing cost value is arranged at a preset position after being arranged according to the size of the obtained single showing cost value.
10. The apparatus of claim 7, wherein the first predictive model is trained by:
acquiring a first training sample set, wherein the first training sample comprises a sample total display cost value and a sample expected display amount which are preset aiming at information to be displayed of a sample, and a corresponding marking click rate threshold value and a marking single display cost value;
and training to obtain a first prediction model by using a machine learning method and taking the total sample display cost value and the sample expected display amount in the first training sample set as input, and taking the input total sample display cost value, the marking click rate threshold value corresponding to the sample expected display amount and the marking single display cost value as expected output.
11. The apparatus according to one of claims 7-10, wherein the first prediction model is a model trained based on a linear regression model.
12. The apparatus according to one of claims 7-10, wherein the second predictive model is trained by:
acquiring a second training sample set, wherein the second training sample comprises pre-acquired characteristic information of sample display information, sample user information of a sample user browsing the sample display information, and corresponding marking information used for representing whether the sample user clicks the sample display information;
and training to obtain a second prediction model by using a machine learning method and taking the feature information and the sample user information in the second training sample set as input and taking the input feature information and the marking information corresponding to the sample user information as expected output.
13. A server, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.
14. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290050.2A CN111126649B (en) | 2018-10-31 | 2018-10-31 | Method and device for generating information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290050.2A CN111126649B (en) | 2018-10-31 | 2018-10-31 | Method and device for generating information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111126649A true CN111126649A (en) | 2020-05-08 |
| CN111126649B CN111126649B (en) | 2023-08-11 |
Family
ID=70494288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811290050.2A Active CN111126649B (en) | 2018-10-31 | 2018-10-31 | Method and device for generating information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126649B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017775A (en) * | 2020-09-09 | 2020-12-01 | 平安科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110231241A1 (en) * | 2010-03-18 | 2011-09-22 | Yahoo! Inc. | Real-time personalization of sponsored search based on predicted click propensity |
| CN103235893A (en) * | 2013-05-06 | 2013-08-07 | 重庆大学 | User-commodity click rate self-adaptive prediction device and method |
| JP2014095949A (en) * | 2012-11-07 | 2014-05-22 | Yahoo Japan Corp | Advertisement processor and advertisement processing method |
| CN104574124A (en) * | 2013-10-10 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method and device for determining exhibition effect of advertisement data |
| CN105208113A (en) * | 2015-08-31 | 2015-12-30 | 北京百度网讯科技有限公司 | Information pushing method and device |
| CN105631711A (en) * | 2015-12-30 | 2016-06-01 | 合一网络技术(北京)有限公司 | Advertisement putting method and apparatus |
| CN106021341A (en) * | 2016-05-09 | 2016-10-12 | 上海二三四五网络科技有限公司 | A control method and device for sequencing presentation information in a user terminal |
| CN106033583A (en) * | 2016-05-18 | 2016-10-19 | 杭州算子科技有限公司 | Advertisement paid listing method and system applied to electronic commerce |
| CN107222526A (en) * | 2017-05-16 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | Push method, device, equipment and the computer-readable storage medium of promotion message |
| CN107526810A (en) * | 2017-08-23 | 2017-12-29 | 广州优视网络科技有限公司 | Establish method and device, methods of exhibiting and the device of clicking rate prediction model |
| US20180005271A1 (en) * | 2015-12-15 | 2018-01-04 | Tencent Technology (Shenzhen) Company Limited | Information processing method, server, and computer storage medium |
| CN108109016A (en) * | 2017-12-30 | 2018-06-01 | 有米科技股份有限公司 | Ad conversion rates predictor method and device, computer equipment and storage medium |
| CN108446382A (en) * | 2018-03-20 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108596755A (en) * | 2018-04-18 | 2018-09-28 | 中国银行股份有限公司 | The recognition methods of the potential valuable client of bank a kind of and system |
-
2018
- 2018-10-31 CN CN201811290050.2A patent/CN111126649B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110231241A1 (en) * | 2010-03-18 | 2011-09-22 | Yahoo! Inc. | Real-time personalization of sponsored search based on predicted click propensity |
| JP2014095949A (en) * | 2012-11-07 | 2014-05-22 | Yahoo Japan Corp | Advertisement processor and advertisement processing method |
| CN103235893A (en) * | 2013-05-06 | 2013-08-07 | 重庆大学 | User-commodity click rate self-adaptive prediction device and method |
| CN104574124A (en) * | 2013-10-10 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method and device for determining exhibition effect of advertisement data |
| CN105208113A (en) * | 2015-08-31 | 2015-12-30 | 北京百度网讯科技有限公司 | Information pushing method and device |
| US20180005271A1 (en) * | 2015-12-15 | 2018-01-04 | Tencent Technology (Shenzhen) Company Limited | Information processing method, server, and computer storage medium |
| CN105631711A (en) * | 2015-12-30 | 2016-06-01 | 合一网络技术(北京)有限公司 | Advertisement putting method and apparatus |
| CN106021341A (en) * | 2016-05-09 | 2016-10-12 | 上海二三四五网络科技有限公司 | A control method and device for sequencing presentation information in a user terminal |
| CN106033583A (en) * | 2016-05-18 | 2016-10-19 | 杭州算子科技有限公司 | Advertisement paid listing method and system applied to electronic commerce |
| CN107222526A (en) * | 2017-05-16 | 2017-09-29 | 百度在线网络技术（北京）有限公司 | Push method, device, equipment and the computer-readable storage medium of promotion message |
| CN107526810A (en) * | 2017-08-23 | 2017-12-29 | 广州优视网络科技有限公司 | Establish method and device, methods of exhibiting and the device of clicking rate prediction model |
| CN108109016A (en) * | 2017-12-30 | 2018-06-01 | 有米科技股份有限公司 | Ad conversion rates predictor method and device, computer equipment and storage medium |
| CN108446382A (en) * | 2018-03-20 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108596755A (en) * | 2018-04-18 | 2018-09-28 | 中国银行股份有限公司 | The recognition methods of the potential valuable client of bank a kind of and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017775A (en) * | 2020-09-09 | 2020-12-01 | 平安科技（深圳）有限公司 | Information recommendation method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111126649B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| CN111125574B (en) | Method and device for generating information | |
| CN109522483B (en) | Method and device for pushing information | |
| CN109976997B (en) | Test method and device | |
| CN107577807B (en) | Method and device for pushing information | |
| CN107679217B (en) | Associated content extraction method and device based on data mining | |
| CN109388548B (en) | Method and apparatus for generating information | |
| US11758088B2 (en) | Method and apparatus for aligning paragraph and video | |
| CN111061956B (en) | Method and apparatus for generating information | |
| CN108121699B (en) | Method and apparatus for outputting information | |
| CN109359194B (en) | Method and apparatus for predicting information categories | |
| CN111147431B (en) | Method and apparatus for generating information | |
| CN108536867B (en) | Method and apparatus for generating information | |
| CN109582825B (en) | Method and apparatus for generating information | |
| CN107908662B (en) | Method and device for realizing search system | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN111191677A (en) | User characteristic data generation method and device and electronic equipment | |
| CN111125502B (en) | Method and device for generating information | |
| CN111695041B (en) | Method and device for recommending information | |
| CN111126649B (en) | Method and device for generating information | |
| CN111026849A (en) | Data processing method and device | |
| CN110881056A (en) | Method and device for pushing information | |
| CN111767290B (en) | Method and apparatus for updating user portraits | |
| CN109408716B (en) | Method and device for pushing information |
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 |