CN111130984B - Method and apparatus for processing information - Google Patents
Method and apparatus for processing information Download PDFInfo
- Publication number
- CN111130984B CN111130984B CN201811291540.4A CN201811291540A CN111130984B CN 111130984 B CN111130984 B CN 111130984B CN 201811291540 A CN201811291540 A CN 201811291540A CN 111130984 B CN111130984 B CN 111130984B
- Authority
- CN
- China
- Prior art keywords
- target
- conversion rate
- information
- conversion
- estimated
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/214—Monitoring or handling of messages using selective forwarding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the application discloses a method and a device for processing information. One embodiment of the method comprises: acquiring an estimated conversion rate and a real conversion rate which are associated with the target pushing information and the target conversion target, wherein the estimated conversion rate is obtained by calculating based on the probability which is predicted by the target prediction model and is associated with the target pushing information and the target conversion target; determining whether the current conversion rate meets a preset correction condition or not based on the estimated conversion rate and the real conversion rate; and if so, generating correction information based on the ratio of the estimated conversion rate to the real conversion rate. The embodiment realizes targeted information generation. The generated correction information may help enable correction of probabilities associated with the target push information and the target transformation target that are subsequently predicted by the target prediction model.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for processing information.
Background
The existing push information includes interactive push information, and a network user can enter a specific website or open a specific window and the like by selecting (for example, clicking or double clicking) the interactive push information. In addition, the client can set a corresponding conversion target for the similar sending information.
For such push information in the cold start phase, the accuracy of the probability predicted by the existing transition probability prediction model for the push information is generally low due to the fact that the user data related to the push information is less, and the like.
Disclosure of Invention
The embodiment of the application provides a method and a device for processing information.
In a first aspect, an embodiment of the present application provides a method for processing information, where the method includes: acquiring an estimated conversion rate and a real conversion rate which are associated with the target pushing information and the target conversion target, wherein the estimated conversion rate is obtained by calculating based on the probability which is predicted by the target prediction model and is associated with the target pushing information and the target conversion target; determining whether the current conversion rate meets a preset correction condition or not based on the estimated conversion rate and the real conversion rate; and if so, generating correction information based on the ratio of the estimated conversion rate to the real conversion rate.
In some embodiments, the correction conditions include the following: the confidence coefficient of the real conversion rate reaches a confidence coefficient threshold value, and the estimated conversion rate is not equal to the real conversion rate; and determining whether the current state meets a preset correction condition based on the estimated conversion rate and the real conversion rate, wherein the step of determining the current state meets the preset correction condition comprises the following steps: determining whether the confidence of the real conversion rate reaches a confidence threshold value or not by adopting positive-phase distribution; in response to determining that the confidence of the true conversion rate reaches a confidence threshold, further determining whether the estimated conversion rate is equal to the true conversion rate; in response to determining that the estimated conversion rate is not equal to the true conversion rate, determining that the correction condition is currently satisfied.
In some embodiments, determining whether a preset correction condition is currently satisfied based on the predicted conversion rate and the actual conversion rate further comprises: and determining that the correction condition is not met currently in response to determining that the confidence of the true conversion rate does not reach a confidence threshold or that the estimated conversion rate is equal to the true conversion rate.
In some embodiments, generating the correction information based on a ratio of the estimated conversion rate and the true conversion rate includes: generating correction information indicating: and dividing the probability related to the target pushing information and the target conversion target, which is predicted subsequently by the target prediction model, by the ratio.
In some embodiments, the target push information corresponds to the information identifier in advance; and after generating the correction information, the method further comprises: in response to receiving a prediction request related to target push information and a target conversion target, acquiring a user identification set and an operation information set, wherein the operation information set comprises operation information which corresponds to user identifications in the user identification set and is associated with push information in a category to which the target push information belongs; for each user identifier in the user identifier set, forming an identifier pair by the user identifier and the information identifier; inputting the operation information corresponding to the user identifications included in each formed identification pair and each identification pair into a target prediction model to obtain a prediction result, wherein the prediction result comprises the probability that the user indicated by each user identification in a user identification set achieves a target conversion target through target push information; based on the correction information, the probability in the prediction result is corrected.
In a second aspect, an embodiment of the present application provides an apparatus for processing information, where the apparatus includes: the obtaining unit is configured to obtain an estimated conversion rate and a real conversion rate which are associated with the target pushing information and the target conversion target, wherein the estimated conversion rate is obtained through calculation based on the probability related to the target pushing information and the target conversion target and predicted by the target prediction model; a determination unit configured to determine whether a preset correction condition is currently satisfied based on the estimated conversion rate and the true conversion rate; a generating unit configured to generate correction information based on a ratio of the estimated conversion rate and the true conversion rate if satisfied.
In some embodiments, the correction condition includes the following: the confidence coefficient of the real conversion rate reaches a confidence coefficient threshold value, and the estimated conversion rate is not equal to the real conversion rate; and the determining unit is further configured to: determining whether the confidence of the real conversion rate reaches a confidence threshold value or not by adopting positive-phase distribution; in response to determining that the confidence of the true conversion rate reaches a confidence threshold, further determining whether the estimated conversion rate is equal to the true conversion rate; in response to determining that the estimated conversion rate is not equal to the true conversion rate, determining that the correction condition is currently satisfied.
In some embodiments, the determining unit is further configured to: and determining that the correction condition is not met currently in response to determining that the confidence of the true conversion rate does not reach a confidence threshold or that the estimated conversion rate is equal to the true conversion rate.
In some embodiments, the generating unit is further configured to: generating correction information indicating: and dividing the probability related to the target pushing information and the target conversion target, which is predicted subsequently by the target prediction model, by the ratio.
In some embodiments, the target push information corresponds to the information identifier in advance; and the above apparatus further comprises: a first obtaining unit configured to obtain a user identifier set and an operation information set in response to receiving a prediction request related to target push information and a target conversion target, wherein the operation information set comprises operation information corresponding to a user identifier in the user identifier set and associated with push information in a category to which the target push information belongs; the forming unit is configured to form an identification pair by the user identification and the information identification for each user identification in the user identification set; the prediction unit is configured to input operation information corresponding to the user identifications included in each formed identification pair and each identification pair into a target prediction model to obtain a prediction result, wherein the prediction result comprises the probability that the user indicated by each user identification in the user identification set achieves a target conversion target through target push information; a correction unit configured to correct the probability in the prediction result based on the correction information.
In a third aspect, an embodiment of the present application provides an electronic device, including: 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 a 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, where the program is executed by a processor to implement the method as described in any implementation manner of the first aspect.
According to the method and the device for processing information, the estimated conversion rate and the real conversion rate associated with the target pushing information and the target conversion target are obtained, and whether the preset correction condition is met currently is determined based on the obtained estimated conversion rate and the obtained real conversion rate, so that the correction information is generated based on the ratio of the estimated conversion rate to the real conversion rate after the correction condition is determined to be met currently. Targeted information generation is achieved, and the correction information can be helpful for correcting the probability related to the target pushing information and the target conversion target and predicted subsequently by the target prediction model.
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 for one embodiment of a method for processing information according to the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for processing information according to the present application;
FIG. 4 is a flow diagram of yet another embodiment of a method for processing information according to the present application;
FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for processing information according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing an electronic device 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 present 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 shows an exemplary system architecture 100 to which embodiments of the method for processing information or the apparatus for processing information 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 client may use the terminal devices 101, 102, 103 to interact with the server 105 over 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, an application for configuring information for a client with respect to target push information, and the like.
The terminal devices 101, 102, 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., 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. For example, the server 105 may support the client to set at least one conversion target for the target push information via the terminal devices 101, 102, 103. Furthermore, after the target push information is pushed to the user group, the server 105 may count the estimated conversion rate and the actual conversion rate associated with the target push information and the target conversion target (the conversion target set by the client for the target push information), and perform corresponding processing operations based on the two conversion rates.
It should be noted that the method for processing information provided in the embodiment of the present application is generally performed by the server 105. Accordingly, the means for processing information is typically provided in the server 105.
It should be noted that 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., 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 processing information in accordance with the present application is shown. The process 200 of the method for processing information comprises the following steps:
In this embodiment, an execution subject of the method for processing information (e.g., the server 105 shown in fig. 1) may obtain the predicted conversion rate and the real conversion rate associated with the target push information and the target conversion target in response to receiving a corresponding information processing instruction (e.g., an information processing instruction for executing the above-described flow 200 with respect to the above-described target push information).
The target push information may be interactive push information in a cold start phase. It should be understood that for any piece of push information, if the push information is not pushed to the user group or is pushed only a limited number of times, and the push information is associated with less user data, the push information may be said to be in the cold start phase. The target push information may be used to introduce a customer's product or service to a user group, for example. It should be noted that the target push information may be push information in various forms (for example, in the form of pictures, text links, and the like), and the embodiment does not limit the form of the target push information.
The target conversion target may be a conversion target set by the client for the target push information. Generally, the client can set at least one conversion target for the target push information. The conversion goals may include, but are not limited to, download completion, installation completion, activation, payment, form submission, phone call placement, and the like.
The estimated conversion rate may be calculated based on a probability predicted by a target prediction model and associated with the target push information and the target conversion target. The target prediction model may be a model obtained by learning in advance by a multitask learning method. The input to the target prediction model may include, for example, at least one identification pair and operational information corresponding to the user identification in each identification pair. Wherein, the identification pair may include a user identification and an information identification of the push information. The operation information corresponding to the user identifier may include operation information associated with push information in a category to which the push information belongs. For example, for any one identifier pair, assuming that the identifier pair includes a user identifier a and an information identifier B, and a category to which push information indicated by the information identifier B belongs is a category C, the operation information corresponding to the user identifier a may include: the information identity of the push information belonging to the category C clicked by the user indicated by the user identity a, and the operation identity of the operation (such as online consultation, telephone dialing, downloading, installation, activation, payment and the like) performed by the user through the push information.
The output of the target prediction model may be, for example, the probability that the user indicated by the user identifier in the input pair of identifiers achieves the target conversion goal described above through the push information indicated by the information identifier in the pair of identifiers.
In this embodiment, the execution main body may respectively calculate the estimated conversion rate and the real conversion rate based on historical estimated conversion data and historical real conversion data related to the target push information and the target conversion target recorded before the current time.
The historical real conversion data may include, for example, user information of a user clicking the target push information, and user information of a user reaching the target conversion target through the target push information. Here, the user information may include, for example, user identification, the number of users, and the like. The execution body may determine a ratio of the number of users who achieve the target conversion target through the target push information to the number of users who click the target push information as the real conversion rate.
The historical pre-estimated conversion data may include, for example, a set of user identifications and a probability that a user indicated by each user identification in the set of user identifications predicted by the target prediction model achieves the target conversion goal through the target push information. The execution main body can select the user identifier of the user clicking the target push information from the user identifier set based on the historical real conversion data to form a user identifier group. Then, the executing entity may calculate a sum of probabilities that users indicated by each user id in the user id group achieve the target conversion target through the target push information, and the executing entity may determine a ratio of the sum to the number of users clicking the target push information as the estimated conversion rate.
In this embodiment, after obtaining the estimated conversion rate and the actual conversion rate, the execution main body may determine whether a preset correction condition is currently satisfied based on the estimated conversion rate and the actual conversion rate.
As an example, the correction condition may include, for example, that the above estimated conversion rate is not equal to the above true conversion rate. The execution body may compare the estimated conversion rate and the actual conversion rate to determine whether the estimated conversion rate and the actual conversion rate are equal to each other. If not, the execution body can determine that the correction condition is currently met; otherwise, the execution subject may determine that the correction condition is not currently satisfied.
It should be noted that the correction condition may be set according to actual needs, and the content of the correction condition is not limited in this embodiment.
In this embodiment, the executing entity may calculate the ratio of the estimated conversion rate to the actual conversion rate in response to determining that the correction condition is currently satisfied. Here, the estimated conversion rate may be used as a dividend and the actual conversion rate may be used as a divisor when calculating the ratio. Then, the execution subject described above may generate correction information based on the ratio. For example, if the estimated conversion rate is greater than the actual conversion rate, the execution subject may generate correction information indicating: and dividing the probability related to the target pushing information and the target conversion target, which is predicted subsequently by the target prediction model, by the ratio. If the estimated conversion rate is less than the actual conversion rate, the execution subject may determine an inverse of the ratio as a correction value, and generate correction information indicating: and multiplying the probability which is predicted subsequently by the target prediction model and is related to the target pushing information and the target conversion target by the correction value.
It should be noted that the specific content of the correction information may be set according to actual needs, and is not specifically limited herein.
With continued reference to fig. 3, fig. 3 is a schematic diagram of an application scenario of the method for processing information according to the present embodiment. In the application scenario of fig. 3, the client C sets a payment conversion target for the target push information B, and the target push information B has already been pushed to the user group. The target push information B may be, for example, push information of game software for introducing the client C to the user group. The predetermined correction condition may include, for example, that the estimated conversion rate is not equal to the actual conversion rate. The server (as indicated by reference numeral 301) may obtain the estimated conversion rate and the real conversion rate associated with the target push information B and the paid conversion target in response to receiving the information processing instruction to execute the above-described process 200 with respect to the target push information B. The estimated conversion rate can be calculated based on the probability related to the target pushing information B and the paid conversion target predicted by the target prediction model. Here, it is assumed that the estimated conversion is 0.04 (as indicated by reference numeral 302) and the actual conversion is 0.02 (as indicated by reference numeral 303). Then, the server compares the estimated conversion rate 0.04 with the real conversion rate 0.02, so that the two conversion rates are determined to be unequal, and the correction condition is met currently. The server may then calculate a ratio 2 of the estimated conversion of 0.04 to the actual conversion of 0.02 (as indicated by reference numeral 304). Finally, since the predicted conversion rate 0.04 is greater than the true conversion rate 0.02, the server may determine that the probability of the target prediction model prediction is high, and the server may generate correction information (as shown by reference numeral 305) indicating: and dividing the probability related to the target push information B and the payment conversion target, which is predicted subsequently by the target prediction model, by 2.
In the method provided by the above embodiment of the application, the estimated conversion rate and the real conversion rate associated with the target push information and the target conversion target are obtained, and then whether the preset correction condition is currently met or not is determined based on the obtained estimated conversion rate and the obtained real conversion rate, so that after the correction condition is determined to be currently met, the correction information is generated based on the ratio of the estimated conversion rate to the real conversion rate. Targeted information generation is achieved, and the correction information can be helpful for correcting the probability related to the target pushing information and the target conversion target and predicted subsequently by the target prediction model.
With further reference to FIG. 4, a flow 400 of yet another embodiment of a method for processing information is shown. The flow 400 of the method for processing information includes the steps of:
In this embodiment, an executing agent (e.g., the server 105 shown in fig. 1) of the method for processing information may obtain the estimated conversion rate and the real conversion rate associated with the target push information and the target conversion target in response to receiving a corresponding information processing instruction (e.g., an information processing instruction of the above flow 400 executed for the target push information). The estimated conversion rate may be calculated based on a probability predicted by a target prediction model and associated with the target push information and the target conversion target. Here, for the explanation of step 401, reference may be made to the related explanation of step 201 in the embodiment shown in fig. 2, and details are not repeated here.
In the present embodiment, the preset correction condition may include the following items: the confidence level of the true conversion reaches a confidence threshold (e.g., 0.95, etc.), and the estimated conversion is not equal to the true conversion. It should be understood that the confidence threshold may be set according to actual needs, and is not specifically limited herein. In practice, after the execution of step 401, the execution subject can execute step 402.
In this embodiment, the execution subject may determine whether the confidence of the true conversion rate reaches a confidence threshold by using a positive-power distribution. As an example, the execution subject may obtain a confidence interval of positive distribution corresponding to the confidence threshold calculated last. The confidence interval may be calculated by the executing agent or a server in remote communication connection with the executing agent according to the real historical conversion data related to the target pushing information and the target conversion target, and the confidence interval is calculated by the executing agent or the server in remote communication connection with the executing agent according to the real historical conversion data. The executing body may determine whether the real conversion rate is within the confidence interval, and if the real conversion rate is within the confidence interval, the executing body may determine that the confidence of the real conversion rate reaches a confidence threshold; otherwise, the executing agent may determine that the confidence of the true conversion rate does not reach a confidence threshold.
It should be noted that a Normal Distribution (Normal Distribution), also called Gaussian Distribution (Gaussian Distribution), is a probability Distribution. A normal distribution is a distribution of continuous random variables with two parameters, μ and σ ^2, the first parameter μ being the mean of the random variables that follow the normal distribution, and the second parameter σ ^2 being the variance of this random variable, so the normal distribution can be written as N (μ, σ ^ 2).
The Confidence Level is also referred to as reliability, Confidence Level or Confidence coefficient. A Confidence Interval (Confidence Interval) may refer to an estimated Interval of the overall parameter constructed from the sample statistics. In statistics, the confidence interval for a probability sample is an interval estimate for some overall parameter of the sample. The confidence interval exhibits the extent to which the true value of this parameter has a certain probability of falling around the measurement. The confidence interval indicates the degree of plausibility of the measured value of the measured parameter, i.e. the "certain probability" required above, which may be referred to as confidence.
In this embodiment, if the execution main body determines that the confidence of the real conversion rate does not reach the confidence threshold, the execution main body may determine that the correction condition is not currently met, and the execution main body may end the execution of the process 400. If the executing entity determines that the confidence of the real conversion rate reaches the confidence threshold, the executing entity may execute step 403.
At step 403, it is determined whether the estimated conversion rate is equal to the true conversion rate.
In this embodiment, after determining that the confidence of the real conversion rate reaches the confidence threshold, the executing entity may compare the estimated conversion rate with the real conversion rate to determine whether the estimated conversion rate is equal to the real conversion rate. If so, the executing agent may determine that the correction condition is not currently satisfied, and the executing agent may end the execution of the process 400; if not, the executing entity may determine that the correction condition is currently satisfied, and the executing entity may execute step 404.
In this embodiment, the executing entity may calculate the ratio of the estimated conversion rate to the actual conversion rate after determining that the estimated conversion rate is not equal to the actual conversion rate. Here, the estimated conversion rate may be used as a dividend and the actual conversion rate may be used as a divisor when calculating the ratio. Then, the execution body may generate correction information based on the ratio. For example, if the estimated conversion rate is greater than the actual conversion rate, the execution subject may generate correction information indicating: and dividing the probability related to the target push information and the target conversion target, which is predicted subsequently by the target prediction model, by the ratio. If the estimated conversion rate is less than the actual conversion rate, the executing entity may determine an inverse of the ratio as a correction value, and generate correction information indicating: and multiplying the probability which is predicted subsequently by the target prediction model and is related to the target pushing information and the target conversion target by the correction value.
As can be seen from fig. 4, compared with the embodiment corresponding to fig. 2, the flow 400 of the method for processing information in the present embodiment highlights steps extending the method of determining whether the correction condition is currently satisfied. Thus, the scheme described in the present embodiment can improve the effectiveness of the generated correction information.
In an alternative implementation of the method for processing information provided by the embodiments of the present application, after determining that the correction condition is currently satisfied, the execution main body (for example, the server 105 shown in fig. 1) of the method may directly generate the correction information indicating that: and dividing the probability related to the target pushing information and the target conversion target predicted subsequently by the target prediction model by the ratio of the estimated conversion rate to the real conversion rate.
In an optional implementation manner of the method for processing information provided by the embodiments of the present application, the target push information may correspond to the information identifier in advance. The information identifier may uniquely indicate the target push information. After the execution body generates the correction information, the execution body may further execute the following correction operations:
first, the executing agent may obtain a user identifier set and an operation information set in response to receiving a prediction request related to the target push information and the target conversion target. The operation information set may include operation information corresponding to the user identifier in the user identifier set and associated with the push information in the category to which the target push information belongs. For the operation information corresponding to any user identifier, the operation information may include an information identifier of the push information in the category that the user indicated by the user identifier clicked once, and an operation identifier of a series of operations executed after clicking the push information. Taking the push information related to the game software as an example, a series of operations performed by the user after clicking the push information may include, but is not limited to, downloading, installing, activating, paying, and the like.
As an example, the executing entity may obtain a preset first user information set associated with a category to which the target push information belongs from a server locally or remotely connected thereto. The first user information may include a user identifier and operation information corresponding to the user identifier and associated with the push information in the category. The execution body may extract a user identifier set and an operation information set from the first user information set.
For another example, the executing entity may obtain the preset second user information set from a server locally or remotely connected thereto. The second user information may include a user identifier and various operation information corresponding to the user identifier. The execution main body may select second user information including operation information related to push information of a category to which the target push information belongs from the second user information set, and may form a second user information group. Then, the execution main body may extract, from the second user information group, a user identifier set and operation information that corresponds to each user identifier in the user identifier set and is associated with the push information in the category, and combine the extracted operation information into an operation information set.
Then, the executing agent may combine each user identifier in the user identifier set and the information identifier of the target push information into an identifier pair.
Then, the execution subject may input the formed identifier pairs and the operation information corresponding to the user identifier included in each identifier pair into the target prediction model, so as to obtain a prediction result. The prediction result may include a probability that the user indicated by each user identifier in the user identifier set achieves the target conversion target through the target push information.
Finally, the execution subject may correct the probability in the prediction result based on the generated correction information. For example, if the generated correction information is used to indicate that the probabilities related to the target push information and the target conversion target predicted subsequently by the target prediction model are divided by the ratio of the predicted conversion rate and the actual conversion rate, the executing entity may divide the probabilities in the prediction result by the ratio respectively.
When pushing the target push information using the information push service, the client generally pays a corresponding fee to a provider of the information push service (e.g., the execution subject). The cost is generally calculated by the provider based on the probability associated with the target pushing information and the target conversion target predicted by the target prediction model. After the execution main body generates the correction information, the probability associated with the target pushing information and the target conversion target and predicted subsequently by the target prediction model is corrected, so that the excess cost of customers can be avoided as much as possible, and the property loss of a provider of the information pushing service can be reduced.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for processing information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable in various electronic devices.
As shown in fig. 5, the apparatus 500 for processing information of the present embodiment includes: the obtaining unit 501 is configured to obtain an estimated conversion rate and a real conversion rate associated with the target pushing information and the target conversion target, where the estimated conversion rate may be calculated based on a probability predicted by the target prediction model and related to the target pushing information and the target conversion target; the determination unit 502 is configured to determine whether a preset correction condition is currently satisfied based on the estimated conversion rate and the true conversion rate; the generating unit 503 is configured to generate the correction information based on a ratio of the estimated conversion rate and the true conversion rate, if satisfied.
In the present embodiment, in the apparatus 500 for processing information: the specific processing of the obtaining unit 501, the determining unit 502, and the generating unit 503 and the technical effects thereof can refer to the related descriptions of step 201, step 202, and step 203 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementations of the present embodiment, the correction condition may include the following: the confidence coefficient of the real conversion rate reaches a confidence coefficient threshold value, and the estimated conversion rate is not equal to the real conversion rate; and the determining unit 502 may be further configured to: determining whether the confidence of the real conversion rate reaches a confidence threshold value or not by adopting positive-phase distribution; in response to determining that the confidence of the true conversion rate reaches a confidence threshold, further determining whether the estimated conversion rate is equal to the true conversion rate; in response to determining that the estimated conversion rate is not equal to the true conversion rate, determining that the correction condition is currently satisfied.
In some optional implementations of this embodiment, the determining unit 502 may be further configured to: and determining that the correction condition is not met currently in response to determining that the confidence of the true conversion rate does not reach a confidence threshold or that the estimated conversion rate is equal to the true conversion rate.
In some optional implementations of this embodiment, the generating unit 503 may be further configured to: generating correction information indicating: and dividing the probability related to the target pushing information and the target conversion target, which is predicted subsequently by the target prediction model, by the ratio.
In some optional implementation manners of this embodiment, the target push information may correspond to the information identifier in advance; and the apparatus 500 may further include: a first obtaining unit (not shown in the figure), configured to, in response to receiving a prediction request related to target push information and a target conversion target, obtain a user identification set and an operation information set, where the operation information set may include operation information corresponding to a user identification in the user identification set and associated with push information in a category to which the target push information belongs; a composing unit (not shown in the figure) configured to, for each user identifier in the user identifier set, compose the user identifier and the information identifier into an identifier pair; a prediction unit (not shown in the figure), configured to input the operation information corresponding to the user identifier included in each identifier pair and each identifier pair in the identifier pairs into a target prediction model, so as to obtain a prediction result, where the prediction result may include a probability that a user indicated by each user identifier in the user identifier set achieves a target conversion target through target push information; a correction unit (not shown in the figure) configured to correct the probability in the prediction result based on the correction information.
The device provided by the above embodiment of the application determines whether the preset correction condition is currently met or not by obtaining the estimated conversion rate and the real conversion rate associated with the target push information and the target conversion target and then determining whether the preset correction condition is currently met or not based on the obtained estimated conversion rate and the real conversion rate, so that the correction information is generated based on the ratio of the estimated conversion rate to the real conversion rate after the correction condition is determined to be currently met. Targeted information generation is achieved, and the correction information can be helpful for correcting the probability related to the target pushing information and the target conversion target and predicted subsequently by the target prediction model.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use in implementing an electronic device (e.g., server 105 of FIG. 1) of an embodiment of the present application is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the use range of the embodiment 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 Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, 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 the 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 above-described functions defined in the system of the present application are executed when the computer program is executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage 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 storage 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 storage 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 any of a variety of 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 storage 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 + +, 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 or flowchart illustration, and combinations of blocks in the block diagrams 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, a determination unit, and a generation unit. The names of the units do not form a limitation to the units themselves in some cases, and for example, the acquiring unit may also be described as a "unit that acquires the predicted conversion rate and the actual conversion rate associated with the target push information and the target conversion target".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiment; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to: acquiring an estimated conversion rate and a real conversion rate which are associated with the target pushing information and the target conversion target, wherein the estimated conversion rate can be obtained by calculating based on the probability which is predicted by the target prediction model and is associated with the target pushing information and the target conversion target; determining whether the current conversion rate meets a preset correction condition or not based on the estimated conversion rate and the real conversion rate; and if so, generating correction information based on the ratio of the estimated conversion rate to the real conversion rate.
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 (10)
1. A method for processing information, comprising:
acquiring an estimated conversion rate and a real conversion rate which are associated with target pushing information and a target conversion target, wherein the estimated conversion rate is obtained by calculating based on probabilities which are predicted by a target prediction model and are associated with the target pushing information and the target conversion target, and the target conversion target is a conversion target which is set aiming at the target pushing information;
determining whether a preset correction condition is met currently or not based on the estimated conversion rate and the real conversion rate;
if so, generating correction information based on the ratio of the estimated conversion rate to the real conversion rate, wherein the correction information is used for correcting the probability, which is predicted by the target prediction model and is related to the target push information and the target conversion target;
the target push information corresponds to an information identifier in advance; and
after the generating correction information, the method further comprises:
in response to receiving a prediction request related to the target push information and the target conversion target, acquiring a user identifier set and an operation information set, wherein the operation information set comprises operation information which corresponds to user identifiers in the user identifier set and is associated with push information in a category to which the target push information belongs;
for each user identifier in the user identifier set, forming an identifier pair by the user identifier and the information identifier;
inputting the operation information corresponding to the user identifications included in each formed identification pair and each identification pair into the target prediction model to obtain a prediction result, wherein the prediction result comprises the probability that the user indicated by each user identification in the user identification set achieves the target conversion target through the target push information;
correcting the probability in the prediction result based on the correction information.
2. The method of claim 1, wherein the correction condition comprises the following: the confidence of the real conversion rate reaches a confidence threshold value, and the estimated conversion rate is not equal to the real conversion rate; and
determining whether a preset correction condition is currently met based on the estimated conversion rate and the real conversion rate includes:
determining whether the confidence of the true conversion rate reaches the confidence threshold value by adopting positive-Taiwan distribution;
in response to determining that the confidence in the true conversion reaches the confidence threshold, further determining whether the estimated conversion is equal to the true conversion;
determining that the correction condition is currently satisfied in response to determining that the estimated conversion rate is not equal to the true conversion rate.
3. The method of claim 2, wherein said determining whether a preset correction condition is currently satisfied based on said estimated conversion rate and said actual conversion rate further comprises:
responsive to determining that the confidence of the true conversion does not meet the confidence threshold, or that the estimated conversion is equal to the true conversion, determining that the correction condition is not currently met.
4. The method of any of claims 1-3, wherein said generating correction information based on a ratio of said estimated conversion rate and said actual conversion rate comprises:
generating correction information indicating: dividing the probability related to the target push information and the target conversion target predicted subsequently by the target prediction model by the ratio.
5. An apparatus for processing information, comprising:
an obtaining unit configured to obtain an estimated conversion rate and a real conversion rate associated with target push information and a target conversion target, wherein the estimated conversion rate is calculated based on a probability related to the target push information and the target conversion target predicted by a target prediction model, and the target conversion target is a conversion target set for the target push information;
a determination unit configured to determine whether a preset correction condition is currently satisfied based on the estimated conversion rate and the true conversion rate;
a generating unit configured to generate correction information for correcting the probability predicted by the target prediction model and related to the target push information and a target conversion target based on a ratio of the predicted conversion rate and the actual conversion rate if the ratio is satisfied;
the target push information corresponds to an information identifier in advance; and
the device further comprises:
a first obtaining unit configured to obtain a user identifier set and an operation information set in response to receiving a prediction request related to the target push information and the target conversion target, wherein the operation information set includes operation information corresponding to a user identifier in the user identifier set and associated with push information in a category to which the target push information belongs;
a composing unit configured to, for each user identifier in the user identifier set, compose the user identifier and the information identifier into an identifier pair;
the prediction unit is configured to input operation information corresponding to the user identifiers included in each identifier pair and each identifier pair into the target prediction model to obtain a prediction result, wherein the prediction result includes a probability that the user indicated by each user identifier in the user identifier set achieves the target conversion target through the target push information;
a correction unit configured to correct a probability in the prediction result based on the correction information.
6. The apparatus of claim 5, wherein the correction condition comprises: the confidence of the real conversion rate reaches a confidence threshold value, and the estimated conversion rate is not equal to the real conversion rate; and
the determination unit is further configured to:
determining whether the confidence of the true conversion rate reaches the confidence threshold value by adopting positive-Taiwan distribution;
in response to determining that the confidence in the true conversion reaches the confidence threshold, further determining whether the estimated conversion is equal to the true conversion;
determining that the correction condition is currently satisfied in response to determining that the estimated conversion rate is not equal to the true conversion rate.
7. The apparatus of claim 6, wherein the determining unit is further configured to:
responsive to determining that the confidence of the true conversion does not meet the confidence threshold, or that the estimated conversion is equal to the true conversion, determining that the correction condition is not currently met.
8. The apparatus according to one of claims 5-7, wherein the generating unit is further configured to:
generating correction information indicating: dividing the probability related to the target pushing information and the target conversion target predicted subsequently by the target prediction model by the ratio.
9. An electronic device, 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 1-4.
10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291540.4A CN111130984B (en) | 2018-10-31 | 2018-10-31 | Method and apparatus for processing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291540.4A CN111130984B (en) | 2018-10-31 | 2018-10-31 | Method and apparatus for processing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111130984A CN111130984A (en) | 2020-05-08 |
| CN111130984B true CN111130984B (en) | 2022-07-05 |
Family
ID=70494680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811291540.4A Active CN111130984B (en) | 2018-10-31 | 2018-10-31 | Method and apparatus for processing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111130984B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114422584B (en) * | 2021-12-16 | 2023-07-07 | 北京百度网讯科技有限公司 | Method, device and storage medium for pushing resources |
| CN116662672B (en) * | 2023-07-27 | 2024-02-06 | 中信证券股份有限公司 | Value object information transmitting method, device, equipment and computer readable medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940703A (en) * | 2016-01-04 | 2017-07-11 | 腾讯科技（北京）有限公司 | Pushed information roughing sort method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428076A (en) * | 2013-08-22 | 2013-12-04 | 北京奇虎科技有限公司 | Method and device for transmitting information to multi-type terminals or applications |
| KR102072176B1 (en) * | 2013-08-26 | 2020-01-31 | 에스케이플래닛 주식회사 | Service providing device for transferring push/target message, push/target message transfer system comprising the same, control method thereof and computer readable medium having computer program recorded therefor |
| CN104050589B (en) * | 2014-06-03 | 2017-07-14 | 江苏省东方世纪网络信息有限公司 | The method and system that a kind of social public platform ad click conversion ratio is assessed |
| CN106156878B (en) * | 2015-04-21 | 2020-09-15 | 深圳市腾讯计算机系统有限公司 | Advertisement click rate correction method and device |
| CN106548364B (en) * | 2016-09-27 | 2020-12-11 | 腾讯科技（北京）有限公司 | Information sending method and device |
| CN106779641B (en) * | 2016-12-29 | 2020-04-28 | 腾讯科技（深圳）有限公司 | Information processing method and information processing apparatus |
| CN106777396A (en) * | 2017-03-01 | 2017-05-31 | 合网络技术（北京）有限公司 | The put-on method and device of a kind of promotion message |
-
2018
- 2018-10-31 CN CN201811291540.4A patent/CN111130984B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940703A (en) * | 2016-01-04 | 2017-07-11 | 腾讯科技（北京）有限公司 | Pushed information roughing sort method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111130984A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108880931B (en) | Method and apparatus for outputting information | |
| CN108520470B (en) | Method and apparatus for generating user attribute information | |
| CN108933695B (en) | Method and apparatus for processing information | |
| CN109710507B (en) | Automatic testing method and device | |
| WO2020088050A1 (en) | Information generation method and device | |
| CN109272348B (en) | Method and device for determining number of active users, storage medium and electronic equipment | |
| CN108810047B (en) | Method and device for determining information push accuracy rate and server | |
| CN111130984B (en) | Method and apparatus for processing information | |
| CN111125503B (en) | Method and apparatus for generating information | |
| CN110097457B (en) | Information generation method, electronic device, and computer-readable medium | |
| CN109885564B (en) | Method and apparatus for transmitting information | |
| CN112989203B (en) | Material throwing method, device, equipment and medium | |
| CN111787041A (en) | Method and apparatus for processing data | |
| CN108449186B (en) | Security verification method and device | |
| CN109218024B (en) | Method and device for controlling authority | |
| CN111131359B (en) | Method and apparatus for generating information | |
| CN109597819B (en) | Method and apparatus for updating a database | |
| CN109348298B (en) | Method and equipment for pushing and playing multimedia data stream | |
| CN108804442B (en) | Serial number generation method and device | |
| CN109493134A (en) | Method and apparatus for pushed information | |
| CN112308661B (en) | Order processing method and device | |
| CN115408297A (en) | Test method, device, equipment and medium | |
| CN114157578A (en) | Network state prediction method and device | |
| CN111131355B (en) | Method and apparatus for processing information | |
| CN110209883B (en) | Method and device for judging validity of user historical data |
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 |