CN111125572A

CN111125572A - Method and apparatus for processing information

Info

Publication number: CN111125572A
Application number: CN201811287898.XA
Authority: CN
Inventors: 龙睿
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2018-10-31
Filing date: 2018-10-31
Publication date: 2020-05-08
Anticipated expiration: 2038-10-31
Also published as: CN111125572B

Abstract

The embodiment of the application discloses a method and a device for processing information. One embodiment of the method comprises: acquiring an information set to be presented; for the information to be presented in the information set to be presented, the following steps are executed: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value; and selecting the information to be presented from the information set to be presented as information for presentation based on the generated target numerical value. The embodiment improves the pertinence and diversity of information processing; and the first numerical value used for representing the value of the information to be presented is utilized to determine the quality degree of the information to be presented, so that the accuracy of information processing can be improved.

Description

Method and apparatus for processing information

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

With the development of science and technology, people can browse information for presentation, such as news and advertisements, by using electronic devices, such as mobile phones and computers.

Typically, a technician may predetermine a plurality of information to be presented to the user. Further, one piece of information to be presented may be selected from the plurality of pieces of information to be presented as information to be finally presented to the user.

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 information set to be presented; for the information to be presented in the information set to be presented, the following steps are executed: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value; and selecting the information to be presented from the information set to be presented as information for presentation based on the generated target numerical value.

In some embodiments, before generating the target value for characterizing the degree of goodness of the information to be presented based on the determined first value, the method further comprises: obtaining value data predetermined for the information to be presented; determining a second numerical value for representing the value of presenting the information to be presented based on the acquired value data; and generating a target value for representing the degree of goodness of the information to be presented based on the determined first value, wherein the target value comprises the following steps: and generating a target value for representing the quality degree of the information to be presented based on the determined first value and the second value.

In some embodiments, the information to be presented corresponds to a page to be presented, and is used for a user to click so as to present the page to be presented corresponding to the clicked information to be presented to the user; and determining a second value characterizing the value of presenting the information to be presented based on the obtained value data, including: inputting the information to be presented into a pre-trained click rate estimation model to obtain an estimation result; and determining a second numerical value for representing the value of the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented.

In some embodiments, generating a target value for characterizing the degree of goodness of the information to be presented based on the determined first value and second value comprises: and performing weighted summation processing on the first numerical value and the second numerical value corresponding to the information to be presented based on the weights pre-distributed to the first numerical value and the second numerical value, and obtaining a processing result as a target numerical value for representing the quality degree of the information to be presented.

In some embodiments, determining a first value that characterizes a value of the information to be presented includes: and inputting the information to be presented into a pre-trained value model to obtain a first numerical value for representing the value of the information to be presented.

In some embodiments, the value model comprises a first value model trained by: acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection within a preset time period and is used for being presented to a user using the user terminal; the following steps are executed for sample presentation information in the sample presentation information set: determining the time length for a user to browse the information for sample presentation by using the user terminal, and determining a first numerical value corresponding to the information for sample presentation based on the determined time length; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information; and training to obtain a first value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

In some embodiments, the value model comprises a second value model, the second value model being trained by: acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection and used for being presented to a user using the user terminal within a preset time period, wherein the sample presentation information is information in a sample window on a sample page; the following steps are executed for sample presentation information in the sample presentation information set: determining the probability of a user performing preset operation on the sample presentation information by using a user terminal, and determining a first numerical value corresponding to the sample presentation information based on the determined probability, wherein the preset operation is to close a sample window which comprises the sample presentation information and is on a sample page corresponding to the sample presentation information; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information; and training to obtain a second value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

In some embodiments, selecting information to be presented as information for presentation from the set of information to be presented based on the generated target value includes: sequencing the information to be presented in the information set to be presented according to the size sequence of the generated target numerical values to obtain an information sequence to be presented; and selecting information to be presented from the information sequence to be presented as information for presentation.

In a second aspect, an embodiment of the present application provides an apparatus for processing information, the apparatus including: an information acquisition unit configured to acquire a set of information to be presented; a numerical value generating unit configured to perform the following steps for the information to be presented in the information to be presented set: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value; and the information selecting unit is configured to select the information to be presented from the information set to be presented as the information for presentation based on the generated target numerical value.

In some embodiments, the numerical value generation unit is further configured to: obtaining value data predetermined for the information to be presented; determining a second numerical value for representing the value of presenting the information to be presented based on the acquired value data; and generating a target value for representing the degree of goodness of the information to be presented based on the determined first value and the second value.

In some embodiments, the information to be presented corresponds to a page to be presented, and is used for a user to click so as to present the page to be presented corresponding to the clicked information to be presented to the user; and the numerical value generation unit is further configured to: inputting the information to be presented into a pre-trained click rate estimation model to obtain an estimation result; and determining a second numerical value for representing the value of the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented.

In some embodiments, the numerical value generation unit is further configured to: and performing weighted summation processing on the first numerical value and the second numerical value corresponding to the information to be presented based on the weights pre-distributed to the first numerical value and the second numerical value, and obtaining a processing result as a target numerical value for representing the quality degree of the information to be presented.

In some embodiments, the numerical value generation unit is further configured to: and inputting the information to be presented into a pre-trained value model to obtain a first numerical value for representing the value of the information to be presented.

In some embodiments, the information selecting unit includes: the information sorting module is configured to sort the information to be presented in the information set to be presented according to the size sequence of the generated target numerical values to obtain an information sequence to be presented; and the information selecting module is configured to select the information to be presented from the information sequence to be presented as the information for presentation.

In a third aspect, an embodiment of the present application provides a server, including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement the method of any of the embodiments of the method for processing information described above.

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 of any of the above-described methods for processing information.

According to the method and the device for processing the information, the information set to be presented is obtained, and then the following steps are executed for the information to be presented in the information set to be presented: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the degree of goodness of the information to be presented based on the determined first value, and finally selecting the information to be presented from the information set to be presented as information for presentation based on the generated target value, so that the first value for representing the value of the information to be presented is effectively utilized, the target value for representing the degree of goodness of the information to be presented is determined, and further, based on the target value, better information to be presented is selected from the information set to be presented as information for presentation to a user, thereby improving the pertinence and diversity of information processing; and the first numerical value used for representing the value of the information to be presented is utilized to determine the quality degree of the information to be presented, so that the accuracy of information processing can be improved.

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 an embodiment of 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 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 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 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 having a display screen and supporting information transmission, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), 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., multiple pieces of software or software modules 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 server that supports information for presentation displayed on the

terminal apparatuses

101, 102, 103. The background server may obtain the information set to be presented, analyze and otherwise process data such as the information set to be presented, and feed back a processing result (for example, information for presentation) to the terminal device.

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, and accordingly, the apparatus for processing 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., multiple pieces of 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. In the case where data used in obtaining presentation information does not need to be acquired from a remote location, the system architecture described above may include no network and terminal devices, but only a server.

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 method for processing information comprises the following steps:

step 201, acquiring an information set to be presented.

In this embodiment, an execution subject of the method for processing information (e.g., a server shown in fig. 1) may acquire the set of information to be presented by a wired connection manner or a wireless connection manner. The information to be presented is information to be presented to the user, and may include but is not limited to at least one of the following: text, numbers, pictures, video, links. The set of information to be presented may comprise at least one information to be presented.

Specifically, the execution main body may obtain at least one piece of information to be presented, which is pre-stored locally, to form an information set to be presented; at least one piece of information to be presented sent by a communication-connected electronic device (e.g., the terminal device shown in fig. 1) may also be obtained to form an information set to be presented.

Step 202, for the information to be presented in the information to be presented set, executing the following steps: determining a first value for characterizing the value of the information to be presented; and generating a target value for representing the quality degree of the information to be presented based on the determined first value.

In this embodiment, for the information to be presented in the information to be presented set obtained in step 201, the executing main body may execute the following steps:

at step 2021, a first value is determined that characterizes the value of the information to be presented.

The value of the information to be presented can be embodied in the effect generated by the user browsing the content of the information to be presented. The first value may be used to characterize the value of the information to be presented, and the larger the value, the higher the value that can be characterized. Here, the execution body may determine the first numerical value for characterizing the value of the information to be presented in various methods.

As an example, the information to be presented includes text information, and the execution subject may determine the number of words included in the information to be presented, and then determine a first numerical value representing a value of the information to be presented based on the determined number. For example, the executing entity may directly determine the determined amount as a first numerical value for characterizing the value of the information to be presented; alternatively, the determined number and a preset value may be subjected to a product, and the obtained product result may be determined as a first value for representing the value of the information to be presented. It can be understood that the more the text included in the information to be presented, the longer the time for the user to browse the information to be presented, and further, the longer the time for the user to stay on the page where the information to be presented is located, so the higher the value of the information to be presented is.

In some optional implementations of this embodiment, the executing entity may determine the first numerical value for characterizing the value of the information to be presented by: and inputting the information to be presented into a pre-trained value model to obtain a first numerical value for representing the value of the information to be presented.

The value model may be used to represent the correspondence between the information to be presented and a first value that represents the value of the information to be presented. Specifically, as an example, the value model may be a correspondence table in which a plurality of pieces of information to be presented and corresponding first numerical values are stored, the correspondence table being prepared in advance by a technician based on statistics of a large amount of information to be presented and the first numerical values corresponding to the information to be presented; the model may be a model obtained by training an initial model (e.g., a neural network) by a machine learning method based on a preset training sample.

In some alternative implementations of the present embodiment, the value model may include a first value model. The first value model may be used to characterize a correspondence of the information to be presented and a first value characterizing a value of the information to be presented. Specifically, the first value model is obtained by training through the following steps:

first, a sample presentation information set composed of sample presentation information outputted to a user terminal connected to a communication terminal within a predetermined time period for presentation to a user using the user terminal is acquired.

Wherein, the information set for sample presentation may include a plurality of information for sample presentation. The sample presentation information is information selected from a set of information to be presented for the sample. The preset time period may be a time period (e.g., one month) predetermined by a technician. The user terminal of the communication connection may comprise at least one.

Then, for the information for sample presentation in the information set for sample presentation, the following steps are executed: determining the time length for a user to browse the information for sample presentation by using the user terminal, and determining a first numerical value corresponding to the information for sample presentation based on the determined time length; and forming a training sample by using the sample presentation information and the first numerical value corresponding to the sample presentation information.

Here, a time period during which the information for sample presentation is displayed on the user terminal may be determined as a time period during which the user browses the information for sample presentation using the user terminal.

In this implementation manner, various methods may be adopted to determine the first value corresponding to the sample presentation information based on the determined duration, for example, the determined duration may be directly determined as the first value corresponding to the sample presentation information; or, the determined duration and a preset value may be subjected to product operation, and a product operation result is determined as a first value corresponding to the sample presentation information.

It will be appreciated that a plurality of training samples may be obtained using the set of information for sample presentation.

And finally, training to obtain a first value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking a first value corresponding to the input sample presentation information as expected output.

Specifically, a machine learning method may be used to train a predetermined initial model (for example, a neural network) by using, as an input, sample presentation information included in a training sample among the formed training samples and using a first numerical value corresponding to the input sample presentation information as an expected output, thereby finally obtaining a first value model.

In some alternative implementations of the present embodiment, the value model may include a second value model. The second value model may be for characterizing a correspondence of the information to be presented and the first value for characterizing the value of the information to be presented. Specifically, the second value model is obtained by training through the following steps:

Wherein the information for sample presentation is information located in a sample window on a sample page. The sample page is a preset page. The sample window is a preset window for presenting information for sample presentation. When the user browses the sample page, the sample window on the sample page may be closed. It will be appreciated that closing the sample window by the user may characterize the user as not being interested in the content of the information presented by the sample in the sample window.

Then, for the information for sample presentation in the information set for sample presentation, the following steps are executed: determining the probability of a user performing preset operation on the sample presentation information by using a user terminal, and determining a first numerical value corresponding to the sample presentation information based on the determined probability; and forming a training sample by using the sample presentation information and the first numerical value corresponding to the sample presentation information.

The preset operation is to close a sample window including the information for sample presentation on a sample page corresponding to the information for sample presentation.

Specifically, it may be detected whether a user performs a preset operation on information for sample presentation when browsing a sample page; if the preset operation is executed, the probability that the user executes the preset operation on the information for the sample presentation by using the user terminal is determined to be 100%; if the predetermined operation is not performed, the probability may be determined to be 0%.

It can be understood that the larger the probability that the user performs the preset operation on the information for sample presentation, the less the representation user is interested in the information for sample presentation, and the lower the value of the information for sample presentation can be represented. Thus, in this implementation, the determined probability is inversely related to the first value, i.e. the greater the probability, the smaller the first value. Specifically, various methods may be employed to determine the first numerical value corresponding to the sample presentation information based on the determined probability, for example, the negative of the determined probability may be determined as the first numerical value corresponding to the sample presentation information; alternatively, the reciprocal of the determined probability may be determined as the first numerical value corresponding to the sample presentation information.

And finally, training to obtain a second value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

Specifically, a machine learning method may be used to train a predetermined initial model (for example, a neural network) by using, as an input, sample presentation information included in a training sample among the formed training samples, and using a first numerical value corresponding to the input sample presentation information as an expected output, thereby finally obtaining a second numerical value model.

In particular, the value model may include both the first value model and the second value model.

It should be noted that, in practice, the execution subject of the step for generating the models (the first value model and the second value model) may be the same as or different from the execution subject of the method for processing information. If so, the performing agent for the step of generating the model may store the trained model locally after the model is trained. If not, the executive agent of the step for generating the model may send the trained model to the executive agent of the method for processing information after training the model.

Step 2022, generating a target value for representing the degree of goodness of the information to be presented based on the determined first value.

The target value is used for representing the quality degree of the information to be presented, and the larger the target value is, the better the information to be presented can be represented.

Specifically, the executing entity may directly determine the determined first value as a target value for representing the degree of superiority and inferiority of the information to be presented, or may process (for example, multiply by a preset value) the determined first value, and determine a processing result as the target value for representing the degree of superiority and inferiority of the information to be presented.

Step 203, based on the generated target value, selecting information to be presented from the information set to be presented as information for presentation.

In this embodiment, based on the target value generated in step 202, the execution subject may select information to be presented from the information set to be presented as information for presentation. Wherein the presentation information is information that is ultimately for presentation to a user.

Specifically, the executing agent may select information to be presented as information for presentation from the information set to be presented by using various methods based on the generated target value. For example, the information to be presented, of which the corresponding target value is greater than or equal to a preset threshold value, may be selected from the information set to be presented as the information for presentation; or, the information to be presented with the largest corresponding target value may be selected from the information set to be presented as the information for presentation.

In some optional implementation manners of this embodiment, based on the generated target value, the executing body may further select information to be presented as information for presentation from the information set to be presented by the following steps: first, the execution body may sort the information to be presented in the information set to be presented according to the size order of the generated target numerical values, so as to obtain an information sequence to be presented. Then, the execution main body may select information to be presented from the information sequence to be presented as information for presentation.

Specifically, as an example, the execution main body may sort the information to be presented in the information set to be presented according to the descending order of the corresponding target numerical values, so as to obtain an information sequence to be presented. Furthermore, a preset number (for example, 1) of information to be presented, which is sorted at the top, can be selected from the information sequence to be presented as information for presentation; or, the execution main body may sort the information to be presented in the information set to be presented according to the order from small to large of the corresponding target numerical values, so as to obtain an information sequence to be presented. Furthermore, a preset number of pieces of information to be presented, which are sorted in the sequence of information to be presented, may be selected as information for presentation.

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 server 301 may first obtain a set of information to be presented 302, where the set of information to be presented 302 may include information to be presented 3021 (e.g., "a-brand mobile performance upgrade") and information to be presented 3022 ("B-brand mobile price down"). Then, for the information to be presented 3021, the server 301 may perform the following steps: determining a first value 3031 (e.g., "8") characterizing the value of the information to be presented 3021; based on the first numerical value 3031, a target numerical value 3041 (e.g., "80" (the target numerical value "80" may be obtained by multiplying the first numerical value "8" and a preset numerical value "10") for characterizing the degree of superiority and inferiority of the information to be presented 3021 is generated). Then, for the information to be presented 3022, the server 301 may similarly perform the following steps: determining a first value 3032 (e.g., "9") characterizing the value of the information to be presented 3022; based on the first numerical value 3032, a target numerical value 3042 (e.g., "90" (the target numerical value "90" may be obtained by multiplying the first numerical value "9" and a preset numerical value "10") for characterizing the degree of superiority and inferiority of the information to be presented 3022) is generated. Finally, the server 301 may select information to be presented from the information set to be presented 302 as the information for presentation 305 based on the generated

target values

3041, 3042. Specifically, referring to fig. 3, the server 301 may select, from the information to be presented set 303, information to be presented with a larger corresponding target value as the information 305 for presentation, that is, select the information to be presented 3022 as the information 305 for presentation.

In addition, after obtaining the information 305 for presentation, the server 301 may also send the information 305 for presentation to the terminal device 306 in communication connection for presentation on the terminal device for browsing by the user using the terminal device 306.

The method provided by the embodiment of the application effectively utilizes the first numerical value for representing the value of the information to be presented, determines the target numerical value for representing the degree of goodness and badness of the information to be presented, and further can select better information to be presented from the information set to be presented as the information for presentation to the user based on the target numerical value, so that the pertinence and diversity of information processing are improved; and the first numerical value used for representing the value of the information to be presented is utilized to determine the quality degree of the information to be presented, so that the accuracy of information processing can be improved.

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:

step 401, obtaining an information set to be presented.

In this embodiment, an execution subject of the method for processing information (e.g., a server shown in fig. 1) may acquire the set of information to be presented by a wired connection manner or a wireless connection manner. The information to be presented is information provided by the information provider and to be presented to the user, and may include, but is not limited to, at least one of the following: text, numbers, pictures, video, links. The set of information to be presented may comprise at least one information to be presented.

Step 402, for the information to be presented in the information to be presented set, executing the following steps: determining a first value for characterizing the value of the information to be presented; obtaining value data predetermined for the information to be presented; determining a second numerical value for representing the value of presenting the information to be presented based on the acquired value data; and generating a target value for representing the quality degree of the information to be presented based on the determined first value and the second value.

In this embodiment, for the information to be presented in the information to be presented set obtained in step 401, the executing main body may execute the following steps:

step 4021, determining a first value characterizing the value of the information to be presented.

The value of the information to be presented can be embodied in the effect generated by the user browsing the content of the information to be presented. The first value may be used to characterize the value of the information to be presented, and the larger the value, the higher the value characterized may be. Here, the method described in step 2021 may be adopted to determine the first numerical value for representing the value of the information to be presented, and details are not described here.

Step 4022, obtaining value data predetermined for the information to be presented.

In practice, when the information to be presented provided by the information provider is presented, the information provider needs to pay corresponding costs, such as article cost, money cost, point cost, and the like. It will be appreciated that the more cost the information provider pays, the higher the value of presenting the information to be presented can be represented. Here, the value data can be used to determine how much to pay the information provider of the information to be presented when presenting the information to be presented. For example, the information to be presented includes text information. Value data may be used to characterize the price paid by the information provider of the information to be presented for each thousand words presented.

Step 4023, determining a second numerical value for representing the value of presenting the information to be presented, based on the obtained value data.

The second value may be used to represent the value of the operation of presenting the information to be presented, and the larger the value, the higher the value of the represented information to be presented may be.

Specifically, the executing entity may determine the second value for representing the value of presenting the information to be presented by using various methods based on the obtained value data. For example, when the value data is used to represent the cost (e.g., price) paid by the information provider of the information to be presented for each 1000 characters presented, the execution subject may determine the number of characters included in the information to be presented, then perform quotient calculation on the determined number and the value 1000, multiply the quotient calculation result by the cost value (e.g., price) represented by the value data to obtain the total cost value corresponding to the information to be presented, and further determine a second value used to represent the value of presenting the information to be presented by using the total cost value corresponding to the information to be presented.

As an example, the total cost value corresponding to the information to be presented may be directly determined as a second numerical value used for representing the value of presenting the information to be presented; alternatively, the total cost value corresponding to the information to be presented may be processed (for example, multiplied by a preset numerical value), and the processing result may be determined as a second numerical value used for representing the value of presenting the information to be presented.

In some optional implementation manners of this embodiment, the information to be presented corresponds to a page to be presented, and is used for a user to click, so as to present the page to be presented corresponding to the clicked information to be presented to the user. Furthermore, the value data may be used to represent a cost paid by an information provider of the information to be presented when the presentation times of presenting the information to be presented is a preset number and the user clicks the information to be presented once. And the executing body can determine a second numerical value for representing the value of the information to be presented based on the acquired value data by the following steps:

firstly, the execution main body can input the information to be presented into a pre-trained click rate estimation model to obtain an estimation result.

The estimated result can be used for representing the predicted click rate corresponding to the information to be presented. The predicted click rate is a result obtained by predicting the click rate. The Click Rate is also called Click Through Rate (CTR) and is used to indicate the ratio of the number of clicked times of the information to be presented to the number of presented times of the information to be presented. The click rate estimation model can be used for representing the corresponding relation between the information to be presented and the estimation result. The click rate estimation model may be a model obtained by training an initial model. The initial model may include, but is not limited to, at least one of the following: an FM (Factorization Machine) model, an FFM (Field-aware Factorization Machine), a neural network model, and the like.

It should be noted that the method for training to obtain the click rate estimation model is a well-known technique widely studied and applied at present, and is not described herein again.

Then, the executing body may determine a second numerical value for representing the value of presenting the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented.

Specifically, the executing entity may determine, by using various methods, a second numerical value representing the value of the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented. For example, when the number of times of presenting the information to be presented is represented by the value data is 1000 times, and each time the user clicks once, the cost (for example, the price) paid by the information provider of the information to be presented is determined, the executing body may perform a product of the obtained estimated result and the value 1000, determine the number of times of clicking the information to be presented in the process of presenting the information to be presented 1000 times, further perform a product of the number of times of clicking and the cost value (for example, the price) represented by the value data, obtain a total cost value corresponding to the information to be presented, and finally determine a second value for representing the value of presenting the information to be presented by using the total cost value corresponding to the information to be presented.

Step 4024, generating a target value for representing the degree of goodness of the information to be presented based on the determined first value and the second value.

Specifically, the executing entity may generate a target value for representing the degree of superiority and inferiority of the information to be presented by using various methods based on the determined first value and the second value. For example, the determined first value and the second value may be summed, and the result of the summation may be determined as a target value for characterizing the degree of goodness of the information to be presented.

In some optional implementations of this embodiment, the executing entity may generate, based on the determined first value and the second value, a target value for characterizing the degree of superiority and inferiority of the information to be presented by: the executing agent may perform weighted summation processing on the first numerical value and the second numerical value corresponding to the information to be presented based on the weights pre-assigned to the first numerical value and the second numerical value, and obtain a processing result as a target numerical value for representing the degree of superiority and inferiority of the information to be presented.

Step 403, based on the generated target value, selecting information to be presented from the information set to be presented as information for presentation.

In this embodiment, based on the target value generated in step 402, the execution main body may select information to be presented from the information set to be presented as information for presentation. Wherein the presentation information is information that is ultimately for presentation to a user.

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 a step of determining a target value corresponding to information to be presented by using a first value and a second value corresponding to the information to be presented. Therefore, the scheme described by the embodiment can introduce more data related to the quality degree of the information to be presented, so that the accuracy of the determined target value can be improved.

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: an information acquisition unit 501, a numerical value generation unit 502, and an information selection unit 503. Wherein the information obtaining unit 501 is configured to obtain a set of information to be presented; the numerical value generating unit 502 is configured to, for information to be presented in the set of information to be presented, perform the following steps: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value; the information selecting unit 503 is configured to select information to be presented as information for presentation from the set of information to be presented based on the generated target value.

In this embodiment, the information obtaining unit 501 of the apparatus for processing information may obtain the set of information to be presented by a wired connection manner or a wireless connection manner. The information to be presented is information to be presented to the user, and may include but is not limited to at least one of the following: text, numbers, pictures, video, links. The set of information to be presented may comprise at least one information to be presented.

In this embodiment, for the information to be presented in the information set to be presented obtained by the information obtaining unit 501, the numerical value generating unit 502 may perform the following steps:

step 5021, a first numerical value for representing the value of the information to be presented is determined.

Step 5022, based on the determined first numerical value, a target numerical value used for representing the quality degree of the information to be presented is generated.

In this embodiment, based on the target value generated by the value generating unit 502, the information selecting unit 503 may select information to be presented as information for presentation from the information set to be presented. Wherein the presentation information is information that is ultimately for presentation to a user.

In some optional implementations of this embodiment, the numerical value generating unit 502 may be further configured to: obtaining value data predetermined for the information to be presented; determining a second numerical value for representing the value of presenting the information to be presented based on the acquired value data; and generating a target value for representing the degree of goodness of the information to be presented based on the determined first value and the second value.

In some optional implementation manners of this embodiment, the information to be presented corresponds to a page to be presented, and is used for a user to click, so as to present the page to be presented corresponding to the clicked information to be presented to the user; and the numerical value generation unit 502 may be further configured to: inputting the information to be presented into a pre-trained click rate estimation model to obtain an estimation result; and determining a second numerical value for representing the value of the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented.

In some optional implementations of this embodiment, the numerical value generating unit 502 may be further configured to: and performing weighted summation processing on the first numerical value and the second numerical value corresponding to the information to be presented based on the weights pre-distributed to the first numerical value and the second numerical value, and obtaining a processing result as a target numerical value for representing the quality degree of the information to be presented.

In some optional implementations of this embodiment, the numerical value generating unit 502 may be further configured to: and inputting the information to be presented into a pre-trained value model to obtain a first numerical value for representing the value of the information to be presented.

In some optional implementations of this embodiment, the value model includes a first value model, and the first value model is trained by: acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection within a preset time period and is used for being presented to a user using the user terminal; the following steps are executed for sample presentation information in the sample presentation information set: determining the time length for a user to browse the information for sample presentation by using the user terminal, and determining a first numerical value corresponding to the information for sample presentation based on the determined time length; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information; and training to obtain a first value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

In some optional implementations of this embodiment, the value model includes a second value model, and the second value model is obtained by training: acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection and used for being presented to a user using the user terminal within a preset time period, wherein the sample presentation information is information in a sample window on a sample page; the following steps are executed for sample presentation information in the sample presentation information set: determining the probability of a user performing preset operation on the sample presentation information by using a user terminal, and determining a first numerical value corresponding to the sample presentation information based on the determined probability, wherein the preset operation is to close a sample window which comprises the sample presentation information and is on a sample page corresponding to the sample presentation information; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information; and training to obtain a second value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

In some optional implementations of this embodiment, the information selecting unit 503 may include: an information sorting module (not shown in the figure) configured to sort the information to be presented in the information set to be presented according to the size sequence of the generated target numerical values, so as to obtain an information sequence to be presented; and an information selecting module (not shown in the figure) configured to select information to be presented from the information sequence to be presented as information for presentation.

It will be understood that the elements described in the apparatus 500 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 500 and the units included therein, and are not described herein again.

The device 500 provided by the above embodiment of the present application effectively utilizes the first value for representing the value of the information to be presented, determines the target value for representing the degree of goodness of the information to be presented, and further, based on the target value, selects the better information to be presented from the information set to be presented as the information for presentation to the user, thereby improving the pertinence and diversity of information processing; and the first numerical value used for representing the value of the information to be presented is utilized to determine the quality degree of the information to be presented, so that the accuracy of information processing can be 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 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 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 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 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 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.

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 information acquisition unit, a numerical value generation unit, and an information selection unit. The names of these units do not in some cases constitute a limitation on the unit itself, and for example, the information acquisition unit may also be described as a "unit that acquires information to be presented".

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 an information set to be presented; for the information to be presented in the information set to be presented, the following steps are executed: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value; and selecting the information to be presented from the information set to be presented as information for presentation based on the generated target numerical value.

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

1. A method for processing information, comprising:

acquiring an information set to be presented;

for the information to be presented in the information set to be presented, executing the following steps: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value;

and selecting the information to be presented from the information set to be presented as information for presentation based on the generated target numerical value.

2. The method of claim 1, wherein before generating the target value for characterizing the degree of goodness of the information to be presented based on the determined first value, the method further comprises:

obtaining value data predetermined for the information to be presented;

determining a second numerical value for representing the value of presenting the information to be presented based on the acquired value data; and

generating a target value for representing the degree of goodness of the information to be presented based on the determined first value, including:

and generating a target value for representing the quality degree of the information to be presented based on the determined first value and the second value.

3. The method according to claim 2, wherein the information to be presented corresponds to a page to be presented, and is used for a user to click so as to present the page to be presented corresponding to the clicked information to be presented to the user; and

the determining, based on the obtained value data, a second value characterizing a value of presenting the information to be presented includes:

inputting the information to be presented into a pre-trained click rate estimation model to obtain an estimation result;

and determining a second numerical value for representing the value of the information to be presented based on the obtained estimation result and the value data corresponding to the information to be presented.

4. The method of claim 2, wherein generating a target value for characterizing the degree of goodness of the information to be presented based on the determined first value and second value comprises:

and performing weighted summation processing on the first numerical value and the second numerical value corresponding to the information to be presented based on the weights pre-distributed to the first numerical value and the second numerical value, and obtaining a processing result as a target numerical value for representing the quality degree of the information to be presented.

5. The method of claim 1, wherein determining the first value characterizing the value of the information to be presented comprises:

and inputting the information to be presented into a pre-trained value model to obtain a first numerical value for representing the value of the information to be presented.

6. The method of claim 5, wherein the value model comprises a first value model trained by:

acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection within a preset time period and is used for being presented to a user using the user terminal;

for the information for sample presentation in the information set for sample presentation, executing the following steps: determining the time length for a user to browse the information for sample presentation by using the user terminal, and determining a first numerical value corresponding to the information for sample presentation based on the determined time length; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information;

and training to obtain a first value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

7. The method of claim 5, wherein the value model comprises a second value model trained by:

acquiring a sample presentation information set consisting of sample presentation information which is output to a user terminal in communication connection and used for being presented to a user using the user terminal within a preset time period, wherein the sample presentation information is information in a sample window on a sample page;

for the information for sample presentation in the information set for sample presentation, executing the following steps: determining the probability of a user performing a preset operation on the sample presentation information by using a user terminal, and determining a first numerical value corresponding to the sample presentation information based on the determined probability, wherein the preset operation is to close a sample window which comprises the sample presentation information and is on a sample page corresponding to the sample presentation information; forming a training sample by using the sample presentation information and a first numerical value corresponding to the sample presentation information;

and training to obtain a second value model by using a machine learning method and taking the sample presentation information included in the training samples in the formed training samples as input and taking the first value corresponding to the input sample presentation information as expected output.

8. The method according to one of claims 1 to 7, wherein the selecting information to be presented from the set of information to be presented as information for presentation based on the generated target value comprises:

sequencing the information to be presented in the information set to be presented according to the size sequence of the generated target numerical values to obtain an information sequence to be presented;

and selecting information to be presented from the information sequence to be presented as information for presentation.

9. An apparatus for processing information, comprising:

an information acquisition unit configured to acquire a set of information to be presented;

a value generating unit configured to perform the following steps for the information to be presented in the information to be presented set: determining a first value for characterizing the value of the information to be presented; generating a target value for representing the quality degree of the information to be presented based on the determined first value;

and the information selecting unit is configured to select information to be presented from the information set to be presented as information for presentation based on the generated target numerical value.

10. The apparatus of claim 9, wherein the numerical value generation unit is further configured to:

obtaining value data predetermined for the information to be presented;

11. The device according to claim 10, wherein the information to be presented corresponds to a page to be presented, and is used for a user to click, so as to present the page to be presented corresponding to the clicked information to be presented to the user; and

the numerical value generation unit is further configured to:

12. The apparatus of claim 10, wherein the numerical value generation unit is further configured to:

13. The apparatus of claim 9, wherein the numerical value generation unit is further configured to:

14. The apparatus of claim 13, wherein the value model comprises a first value model trained by:

15. The apparatus of claim 13, wherein the value model comprises a second value model trained by:

16. The apparatus according to one of claims 9-15, wherein the information extracting unit comprises:

the information sorting module is configured to sort the information to be presented in the information set to be presented according to the size sequence of the generated target numerical values to obtain an information sequence to be presented;

and the information selecting module is configured to select the information to be presented from the information sequence to be presented as the information for presentation.

17. 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 1-8.

18. 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 1-8.