CN111125501B - Method and device for processing information - Google Patents
Method and device for processing information Download PDFInfo
- Publication number
- CN111125501B CN111125501B CN201811287919.8A CN201811287919A CN111125501B CN 111125501 B CN111125501 B CN 111125501B CN 201811287919 A CN201811287919 A CN 201811287919A CN 111125501 B CN111125501 B CN 111125501B
- Authority
- CN
- China
- Prior art keywords
- presentation
- image
- product
- product image
- sample
- 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
Classifications
-
- 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
Abstract
The embodiment of the application discloses a method and a device for processing information. One embodiment of the method comprises the following steps: acquiring user information of a target user and a product image set to be presented; inputting the product image to be presented and user information into a pre-trained first evaluation model to obtain a first evaluation result, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented; and selecting the product image to be presented from the product image set to be presented as the product image for presentation based on the obtained first evaluation result. This embodiment improves the pertinence and diversity of information processing.
Description
Technical Field
Embodiments of the present application relate to the field of computer technology, and in particular, to a method and apparatus for processing information.
Background
Currently, a product provider may recommend a product to a user by pushing a product image to a terminal (e.g., a cell phone, a computer, etc.) used by the user.
In general, different users have different preferences. Thus, a user who browses the pushed product image may or may not be interested in the product indicated by the product image.
Disclosure of Invention
The embodiment of the application provides a method and a device for processing information.
In a first aspect, embodiments of the present application provide a method for processing information, the method including: acquiring user information of a target user and a product image set to be presented; inputting the product image to be presented and user information into a pre-trained first evaluation model to obtain a first evaluation result, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented; and selecting the product image to be presented from the product image set to be presented as the product image for presentation based on the obtained first evaluation result.
In some embodiments, the product image to be presented in the set of product images to be presented corresponds to at least one background image; and after selecting the product image to be presented from the set of product images to be presented as the product image for presentation, the method further comprises: for a presentation product image of the selected presentation product images, the following steps are performed: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; and selecting the presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image.
In some embodiments, after selecting the presentation image from the presentation images corresponding to the presentation product images as the target presentation image corresponding to the presentation product image, the method further comprises: and outputting the selected image for target presentation to a terminal used by a target user.
In some embodiments, selecting the presentation image from the presentation images corresponding to the presentation product image as the target presentation image corresponding to the presentation product image includes: inputting the presentation image and the user information into a pre-trained second evaluation model for the presentation image corresponding to the presentation product image to obtain a second evaluation result, wherein the second evaluation result is used for representing the interest degree of the user corresponding to the input user information on the input presentation image; and selecting the presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image based on the obtained second evaluation result.
In some embodiments, the first evaluation model is trained by: acquiring a plurality of sample presentation product images; for a sample presentation product image among a plurality of sample presentation product images, performing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; forming a training sample by using the sample presentation product image, the acquired sample user information and the determined sample first evaluation result; and using a machine learning method, taking sample user information and a sample presentation product image which are included in a training sample in the formed training samples as input, taking a sample first evaluation result corresponding to the input sample user information and the sample presentation product image as expected output, and training to obtain a first evaluation model.
In some embodiments, the user information includes at least one of: attribute information, history behavior information.
In a second aspect, embodiments of the present application provide an apparatus for processing information, the apparatus comprising: the acquisition unit is configured to acquire user information of a target user and a product image set to be presented; the input unit is configured to input the product image to be presented and the user information into a pre-trained first evaluation model for the product image to be presented in the product image set to be presented, and a first evaluation result is obtained, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented; and a selection unit configured to select a product image to be presented from the set of product images to be presented as a product image for presentation based on the obtained first evaluation result.
In some embodiments, the product image to be presented in the set of product images to be presented corresponds to at least one background image; the apparatus further comprises: an adding unit configured to execute the following steps for a presentation product image among the selected presentation product images: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; and selecting the presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image.
In some embodiments, the apparatus further comprises: and an output unit configured to output the selected image for target presentation to a terminal used by the target user.
In some embodiments, the adding unit is further configured to: inputting the presentation image and the user information into a pre-trained second evaluation model for the presentation image corresponding to the presentation product image to obtain a second evaluation result, wherein the second evaluation result is used for representing the interest degree of the user corresponding to the input user information on the input presentation image; and selecting the presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image based on the obtained second evaluation result.
In some embodiments, the first evaluation model is trained by: acquiring a plurality of sample presentation product images; for a sample presentation product image among a plurality of sample presentation product images, performing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; forming a training sample by using the sample presentation product image, the acquired sample user information and the determined sample first evaluation result; and using a machine learning method, taking sample user information and a sample presentation product image which are included in a training sample in the formed training samples as input, taking a sample first evaluation result corresponding to the input sample user information and the sample presentation product image as expected output, and training to obtain a first evaluation model.
In some embodiments, the user information includes at least one of: attribute information, history behavior information.
In a third aspect, an embodiment of the present application provides a server, including: one or more processors; and a storage device having one or more programs stored thereon, which when executed by the 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, embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method of any of the embodiments of the methods for processing information described above.
According to the method and the device for processing information, the user information of the target user and the product image set to be presented are obtained, then the product image to be presented in the product image set to be presented is input into the first pre-trained evaluation model, a first evaluation result is obtained, wherein the first evaluation result is used for representing the interested degree of the user corresponding to the input user information on the product indicated by the input product image to be presented, finally the product image to be presented is selected from the product image set to be presented as the product image for presentation based on the obtained first evaluation result, and therefore the interested degree of the target user on the product image to be presented is evaluated by effectively utilizing the first evaluation model, the interested product image of the target user is selected from the product image set to be presented as the product image finally used for presentation to the user based on the evaluation result, and the pertinence and the diversity of information processing are improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings, in which:
FIG. 1 is an exemplary system architecture diagram in which an embodiment of the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method for processing information according to the present application;
FIG. 3 is a schematic illustration of one application scenario of a method for processing information according to an embodiment of the present application;
FIG. 4 is a flow chart of yet another embodiment of a method for processing information according to the present application;
FIG. 5 is a schematic structural diagram of one embodiment of an apparatus for processing information according to the present application;
FIG. 6 is a schematic diagram of a computer system suitable for use in implementing embodiments of the present application.
Detailed Description
The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting 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, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the methods for processing information or the apparatuses for processing information of the present application may be applied.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
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 having a display screen and supporting information transmission, including but not limited to smart phones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. Which may be implemented as multiple software or software modules (e.g., multiple software or software modules for providing distributed services) or as a single software or software module. The present invention is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background server that provides support for presentation product images displayed on the terminal devices 101, 102, 103. The background server can acquire the product image set to be presented, analyze and the like data of the product image set to be presented, and feed back the processing result (for example, the product image 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 device for processing information is generally disposed in the server 105.
The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (e.g., a plurality of software or software modules for providing distributed services), or as a single software or software module. The present invention 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 the process of obtaining an image of a product for presentation need not be acquired from a remote place, the above-described system architecture 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 according to the present application is shown. The method for processing information comprises the following steps:
step 201, obtaining user information of a target user and a product image set to be presented.
In this embodiment, the execution subject of the method for processing information (e.g., the server shown in fig. 1) may acquire the user information of the target user and the set of product images to be presented through a wired connection or a wireless connection. The target user is a user of the presentation product image corresponding to the target user to be determined. The presentation product image corresponding to the target user is a product image for presentation to the target user. The product image may indicate a product. Specifically, as an example, the product image may be an image obtained by photographing a product. The user information of the target user may be used to characterize the target user, and may include, but is not limited to, at least one of: text, numerical values, symbols, images.
In some alternative implementations of the present embodiment, the user information may include, but is not limited to, at least one of: attribute information, history behavior information. Wherein the attribute information may be used to characterize attributes of the user, such as gender attributes, age attributes, etc. The historical behavior information may be used to indicate a user's historical behavior, for example, the historical behavior information may include product images that the user has historically browsed and historical times that the product images were browsed.
Specifically, the execution body may acquire user information of the target user stored locally in advance, or may acquire user information of the target user transmitted from an electronic device (for example, a terminal device shown in fig. 1) connected to the execution body in a communication manner.
In this embodiment, the product image to be presented may be a predetermined product image to be presented to the user. The set of product images to be presented comprises at least one product image to be presented. Specifically, the executing body may acquire at least one product image to be presented, which is stored locally in advance, to form a product image set to be presented; or the execution body can acquire at least one product image to be presented, which is sent by the electronic equipment in communication connection with the execution body, so as to form a product image set to be presented.
Step 202, for a product image to be presented in a product image set to be presented, inputting the product image to be presented and user information into a pre-trained first evaluation model to obtain a first evaluation result.
In this embodiment, for the product image to be presented in the product image set to be presented obtained in step 201, the execution subject may input the product image to be presented and the user information into a first pre-trained evaluation model, so as to obtain a first evaluation result. Wherein, the first evaluation result is used for representing the interest degree of the user corresponding to the input user information on the product indicated by the input image of the product to be presented, and may include, but is not limited to, at least one of the following: literal, numerical, symbolic. For example, the first evaluation result may include a value of "0" or a value of "1", where the value of "0" may be used to characterize that the user corresponding to the entered user information is not interested in the product indicated by the entered image of the product to be presented; the value "1" may be used to characterize that the user to whom the entered user information corresponds is interested in the product indicated by the entered image of the product to be presented.
In this embodiment, the first evaluation model may be used to characterize a correspondence between the product image to be presented and the user information, and the first evaluation result corresponding to the product image to be presented and the user information. Specifically, as an example, the first evaluation model may be a table that is preset by a technician based on statistics of a large number of product images to be presented, user information of a user, and first evaluation results, and stores a plurality of corresponding relationship tables of the product images to be presented, the user information, and the first evaluation results corresponding to the product images to be presented and the user information.
Here, the first evaluation result in the correspondence table may be obtained by labeling by a technician, or may be generated based on a preset rule. Here, the preset rule may be a rule set in advance by a technician for the product image to be presented, for determining the user information and the first evaluation result corresponding to the product image to be presented based on the user information. For example, the product indicated by the product image to be presented is a skin care product. For the product image to be presented, the preset rule may be: the user information indicates that the user is female, and the first evaluation result is 'interested'; the user information indicates that the user is male and the first evaluation result is "not interested".
The first evaluation model may be a model obtained by training an initial model (for example, a neural network, an FM (Factorization Machine, factorizer) model, or the like) by a machine learning method based on a predetermined training sample.
In some alternative implementations of the present embodiment, the first evaluation model may be obtained by training the following steps:
at step 2021, a plurality of sample presentation product images are acquired.
Here, the sample presentation image is a product image for presentation to the user, which is determined from a predetermined sample to-be-presented product image. The plurality of sample presentation product images may be a plurality of product images for presentation to a user or a plurality of product images for presentation to a plurality of users.
Specifically, a plurality of pre-stored product images for presentation may be acquired as a plurality of sample product images for presentation, or a plurality of product images for presentation transmitted by an electronic device connected in communication may be acquired as sample product images for presentation.
Step 2022, for a sample presentation product image among the plurality of sample presentation product images, executing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; a training sample is composed using the sample presentation product image, the acquired sample user information, and the determined sample first evaluation result.
Here, for a sample presentation product image among a plurality of sample presentation product images, the following steps may be performed:
first, user information of a user corresponding to a terminal presenting the sample presentation product image is acquired as sample user information.
The user corresponding to the terminal presenting the sample presentation product image may be a user using the terminal. Specifically, user information of a user corresponding to a terminal presenting the sample presentation product image stored in advance may be acquired as sample user information, or user information transmitted by a terminal presenting the sample presentation product image may be acquired as sample user information.
Then, based on the acquired sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image is determined.
In particular, various methods may be employed to determine a sample first evaluation result that characterizes a degree of interest of a user in a product indicated by the sample presentation product image based on the acquired sample user information. For example, a technician may mark the obtained sample user information and the first sample evaluation result corresponding to the sample presentation product image, so as to determine the obtained sample user information and the first sample evaluation result corresponding to the sample presentation product image; alternatively, the acquired sample user information and the sample first evaluation result corresponding to the sample presentation product image may be generated based on the preset rule.
Finally, a training sample is composed using the sample presentation product image, the acquired sample user information, and the determined sample first evaluation result.
It will be appreciated that a plurality of training samples may be obtained using a plurality of sample presentation product images.
Step 2023, using a machine learning method, taking sample user information and a sample presentation product image included in a training sample in the composed training samples as inputs, and taking a sample first evaluation result corresponding to the input sample user information and sample presentation product image as a desired output, and training to obtain a first evaluation model.
Specifically, a machine learning method may be used, in which sample user information and a sample presentation product image included in a training sample included in the composed training sample are input, a sample first evaluation result corresponding to the input sample user information and sample presentation product image is output as an expected output, and a predetermined initial model (for example, a neural network, an FM model, etc.) is trained, so as to finally obtain a first evaluation model.
In practice, the execution subject of the step for generating the first evaluation model may be the same as or different from the execution subject of the method for processing information. If the same, the execution subject of the step for generating the first evaluation model may store the trained first evaluation model locally after training to obtain the first evaluation model. If it is different, the execution subject of the step for generating the first evaluation model may send the trained first evaluation model to the execution subject of the method for processing information after training to obtain the first evaluation model.
And 203, selecting a product image to be presented from the product image set to be presented as a product image for presentation based on the obtained first evaluation result.
In this embodiment, based on the first evaluation result obtained in step 202, the execution subject may select the product image to be presented from the set of product images to be presented as the product image for presentation. The selected product image for presentation is the product image for presentation to the target user.
Specifically, the execution subject may select, based on the degree of interest indicated by the obtained first evaluation result, the product image to be presented from the set of product images to be presented as the product image for presentation by using various methods. For example, the product image to be presented with the highest interest degree indicated by the corresponding first evaluation result may be selected as the product image 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 user information 303 of a target user using the terminal device 302 from the communicatively connected terminal device 302, and a pre-stored set of product images 304 to be presented. The product image to be presented 304 includes a product image to be presented 3041 and a product image to be presented 3042. Then, for the to-be-presented product image 3041, the server 301 may input the to-be-presented product image 3041 and the user information 303 into the pre-trained first evaluation model 305, obtaining a first evaluation result (e.g., the numerical value "9") 3061. Here, the first evaluation result may be used to characterize the degree of interest of the target user in the product indicated by the product image 3041 to be presented (e.g., the larger the value, the higher the degree of interest). Similarly, for the product image to be presented 3042, the server 301 may input the product image to be presented 3042 and the user information 303 into the first evaluation model 305 to obtain a first evaluation result (e.g., a numerical value of "7") 3062. Finally, the server 301 may select, based on the obtained first evaluation result, a product image to be presented from the set of product images to be presented 304 as a product image for presentation 307. For example, the server 301 may select, from the set of product images to be presented 304, a product image to be presented having a larger value in the corresponding first evaluation result as the product image 307 for presentation, that is, select the product image 3041 to be presented as the product image 307 for presentation.
The method provided by the embodiment of the invention effectively utilizes the first evaluation model to evaluate the interested degree of the target user aiming at the product image to be presented, is beneficial to selecting the product image to be presented, which is interested by the target user, from the product image set to be presented based on the evaluation result as the product image finally used for presenting to the user, and improves the pertinence and the diversity of information processing.
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 comprises the steps of:
step 401, obtaining user information of a target user and a set of images of products to be presented.
In this embodiment, the execution subject of the method for processing information (e.g., the server shown in fig. 1) may acquire the user information of the target user and the set of product images to be presented through a wired connection or a wireless connection. The target user is a user of the presentation product image corresponding to the target user to be determined. The presentation product image corresponding to the target user is a product image for presentation to the target user. The product image may indicate a product. Specifically, as an example, the product image may be an image obtained by photographing a product. The user information of the target user may be used to characterize the target user, and may include, but is not limited to, at least one of: text, numerical values, symbols, images. The product image to be presented may be a predetermined product image to be presented to the user. The set of product images to be presented comprises at least one product image to be presented.
Step 402, for a product image to be presented in a product image set to be presented, inputting the product image to be presented and user information into a pre-trained first evaluation model to obtain a first evaluation result.
In this embodiment, for the product image to be presented in the product image set to be presented obtained in step 401, the execution subject may input the product image to be presented and the user information into a first pre-trained evaluation model, so as to obtain a first evaluation result. Wherein, the first evaluation result is used for representing the interest degree of the user corresponding to the input user information on the product indicated by the input image of the product to be presented, and may include, but is not limited to, at least one of the following: literal, numerical, symbolic. The first evaluation model may be used to characterize a correspondence between the to-be-presented product image and the user information and the input first evaluation result corresponding to the to-be-presented product image and the user information.
Step 403, selecting a product image to be presented from the product image set to be presented as a product image for presentation based on the obtained first evaluation result.
In this embodiment, based on the first evaluation result obtained in step 402, the execution subject may select the product image to be presented from the set of product images to be presented as the product image for presentation. The selected product image for presentation is the product image for presentation to the target user.
Step 404, for the presentation product image in the selected presentation product images, executing the following steps: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; and selecting the presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image.
In this embodiment, the product image to be presented in the product image set to be presented corresponds to at least one background image. Specifically, the at least one background image corresponding to the product image to be presented may be a background image predetermined by a technician based on the product image to be presented. Further, the execution subject may execute the following steps for the presentation product image among the presentation product images selected in step 403:
step 4041, at least one background image corresponding to the product image for presentation is acquired.
Specifically, at least one background image corresponding to the product image for presentation stored in advance may be acquired, or at least one background image corresponding to the product image for presentation transmitted by the electronic device connected in communication may be acquired.
Step 4042, adding the product image for presentation to the background image in the acquired at least one background image, to obtain a presentation image corresponding to the product image for presentation.
The presentation image is an image which simultaneously comprises a presentation product image and a background image corresponding to the presentation product image. Specifically, the execution subject may add the product image for presentation to the background image by using various methods, so as to obtain the image for presentation corresponding to the product image for presentation. For example, the execution subject may superimpose the product image for presentation on a preset position of the background image, and determine the superimposed image as the image for presentation corresponding to the product image for presentation; alternatively, the execution subject may perform image fusion on the product image for presentation and the background image by using an image fusion method, and determine the fused image as the image for presentation corresponding to the product image for presentation.
It should be noted that, the method of image fusion is a well-known technique widely studied and applied at present, and will not be described here.
Step 4043, selecting the presentation image from the obtained presentation images corresponding to the presentation product images as the target presentation image corresponding to the presentation product image.
Wherein the image for target presentation may be an image that is ultimately intended for presentation to a target user. It will be appreciated that since the presentation image corresponds to at least one background image, the obtained presentation image to which the presentation product image corresponds includes at least one.
Specifically, the execution subject may select, by using various methods, a presentation image from at least one presentation image corresponding to the obtained presentation product image as the target presentation image corresponding to the presentation product image. As an example, when the product image for presentation corresponds to only one image for presentation, the execution subject may directly determine the image for presentation as the target image for presentation to which the product image for presentation corresponds; when the product image for presentation corresponds to at least two images for presentation, the execution subject may select the image for presentation from the at least two images for presentation corresponding to the product image for presentation as the target image for presentation corresponding to the product image for presentation in a random selection manner.
In some optional implementations of this embodiment, the executing entity may further select the image for presentation from the images for presentation corresponding to the product image for presentation as the target image for presentation corresponding to the product image for presentation by:
First, the execution subject may input the presentation image and user information of the target user into a pre-trained second evaluation model for the presentation image in the presentation image corresponding to the presentation product image, and obtain a second evaluation result.
Wherein, the second evaluation result may be used for representing the interest degree of the user corresponding to the input user information in the input image for presentation, and may include, but is not limited to, at least one of the following: literal, numerical, symbolic. For example, the second evaluation result may include a value of "0" or a value of "1", where the value of "0" may be used to characterize that the user to which the input user information corresponds is not interested in the input presentation image; the value "1" may be used to characterize that the user to which the entered user information corresponds is interested in the entered presentation image.
In this implementation, the second evaluation model may be used to characterize a correspondence between the presentation image and the user information and the second evaluation result corresponding to the input presentation image and user information. Specifically, as an example, the second evaluation model may be a table in which a plurality of images for presentation, and correspondence relation between user information and second evaluation results corresponding to the images for presentation and the user information are stored, which are predetermined by a technician in advance based on statistics of a large number of images for presentation, user information of the user, and the second evaluation results.
Here, the second evaluation result in the correspondence table may be obtained by labeling by a technician, or may be generated based on a preset rule. Here, the preset rule may be a rule set in advance for the technician for the presentation image for determining the user information and the second evaluation result corresponding to the presentation image based on the user information. For example, a presentation image may be used for user click, for which the preset rules may be: the user information indicates that the user clicks the image for presentation, and the second evaluation result is "interested"; the user information indicates that the user has not clicked on the image for presentation, and the second evaluation result is "no interest".
The second evaluation model may be a model obtained by training an initial model (for example, a neural network, an FM model, or the like) by a machine learning method based on a predetermined training sample. It should be noted that the training process of the second evaluation model is substantially the same as the training process of the first evaluation model in the embodiment corresponding to fig. 2, and will not be described herein.
Then, the execution subject may select, based on the obtained second evaluation result, a presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image.
Specifically, the execution subject may select, based on the degree of interest indicated by the obtained second evaluation result, the image for presentation from the images for presentation corresponding to the product images for presentation as the image for target presentation corresponding to the product image for presentation by using various methods. For example, the presentation image with the highest degree of interest indicated by the corresponding second evaluation result may be selected as the target presentation image.
In some optional implementations of this embodiment, after selecting the presentation image from the presentation images corresponding to the presentation product images as the target presentation image corresponding to the presentation product image, the execution subject may further output the selected target presentation image to a terminal used by the target user.
The steps 401, 402, and 403 are identical to the steps 201, 202, and 203 in the foregoing embodiments, and the descriptions of the steps 201, 202, and 203 are also applicable to the steps 401, 402, and 403, which are not repeated herein.
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 this embodiment highlights the step of obtaining the target presentation image corresponding to the presentation product image based on the background image corresponding to the presentation product image after obtaining the presentation product image. Therefore, the scheme described in the embodiment can further determine the display background of the product image for presentation, and generate the target presentation image for presentation to the user finally, so that the comprehensiveness of information processing is improved.
With further reference to fig. 5, as an implementation of the method shown in the foregoing figures, the present application provides an embodiment of an apparatus for processing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 5, the apparatus 500 for processing information of the present embodiment includes: an acquisition unit 501, an input unit 502, and a selection unit 503. Wherein the obtaining unit 501 is configured to obtain user information of a target user and a set of product images to be presented; the input unit 502 is configured to input the product image to be presented and the user information into a pre-trained first evaluation model for obtaining a first evaluation result, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented; the selection unit 503 is configured to select a product image to be presented from a set of product images to be presented as a product image for presentation based on the obtained first evaluation result.
In the present embodiment, the acquisition unit 501 of the apparatus for processing information may acquire the user information of the target user and the set of images of the product to be presented by a wired connection manner or a wireless connection manner. The target user is a user of the presentation product image corresponding to the target user to be determined. The presentation product image corresponding to the target user is a product image for presentation to the target user. The product image may indicate a product. Specifically, as an example, the product image may be an image obtained by photographing a product. The user information of the target user may be used to characterize the target user, and may include, but is not limited to, at least one of: text, numerical values, symbols, images.
In this embodiment, the product image to be presented may be a predetermined product image to be presented to the user. The set of product images to be presented comprises at least one product image to be presented.
In this embodiment, for a product image to be presented in the product image set to be presented obtained by the obtaining unit 501, the input unit 502 may input the product image to be presented and user information into a first evaluation model trained in advance, to obtain a first evaluation result. Wherein, the first evaluation result is used for representing the interest degree of the user corresponding to the input user information on the product indicated by the input image of the product to be presented, and may include, but is not limited to, at least one of the following: literal, numerical, symbolic.
In this embodiment, the first evaluation model may be used to characterize a correspondence between the product image to be presented and the user information and the first evaluation result corresponding to the input product image to be presented and the user information.
In the present embodiment, based on the first evaluation result obtained by the input unit 502, the selection unit 503 may select a product image to be presented from a set of product images to be presented as a product image for presentation. The selected product image for presentation is the product image for presentation to the target user.
In some optional implementations of the present embodiments, the product image to be presented in the set of product images to be presented corresponds to at least one background image; the apparatus 500 may further include: an adding unit (not shown in the figure) configured to perform the following steps for a presentation product image among the selected presentation product images: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; and selecting the presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image.
In some optional implementations of this embodiment, the apparatus 500 may further include: an output unit (not shown in the figure) configured to output the selected image for target presentation to a terminal used by the target user.
In some optional implementations of the present embodiment, the adding unit may be further configured to: inputting the presentation image and the user information into a pre-trained second evaluation model for the presentation image corresponding to the presentation product image to obtain a second evaluation result, wherein the second evaluation result is used for representing the interest degree of the user corresponding to the input user information on the input presentation image; and selecting the presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image based on the obtained second evaluation result.
In some alternative implementations of the present embodiment, the first evaluation model may be obtained by training the following steps: acquiring a plurality of sample presentation product images; for a sample presentation product image among a plurality of sample presentation product images, performing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; forming a training sample by using the sample presentation product image, the acquired sample user information and the determined sample first evaluation result; and using a machine learning method, taking sample user information and a sample presentation product image which are included in a training sample in the formed training samples as input, taking a sample first evaluation result corresponding to the input sample user information and the sample presentation product image as expected output, and training to obtain a first evaluation model.
In some alternative implementations of the present embodiment, the user information may include, but is not limited to, at least one of: attribute information, history behavior information.
It will be appreciated that the elements described in the apparatus 500 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting benefits described above with respect to the method are equally applicable to the apparatus 500 and the units contained therein, and are not described in detail herein.
The device 500 provided in the above embodiment of the present application effectively uses the first evaluation model to evaluate the interest degree of the target user with respect to the product image to be presented, which is helpful for selecting the product image to be presented, which is interested by the target user, from the product image set to be presented as the product image to be presented to the user finally, based on the evaluation result, thereby improving the pertinence and diversity of information processing.
Referring now to FIG. 6, there is illustrated a schematic diagram of a computer system 600 suitable for use in implementing a server of an embodiment of the present application. The server illustrated in fig. 6 is merely an example, and should not be construed as limiting the functionality and scope of use of the embodiments herein.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which 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 required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through 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, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; 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 drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, according to embodiments of the present disclosure, the processes described above with reference to 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 shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 601. It should be noted that, the computer readable medium described in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any 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 context of this document, 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 the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. 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 of the foregoing. 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 flowcharts 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 involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, an input unit, and a selection unit. Wherein the names of these units do not constitute a limitation of the unit itself in some cases, for example, the acquisition unit may also be described as "unit acquiring user information of the target user and the set of product images to be presented".
As another aspect, the present application also provides a computer-readable medium that may be contained in the server described in the above embodiment; or may exist alone without being assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: acquiring user information of a target user and a product image set to be presented; inputting the product image to be presented and user information into a pre-trained first evaluation model to obtain a first evaluation result, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented; and selecting the product image to be presented from the product image set to be presented as the product image for presentation based on the obtained first evaluation result.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the invention referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the invention. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.
Claims (10)
1. A method for processing information, comprising:
acquiring user information of a target user and a product image set to be presented;
inputting the product image to be presented and the user information into a pre-trained first evaluation model for obtaining a first evaluation result, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented;
selecting a product image to be presented from the product image set to be presented as a product image for presentation based on the obtained first evaluation result;
the product image to be presented in the product image set to be presented corresponds to at least one background image; and
after the selecting the product image to be presented from the product image set to be presented as the product image for presentation, the method further comprises:
for a presentation product image of the selected presentation product images, the following steps are performed: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; selecting a presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product images;
The selecting the presentation image from the presentation images corresponding to the presentation product images as the target presentation image corresponding to the presentation product image includes:
inputting the presentation image and the user information into a pre-trained second evaluation model for the presentation image corresponding to the presentation product image to obtain a second evaluation result, wherein the second evaluation result is used for representing the interest degree of the user corresponding to the input user information on the input presentation image;
and selecting the presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image based on the obtained second evaluation result.
2. The method of claim 1, wherein after the selecting the presentation image from the presentation images corresponding to the presentation product images as the target presentation image corresponding to the presentation product image, the method further comprises:
and outputting the selected image for target presentation to a terminal used by the target user.
3. The method of claim 1, wherein the first evaluation model is trained by:
Acquiring a plurality of sample presentation product images;
for a sample presentation product image among a plurality of sample presentation product images, performing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; forming a training sample by using the sample presentation product image, the acquired sample user information and the determined sample first evaluation result;
and using a machine learning method, taking sample user information and a sample presentation product image which are included in a training sample in the formed training samples as input, taking a sample first evaluation result corresponding to the input sample user information and the sample presentation product image as expected output, and training to obtain a first evaluation model.
4. A method according to one of claims 1-3, wherein the user information comprises at least one of: attribute information, history behavior information.
5. An apparatus for processing information, comprising:
the acquisition unit is configured to acquire user information of a target user and a product image set to be presented;
The input unit is configured to input the product image to be presented and the user information into a pre-trained first evaluation model for the product image to be presented in the product image set to be presented, and a first evaluation result is obtained, wherein the first evaluation result is used for representing the interest degree of a user corresponding to the input user information on a product indicated by the input product image to be presented;
a selecting unit configured to select a product image to be presented from the set of product images to be presented as a product image for presentation based on the obtained first evaluation result;
the product image to be presented in the product image set to be presented corresponds to at least one background image; and
the apparatus further comprises:
an adding unit configured to execute the following steps for a presentation product image among the selected presentation product images: acquiring at least one background image corresponding to the product image for presentation; adding the product image for presentation to the background image of the at least one acquired background image to obtain a presentation image corresponding to the product image for presentation; selecting a presentation image from the obtained presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product images;
The adding unit is further configured to:
inputting the presentation image and the user information into a pre-trained second evaluation model for the presentation image corresponding to the presentation product image to obtain a second evaluation result, wherein the second evaluation result is used for representing the interest degree of the user corresponding to the input user information on the input presentation image;
and selecting the presentation image from the presentation images corresponding to the presentation product images as a target presentation image corresponding to the presentation product image based on the obtained second evaluation result.
6. The apparatus of claim 5, wherein the apparatus further comprises:
and an output unit configured to output the selected image for target presentation to a terminal used by the target user.
7. The apparatus of claim 5, wherein the first evaluation model is trained by:
acquiring a plurality of sample presentation product images;
for a sample presentation product image among a plurality of sample presentation product images, performing the steps of: acquiring user information of a user corresponding to a terminal presenting the sample presentation product image as sample user information; determining, based on the obtained sample user information, a sample first evaluation result for characterizing a degree of interest of the user in the product indicated by the sample presentation product image; forming a training sample by using the sample presentation product image, the acquired sample user information and the determined sample first evaluation result;
And using a machine learning method, taking sample user information and a sample presentation product image which are included in a training sample in the formed training samples as input, taking a sample first evaluation result corresponding to the input sample user information and the sample presentation product image as expected output, and training to obtain a first evaluation model.
8. The apparatus of one of claims 5-7, wherein the user information comprises at least one of: attribute information, history behavior information.
9. 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, causes the one or more processors to implement the method of any of claims 1-4.
10. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287919.8A CN111125501B (en) | 2018-10-31 | 2018-10-31 | Method and device for processing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287919.8A CN111125501B (en) | 2018-10-31 | 2018-10-31 | Method and device for processing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111125501A CN111125501A (en) | 2020-05-08 |
| CN111125501B true CN111125501B (en) | 2023-07-25 |
Family
ID=70485471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811287919.8A Active CN111125501B (en) | 2018-10-31 | 2018-10-31 | Method and device for processing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125501B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112907317B (en) * | 2021-01-27 | 2023-08-04 | 北京百度网讯科技有限公司 | Information pushing method, device, equipment, storage medium and program product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107862058A (en) * | 2017-11-10 | 2018-03-30 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| WO2018166288A1 (en) * | 2017-03-15 | 2018-09-20 | 北京京东尚科信息技术有限公司 | Information presentation method and device |
| CN108573054A (en) * | 2018-04-24 | 2018-09-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201212518D0 (en) * | 2012-07-13 | 2012-08-29 | Deepmind Technologies Ltd | Method and apparatus for image searching |
| US20140072226A1 (en) * | 2012-09-13 | 2014-03-13 | International Business Machines Corporation | Searching and Sorting Image Files |
| US9384422B2 (en) * | 2014-04-04 | 2016-07-05 | Ebay Inc. | Image evaluation |
| CN106295832B (en) * | 2015-05-12 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Product information pushing method and device |
| CN105975581B (en) * | 2016-05-05 | 2019-05-17 | 腾讯科技（北京）有限公司 | Methods of exhibiting, client and the server of media information |
| CN106407425A (en) * | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| CN107292713A (en) * | 2017-06-19 | 2017-10-24 | 武汉科技大学 | A kind of rule-based individual character merged with level recommends method |
-
2018
- 2018-10-31 CN CN201811287919.8A patent/CN111125501B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018166288A1 (en) * | 2017-03-15 | 2018-09-20 | 北京京东尚科信息技术有限公司 | Information presentation method and device |
| CN107862058A (en) * | 2017-11-10 | 2018-03-30 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN108573054A (en) * | 2018-04-24 | 2018-09-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
Non-Patent Citations (1)
| Title |
|---|
| 一种新型异源图像融合质量评价模型;宋乐;林玉池;刘启海;赵美蓉;冯伟昌;;激光与红外(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111125501A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804450B (en) | Information pushing method and device | |
| CN107944481B (en) | Method and apparatus for generating information | |
| CN107577807B (en) | Method and device for pushing information | |
| CN111125574B (en) | Method and device for generating information | |
| CN109446442B (en) | Method and apparatus for processing information | |
| CN109255037B (en) | Method and apparatus for outputting information | |
| CN109271557B (en) | Method and apparatus for outputting information | |
| CN108804452B (en) | Multimedia resource cover display method and device | |
| CN109413056B (en) | Method and apparatus for processing information | |
| CN109873756B (en) | Method and apparatus for transmitting information | |
| CN111061956A (en) | Method and apparatus for generating information | |
| CN113971243A (en) | Data processing method, system, equipment and storage medium applied to questionnaire survey | |
| CN110866040A (en) | User portrait generation method, device and system | |
| CN110825988A (en) | Information display method and device and electronic equipment | |
| CN108600329B (en) | Method and equipment for pushing information and displaying information | |
| CN111897950A (en) | Method and apparatus for generating information | |
| CN108038172B (en) | Search method and device based on artificial intelligence | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN108600780B (en) | Method for pushing information, electronic device and computer readable medium | |
| CN109101309B (en) | Method and apparatus for updating user interface | |
| CN107885872B (en) | Method and device for generating information | |
| CN108509442B (en) | Search method and apparatus, server, and computer-readable storage medium | |
| CN111125502B (en) | Method and device for generating information | |
| CN109472028B (en) | Method and device for generating information | |
| CN111125501B (en) | Method and device for processing information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |