CN111339291B - Information display method and device and storage medium - Google Patents
Information display method and device and storage medium Download PDFInfo
- Publication number
- CN111339291B CN111339291B CN201811549935.XA CN201811549935A CN111339291B CN 111339291 B CN111339291 B CN 111339291B CN 201811549935 A CN201811549935 A CN 201811549935A CN 111339291 B CN111339291 B CN 111339291B
- Authority
- CN
- China
- Prior art keywords
- information
- display
- sample
- display information
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses an information display method, an information display device and a storage medium, which are used for improving the display effect and the user experience of information display. The information display method comprises the following steps: aiming at any display position, obtaining matching reference information between the display position and each display information in a display information set, wherein the matching reference information is determined according to matching parameters, and the matching parameters at least comprise content similarity between the original information and the display information; and distributing display information meeting the limiting conditions for the display position according to the matching reference information.
Description
Technical Field
The invention relates to the technical field of computer networks, in particular to an information display method, an information display device and a storage medium.
Background
The information flow uses a machine algorithm to accurately recommend and distribute news information, so that users can see favorite contents. The recommendation mechanism breaks through the traditional classification mode of news pages and presents the news pages in an 'information flow' mode flowing in real time like a waterfall. From the aspect of display form, the contents in the information flow are arranged up and down according to similar specification styles. Specific presentation information may be interspersed in the information stream, intermixed with the content.
In the prior art, when specific presentation information is inserted into an information stream, the whole process can be regarded as an allocation problem on a bipartite graph G = (I ═ J, E), as shown in fig. 1 a. I is a Supply set, represents a display position set under various limiting conditions, and comprises a plurality of display position nodes, wherein each display position node I corresponds to different weights s i Representing the total number of the display positions under the limiting condition, wherein J is a Demand set representing an information set to be displayed and comprises a plurality of display information nodes, and each display information node J corresponds to different weights d j The number of presentations required for the presentation information is indicated. Display position node and display information nodeAnd a connecting line (i, j) between the points belongs to E, and the showing position node meets the limiting condition of the showing information node.
However, in the process of allocating the display information node to the display position node, currently, the optimal matching between the display position node and the display information node is mainly considered, so that the shortage of the information to be displayed is minimized, and thus, the following problems may exist in the allocation result: the information to be displayed is not matched with the content of the displayed information in the current information stream, for example, a piece of financial displayed information is inserted between two pieces of sports content, so that on one hand, the displayed effect of the displayed information is reduced, and on the other hand, the user experience is also influenced.
Disclosure of Invention
The embodiment of the invention provides an information display method, an information display device and a storage medium, which are used for improving the display effect and the user experience of information display.
In a first aspect, an information display method is provided, including:
aiming at any display position, obtaining matching reference information between the display position and each display information in a display information set, wherein the matching reference information is determined according to matching parameters, and the matching parameters at least comprise content similarity between the native information and the display information;
and distributing display information meeting the limiting conditions for the display positions according to the matching reference information.
In a second aspect, an information display device is provided, comprising:
an obtaining unit, configured to obtain, for any display position, matching reference information between the display position and each piece of display information in a display information set, where the matching reference information is determined according to a matching parameter, and the matching parameter at least includes content similarity between the native information and the display information;
and the distribution unit is used for distributing the display information meeting the limiting conditions for the display position according to the matching reference information.
In a third aspect, a computing device is provided, which includes at least one processor and at least one memory, wherein the memory stores a computer program, and when the program is executed by the processor, the computer program causes the processor to execute the steps of the information presentation method.
In a fourth aspect, a computer-readable medium is provided, which stores a computer program executable by a computing device, and when the program is run on the computing device, the computer program causes the computing device to execute the steps of the information presentation method described above.
According to the information display method, the information display device and the storage medium, when the display information is distributed to the display position, the content similarity between the original information adjacent to the display position and the display information is considered, so that the content between the display information and the original information adjacent to the display position is more matched, the user experience is improved, the probability that the user browsing the original information browses the display information is increased, and the display effect of the display information is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1a is a schematic diagram illustrating a process of allocating a display position node to a display information node in the prior art;
FIG. 1b is a schematic diagram of an application scenario according to an embodiment of the present invention;
FIG. 2 is a schematic view illustrating an implementation flow of a method for determining content similarity between native information and display information according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a training process of an information classification model according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating an implementation of an information displaying method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of matching between a display location and display information according to an embodiment of the present invention;
FIG. 6a is a schematic structural diagram of an information presentation system according to an embodiment of the present invention;
FIG. 6b is a schematic diagram illustrating an implementation flow of matching display position and display information according to an embodiment of the present invention;
FIG. 6c is a schematic diagram of a display information display interface according to an embodiment of the present invention;
FIG. 7 is a schematic structural diagram of an information display device according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a computing device according to an embodiment of the present invention.
Detailed Description
First, some terms related to the embodiments of the present invention are explained to facilitate understanding by those skilled in the art.
Native information: in order to distinguish from the display information inserted in the information stream, in the embodiment of the present invention, original content in the information stream is referred to as native information, and the display forms of the native information and the display information may include texts, pictures, videos, or the like.
The terminal device according to the embodiments of the present invention may be a Personal Computer (PC), a tablet PC, a Personal Digital Assistant (PDA), a Personal Communication Service (PCs) phone, a notebook, a mobile phone, or a Computer having a mobile terminal, for example, a portable, pocket, hand-held, computer-embedded or vehicle-mounted mobile device, which can provide a device for providing a voice and/or data access network to a user, and exchange voice and/or data with wireless connectivity.
It should be noted that, the "plurality" or "a plurality" mentioned herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are merely for illustrating and explaining the present invention, and are not intended to limit the present invention, and that the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
Fig. 1b is a schematic view of an application scenario of the information displaying method according to the embodiment of the present invention. The user 10 accesses the information presentation server 12 through an application client installed in the terminal device 11, where the application client may be a browser of a web page or an application client installed in a terminal device, such as a mobile phone or a tablet computer. The information display server 12 may provide information display services for users, the application server 13 may provide information display positions, the information display server 12 may collect the requirements of the users for information display and the information display positions that the application server 13 may provide, and accordingly select corresponding display information from the display information to display through the application server 13, and the application server 13 may provide different internet services for the users, for example, information browsing services and video viewing services. In specific implementation, the type of the display information should be consistent with the service type provided by the application server 13, for example, if the application server 13 provides a consultation browsing service, the display information may be text information, picture information, and the like; the application server 13 provides a video viewing service, and the presentation information may be video information or the like.
The terminal device 11 and the information display server 12 and the application server 13 are communicatively connected through a network, which may be a local area network, a cellular network, a wide area network, and the like. The terminal device 11 may be a portable device (e.g., a mobile phone, a tablet, a notebook Computer, etc.) or a Personal Computer (PC), and the information presentation server 12 and the application server 13 may be any devices capable of providing internet services.
The information display method provided by the embodiment of the invention can be applied to the information display server 12, and the information display server 12 distributes corresponding display information to the information display position according to the collected information display requirements and the information display position and according to the information display method provided by the embodiment of the invention.
It should be understood that, in the implementation, the information presentation server 12 and the application server 13 may be combined.
In order to match the display information with the original information content of the adjacent position of the display position and improve the user experience and the information display effect, the display information with the information content similar to the original information content of the adjacent position of the display position can be selected from the display information for display. In the embodiment of the invention, whether the display information is similar to the native information can be judged by determining the content similarity between the display information and the native information.
In specific implementation, for the native information and the presentation information in the presentation information set, the content similarity between the native information and the presentation information may be determined according to the following procedure, as shown in fig. 2, including the following steps:
and S21, respectively determining feature vectors of the display information and the native information by using the information classification model.
The information classification model is obtained by training by using sample information with labels as training samples. The label represents the information type corresponding to the sample information, and the information type may include entertainment information, sports information, science and technology information, financial information, and the like. Before training begins, labeling a corresponding label for each piece of training sample information to identify an information type of the piece of sample information, and initializing a model parameter of an information classification model, where a training target is to determine a probability that the piece of sample information corresponds to N types of information, and N is the number of the information types, where N may be set according to direct needs, which is not limited in this embodiment of the present invention, and for example, N =10 may be set.
In specific implementation, a bayesian algorithm, a decision tree and its variants, a support vector machine and a neural network algorithm, a maximum entropy algorithm, a document theme generation (LDA) algorithm, a Logistic Regression (LR) algorithm, etc. may be used to train the sample information to obtain an information classification model, for understanding, the following takes the neural network algorithm as an example, and the information training model may be obtained by training the sample information according to the process shown in fig. 3, including the following steps:
and S31, reading sample information.
The sample information may be text, or may be pictures, videos, and the like.
And S32, extracting sample characteristics from the read sample information.
Wherein, the sample information comprises information title and/or information content. In the embodiment of the invention, the sample characteristics can be extracted from the information title and/or the information content. In specific implementation, the information title and/or the information content may be segmented to obtain a plurality of words. In this step, for the sample information and/or the information content included in the sample information, a word segmentation tool is used to perform word segmentation to obtain a plurality of words.
It should be noted that, for text-type information, the sample information may include an information title and information content, and for video-type information, in addition to the information title, a content description or a content introduction may be acquired as the information content.
In specific implementation, if the sample information is a picture or a video, besides extracting text features in a title or a content description of the picture or the video by using the method, features can be extracted from the picture or the video frame by using a convolutional neural network.
And S33, converting the extracted sample features into sample feature vectors, and inputting the sample feature vectors into the information classification model to obtain an output result.
In a specific implementation, the words obtained in step S32 may be converted into corresponding word vectors, for example, the words may be converted into their corresponding vectors by One Hot replication, or the words may be converted into vectors by word2vec, and the like, which is not limited in the embodiment of the present invention.
And converting the words into vectors, and then distributing the input information to the model to obtain an output result, wherein the output result comprises the prediction probability of the sample information corresponding to each prediction label, and the prediction probability of the sample information corresponding to each prediction label forms a characteristic vector corresponding to the sample information.
For example, for a certain sample of information, the output result is {0.1,0,0.88,0, 0.01,0}, and the vectors of each dimension respectively correspond to different labels, such as: if the label corresponding to the maximum probability is a sports label, the sample information can be determined to be sports information.
And S34, judging whether the output result of the information classification model is stable or not according to the label corresponding to the sample information and the prediction probability corresponding to each prediction label, if so, finishing the training, and if not, executing the step S35.
In this step, it is determined whether the predicted label with the maximum probability corresponding to the sample information is consistent with the label initially labeled to the sample information, if so, it is further determined whether the accuracy of the output result of the information distribution model reaches a preset value, if so, it is determined that the output result is stable, and if not, or the predicted label with the maximum probability is inconsistent with the label initially labeled to the sample information, it is determined that the output result is unstable.
And S35, adjusting model parameters and executing the step S31.
In this step, the parameters of the information classification model are adjusted, and training is restarted until the output result of the information classification model is judged to be stable, so that the information classification model can be obtained.
In order to reduce the amount of calculation in the information classification model training, in the implementation, only one of the information title and the information content may be used as the input data for the model training, and naturally, in order to improve the accuracy of the model training result, the information title and the information content may be used as the input data for the model training at the same time.
And extracting feature vectors capable of representing the features of the display information and the native information from the display information and the native information by using the trained information classification model. Taking N =10 as an example, the extracted feature vector is a 10-dimensional vector.
In specific implementation, in order to improve the accuracy of the feature vector, in the embodiment of the present invention, an experience rule may be added to the extracted feature vector, where the experience rule is a correspondence between the key terms and information types corresponding to the key terms, for example, for a basketball game, the corresponding information type may be preset as sports information, so that the sports information may be determined as long as the display information or the native information includes the basketball game; for another example, the type of information corresponding to the word zhongelin may be preset as entertainment information, so that as long as the display information or the original information contains zhongelin, it may be determined as entertainment information or the like. The keyword words may be words with the highest occurrence frequency in the information, that is, words with the highest word frequency. Based on this, after obtaining the feature vector corresponding to the presentation information and the native information according to the output result of the information classification model, further determining whether the key word has a corresponding information type, if so, updating the feature vector with a probability corresponding to the information type label corresponding to the key word of 1, for example, in the above example, the probability corresponding to the sports information is 0.88, if it is determined that the information is the sports information according to the key word, the probability corresponding to the sports information may be modified to 1, and the updated feature vector is as follows: {0.1,0,1,0,0,0,0,0.01,0.01,0}.
And S22, determining the content similarity between the feature vector of the display information and the feature vector of the native information.
In this step, a result obtained by normalizing the dot product result of the feature vector corresponding to the presentation information and the feature vector of the native information may be determined as the content similarity between the two.
In order to improve the matching speed between the display position and the display information, in the specific implementation, for each display information contained in the display information set, the content similarity between the display information and each piece of native information in the current information stream may be predetermined, so that when the display position and the display information need to be matched, the matching may be directly performed according to the similarity between the display position and the display information.
As shown in fig. 4, in the embodiment of the present invention, the matching between the display position and the display information may be performed according to the following method:
s41, aiming at any display position, obtaining matching reference information between the display position and each piece of display information in the display information set.
The matching reference information is determined according to the matching parameters, and the matching parameters at least comprise content similarity between the native information adjacent to the display position and the display information.
As shown in fig. 5, which is a schematic diagram of matching between the presentation position and the presentation information, for the presentation position i, the adjacent native information may be content i or content i +1, or information i and information i +1. In the latter case, that is, when the original information adjacent to the display position includes the information i and the information i +1, when determining the content similarity between the display information and the original information, corresponding weights may be preset for the information i and the information i +1, and the content similarity between the display information and the original information may be determined according to the weights of the information i and the information i +1. The weights corresponding to the information i and the information i +1 may be the same, that is, 0.5, or different, and may be set according to actual needs in specific implementation. Taking the weights corresponding to the information i and the information i +1 as 0.1 and 0.9, respectively, the content similarity between the presentation information and the native information can be determined according to the following formula: α × 0.1+ β × 0.9, where α represents a dot product of the feature vector corresponding to the presentation information and the information i, and β represents a dot product of the feature vector corresponding to the presentation information and the information i +1.
In specific implementation, after obtaining the feature vectors corresponding to the native information and the display information, the similarity between the native information and the display information may also be determined by using cosine distance, pearson distance, KL (relative entropy) distance methods, and the like, which is not limited in the embodiment of the present invention.
And S42, distributing display information meeting the limiting conditions for the display position according to the matching reference information.
In one embodiment, the presentation information may be sorted according to content similarity between each presentation information in the presentation information set and the native information adjacent to the presentation position, and the presentation information that satisfies the constraint condition and is allocated to the presentation position is sequentially selected from the presentation information set.
For example, the presentation position may be assigned with presentation information that satisfies the constraint condition and matches the reference information most. If the matching parameters only contain the content similarity, the corresponding display information with the maximum content similarity is selected in the step.
In specific implementation, the limitation condition generally includes a limitation condition predefined by the display information provider, and may also include a limitation condition predefined by the display position provider, for example, a position interval between adjacent display information, a position where the display information must be displayed, a position where the display information cannot be displayed, and the like.
In specific implementation, the matching parameter may further include at least one of the following: the probability of the presentation location being presented and the probability of the presentation information being presented.
The probability of the display position being displayed is determined according to the browsing times and the display position displaying times of the display page containing the display position. For example, if the number of times that the presentation page including the presentation position is viewed is 10000 times and the number of times that the presentation position is presented is 500 times, it can be determined that the probability that the presentation position is presented is 500/10000=5%. The probability of the displayed display information is determined according to the number of display positions required to display the display information and the number of display positions meeting the display limiting condition corresponding to the display information, for example, the number of required display times of the display information is 100 times, and the number of display positions meeting the display limiting condition corresponding to the display information is 200, then the probability of the displayed display information is 100/200=50%, and in the information display process, the speed of displaying the display information can be controlled according to the probability of the displayed display information.
In particular, if the matching parameters include the content similarity and the probability that the display position is displayed and/or the probability that the display information is displayed, the matching reference information may be determined according to the content similarity between the native information and the display information and the probability that the display position is displayed and/or the probability that the display information is displayed. In one embodiment, the determination may be based on a product of content similarity between the native information and the presentation information and a probability that the presentation location is presented and/or a probability that the presentation information is presented. Taking the matching parameters including the content similarity, the probability of the display position being displayed, and the probability of the display information being displayed as an example, the specific implementation may determine the matching reference information between the display information and the native information according to the following formula: simi (i, j) locationimprob (i) Theta (j), wherein:
simi (i, j) represents the content similarity between the presentation position i and the presentation information j;
LocationImpProb (i) represents the probability that the presentation position is presented;
theta (j) represents the probability that the presentation information j is presented.
For a better understanding of the embodiments of the present invention, a detailed implementation of the embodiments of the present invention will be described below with reference to the information display system architecture diagram provided by the embodiments of the present invention. As shown in fig. 6a, it is a schematic diagram of an information presentation system architecture, which is composed of three parts: the system comprises a display information off-line inquiry system, an off-line model training system and an on-line information display system, wherein:
the off-line model training system is used for training sample information by utilizing various classification algorithms, wherein the sample information comprises native information from the on-line information display system and display information from a display information set, native information features and display information features are extracted from the native information and the display information and serve as input of an information classification model, bayesian algorithm, decision tree and variation thereof, support vector machine and neural network algorithm, maximum entropy algorithm, document theme generation (LDA) algorithm, logistic Regression (LR) algorithm and the like can be used for training the sample information in the training process, output model parameters of the trained information classification model can be used for extracting the display information off line or extracting the native information features on line, and output results are used for determining content similarity between the two.
The online information display system is used for acquiring the original information of the adjacent positions of the display positions when the display positions need to be matched with the display information, extracting the information characteristics of the original information by using the model parameters output by the information classification model obtained by the training of the offline model training system, calculating the content similarity of the original information and the display information by using the extracted characteristics, and outputting the determined content similarity to the display information release engine for selection of matching with the proper display information. The online native information can also be used as sample information for training an information classification model.
The display information off-line query system is used for querying available display positions in a future period of time, extracting information characteristics of display information by using model parameters of an information classification model output by the on-line information display system according to the display information provided by a display information provider, querying display positions meeting requirements in the available display positions by using the extracted information characteristics, for example, judging display positions which are required by the display information provider and are related to sports according to the extracted information characteristics, wherein the required number is 50, the available display positions are assumed to be 100, the display positions which are related to the sports are 80, and outputting query results to the provider. In particular, the presentation information provided by the presentation information provider can also be used for training the information distribution model.
Based on the system architecture diagram shown in fig. 6a, the information display method provided in the embodiment of the present invention may be implemented according to the flow shown in fig. 6 b:
s61, the displayed information offline inquiry system receives the information inquiry request.
In specific implementation, when the information provider needs to display the display information, the information provider can submit an information query request to the display information offline query system, wherein the information query request carries the display information to be displayed.
S62, the displayed information offline inquiry system extracts first information features from the displayed information by using the information classification model.
In this step, the displayed information offline query system extracts the first information feature from the displayed information by using the information classification model obtained by the training of the offline model training system.
And S63, inquiring the display position meeting the requirement in the available display positions according to the extracted first information characteristic by the display information offline inquiry system.
And S64, the display information offline query system returns a query result.
In this step, the display information offline inquiry system returns the number of available display positions to the information provider.
And S65, receiving a display position reservation request by the offline model training system.
In specific implementation, the information provider submits a display position reservation request through the information display and subscription system if determining to reserve the available display position for information display according to the query result, wherein the display position reservation request carries information to be displayed.
And S66, the off-line model training system extracts the second information characteristic of the display information by using the information classification model and submits the second information characteristic to the on-line information display system.
And the offline model training system adds the received display information into the display information set, and extracts the second information characteristic of the received display information by using the information classification model.
In addition, the offline model training can also add the obtained display information to the sample information for the update training of the information classification model.
And S67, when the display position needs to be matched with the display information, the online display system acquires the native information of the position close to the display position.
And S68, the online display system extracts a third information characteristic of the original information by using the information classification model.
And S69, the online display system determines the content similarity between the display information and the original information according to the second information characteristic and the third information characteristic.
S610, the online display system determines matching reference information corresponding to each display information.
In specific implementation, the online display system can determine matching reference information corresponding to each piece of display information according to the content similarity between the display information and the original information, the probability of the display position being displayed and the probability of the display information being displayed.
S611, the online display system sequences the display information according to the matching reference information corresponding to the display information.
In specific implementation, the online display system can be sorted according to the sequence of the matching reference information from large to small.
And S612, sequentially selecting the display information which is distributed for the display positions and meets the limiting conditions by the online display system according to the sequencing result.
In specific implementation, the online display system selects the display information which meets the limiting conditions and is the largest in matching reference information to be distributed to the display position.
According to the information display method provided by the embodiment of the invention, when the display information is inserted into the information stream, the content similarity between the native information and the display information is referred, so that the native information and the display information have relevance in content, as shown in fig. 6c, when the display information is inserted into the information stream of the code information, the native information of the adjacent position of the current display position can be obtained, the content similarity between the native information and each display information in the display information set is determined, and the display information which has high content similarity and meets the limited condition is selected to be inserted for display according to the content similarity, for example, the digital information 1 and the digital information 2 are computer product evaluation contents, and according to the matching result, a mobile phone product is distributed to the display position between the digital information 1 and the digital information 2 for display.
The information display method provided by the embodiment of the invention can be applied to an advertisement putting system, the display information offline inquiry part is used for screening out advertisement orders meeting the limiting conditions, the model training part is used for training an information classification model by utilizing advertisement texts and common texts, such as news texts, and the like, and the online information display part can be used for determining the matching reference information between the advertisement texts and texts in the information flow according to the display positions when the advertisement texts are required to be distributed to the display positions, and accordingly distributing the advertisement texts meeting the limiting conditions and having the maximum matching reference information for the display positions to display.
Based on the same inventive concept, the embodiment of the invention also provides an information display device, and as the principle of solving the problems of the device is similar to the information display method, the implementation of the device can refer to the implementation of the method, and repeated parts are not described again.
As shown in fig. 7, which is a schematic structural diagram of an information display apparatus provided in an embodiment of the present invention, the information display apparatus includes:
the sorting unit 71 is configured to sort, for any display position, the display information in the display information set according to matching reference information between the display position and each display information in the display information set, where the matching reference information is determined according to matching parameters, and the matching parameters at least include content similarity between the native information and the display information;
and an allocating unit 72, configured to sequentially select, from the sorted display information, the display information that is allocated to the display position and meets the limiting condition.
Optionally, the matching parameters further comprise at least one of: the display method comprises the steps that the probability of displaying the display position and the probability of displaying the display information are determined according to the browsing times of the display page containing the display position and the displayed times of the display position, and the displayed probability of the display information is determined according to the display times of the display information and the number of the display positions which are predicted to be used for displaying the display information.
Optionally, the information displaying apparatus provided in the embodiment of the present invention further includes:
and the second determining unit is used for determining the matching reference information according to the product of the content similarity between the native information and the display information and the probability of the display position being displayed and/or the probability of the display information being displayed before the sorting unit sorts the display information in the display information set according to the matching reference information between the display position and each display information in the display information set aiming at any display position.
Optionally, the information display apparatus provided in the embodiment of the present invention further includes:
the second determining unit is used for determining the feature vectors of the display information and the native information respectively by using an information classification model, wherein the information classification model is obtained by training sample information with labels; and determining the content similarity between the feature vector of the display information and the feature vector of the native information according to the feature vector of the display information and the feature vector of the native information.
Optionally, the information displaying apparatus provided in the embodiment of the present invention further includes:
the model training unit is used for reading sample information, and the sample information comprises an information title and/or information content; respectively segmenting the information title and/or the information content to obtain a plurality of words; converting each word obtained by word segmentation into a word vector, and inputting the word vector into the information classification model to obtain an output result, wherein the output result comprises the prediction probability of the sample information corresponding to each prediction label; judging whether the output result of the information classification model is stable or not according to the label corresponding to the sample information and the prediction probability corresponding to each prediction label; and if the information classification model is unstable, adjusting the model parameters to continue training until the output result of the information classification model is stable.
For convenience of description, the above parts are separately described as modules (or units) according to functional division. Of course, the functionality of the various modules (or units) may be implemented in the same or in multiple pieces of software or hardware in practicing the invention.
Having described the information presentation method and apparatus according to an exemplary embodiment of the present invention, a computing apparatus according to another exemplary embodiment of the present invention is next described.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Accordingly, various aspects of the present invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
In some possible embodiments, a computing device according to the present invention may include at least one processor, and at least one memory. Wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of the information presentation method according to various exemplary embodiments of the present invention described above in this specification. For example, the processor may execute step S41 shown in fig. 4, and rank, for any display position, the display information in the display information set according to the matching reference information corresponding to the display position; and S42, sequentially selecting the display information which is distributed for the display position and meets the limiting condition from the sorted display information.
The computing device 80 according to this embodiment of the invention is described below with reference to fig. 8. The computing device 80 shown in fig. 8 is only an example and should not impose any limitations on the functionality or scope of use of embodiments of the present invention.
As shown in fig. 8, the computing apparatus 80 is in the form of a general purpose computing device. Components of computing device 80 may include, but are not limited to: the at least one processor 81, the at least one memory 82, and a bus 83 connecting the various system components including the memory 82 and the processor 81.
The memory 82 may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 821 and/or cache memory 822, and may further include Read Only Memory (ROM) 823.
The computing apparatus 80 may also communicate with one or more external devices 84 (e.g., keyboard, pointing device, etc.), as well as with one or more devices that enable a user to interact with the computing apparatus 80, and/or with any devices (e.g., router, modem, etc.) that enable the computing apparatus 80 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interfaces 85. Also, computing device 80 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) through network adapter 86. As shown, network adapter 86 communicates with other modules for computing device 80 over bus 83. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computing device 80, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
In some possible embodiments, the various aspects of the information presentation method provided by the present invention may also be implemented in the form of a program product, which includes program code for causing a computer device to execute the steps in the information presentation method according to the various exemplary embodiments of the present invention described above in this specification when the program product runs on the computer device, for example, the computer device may execute step S41 shown in fig. 4, and rank the presentation information in the presentation information set according to the matching reference information corresponding to the presentation position for any presentation position; and S42, sequentially selecting the display information which is distributed for the display position and meets the limiting condition from the sorted display information.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A 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 (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable 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.
The program product for information presentation of embodiments of the present invention may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a computing device. However, the program product of the present invention is not limited in this regard and, in the present document, a 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.
A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may be any readable medium that is not a 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 readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device over any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., over the internet using an internet service provider).
It should be noted that although in the above detailed description several units or sub-units of the apparatus are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the units described above may be embodied in one unit, according to embodiments of the invention. Conversely, the features and functions of one unit described above may be further divided into embodiments by a plurality of units.
Moreover, while the operations of the method of the invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (14)
1. An information display method, comprising:
aiming at any display position, obtaining matching reference information between the display position and each piece of display information in a display information set, wherein the matching reference information is determined according to matching parameters, and the matching parameters at least comprise the original information adjacent to the display position and the content similarity between the display information;
and distributing display information meeting the limiting conditions for the display positions according to the matching reference information.
2. The method of claim 1, wherein determining content similarity between the native information and the presentation information comprises:
respectively determining the feature vectors of the display information and the native information by using an information classification model, wherein the information classification model is obtained by training sample information with labels;
and determining the content similarity between the feature vector of the display information and the feature vector of the native information according to the feature vectors of the display information and the native information.
3. The method according to claim 1, wherein allocating, according to the matching reference information, presentation information satisfying a constraint condition to the presentation position includes:
sorting the display information in the display information set according to the matching reference information;
and sequentially selecting the display information meeting the limiting conditions for the display positions from the display information set.
4. The method of claim 1, wherein the matching parameters further comprise at least one of: the display method comprises the steps that the probability of displaying the display position and the probability of displaying the display information are determined, wherein the probability of displaying the display position is determined according to the number of times of browsing a display page containing the display position and the number of times of displaying the display position, and the probability of displaying the display information is determined according to the number of times of displaying the display information and the number of display positions meeting the display limiting conditions corresponding to the display information.
5. The method of claim 4, wherein obtaining matching reference information between the presentation location and presentation information in a set of presentation information comprises:
and determining the matching reference information according to the content similarity between the native information and the display information and the probability of the display position being displayed and/or the probability of the display information being displayed.
6. The method of claim 2, wherein training with labeled sample information to obtain the information classification model comprises:
reading sample information;
extracting sample characteristics from the read sample information;
converting the extracted sample features into sample feature vectors, and inputting the sample feature vectors into the information classification model to obtain an output result, wherein the output result comprises the prediction probability of the sample information corresponding to each prediction label;
judging whether the output result of the information classification model is stable or not according to the label corresponding to the sample information and the prediction probability corresponding to each prediction label;
and if the information classification model is unstable, adjusting the model parameters to continue training until the output result of the information classification model is stable.
7. An information presentation device, comprising:
an obtaining unit, configured to obtain, for any display position, matching reference information between the display position and each piece of display information in a display information set, where the matching reference information is determined according to a matching parameter, and the matching parameter at least includes content similarity between native information adjacent to the display position and the display information;
and the distribution unit is used for distributing the display information meeting the limiting conditions for the display position according to the matching reference information.
8. The apparatus of claim 7, further comprising:
the first determining unit is used for determining the feature vectors of the display information and the native information respectively by using an information classification model, wherein the information classification model is obtained by training sample information with labels; and determining the content similarity between the feature vector of the display information and the feature vector of the native information according to the feature vectors of the display information and the native information.
9. The apparatus of claim 7, wherein the allocation unit is specifically configured to:
sorting the display information in the display information set according to the matching reference information;
and sequentially selecting the display information meeting the limiting conditions for the display positions from the display information set.
10. The apparatus of claim 7, wherein the matching parameters further comprise at least one of: the display method comprises the steps that the display position is displayed according to the display information requirement, and the display information is displayed according to the display limiting condition.
11. The apparatus of claim 7,
the obtaining unit is used for determining the matching reference information according to the content similarity between the native information and the display information and the probability of the display position being displayed and/or the probability of the display information being displayed.
12. The apparatus of claim 8, further comprising:
the model training unit is used for reading sample information and extracting sample characteristics from the read sample information; converting the extracted sample features into sample feature vectors, and inputting the sample feature vectors into the information classification model to obtain an output result, wherein the output result comprises the prediction probability of the sample information corresponding to each prediction label; judging whether the output result of the information classification model is stable or not according to the label corresponding to the sample information and the prediction probability corresponding to each prediction label; and if the information classification model is unstable, adjusting the model parameters and continuing training until the output result of the information classification model is stable.
13. A computing device comprising at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 6.
14. A computer-readable medium, in which a computer program is stored which is executable by a computing device, the program, when run on the computing device, causing the computing device to perform the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549935.XA CN111339291B (en) | 2018-12-18 | 2018-12-18 | Information display method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811549935.XA CN111339291B (en) | 2018-12-18 | 2018-12-18 | Information display method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111339291A CN111339291A (en) | 2020-06-26 |
| CN111339291B true CN111339291B (en) | 2022-12-30 |
Family
ID=71184985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811549935.XA Active CN111339291B (en) | 2018-12-18 | 2018-12-18 | Information display method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339291B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763123A (en) * | 2021-08-12 | 2021-12-07 | 阿里巴巴（中国）有限公司 | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2395808A (en) * | 2002-11-27 | 2004-06-02 | Sony Uk Ltd | Information retrieval |
| CN102346778B (en) * | 2011-10-11 | 2013-08-21 | 北京百度网讯科技有限公司 | Method and equipment for providing searching result |
| CN104112213B (en) * | 2013-04-19 | 2018-09-04 | 腾讯科技（深圳）有限公司 | The method and device of recommendation information |
| JP6157205B2 (en) * | 2013-05-10 | 2017-07-05 | 株式会社Ｎｔｔドコモ | Information processing system and information processing apparatus |
| CN106257448A (en) * | 2015-06-19 | 2016-12-28 | 阿里巴巴集团控股有限公司 | The methods of exhibiting of a kind of key word and device |
| CN105515956A (en) * | 2015-12-31 | 2016-04-20 | 小米科技有限责任公司 | Method and device for displaying communication messages |
| CN105677880B (en) * | 2016-01-12 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Dynamic divides the implementation method and device of display area |
| CN108694211B (en) * | 2017-04-11 | 2023-05-12 | 腾讯科技（深圳）有限公司 | Application distribution method and device |
| CN107577807B (en) * | 2017-09-26 | 2020-11-10 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
-
2018
- 2018-12-18 CN CN201811549935.XA patent/CN111339291B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111339291A (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9934515B1 (en) | Content recommendation system using a neural network language model | |
| CN109086439B (en) | Information recommendation method and device | |
| CN108319723B (en) | Picture sharing method and device, terminal and storage medium | |
| US10902077B2 (en) | Search result aggregation method and apparatus based on artificial intelligence and search engine | |
| CN109918662B (en) | Electronic resource label determination method, device and readable medium | |
| CN107256267A (en) | Querying method and device | |
| US11449553B2 (en) | Systems and methods for generating real-time recommendations | |
| CN102930054A (en) | Data search method and data search system | |
| CN111241394B (en) | Data processing method, data processing device, computer readable storage medium and electronic equipment | |
| US10678831B2 (en) | Page journey determination from fingerprint information in web event journals | |
| US10825071B2 (en) | Adaptive multi-perceptual similarity detection and resolution | |
| US10831809B2 (en) | Page journey determination from web event journals | |
| CN111950593A (en) | Method and device for recommending model training | |
| CN112989212B (en) | Media content recommendation method, device and equipment and computer storage medium | |
| CN109977292B (en) | Search method, search device, computing equipment and computer-readable storage medium | |
| CN111414561A (en) | Method and apparatus for presenting information | |
| CN112328889A (en) | Method and device for determining recommended search terms, readable medium and electronic equipment | |
| CN111339291B (en) | Information display method and device and storage medium | |
| CN112784157A (en) | Training method of behavior prediction model, behavior prediction method, device and equipment | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN110083687A (en) | A kind of information conversion method, equipment and storage medium | |
| CN117132323A (en) | Recommended content analysis method, recommended content analysis device, recommended content analysis equipment, recommended content analysis medium and recommended content analysis program product | |
| CN115329183A (en) | Data processing method, device, storage medium and equipment | |
| CN112632962A (en) | Method and device for realizing natural language understanding in human-computer interaction system | |
| CN113743973A (en) | Method and device for analyzing market hotspot trend |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40024224 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |