CN114519606A - Information propagation effect prediction method and device - Google Patents
Information propagation effect prediction method and device Download PDFInfo
- Publication number
- CN114519606A CN114519606A CN202210115066.XA CN202210115066A CN114519606A CN 114519606 A CN114519606 A CN 114519606A CN 202210115066 A CN202210115066 A CN 202210115066A CN 114519606 A CN114519606 A CN 114519606A
- Authority
- CN
- China
- Prior art keywords
- propagation
- target data
- characteristic information
- information
- effect
- 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.)
- Pending
Links
- 230000000694 effects Effects 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 95
- 230000008569 process Effects 0.000 claims abstract description 48
- 238000010586 diagram Methods 0.000 claims abstract description 40
- 238000000605 extraction Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 238000011176 pooling Methods 0.000 claims description 7
- 238000011217 control strategy Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 6
- 230000006855 networking Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 241001330002 Bambuseae Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method and a device for predicting an information propagation effect. One embodiment of the method comprises: determining a propagation graph of the target data in a propagation process; extracting first characteristic information of the propagation map, wherein a time attenuation parameter is used in the process of obtaining the first characteristic information; and predicting the propagation effect of the target data through a pre-trained prediction model according to the first characteristic information. The application provides a method for predicting the propagation effect of target data according to the propagation diagram of the target data, and the accuracy of the predicted propagation effect of the target data is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for predicting an information propagation effect.
Background
With the rapid development of mobile internet technology, various social network media platforms such as bamboo shoots in spring after rain appear rapidly. Because the user group on each large social network media platform is large and the propagation mode is simple, more and more e-commerce platforms start to carry out advertisement putting on the network media platforms, which can usually get more attention to better realize the purpose of commodity brand promotion. However, in the prior art, the propagation effect of the online advertisement is generally predicted by using the content characteristics of the advertisement, and the prediction result is not accurate.
Disclosure of Invention
The embodiment of the application provides a method and a device for predicting an information propagation effect.
In a first aspect, an embodiment of the present application provides a method for predicting an information propagation effect, including: determining a propagation graph of the target data in a propagation process; extracting first characteristic information of the propagation map, wherein a time attenuation parameter is used in the process of obtaining the first characteristic information; and predicting the propagation effect of the target data through a pre-trained prediction model according to the first characteristic information.
In some embodiments, the extracting the first feature information of the propagation map includes: and extracting first characteristic information of the propagation map through a transformer model, wherein the transformer model is used for representing the corresponding relation between the propagation map and the first characteristic information.
In some embodiments, the extracting, by the transformer model, the first feature information of the propagation map includes: determining a propagation sequence from a source user publishing the target data to each target user participating in the propagation process of the target data according to the propagation diagram representing the propagation diagram; and inputting each propagation sequence into a transformer model to obtain first characteristic information of the propagation diagram.
In some embodiments, the inputting each propagation sequence into the transformer model to obtain the first characteristic information of the propagation map includes: inputting each propagation sequence into a converter model according to the time sequence of the target user at the tail part in each propagation sequence participating in the propagation process of the target data, and determining high-order node representation information and time attenuation parameters of user nodes corresponding to each propagation sequence; and obtaining first characteristic information according to the high-order node representation information and the time attenuation parameters corresponding to the propagation sequences.
In some embodiments, the obtaining the first feature information according to the high-order node representation information and the time attenuation parameter corresponding to each propagation sequence includes: and carrying out weighting and pooling operation on the high-order node representation information and the time attenuation parameters corresponding to each propagation sequence to obtain first characteristic information.
In some embodiments, the above method further comprises: extracting second characteristic information of the target data; and predicting the propagation effect of the target data through the pre-trained prediction model according to the first characteristic information, wherein the predicting comprises the following steps: and predicting the propagation effect of the target data through the pre-prediction model by combining the first characteristic information and the second characteristic information.
In some embodiments, the predicting, by the prediction model, a propagation effect of the target data in combination with the first feature information and the second feature information includes: combining the first characteristic information and the second characteristic information to obtain combined characteristic information; and determining the propagation effect of the target data through a prediction model based on the combined characteristic information, wherein the prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect.
In some embodiments, the above method further comprises: and in response to the fact that the propagation effect representation target data are highly concerned in the preset time period, other propagation data are launched according to the launching mode of the target data.
In some embodiments, the above method further comprises: and optimizing the operation cost control strategy of the target data according to the propagation effect of the target data.
In a second aspect, an embodiment of the present application provides an apparatus for predicting an information propagation effect, including: a determining unit configured to determine a propagation map of the target data in a propagation process; a first extraction unit configured to extract first feature information of the propagation map, wherein a time decay parameter is used in obtaining the first feature information; and the prediction unit is configured to predict the propagation effect of the target data through the pre-trained prediction model according to the first characteristic information.
In some embodiments, the first extraction unit is further configured to: and extracting first characteristic information of the propagation map through a transformer model, wherein the transformer model is used for representing the corresponding relation between the propagation map and the first characteristic information.
In some embodiments, the first extraction unit is further configured to: determining a propagation sequence from a source user publishing the target data to each target user participating in the propagation process of the target data according to the propagation diagram; and inputting each propagation sequence into a transformer model to obtain first characteristic information of the propagation diagram.
In some embodiments, the first extraction unit is further configured to: inputting each propagation sequence into a converter model according to the time sequence of the target user at the tail part in each propagation sequence participating in the propagation process of the target data, and determining high-order node representation information and time attenuation parameters of user nodes corresponding to each propagation sequence; and obtaining first characteristic information according to the high-order node representation information and the time attenuation parameters corresponding to the propagation sequences.
In some embodiments, the first extraction unit is further configured to: and carrying out weighting and pooling operation on the high-order node representation information and the time attenuation parameters corresponding to each propagation sequence to obtain first characteristic information.
In some embodiments, the above apparatus further comprises: a second extraction unit configured to: extracting second characteristic information of the target data; and a prediction unit further configured to: and predicting the propagation effect of the target data through the prediction model by combining the first characteristic information and the second characteristic information.
In some embodiments, the prediction unit is further configured to: combining the first characteristic information and the second characteristic information to obtain combined characteristic information; and determining the propagation effect of the target data through a prediction model based on the combined characteristic information, wherein the prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect.
In some embodiments, the above apparatus further comprises: a first optimization unit configured to: and in response to the fact that the propagation effect representation target data are highly concerned in the preset time period, other propagation data are launched according to the launching mode of the target data.
In some embodiments, the above apparatus further comprises: a second optimization unit configured to: and optimizing the operation cost control strategy of the target data according to the propagation effect of the target data.
In a third aspect, the present application provides a computer-readable medium, on which a computer program is stored, where the program, when executed by a processor, implements the method as described in any implementation manner of the first aspect.
In a fourth aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement a method as described in any implementation of the first aspect.
According to the information propagation effect prediction method and device, the propagation diagram of the target data in the propagation process is determined; extracting first characteristic information of the propagation map; according to the first characteristic information, the propagation effect of the target data is predicted, so that a method for predicting the propagation effect of the target data according to the propagation diagram of the target data is provided, and the accuracy of the predicted propagation effect of the target data is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for predicting the effectiveness of information dissemination in accordance with the present application;
FIG. 3 is a schematic illustration of a propagation map according to the present embodiment;
fig. 4 is a schematic diagram of an application scenario of the prediction method of the information propagation effect according to the present embodiment;
FIG. 5 is a flow diagram of yet another embodiment of a method for predicting the effectiveness of information dissemination in accordance with the present application;
FIG. 6 is a network architecture diagram suitable for use in one embodiment of the present application;
fig. 7 is a block diagram of an embodiment of an information dissemination effect prediction apparatus according to the present application;
FIG. 8 is a block diagram of a computer system suitable for use in implementing embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary architecture 100 to which the information dissemination effect prediction method and apparatus of the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The communication connections between the terminal devices 101, 102, 103 form a topological network, and the network 104 serves to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may be hardware devices or software that support network connections for data interaction and data processing. When the terminal devices 101, 102, and 103 are hardware, they may be various electronic devices supporting network connection, information acquisition, interaction, display, processing, and the like, including but not limited to smart phones, tablet computers, electronic book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background processing server that predicts the propagation effect of target data from the propagation map of the target data based on the propagation effect prediction request issued by the terminal apparatuses 101, 102, 103. Optionally, the server may further optimize a target data delivery policy and an operation cost control policy according to a propagation effect of the target data. As an example, the server 105 may be a cloud server.
The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be further noted that the information dissemination effect prediction method provided by the embodiment of the present application may be executed by a server, a terminal device, or by the server and the terminal device in cooperation with each other. Accordingly, each part (for example, each unit) included in the information propagation effect prediction apparatus may be provided entirely in the server, entirely in the terminal device, or in each of the server and the terminal device.
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 an implementation. When the electronic device on which the prediction method of the information dissemination effect is executed does not need to perform data transmission with other electronic devices, the system architecture may include only the electronic device (e.g., a server or a terminal device) on which the prediction method of the information dissemination effect is executed.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for predicting the effect of information dissemination is shown, comprising the steps of:
In this embodiment, an execution subject (for example, a terminal device or a server in fig. 1) of the prediction method of the information dissemination effect may obtain the target data from a remote location or a local location based on a wired connection manner or a wireless connection manner, and determine a dissemination pattern of the target data in a dissemination process.
The target data may be data that achieves its data value by propagating between different users. By way of example, the targeting data may be online advertisements that characterize arbitrary content in arbitrary presentation forms. Presentation forms for targeted advertising, including but not limited to text, still images, moving images, video, and the like; for the content of the targeted advertisement, for example, the targeted advertisement is an advertisement shot by an e-commerce platform based on the characteristics of the article.
By determining the propagation process of the target data among different users, the execution body can determine the propagation graph of the target data. As an example, the e-commerce platform performs advertisement delivery on the social network media platform, and specifically publishes the target data through the source user performing the advertisement delivery. After the source user publishes the target data through the account of the social network media platform, other users of the social network media platform can participate in the transmission process of the target data through modes of commenting, agreeing, forwarding and the like.
In the target data transmission process, the executing entity may determine an account and a participation manner of each user participating in the target data transmission process, so as to obtain a transmission diagram.
In the target data propagation process, a propagation graph of the target data can be obtained according to a propagation path from a source user who issues the target data to each target user who participates in the target data propagation process. As an example, first, the execution subject collects the like, comment and forwarding records of the user on the target data in a certain social network media platform (e.g., microblog); the record is then converted into a network structure: g ═ V, E >, wherein V represents the node set, the node represents the users participating in the process of propagating the targeted advertisement; and E represents an edge set, each edge is used for connecting two user nodes and representing the relationship between the two connected user nodes. The basis for judging that two user nodes are not connected is the relationship of comment, forwarding and the like of the user nodes on the item advertisement. Finally, according to the network structure: g ═ V, E >, a propagation map (i.e., propagation Cascade map, Cascade Graph) can be built.
As shown in FIG. 3, a propagation diagram 300 of target data in a social networking media platform is shown. Wherein the advertisement is targeted to the source user a. After the source user A publishes the target advertisement, users B, C respectively forward the target advertisement published by the source user A, users D comment the target advertisement forwarded by the user B, users E, F respectively forward the target advertisement forwarded by the user C, and users G comment the target advertisement forwarded by the user E.
In this embodiment, the execution subject may extract first feature information of the propagation map. Wherein the time decay parameter is used in the process of obtaining the first characteristic information. The time attenuation parameter is used for representing attenuation information of the propagation value of the target user corresponding to the propagation diagram in the propagation process.
In this embodiment, the execution main body may extract the first feature information of the propagation map through the first feature extraction network.
The first feature extraction network may be any network model having a feature extraction function. For example, the first feature extraction Network may be CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), fast RCNN (fast cyclic Convolutional Neural Networks).
In some optional implementations of this embodiment, the executing main body may execute the step 202 by: through the transformer model, first characteristic information of the propagation map is extracted.
Wherein the transformer model is used for representing the corresponding relation between the propagation diagram and the first characteristic information
The Transformer model is a classic encoder-decoder model, and the encoder and decoder process information using an attention mechanism, such as a multi-head attention mechanism. Specifically, the transformer model encodes the propagation map through an encoder to obtain encoded information, and decodes the encoded information through a decoder to obtain high-order representation information of the propagation map, that is, the first characteristic information.
In the implementation mode, the first characteristic information of the propagation map is extracted through the converter model, and the accuracy of the obtained second characteristic information is improved.
In some optional implementations of this embodiment, the executing entity may extract the first feature information of the propagation map through the transformer model by executing:
firstly, according to the propagation diagram representing the propagation diagram, a propagation sequence from a source user publishing target data to each target user participating in the propagation process of the target data is determined.
With continued reference to FIG. 3, the source user to which the target data corresponds is user A, and the target users participating in the dissemination of the target advertisement include user B, C, D, E, F, G. The sequence of propagation from the source user to each target user includes a-B, A-B-D, A-C, A-C-E, A-C-E-G, A-C-F.
Secondly, inputting each propagation sequence into a transformer model to obtain first characteristic information of the propagation diagram.
It can be noted that the lengths of the propagation sequences corresponding to each user node are greatly different with probability, and in order to ensure the consistency of the lengths of the propagation sequences input into the transform model, a padding operation may be performed on sequences with insufficient lengths, and the padded padding value is 0.
As an example, for each propagation sequence, the execution subject may determine embedding (embedding) information of each user node in the propagation sequence, and input the embedding information and the position encoding information corresponding to the propagation sequence into the transformer model, thereby obtaining the second feature information of the propagation map. Wherein the position-coding information characterizes the position of the embedded information of the user node in the propagation sequence.
In the implementation manner, the propagation sequence corresponding to each target user in the propagation diagram is input to the transformer model, so that the transformer model can learn more propagation characteristics, and the accuracy and the expressive force of the obtained first characteristic information are further improved.
In some optional implementations of this embodiment, the executing body may execute the second step by:
firstly, inputting each propagation sequence into a converter model according to the time sequence of target users at the tail part in each propagation sequence participating in the propagation process of target data, and determining high-order node representation information and time attenuation parameters of user nodes corresponding to each propagation sequence; then, first characteristic information is obtained according to the high-order node representation information and the time attenuation parameter corresponding to each propagation sequence.
With continued reference to fig. 3, the target user B, D, C, E, G, F at the end of the propagation sequence a-B, A-B-D, A-C, A-C-E, A-C-E-G, A-C-F participates in the target advertisement propagation process in the order of B, C, D, E, F, G, and then each propagation sequence may be input into the transformer model in the order of a-B, A-C, A-B-D, A-C-E, A-C-F, A-C-E-G to determine the high-order node representation information and the time attenuation parameters of the user node corresponding to each propagation sequence. The time attenuation parameter is used for representing attenuation information of the propagation value of a target user corresponding to the propagation sequence in the propagation process.
After obtaining the high-order node representing information and the time attenuation parameter corresponding to each propagation sequence in the propagation graph, the execution main body may perform Weighted Sum Pooling (weighting and Pooling) operation on the high-order node representing information and the time attenuation parameter corresponding to each propagation sequence to obtain the first characteristic information of the propagation graph.
In the implementation manner, each propagation sequence is input into the converter model according to the time sequence of the target user at the tail part in each propagation sequence participating in the propagation process of the target data, so that the converter model can learn the attenuation information in the propagation process of the target data, and the accuracy of the obtained first characteristic information is further improved.
And step 203, predicting the propagation effect of the target data through the pre-trained prediction model according to the first characteristic information.
In this embodiment, the execution subject may predict the propagation effect of the target data through a pre-trained prediction model according to the first feature information.
As an example, the execution body described above may predict the propagation effect of the target data from the first feature information by a prediction model having a prediction function. It should be noted that the propagation process in step 201 is only a part of the propagation process of the target data from the beginning of propagation, and the present embodiment may predict the propagation effect of the whole propagation process from the beginning of propagation to a future time according to a part of the propagation diagram.
In some optional implementations of this embodiment, the execution main body may further perform the following operations: second feature information of the target data is extracted.
In this embodiment, the execution main body may extract the second feature information of the target data through a second feature extraction network.
The second feature extraction network may be any network model having a feature extraction function. For example, the second feature extraction Network may be CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), fast RCNN (fast cyclic Convolutional Neural Networks).
In this implementation, the executing main body may execute the step 203 as follows: and predicting the propagation effect of the target data by combining the first characteristic information and the second characteristic information.
The execution main body can predict a first transmission effect of the target data according to the first characteristic information; predicting a second propagation effect of the target data according to the second characteristic information; thereby, the propagation effect of the target data is obtained according to the first propagation effect and the second propagation effect. For example, the first propagation effect and the second propagation effect are weighted and summed to obtain the propagation effect of the target data. The execution main body can obtain a first propagation effect and a second propagation effect according to the first characteristic information and the second characteristic information in sequence through the neural network model.
Wherein the propagation effect can be characterized in the form of a numerical value. Wherein, the propagation effect numerical value can represent the total number of people in the target data propagation process.
In this implementation manner, a method for predicting the propagation effect of the target data by combining the first characteristic information of the propagation diagram of the target data and the second characteristic information of the target data is provided, so that the accuracy of the predicted propagation effect of the target data is improved.
In some optional implementations of this embodiment, the executing main body may execute the step 203 by:
first, the first characteristic information and the second characteristic information are combined to obtain combined characteristic information. Then, based on the combined feature information, the propagation effect of the target data is determined by the prediction model. The prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect. The prediction model may adopt any Network model with a prediction function, for example, a BP Network (Back-ProPagation Network) is also called a Back-ProPagation neural Network.
As an example, the execution body may first concatenate the first feature information and the second feature information to obtain combined feature information, and then input the combined feature information into the prediction model to obtain the propagation effect.
In the implementation mode, the propagation effect of the target data is predicted through the prediction model based on the combined characteristic information, and the accuracy of the prediction result is further improved.
With continuing reference to fig. 4, fig. 4 is a schematic diagram 400 of an application scenario of the prediction method for information propagation effect according to the present embodiment. In the application scenario of FIG. 4, an advertiser 401 cooperates with a source user 402, and the source user 402 posts a targeted advertisement on a social networking media platform 404 through a terminal device 403. After a period of targeted advertising, advertisers 401 intend to predict the effectiveness of the dissemination of targeted advertisements published by source users 401. Then, the advertiser 401 issues a propagation effect prediction request to the server 406 through the terminal device 405. First, the server 406 extracts first feature information of a propagation graph of a targeted advertisement in a social networking media platform. Then, second feature information of the target advertisement is extracted. Wherein the propagation graph characterizes a propagation graph of the target advertisement among the target users in the social networking media platform. And finally, predicting the propagation effect of the target advertisement by combining the first characteristic information and the second characteristic information.
The method provided by the above embodiment of the present application determines a propagation graph of the target data in a propagation process; extracting first characteristic information of the propagation map; according to the first characteristic information, the propagation effect of the target data is predicted, so that a method for predicting the propagation effect of the target data according to the propagation diagram of the target data is provided, and the accuracy of the predicted propagation effect of the target data is improved.
In some optional implementations of this embodiment, the execution main body may further perform the following operations: and optimizing the delivery strategy of the target data according to the propagation effect of the target data.
As an example, when the propagation effect representation target data is highly concerned by users in the social network media platform within a preset time period, the executing subject may continue to deliver the target data to the source user; when the propagation effect representation target data is of low interest to the user in the social network media platform within the preset time period, the executing body may terminate the target data delivery at the source user.
As yet another example, when the advertiser intends to increase the propaganda intensity of the target advertisement, the execution book block may determine other users to be collaborated similar to the source user from the social network media platform, so as to target the other users to be collaborated as the source user. The execution main body can determine the dimension similarity between the users from different dimensions (for example, the number of fans of the users, the structure of the fans, the activity of the fans and the purchase quantity of the fans), and further determine the similarity between the users according to the dimension similarity.
In the implementation mode, the advertisement delivery strategy can be optimized by the aid of the propagation effect of the target data, and the advertisement is guided to propagate better.
In some optional implementations of the embodiment, the executing entity may optimize the advertisement delivery policy by: and in response to the fact that the transmission effect representation target data are highly concerned in the preset time period, other transmission data are released according to the releasing mode of the target data.
In the implementation mode, the propagation effect of the target data can be referred to, other delivery modes of the propagation data can be guided, and the practicability of propagation effect prediction is expanded.
Furthermore, the execution subject can determine the similarity between different data, and then deliver advertisements similar to the target data according to the delivery mode of the target data. The execution main body can respectively extract the feature information of the target data and other propagation data through the feature extraction model, so that the similarity between the data is determined based on a similarity determination mode such as cosine similarity.
In some optional implementation manners of this embodiment, the executing book body may further perform the following operations: and optimizing an operation cost control strategy of the target data according to the influence of the target data.
As an example, for a certain commodity, if it is predicted that the target advertisement promoting the commodity is highly concerned in a future period of time, it may be determined that the commodity will be about to meet a wave of purchase tide on the e-commerce platform, and based on this, the merchant or the platform may be prompted to make a replenishment so as to prevent the increase of inventory cost caused by too early or too late stock stocking, and reduce the cost of operating inventory and the like.
With continuing reference to FIG. 5, an exemplary flow 500 of one embodiment of a method for predicting an effect of information dissemination in accordance with the present application is shown and includes the steps of:
And step 505, extracting second characteristic information of the target data.
And step 506, combining the first characteristic information and the second characteristic information to obtain combined characteristic information.
And 507, determining the propagation effect of the target data through the prediction model based on the combined characteristic information.
The prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect.
And step 508, optimizing a delivery strategy and/or an operation cost control strategy of the target data according to the propagation effect of the target data.
As can be seen from this embodiment, compared with the embodiment corresponding to fig. 2, the flow 500 of the information propagation effect prediction method in this embodiment specifically illustrates a determination process of the first characteristic information, a determination process of the propagation effect, and an application process of the propagation effect of the target data, so that the accuracy and the practicability of the propagation effect are further improved.
To further illustrate the information processing process of the present application, as shown in fig. 6, a network architecture 600 suitable for the present application is specifically illustrated as follows:
1. according to the propagation diagram of the target data in the social network media platform, the propagation sequences of A-B, A-C, A-B-D, A-C-E, A-C-F, A-C-E-G and the like are determined according to the time t of the target user participating in the propagation of the target advertisement, and node embedding information of user nodes in each propagation sequence is obtained.
2. And inputting the embedded information and the position coding information of the nodes corresponding to each propagation sequence into a converter model to obtain high-order node representation information and a time attenuation parameter lambda corresponding to each propagation sequence.
3. And weighting and pooling high-order node representation information and time attenuation parameters corresponding to each propagation sequence to obtain first characteristic information.
4. And extracting information of the target advertisement to obtain second characteristic information.
5. And combining the first characteristic information and the second characteristic information to obtain the propagation effect of the target data through the prediction model.
With continuing reference to fig. 7, as an implementation of the method shown in the above-mentioned figures, the present application provides an embodiment of an information propagation effect prediction apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied to various electronic devices.
As shown in fig. 7, the information propagation effect prediction apparatus includes: a determining unit 701 configured to determine a propagation map of the target data in a propagation process; a first extraction unit 702 configured to extract second feature information of the propagation map, wherein a time decay parameter is used in obtaining the first feature information; a prediction unit 703 configured to predict a propagation effect of the target data through a pre-trained prediction model according to the first feature information.
In some optional implementations of this embodiment, the first extracting unit 702 is further configured to: and extracting first characteristic information of the propagation map through a transformer model, wherein the transformer model is used for representing the corresponding relation between the propagation map and the first characteristic information.
In some optional implementations of this embodiment, the first extracting unit 702 is further configured to: determining a propagation sequence from a source user publishing the target data to each target user participating in the propagation process of the target data according to the propagation diagram; and inputting each propagation sequence into a transformer model to obtain first characteristic information of the propagation diagram.
In some optional implementations of the present embodiment, the first extracting unit 702 is further configured to: inputting each propagation sequence into a converter model according to the time sequence of the target user at the tail part in each propagation sequence participating in the propagation process of the target data, and determining high-order node representation information and time attenuation parameters of user nodes corresponding to each propagation sequence; and obtaining first characteristic information according to the high-order node representation information and the time attenuation parameters corresponding to the propagation sequences.
In some optional implementations of the present embodiment, the first extracting unit 702 is further configured to: and carrying out weighting and pooling operation on the high-order node representation information and the time attenuation parameters corresponding to each propagation sequence to obtain first characteristic information.
In some optional implementations of this embodiment, the apparatus further includes: a second extraction unit (not shown in the figure) configured to: extracting second characteristic information of the target data; and a prediction unit 703, further configured to: and predicting the propagation effect of the target data by combining the first characteristic information and the second characteristic information.
In some optional implementations of this embodiment, the prediction unit 703 is further configured to: combining the first characteristic information and the second characteristic information to obtain combined characteristic information; and determining the propagation effect of the target data through a prediction model based on the combined characteristic information, wherein the prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect.
In some optional implementations of this embodiment, the apparatus further includes: a first optimization unit (not shown in the figures) configured to: and in response to the fact that the propagation effect representation target data are highly concerned in the preset time period, other propagation data are launched according to the launching mode of the target data.
In some optional implementations of this embodiment, the apparatus further includes: a second optimization unit (not shown in the figures) configured to: and optimizing the operation cost control strategy of the target data according to the propagation effect of the target data.
In this embodiment, a determining unit in the information propagation effect prediction apparatus determines a propagation map of target data in a propagation process; the first extraction unit extracts second characteristic information of the propagation map; the prediction unit predicts the propagation effect of the target data according to the first feature information, thereby providing a method for predicting the propagation effect of the target data according to the propagation map of the target data, and improving the accuracy of the predicted propagation effect of the target data.
Referring now to FIG. 8, shown is a block diagram of a computer system 800 suitable for use in implementing devices of embodiments of the present application (e.g., devices 101, 102, 103, 105 shown in FIG. 1). The apparatus shown in fig. 8 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in fig. 8, the computer system 800 includes a processor (e.g., CPU, central processing unit) 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the system 800 are also stored. The processor 801, the ROM802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.
In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program, when executed by the processor 801, performs the above-described functions defined in the methods of the present application.
It should be noted that the computer readable medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the client computer, partly on the client computer, as a stand-alone software package, partly on the client computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the client computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a determination unit, a first extraction unit, and a prediction unit. Here, the names of the units do not constitute a limitation to the unit itself in some cases, and for example, the first extraction unit may also be described as a "unit that extracts the first feature information of the propagation map".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the computer device to: determining a propagation graph of the target data in a propagation process; extracting first characteristic information of the propagation map; and predicting the propagation effect of the target data according to the first characteristic information.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements in which any combination of the features described above or their equivalents does not depart from the spirit of the invention disclosed above. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (12)
1. A method for predicting information propagation effect comprises the following steps:
determining a propagation graph of the target data in a propagation process;
extracting first characteristic information of the propagation map, wherein a time attenuation parameter is used in the process of obtaining the first characteristic information;
and predicting the propagation effect of the target data through a pre-trained prediction model according to the first characteristic information.
2. The method of claim 1, wherein the extracting first feature information of the propagation map comprises:
and extracting first characteristic information of the propagation map through a transformer model, wherein the transformer model is used for representing the corresponding relation between the propagation map and the first characteristic information.
3. The method of claim 2, wherein the extracting first feature information of the propagation map through a transformer model comprises:
determining a propagation sequence from a source user who issues the target data to each target user who participates in the propagation process of the target data according to the propagation diagram;
and inputting each propagation sequence into the transformer model to obtain first characteristic information of the propagation diagram.
4. The method of claim 3, wherein the inputting each propagation sequence into the transformer model to obtain first characteristic information of the propagation map comprises:
inputting each propagation sequence into the converter model according to the time sequence of the target user at the tail part in each propagation sequence participating in the propagation process of the target data, and determining high-order node representation information and time attenuation parameters of user nodes corresponding to each propagation sequence;
and obtaining the first characteristic information according to the high-order node representation information and the time attenuation parameter corresponding to each propagation sequence.
5. The method according to claim 4, wherein the obtaining the first feature information according to the high-order node representation information and the time attenuation parameter corresponding to each propagation sequence includes:
and carrying out weighting and pooling operation on the high-order node representation information and the time attenuation parameters corresponding to each propagation sequence to obtain the first characteristic information.
6. The method according to any one of claims 1-5, further comprising:
extracting second characteristic information of the target data; and
the predicting the propagation effect of the target data through a pre-trained prediction model according to the first feature information comprises the following steps:
and predicting the propagation effect of the target data through the prediction model by combining the first characteristic information and the second characteristic information.
7. The method of claim 6, wherein the predicting, by the predictive model, the propagation effect of the target data in combination with the first feature information and the second feature information comprises:
combining the first characteristic information and the second characteristic information to obtain combined characteristic information;
and determining the propagation effect of the target data through the prediction model based on the combined characteristic information, wherein the prediction model is used for representing the corresponding relation between the combined characteristic information corresponding to the target data and the propagation effect.
8. The method according to any one of claims 1-7, further comprising:
and in response to determining that the propagation effect represents that the target data is highly concerned within a preset time period, releasing other propagation data by referring to a releasing mode of the target data.
9. The method according to any one of claims 1-7, further comprising:
and optimizing the operation cost control strategy of the target data according to the propagation effect of the target data.
10. An apparatus for predicting the effect of information propagation, comprising:
a determining unit configured to determine a propagation map of the target data in a propagation process;
a first extraction unit configured to extract second feature information of the propagation map, wherein a time decay parameter is used in obtaining the first feature information;
a prediction unit configured to predict a propagation effect of the target data through a pre-trained prediction model according to the first feature information.
11. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-9.
12. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210115066.XA CN114519606A (en) | 2022-01-29 | 2022-01-29 | Information propagation effect prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210115066.XA CN114519606A (en) | 2022-01-29 | 2022-01-29 | Information propagation effect prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114519606A true CN114519606A (en) | 2022-05-20 |
Family
ID=81596239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210115066.XA Pending CN114519606A (en) | 2022-01-29 | 2022-01-29 | Information propagation effect prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114519606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759482A (en) * | 2022-12-29 | 2023-03-07 | 人民网股份有限公司 | Social media content propagation prediction method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381581A (en) * | 2020-11-17 | 2021-02-19 | 东华理工大学 | Advertisement click rate estimation method based on improved Transformer |
| CN113590849A (en) * | 2021-01-27 | 2021-11-02 | 腾讯科技（深圳）有限公司 | Multimedia resource classification model training method and multimedia resource recommendation method |
| CN113610299A (en) * | 2021-08-06 | 2021-11-05 | 华侨大学 | Information propagation prediction method and device based on characteristic attenuation reinforced neural network |
| CN113688600A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Information propagation prediction method based on topic perception attention network |
| EP3916641A1 (en) * | 2020-05-27 | 2021-12-01 | Babylon Partners Limited | Continuous time self attention for improved computational predictions |
-
2022
- 2022-01-29 CN CN202210115066.XA patent/CN114519606A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3916641A1 (en) * | 2020-05-27 | 2021-12-01 | Babylon Partners Limited | Continuous time self attention for improved computational predictions |
| CN112381581A (en) * | 2020-11-17 | 2021-02-19 | 东华理工大学 | Advertisement click rate estimation method based on improved Transformer |
| CN113590849A (en) * | 2021-01-27 | 2021-11-02 | 腾讯科技（深圳）有限公司 | Multimedia resource classification model training method and multimedia resource recommendation method |
| CN113610299A (en) * | 2021-08-06 | 2021-11-05 | 华侨大学 | Information propagation prediction method and device based on characteristic attenuation reinforced neural network |
| CN113688600A (en) * | 2021-09-08 | 2021-11-23 | 北京邮电大学 | Information propagation prediction method based on topic perception attention network |
Non-Patent Citations (2)
| Title |
|---|
| 刘海峰: "社交网络用户交互模型及行为偏好预测研究", 《中国博士学位论文全文数据库 信息科技辑》, no. 4, 15 April 2015 (2015-04-15), pages 139 - 32 * |
| 吴茂贵等: "《智能系统与技术丛书 深入浅出Embedding 原理解析与应用实践》", 30 June 2021, 机械工业出版社, pages: 85 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759482A (en) * | 2022-12-29 | 2023-03-07 | 人民网股份有限公司 | Social media content propagation prediction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522483B (en) | Method and device for pushing information | |
| KR102123264B1 (en) | Method, apparatus, and system of improving online advertisement performance | |
| CN110555714A (en) | method and apparatus for outputting information | |
| CN109857908B (en) | Method and apparatus for matching videos | |
| CN109829164B (en) | Method and device for generating text | |
| CN113015010B (en) | Push parameter determination method, device, equipment and computer readable storage medium | |
| CN109493138B (en) | Information recommendation method and device, server and storage medium | |
| WO2019232093A1 (en) | Electronic content based on neural networks | |
| CN110866040A (en) | User portrait generation method, device and system | |
| CN111340220A (en) | Method and apparatus for training a predictive model | |
| US11188846B1 (en) | Determining a sequential order of types of events based on user actions associated with a third party system | |
| CN114519606A (en) | Information propagation effect prediction method and device | |
| CN114119123A (en) | Information pushing method and device | |
| CN113011911B (en) | Data prediction method and device based on artificial intelligence, medium and electronic equipment | |
| CN113836390B (en) | Resource recommendation method, device, computer equipment and storage medium | |
| CN113822734A (en) | Method and apparatus for generating information | |
| CN115131052A (en) | Data processing method, computer equipment and storage medium | |
| CN111787042A (en) | Method and device for pushing information | |
| CN116108810A (en) | Text data enhancement method and device | |
| US20230053859A1 (en) | Method and apparatus for outputting information | |
| US11900407B1 (en) | Computer-based systems involving machine learning associated with generation of recommended content and methods of use thereof | |
| CN111784377B (en) | Method and device for generating information | |
| CN111506643B (en) | Method, device and system for generating information | |
| CN109033343B (en) | Method and apparatus for generating information | |
| CN111767290B (en) | Method and apparatus for updating user portraits |
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 |