CN112243021A - Information pushing method, device, equipment and computer readable storage medium - Google Patents
Information pushing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112243021A CN112243021A CN202010447775.9A CN202010447775A CN112243021A CN 112243021 A CN112243021 A CN 112243021A CN 202010447775 A CN202010447775 A CN 202010447775A CN 112243021 A CN112243021 A CN 112243021A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- preset
- user
- order feature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000000605 extraction Methods 0.000 claims description 53
- 238000012545 processing Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 27
- 238000002372 labelling Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000011176 pooling Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000002265 prevention Effects 0.000 claims description 4
- 239000002699 waste material Substances 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 22
- 238000013461 design Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/10—Network architectures or network communication protocols for network security for controlling access to devices or network resources
- H04L63/105—Multiple levels of security
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an information pushing method, an information pushing device, information pushing equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring historical use data of at least one user in a target application; inputting the historical use data into a preset prediction model to obtain the probability of each user handling the target use permission; acquiring at least one target user with the probability of handling the target use permission exceeding a preset probability threshold; and pushing information corresponding to the use authority to the at least one target user. Through predicting the probability of handling the use permission of the user and pushing the pushing information corresponding to the use permission to the user handling the use permission with the probability exceeding the preset probability threshold value, the accurate pushing of the information can be realized, the resource waste is avoided, and the pushing efficiency is improved.
Description
Technical Field
The present application relates to the field of internet, and in particular, to an information pushing method, apparatus, device, and computer-readable storage medium.
Background
With the development of the internet and artificial intelligence, more and more online applications are moving into the lives of users. Such as an online shopping Application (APP), an online office APP, an online music APP, etc. In order to improve the use experience of the user on various applications, various application software provides different use authorities for the user, and when the user transacts the use authorities, more optimized services can be provided for the user according to the use authorities.
In order to enable users to know and handle different usage rights, in the prior art, information related to the usage rights is generally pushed to all users, so that interested users can handle the usage rights and perform trial operation.
However, when information is pushed by the method, part of users do not transact the use authority after knowing the use authority. Therefore, pushing information to all users often consumes resources, and the effect expected by the users cannot be achieved.
Disclosure of Invention
The application provides an information pushing method, an information pushing device, information pushing equipment and a computer readable storage medium, which are used for solving the technical problems that an existing information pushing method consumes resources and is poor in effect.
A first aspect of the present application provides an information pushing method, including:
acquiring historical use data of at least one user in a target application;
inputting the historical use data into a preset prediction model to obtain the probability of each user handling the target use permission;
acquiring at least one target user with the probability of handling the target use permission exceeding a preset probability threshold;
and pushing information corresponding to the use authority to the at least one target user.
In one possible design, the predictive model includes a vectorization sub-network, a low-order feature extraction sub-network, a medium-order feature extraction sub-network, and a high-order feature extraction sub-network;
the step of inputting the historical usage data into a preset prediction model to obtain the probability of transacting the target usage right of each user comprises the following steps:
inputting the historical use data into the vectorization sub-network to obtain a target vector corresponding to the historical use data;
inputting the target vector into the low-order feature extraction sub-network to obtain low-order feature data corresponding to the historical use data; inputting the target vector into the middle-order feature extraction sub-network to obtain middle-order feature data corresponding to the historical use data; the target vector is input into the high-order feature extraction sub-network to obtain high-order feature data corresponding to the historical use data;
and determining the probability of transacting the target use permission of each user according to the low-order feature data, the medium-order feature data and the high-order feature data.
In one possible design, the low-order feature extraction sub-network is an FM model;
correspondingly, the inputting the target vector into the low-order feature extraction sub-network to obtain the low-order feature data corresponding to the historical usage data includes:
inputting the target vector into the FM model for data processing;
and randomly discarding the interaction path in the FM model data processing process through a preset over-fitting prevention technology.
In one possible design, the mid-order feature extraction sub-network includes a convolutional layer, a pooling layer, and a fully-connected layer;
correspondingly, the inputting the target vector into the medium-order feature extraction sub-network to obtain medium-order feature data corresponding to the historical usage data includes:
acquiring characteristic information corresponding to the target vector through the convolutional layer and the pooling layer;
and splicing the characteristic information through the full connection layer to obtain the intermediate-order characteristic data.
In one possible design, the high-order feature extraction sub-network is a multi-head attention model.
In one possible design, before the inputting the historical usage data into the preset predictive model, the method further includes:
acquiring a preset data set to be processed from the data server, wherein the data set to be processed comprises historical use data of a plurality of users and use authority transacting information corresponding to the plurality of users;
marking historical use data of the users through the use authority transacting information to obtain a first data set to be trained;
and training a preset model to be trained through the first data set to be trained to obtain the prediction model.
In one possible design, the obtaining a preset data set to be processed from the data server includes:
and acquiring historical orders in a preset first time threshold from the data server, and/or acquiring historical use data corresponding to a user with a preference score exceeding a preset score threshold of any target item as the to-be-processed data set, wherein the preference score is obtained through calculation of a preset score calculation model, and the number of the browsed target web pages exceeds a preset number threshold within a preset second time threshold.
In a possible design, the data set to be processed further includes information of usage right types corresponding to a plurality of users; the method further comprises the following steps:
marking historical use data of the users through the information of the use authority types to obtain a second data set to be trained;
training a preset model to be trained through the second data set to be trained to obtain a type prediction model;
and inputting the historical use data into the type prediction model to obtain the type information of the transacting use permission of each user.
In one possible design, the data set to be processed further includes personalized browsing information corresponding to a plurality of users; the method further comprises the following steps:
marking historical use data of the users through the personalized browsing information to obtain a third data set to be trained;
training a preset model to be trained through the third data set to be trained to obtain a browsing page prediction model;
inputting the historical use data into the browsing page prediction model to obtain the personalized browsing page information of each user;
and pushing the personalized browsing page information to the at least one user.
A second aspect of the present application provides an information pushing apparatus, including:
the acquisition module is used for acquiring historical use data of at least one user in the target application;
the processing module is used for inputting the historical use data into a preset prediction model to obtain the probability of transacting the target use permission of each user;
the determining module is used for acquiring at least one target user with the probability of transacting the target use permission exceeding a preset probability threshold;
and the pushing module is used for pushing information corresponding to the use permission to the at least one target user.
A third aspect of the present application is to provide an information pushing apparatus, including: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the information push method according to the first aspect.
A fourth aspect of the present application is to provide a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is used for implementing the information pushing method according to the first aspect.
According to the information pushing method, the information pushing device, the information pushing equipment and the computer readable storage medium, the probability of transacting the use permission of the user is predicted, and the pushing information corresponding to the use permission is pushed to the user transacting the use permission with the probability exceeding the preset probability threshold, so that the accurate pushing of the information can be realized, the resource waste is avoided, and the pushing efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art according to these drawings.
FIG. 1 is a schematic diagram of a system architecture on which the present application is based;
fig. 2 is a schematic flowchart of an information pushing method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of an information pushing method according to a second embodiment of the present application;
FIG. 4 is a diagram of a network architecture of a predictive model provided by an embodiment of the present application;
fig. 5 is a schematic flowchart of an information pushing method according to a third embodiment of the present application;
fig. 6 is a diagram illustrating an information pushing method according to a fourth embodiment of the present application;
fig. 7 is a schematic flowchart of an information pushing method according to a fifth embodiment of the present application;
fig. 8 is a schematic diagram of personalized browsing information of a user according to an embodiment of the present application;
fig. 9 is a schematic diagram of information of a personalized browsing page provided in the embodiment of the present application;
fig. 10 is a schematic structural diagram of an information pushing apparatus according to a seventh embodiment of the present application;
fig. 11 is a schematic structural diagram of an information pushing apparatus according to an eighth embodiment of the present application;
fig. 12 is a schematic structural diagram of an information pushing apparatus according to a ninth embodiment of the present application;
fig. 13 is a schematic structural diagram of an information pushing apparatus according to a tenth embodiment of the present application;
fig. 14 is a schematic structural diagram of an information pushing apparatus according to an eleventh embodiment of the present application;
fig. 15 is a schematic structural diagram of an information pushing apparatus according to a twelfth embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained based on the embodiments in the present application belong to the protection scope of the present application.
In view of the above-mentioned technical problems that the existing information pushing method consumes resources and is not good in effect, the present application provides an information pushing method, an information pushing device, information pushing equipment and a computer-readable storage medium.
It should be noted that the information pushing method, apparatus, device, and computer-readable storage medium provided in the present application may be applied in various information pushing scenarios.
For example, the application can be applied to the scenario of using authority information pushing. And predicting by predicting the probability of transacting the use authority of the user, and pushing the push information corresponding to the use authority to the user with the transacting use authority probability exceeding a preset probability threshold.
In addition, the method and the device can also be applied to scenes of personalized information pushing, determine commonly used browsing pages of all users, and push personalized pushing information to the users.
The existing information pushing method generally pushes information corresponding to the use authority for all users of the application. However, even if some users know the push information of the usage right, the users do not deal with the usage right. Therefore, the information pushing method often cannot realize accurate pushing of information, which causes resource waste.
In the process of solving the technical problem, the inventor finds, through research, that, in order to improve the accuracy of information pushing, firstly, the probability of transacting the use permission of each user can be predicted, and information pushing is performed according to the probability.
The inventor further researches and discovers that the probability of handling the use permission of the user is predicted, and the pushing information corresponding to the use permission is pushed to the user handling the use permission with the probability exceeding the preset probability threshold value, so that the accurate pushing of the information can be realized, the resource waste is avoided, and the pushing efficiency is improved.
Fig. 1 is a schematic diagram of a system architecture based on the present application, as shown in fig. 1, the system architecture based on the present application at least includes: the terminal equipment 1, the information push device 2 and the data server 3. The information pushing device 2 is written by C/C + +, Java, Shell or Python languages and the like; the terminal device 1 may be a desktop computer, a tablet computer, or the like. The data server 3 may be a cloud server or a server cluster, and a large amount of data is stored therein. The information push device 2 is in communication connection with the terminal device 1 and the data server 3, respectively, so as to be capable of interacting with the terminal device 1 and the data server 3.
Fig. 2 is a schematic flow chart of an information pushing method according to an embodiment of the present application, and as shown in fig. 2, the method includes:
The execution subject of this embodiment is an information pushing apparatus, and the information pushing apparatus may be disposed in a terminal device, or may be an apparatus independent from the terminal device, which is not limited in this application.
In the present embodiment, in order to realize accurate pushing of usage right information, it is necessary to predict the probability of each user handling usage rights. Therefore, there is a need to obtain historical usage data of at least one user in a target application. The target application can be any application capable of handling the use permission, such as an e-commerce platform, social software, music software and the like. Specifically, the historical usage data of at least one user in the target application may be acquired from a data server in which the historical usage data of a plurality of users is stored in advance. The user can have the usage rights after transacting the user. The privilege is different from that of a common user, for example, for an e-commerce platform, a user transacting the use privilege can enjoy preferential price, package mail, receipt of a coupon and the like corresponding to the use privilege; for music software, users transacting usage rights can listen to and download more music, etc.
By taking the target application as an e-commerce platform, the historical usage data includes, but is not limited to, browsing data, shopping behavior data, content searching data, usage right transaction and usage data, etc. within a preset time of the user.
And 102, inputting the historical use data into a preset prediction model to obtain the probability of transacting the target use permission of each user.
In this embodiment, a prediction model may be preset, and the prediction model may be specifically used for predicting the probability of transacting the usage right by the user. Therefore, after obtaining the historical usage data of at least one user, the historical usage data can be input into the prediction model, and the probability that each user transacts the target usage right can be obtained.
And 103, acquiring at least one target user with the probability of transacting the target use permission exceeding a preset probability threshold.
In the embodiment, if the prediction result is that the probability of transacting the use permission by the user is higher than the preset threshold, it is represented that the user transacts the use permission at a high probability after browsing the push information corresponding to the use permission; on the contrary, if the prediction result is that the probability of transacting the use permission by the user is lower than the preset threshold, the probability of transacting the use permission is smaller after the user browses the push information corresponding to the use permission. Therefore, in order to realize accurate pushing of the usage right information, after obtaining the probability that each user transacts the target usage right, the target user with the probability of transacting the usage right higher than the preset threshold needs to be determined.
The preset threshold may be specifically 0.9. In practical application, a user may set the threshold according to actual requirements, which is not limited in the present application.
And 104, pushing the push information corresponding to the use authority to the at least one target user.
In this embodiment, after determining the target user having the higher probability of handling the usage right than the preset threshold, the push information related to the usage right may be directly pushed to the target user having the higher probability of handling the usage right than the preset threshold. Therefore, accurate information pushing can be achieved, and the return rate of pushed information is improved.
Specifically, the push information may be sent to the terminal device of the user for display.
According to the information pushing method provided by the embodiment, the probability of handling the use permission of the user is predicted, and the pushing information corresponding to the use permission is pushed to the user handling the use permission with the probability exceeding the preset probability threshold value, so that the accurate pushing of the information can be realized, the resource waste is avoided, and the pushing efficiency is improved.
Fig. 3 is a schematic flow chart of an information pushing method provided in the second embodiment of the present application, and based on the first embodiment, as shown in fig. 3, step 102 specifically includes:
and step 203, determining the probability of transacting the target use permission of each user according to the low-order feature data, the medium-order feature data and the high-order feature data.
Fig. 4 is a network architecture diagram of a prediction model provided in an embodiment of the present application, and as shown in fig. 4, the prediction model specifically includes a vectorization sub-network, a low-order feature extraction sub-network, a medium-order feature extraction sub-network, and a high-order feature extraction sub-network.
After acquiring the historical usage data of at least one user based on the network structure diagram, in order to enable the model to process the historical usage data, the historical usage data needs to be vectorized first. Specifically, the historical usage data may be input into a vectorization sub-network, and a target vector corresponding to the historical usage data may be obtained. It should be noted that the vectoring sub-network may be any network model capable of implementing vectoring operation, and the present application is not limited thereto. For example, the vectorization sub-model may be specifically an Embedding layer, and the Embedding layer can convert high-dimensional sparse class features into low-dimensional dense vector features, and then splice the low-dimensional dense vector features with continuous numerical features.
The user usage data may specifically include Category Features (Category Features) and continuous numerical Features (numerical Features), where the Category Features may specifically be Features that cannot be expressed by integers, such as price information with decimal points, user browsing data, and the like, and correspondingly, the numerical Features may be Features that can be expressed by integers, such as the gender of the user (the gender may be encoded as 0 and 1), a user preference class number, and the like.
Further, in order to improve the accuracy of model prediction, a plurality of levels of feature extraction processing may be performed on the target vector. Specifically, the target vector can be input into a low-order feature extraction sub-network to obtain low-order feature data corresponding to the historical usage data; inputting the target vector into a medium-order feature extraction sub-network to obtain medium-order feature data corresponding to the historical use data; and inputting the target vector into the high-order feature extraction sub-network to obtain high-order feature data corresponding to the historical use data.
After the low-order feature data, the medium-order feature data and the high-order feature data are obtained, the low-order feature data, the medium-order feature data and the high-order feature data can be spliced, the spliced low-order feature data, medium-order feature data and high-order feature data are subjected to data processing, and the probability that a user transacts the target use permission is obtained.
Specifically, on the basis of any of the above embodiments, the low-order feature extraction sub-network is an FM model;
correspondingly, step 202 specifically includes:
inputting the target vector into the FM model for data processing;
and randomly discarding the interaction path in the FM model data processing process through a preset over-fitting prevention technology.
In this embodiment, the low-order feature extraction submodel may be specifically an FM model. Accordingly, the target vector may be input into the FM model for data processing. In the model training process, certain paths of FM second-order feature interaction can be randomly discarded by preventing an overfitting technology, and the probability of each interaction path being activated obeys Bernoulli distribution. Where p obeys a bernoulli distribution with parameter beta, each forward propagation is discarded with probability of p during the network training phase.
Specifically, on the basis of any of the above embodiments, the medium-order feature extraction sub-network includes a convolutional layer, a pooling layer, and a fully-connected layer;
correspondingly, step 202 specifically includes:
acquiring characteristic information corresponding to the target vector through the convolutional layer and the pooling layer;
and splicing the characteristic information through the full connection layer to obtain the intermediate-order characteristic data.
In this embodiment, the medium-order feature extraction sub-network may specifically be a convolutional neural network, and the convolutional neural network specifically includes a convolutional layer, a pooling layer, and a fully-connected layer. Correspondingly, the feature information corresponding to the target vector can be obtained through the convolution layer and the pooling layer, and the feature information is further spliced by using the full-connection layer to obtain the middle-order feature data. In the training process, the middle-order feature data, the previous low-order feature data and the previous high-order feature data enter a final combined training layer together, and parameters are continuously updated in an iterative mode.
Specifically, on the basis of any of the above embodiments, the high-order feature extraction sub-network is a multi-head attention mechanism model.
In this embodiment, the high-order feature extraction sub-network may specifically be a multi-head attention mechanism model.
According to the information pushing method provided by the embodiment, the target vector is subjected to the feature extraction processing of multiple levels, so that the probability prediction accuracy can be improved, and a basis is provided for improving the information delivery accuracy.
Fig. 5 is a schematic flow chart of an information pushing method provided in a third embodiment of the present application, and on the basis of any of the above embodiments, as shown in fig. 5, before step 102, the method further includes:
301, acquiring a preset data set to be processed from the data server, wherein the data set to be trained comprises historical use data of a plurality of users and use authority transacting information corresponding to the plurality of users;
In this embodiment, in order to predict the usage authority handling probability by using the prediction model, a preset model to be trained needs to be trained to obtain the prediction model. Specifically, a preset data set to be processed may be obtained from the data server, where the data set to be processed includes historical usage data of multiple users and usage right handling information corresponding to the multiple users, and the historical usage data of the multiple users are labeled through the usage right handling information to obtain a first data set to be trained. And training a preset model to be trained through the first data set to be trained to obtain a prediction model. Because the first data set to be trained is marked by using the use permission transacting information, the probability of transacting the use permission of the user can be determined after historical use data is input into the prediction model subsequently.
Specifically, on the basis of any of the above embodiments, step 301 specifically includes:
and acquiring historical orders in a preset first time threshold from the data server, and/or acquiring historical use data corresponding to a user with a preference score exceeding a preset score threshold of any target item as the to-be-processed data set, wherein the preference score is obtained through calculation of a preset score calculation model, and the number of the browsed target web pages exceeds a preset number threshold within a preset second time threshold.
In this embodiment, in order to improve the prediction accuracy of the prediction model, in the process of acquiring the to-be-processed data set, a historical order may be present in a preset first time threshold, and/or the number of browsing target webpages exceeds a preset number threshold within a preset second time threshold, and/or historical usage data corresponding to a user whose preference score exceeds a preset score threshold for any target item is acquired as the to-be-processed data set, where the preference score is calculated through a preset score calculation model.
According to the information pushing method provided by the embodiment, the first to-be-trained data set is labeled by using the permission transacting information, so that the probability of transacting the use permission of the user can be determined after historical use data is input into the prediction model subsequently.
Fig. 6 is an information pushing method provided in the fourth embodiment of the present application, where on the basis of any of the embodiments, a to-be-processed data set further includes information of usage right types corresponding to a plurality of users; as shown in fig. 6, the method further comprises:
And step 403, inputting the historical use data into the type prediction model to obtain type information of transacting use permission of each user.
In this embodiment, the to-be-processed data set may further include information of usage right types corresponding to a plurality of users. The usage right type may specifically include a quarterly usage right type and an annual usage right type; or, a common usage right type, an advanced usage right type, and the like may be included, where the usage right range corresponding to the common usage right type and the advanced usage right type is different. Therefore, in order to determine the type of the use permission transacted by the user more accurately, the historical use data of a plurality of users can be labeled through the use permission type, and a second data set to be trained is obtained. And then, the preset model to be trained can be trained by using the second data set to be trained to obtain a type prediction model.
Correspondingly, after the type prediction model is obtained through training, the obtained historical use data of the user can be input into the type prediction model, and the type information of the use permission transacted by each user is obtained. Accordingly, after determining the type information of the usage right transacted by each user, the push information of different types of usage rights can be pushed to the users.
According to the information pushing method provided by the embodiment, the preset model to be trained is trained by adopting the second data to be trained, which is obtained by labeling the historical use data of a plurality of users through the use permission types, so that the type of the use permission handled by the users can be determined more accurately, and the information pushing accuracy is further improved.
Fig. 7 is a schematic flow chart of an information pushing method according to a fifth embodiment of the present application, where on the basis of any of the foregoing embodiments, the to-be-processed data set further includes personalized browsing information corresponding to a plurality of users; as shown in fig. 7, the method further comprises:
In this embodiment, the to-be-processed data set may further include personalized browsing information corresponding to a plurality of users, where the personalized browsing information may be generated according to historical browsing data of the users. For the e-commerce platform, the personalized browsing information can be women's clothing, electronic products and the like; for reading software, the personalized browsing information can be speaking, leisure, and the like; the personalized browsing information may be entertainment, sports, etc. for the search engine. In order to realize the pushing of personalized information, historical use data of a plurality of users can be labeled through personalized browsing information, and a third data set to be trained is obtained. And then, the third data set to be trained can be used for training a preset model to be trained to obtain a browsing page prediction model.
Further, after the browsing page prediction model is obtained, the obtained historical use data of the user can be input into the browsing page prediction model, so that the personalized browsing page information of each user can be obtained. And then the personalized browsing page information can be pushed to at least one user. For example, if the personalized browsing information of the user can be a woman dress, the user can be correspondingly pushed more second dresses, preferential information of the woman dress, large activities of the woman dress and the like. Improving user stickiness.
Fig. 8 is a schematic diagram of personalized browsing information of a user provided in the embodiment of the present application, as shown in fig. 9, the user browses a female garment product most of the time, and as shown in fig. 9, the schematic diagram of personalized browsing page information provided in the embodiment of the present application, as shown in fig. 9, a large activity of a female garment can be pushed to the user.
According to the information pushing method provided by the embodiment, the preset model to be trained is trained by adopting the third data to be trained, which is obtained by labeling the historical use data of a plurality of users by using the personalized browsing information, so that the browsing page prediction model is obtained, the personalized browsing page information of the users can be determined more accurately, the information pushing accuracy is further improved, and the user viscosity is improved.
Fig. 10 is a schematic structural diagram of an information pushing apparatus according to a seventh embodiment of the present application, and as shown in fig. 10, the apparatus includes: the system comprises an acquisition module 71, a processing module 72, a determination module 73 and a pushing module 74, wherein the acquisition module 71 is used for acquiring historical use data of at least one user in a target application; a processing module 72, configured to input the historical usage data into a preset prediction model, and obtain a probability that each user transacts the target usage right; the determining module 73 is configured to acquire at least one target user whose probability of transacting the target usage right exceeds a preset probability threshold; a pushing module 74, configured to push, to the at least one target user, pushing information corresponding to the usage right.
The information pushing device provided by the embodiment predicts the probability of handling the use permission by the user, pushes the pushing information corresponding to the use permission to the user handling the use permission probability exceeding the preset probability threshold value, can realize accurate pushing of information, avoids resource waste and improves pushing efficiency.
Fig. 11 is a schematic structural diagram of an information pushing apparatus according to an eighth embodiment of the present application, in which on the basis of the seventh embodiment, the prediction model includes a vectorization sub-network, a low-order feature extraction sub-network, a medium-order feature extraction sub-network, and a high-order feature extraction sub-network, and as shown in fig. 11, the processing module includes: a vectorization unit 81, a processing unit 82, and a probability determination unit 83, where the vectorization unit 81 is configured to input the historical usage data into the vectorization sub-network, and obtain a target vector corresponding to the historical usage data; the processing unit 82 is configured to input the target vector into the low-order feature extraction sub-network to obtain low-order feature data corresponding to the historical usage data; inputting the target vector into the middle-order feature extraction sub-network to obtain middle-order feature data corresponding to the historical use data; the target vector is input into the high-order feature extraction sub-network to obtain high-order feature data corresponding to the historical use data; and a probability determining unit 83, configured to determine, according to the low-order feature data, the medium-order feature data, and the high-order feature data, a probability that each user transacts the target usage right.
Further, on the basis of any of the above embodiments, the low-order feature extraction sub-network is an FM model;
accordingly, the processing unit is configured to:
inputting the target vector into the FM model for data processing;
and randomly discarding the interaction path in the FM model data processing process through a preset over-fitting prevention technology.
Further, on the basis of any of the above embodiments, the medium-order feature extraction sub-network includes a convolutional layer, a pooling layer, and a fully-connected layer;
accordingly, the processing unit is configured to:
acquiring characteristic information corresponding to the target vector through the convolutional layer and the pooling layer;
and splicing the characteristic information through the full connection layer to obtain the intermediate-order characteristic data.
Further, on the basis of any of the above embodiments, the high-order feature extraction sub-network is a multi-head attention mechanism model.
Fig. 12 is a schematic structural diagram of an information pushing apparatus according to a ninth embodiment of the present application, where on the basis of any of the foregoing embodiments, as shown in fig. 12, the apparatus further includes: the system comprises a to-be-processed data set acquisition module 91, a first labeling module 92 and a first training module 93, wherein the to-be-processed data set acquisition module 91 is used for acquiring a preset to-be-processed data set from the data server, and the to-be-processed data set comprises historical use data of a plurality of users and use authority transacting information corresponding to the plurality of users; a first labeling module 92, configured to label, through the usage right handling information, historical usage data of the multiple users to obtain a first to-be-trained data set; the first training module 93 is configured to train a preset model to be trained through the first data set to be trained, so as to obtain the prediction model.
Further, on the basis of any of the above embodiments, the to-be-processed data set obtaining module is configured to:
and acquiring historical orders in a preset first time threshold from the data server, and/or acquiring historical use data corresponding to a user with a preference score exceeding a preset score threshold of any target item as the to-be-processed data set, wherein the preference score is obtained through calculation of a preset score calculation model, and the number of the browsed target web pages exceeds a preset number threshold within a preset second time threshold.
Fig. 13 is a schematic structural diagram of an information pushing apparatus provided in a tenth embodiment of the present application, where on the basis of any of the foregoing embodiments, the to-be-processed data set further includes information of usage right types corresponding to multiple users; as shown in fig. 13, the apparatus further includes: a second labeling module 111 and a second training module 112, where the second labeling module 111 is configured to label historical usage data of the multiple users through the information of the usage permission types, and obtain a second data set to be trained; a second training module 112, configured to train a preset model to be trained through the second data set to be trained, so as to obtain a type prediction model; and the processing module 112 is configured to input the historical usage data into the type prediction model, and obtain type information of each user transacting usage rights.
Fig. 14 is a schematic structural diagram of an information pushing apparatus according to an eleventh embodiment of the present application, where on the basis of any one of the foregoing embodiments, the to-be-processed data set further includes personalized browsing information corresponding to a plurality of users; as shown in fig. 14, the apparatus further includes: third labeling modules 121 and 122, where the third labeling module 121 is configured to label historical usage data of the multiple users through the personalized browsing information to obtain a third data set to be trained; the third training module 122 is configured to train a preset model to be trained through the third data set to be trained, so as to obtain a browsing page prediction model; the processing module 123 is configured to input the historical usage data into the browsing page prediction model, and obtain information of each user personalized browsing page; a pushing module 124, configured to push the personalized browsing page information to the at least one user.
Fig. 15 is a schematic structural diagram of an information pushing apparatus provided in a twelfth embodiment of the present application, and as shown in fig. 15, the information pushing apparatus includes: a memory 131, a processor 132;
a memory 131; a memory 131 for storing instructions executable by the processor 132;
wherein the processor 132 is configured to execute the information pushing method according to any one of the above embodiments by the processor 132.
The memory 131 stores programs. In particular, the program may include program code comprising computer operating instructions. The memory 131 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 132 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement the embodiments of the present Application.
Alternatively, in a specific implementation, if the memory 131 and the processor 132 are implemented independently, the memory 131 and the processor 132 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 15, but this is not intended to represent only one bus or type of bus.
Alternatively, in a specific implementation, if the memory 131 and the processor 132 are integrated on a chip, the memory 131 and the processor 132 may perform the same communication through an internal interface.
Still another embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when executed by a processor, the computer-executable instructions are used to implement the information pushing method according to any one of the above embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (16)
1. An information pushing method, comprising:
acquiring historical use data of at least one user in a target application;
inputting the historical use data into a preset prediction model to obtain the probability of each user handling the target use permission;
acquiring at least one target user with the probability of handling the target use permission exceeding a preset probability threshold;
and pushing information corresponding to the use authority to the at least one target user.
2. The method of claim 1, wherein the predictive models comprise a vectorization sub-network, a low order feature extraction sub-network, an intermediate order feature extraction sub-network, and a high order feature extraction sub-network;
the step of inputting the historical usage data into a preset prediction model to obtain the probability of transacting the target usage right of each user comprises the following steps:
inputting the historical use data into the vectorization sub-network to obtain a target vector corresponding to the historical use data;
inputting the target vector into the low-order feature extraction sub-network to obtain low-order feature data corresponding to the historical use data; inputting the target vector into the middle-order feature extraction sub-network to obtain middle-order feature data corresponding to the historical use data; the target vector is input into the high-order feature extraction sub-network to obtain high-order feature data corresponding to the historical use data;
and determining the probability of transacting the target use permission of each user according to the low-order feature data, the medium-order feature data and the high-order feature data.
3. The method of claim 2, wherein the low order feature extraction sub-network is an FM model;
correspondingly, the inputting the target vector into the low-order feature extraction sub-network to obtain the low-order feature data corresponding to the historical usage data includes:
inputting the target vector into the FM model for data processing;
and randomly discarding the interaction path in the FM model data processing process through a preset over-fitting prevention technology.
4. The method of claim 2, wherein the medium-order feature extraction sub-network comprises a convolutional layer, a pooling layer, and a fully-connected layer;
correspondingly, the inputting the target vector into the medium-order feature extraction sub-network to obtain medium-order feature data corresponding to the historical usage data includes:
acquiring characteristic information corresponding to the target vector through the convolutional layer and the pooling layer;
and splicing the characteristic information through the full connection layer to obtain the intermediate-order characteristic data.
5. The method according to any of claims 1-4, wherein prior to inputting the historical usage data into a pre-set predictive model, further comprising:
acquiring a preset data set to be processed from the data server, wherein the data set to be processed comprises historical use data of a plurality of users and use authority transacting information corresponding to the plurality of users;
marking historical use data of the users through the use authority transacting information to obtain a first data set to be trained;
and training a preset model to be trained through the first data set to be trained to obtain the prediction model.
6. The method according to claim 5, wherein the obtaining the preset data set to be processed from the data server comprises:
and acquiring historical orders in a preset first time threshold from the data server, and/or acquiring historical use data corresponding to a user with a preference score exceeding a preset score threshold of any target item as the to-be-processed data set, wherein the preference score is obtained through calculation of a preset score calculation model, and the number of the browsed target web pages exceeds a preset number threshold within a preset second time threshold.
7. The method according to claim 5, wherein the data set to be processed further includes information of usage right types corresponding to a plurality of users; the method further comprises the following steps:
marking historical use data of the users through the information of the use authority types to obtain a second data set to be trained;
training a preset model to be trained through the second data set to be trained to obtain a type prediction model;
and inputting the historical use data into the type prediction model to obtain the type information of the transacting use permission of each user.
8. The method according to claim 5, wherein the data set to be processed further includes personalized browsing information corresponding to a plurality of users; the method further comprises the following steps:
marking historical use data of the users through the personalized browsing information to obtain a third data set to be trained;
training a preset model to be trained through the third data set to be trained to obtain a browsing page prediction model;
inputting the historical use data into the browsing page prediction model to obtain the personalized browsing page information of each user;
and pushing the personalized browsing page information to the at least one user.
9. An information pushing apparatus, comprising:
the acquisition module is used for acquiring historical use data of at least one user in the target application;
the processing module is used for inputting the historical use data into a preset prediction model to obtain the probability of transacting the target use permission of each user;
the determining module is used for acquiring at least one target user with the probability of transacting the target use permission exceeding a preset probability threshold;
and the pushing module is used for pushing information corresponding to the use permission to the at least one target user.
10. The apparatus of claim 9, wherein the predictive model comprises a vectorization sub-network, a low order feature extraction sub-network, a medium order feature extraction sub-network, and a high order feature extraction sub-network;
the vectorization unit is used for inputting the historical use data into the vectorization sub-network to obtain a target vector corresponding to the historical use data;
the processing unit is used for inputting the target vector into the low-order feature extraction sub-network to obtain low-order feature data corresponding to the historical use data; inputting the target vector into the middle-order feature extraction sub-network to obtain middle-order feature data corresponding to the historical use data; the target vector is input into the high-order feature extraction sub-network to obtain high-order feature data corresponding to the historical use data;
and the probability determining unit is used for determining the probability of transacting the target use permission of each user according to the low-order feature data, the medium-order feature data and the high-order feature data.
11. The apparatus of claim 9 or 10, further comprising:
the data processing system comprises a to-be-processed data set acquisition module, a to-be-processed data set acquisition module and a data processing module, wherein the to-be-processed data set acquisition module is used for acquiring a preset to-be-processed data set from the data server, and the to-be-processed data set comprises historical use data of a plurality of users and use authority transacting information corresponding to the plurality of users;
the first marking module is used for marking the historical use data of the users through the use authority handling information to obtain a first data set to be trained;
and the first training module is used for training a preset model to be trained through the first data set to be trained to obtain the prediction model.
12. The apparatus of claim 11, wherein the pending data set acquisition module is configured to:
and acquiring historical orders in a preset first time threshold from the data server, and/or acquiring historical use data corresponding to a user with a preference score exceeding a preset score threshold of any target item as the to-be-processed data set, wherein the preference score is obtained through calculation of a preset score calculation model, and the number of the browsed target web pages exceeds a preset number threshold within a preset second time threshold.
13. The apparatus according to claim 11, wherein the to-be-processed data set further includes information of usage right types corresponding to a plurality of users; the device further comprises:
the second labeling module is used for labeling the historical use data of the users through the information of the use authority types to obtain a second data set to be trained;
the second training module is used for training a preset model to be trained through the second data set to be trained to obtain a type prediction model;
and the processing module is used for inputting the historical use data into the type prediction model to obtain the type information of the transacting use permission of each user.
14. The apparatus according to claim 11, wherein the to-be-processed data set further includes personalized browsing information corresponding to a plurality of users; the device further comprises:
the third labeling module is used for labeling the historical use data of the users through the personalized browsing information to obtain a third data set to be trained;
the third training module is used for training a preset model to be trained through the third data set to be trained to obtain a browsing page prediction model;
the processing module is used for inputting the historical use data into the browsing page prediction model to obtain the information of each user personalized browsing page;
and the pushing module is used for pushing the personalized browsing page information to the at least one user.
15. An information push apparatus characterized by comprising: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the information push method of any one of claims 1-8 by the processor.
16. A computer-readable storage medium, wherein a computer-executable instruction is stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instruction is used for implementing the information pushing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010447775.9A CN112243021A (en) | 2020-05-25 | 2020-05-25 | Information pushing method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010447775.9A CN112243021A (en) | 2020-05-25 | 2020-05-25 | Information pushing method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112243021A true CN112243021A (en) | 2021-01-19 |
Family
ID=74170419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010447775.9A Pending CN112243021A (en) | 2020-05-25 | 2020-05-25 | Information pushing method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112243021A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196544A (en) * | 2023-11-07 | 2023-12-08 | 恒实建设管理股份有限公司 | Intelligent management method and system for engineering information |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170083949A1 (en) * | 2015-09-18 | 2017-03-23 | Mastercard International Incorporated | Point of sale transaction based targeted advertising technical field |
| CN106897905A (en) * | 2017-02-28 | 2017-06-27 | 百度在线网络技术（北京）有限公司 | Method, device and electronic equipment for pushed information |
| CN107016569A (en) * | 2017-03-21 | 2017-08-04 | 聚好看科技股份有限公司 | The targeted customer's account acquisition methods and device of a kind of networking products |
| US20170329856A1 (en) * | 2015-04-08 | 2017-11-16 | Tencent Technology (Shenzhen) Company Limited | Method and device for selecting data content to be pushed to terminal, and non-transitory computer storage medium |
| CN107908789A (en) * | 2017-12-12 | 2018-04-13 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN109214543A (en) * | 2017-06-30 | 2019-01-15 | 华为技术有限公司 | Data processing method and device |
| CN109257398A (en) * | 2017-07-12 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of method for pushing and equipment of business object |
| CN110324418A (en) * | 2019-07-01 | 2019-10-11 | 阿里巴巴集团控股有限公司 | Method and apparatus based on customer relationship transmission service |
| CN110442810A (en) * | 2019-08-08 | 2019-11-12 | 广州华建工智慧科技有限公司 | A kind of mobile terminal BIM model intelligent buffer method based on DeepFM proposed algorithm |
| CN110443353A (en) * | 2019-07-16 | 2019-11-12 | 天津大学 | The neural network of implication relation between a kind of excavation feature based on short connection |
-
2020
- 2020-05-25 CN CN202010447775.9A patent/CN112243021A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170329856A1 (en) * | 2015-04-08 | 2017-11-16 | Tencent Technology (Shenzhen) Company Limited | Method and device for selecting data content to be pushed to terminal, and non-transitory computer storage medium |
| US20170083949A1 (en) * | 2015-09-18 | 2017-03-23 | Mastercard International Incorporated | Point of sale transaction based targeted advertising technical field |
| CN106897905A (en) * | 2017-02-28 | 2017-06-27 | 百度在线网络技术（北京）有限公司 | Method, device and electronic equipment for pushed information |
| CN107016569A (en) * | 2017-03-21 | 2017-08-04 | 聚好看科技股份有限公司 | The targeted customer's account acquisition methods and device of a kind of networking products |
| CN109214543A (en) * | 2017-06-30 | 2019-01-15 | 华为技术有限公司 | Data processing method and device |
| CN109257398A (en) * | 2017-07-12 | 2019-01-22 | 阿里巴巴集团控股有限公司 | A kind of method for pushing and equipment of business object |
| CN107908789A (en) * | 2017-12-12 | 2018-04-13 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN108647811A (en) * | 2018-04-26 | 2018-10-12 | 中国联合网络通信集团有限公司 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
| CN110324418A (en) * | 2019-07-01 | 2019-10-11 | 阿里巴巴集团控股有限公司 | Method and apparatus based on customer relationship transmission service |
| CN110443353A (en) * | 2019-07-16 | 2019-11-12 | 天津大学 | The neural network of implication relation between a kind of excavation feature based on short connection |
| CN110442810A (en) * | 2019-08-08 | 2019-11-12 | 广州华建工智慧科技有限公司 | A kind of mobile terminal BIM model intelligent buffer method based on DeepFM proposed algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 陈检;: "基于神经网络与因子分解机的点击率预估应用研究", 信息技术与信息化, no. 08 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196544A (en) * | 2023-11-07 | 2023-12-08 | 恒实建设管理股份有限公司 | Intelligent management method and system for engineering information |
| CN117196544B (en) * | 2023-11-07 | 2024-01-30 | 恒实建设管理股份有限公司 | Intelligent management method and system for engineering information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200250732A1 (en) | Method and apparatus for use in determining tags of interest to user | |
| CN111523976A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN107679217B (en) | Associated content extraction method and device based on data mining | |
| CN111784455A (en) | Article recommendation method and recommendation equipment | |
| CN113449187B (en) | Product recommendation method, device, equipment and storage medium based on double images | |
| CN108121814B (en) | Search result ranking model generation method and device | |
| EP2862104A1 (en) | Search method and apparatus | |
| CN110827112A (en) | Deep learning commodity recommendation method and device, computer equipment and storage medium | |
| CN109933678B (en) | Artwork recommendation method and device, readable medium and electronic equipment | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| CN112330382B (en) | Item recommendation method, device, computing equipment and medium | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN109840788A (en) | For analyzing the method and device of user behavior data | |
| CN111612506A (en) | Financial resource deduction method and device and electronic equipment | |
| CN112243021A (en) | Information pushing method, device, equipment and computer readable storage medium | |
| CN109978594B (en) | Order processing method, device and medium | |
| CN117670487A (en) | Cross-platform commodity release method, device, equipment and storage medium | |
| CN112989182A (en) | Information processing method, information processing apparatus, information processing device, and storage medium | |
| CN111598638B (en) | Click rate determination method, device and equipment | |
| CN111489196A (en) | Prediction method and device based on deep learning network, electronic equipment and medium | |
| CN111597454A (en) | Account recommendation method and device | |
| CN113792232B (en) | Page feature calculation method, page feature calculation device, electronic equipment, page feature calculation medium and page feature calculation program product | |
| CN115618126A (en) | Search processing method, system, computer readable storage medium and computer device | |
| CN110837596B (en) | Intelligent recommendation method and device, computer equipment and storage medium | |
| CN112559853B (en) | User tag generation method and device |
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 |